diff --git a/.github/workflows/api-acceptance.yml b/.github/workflows/api-acceptance.yml
index d4437a4c9..ee010ed18 100644
--- a/.github/workflows/api-acceptance.yml
+++ b/.github/workflows/api-acceptance.yml
@@ -62,6 +62,7 @@ jobs:
           OAC_TEST_SERVER_BIN: ${{ runner.temp }}/oac-core-build/oac-core
           OAC_TEST_OFFICIAL_SDK_PYTHON: python
         run: |
+          python services/core/tests/official_schema_test.py
           python services/core/tests/official_client.py
           go test ./services/core/tests/integration -run '^(TestFunctionStateOfficialClientReadsAndLiveEvents|TestSavedReferenceRetryOfficialClient|TestAgentUpdateOfficialClient|TestAgentDeletionOfficialClient|TestSessionAgentFilterOfficialClient|TestSessionDeletionOfficialClient|TestEnvironmentInitialFailureOfficialClient|TestSelfHostedInitialCreationOfficialClient|TestSelfHostedCancellationOfficialClient)$' -count=1
       - uses: ./.github/actions/e2b-provider
diff --git a/.github/workflows/check.yml b/.github/workflows/check.yml
index 151a0c410..0a307c7ad 100644
--- a/.github/workflows/check.yml
+++ b/.github/workflows/check.yml
@@ -184,8 +184,18 @@ jobs:
   compose:
     needs: plan
     if: needs.plan.result == 'success' && contains(fromJSON(needs.plan.outputs.jobs || '[]'), 'compose')
-    runs-on: ${{ vars.OAC_USE_GITHUB_RUNNERS == 'true' && 'ubuntu-22.04' || 'blacksmith-2vcpu-ubuntu-2204' }}
-    timeout-minutes: 20
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - runner: ubuntu-24.04
+            architecture: amd64
+          - runner: ubuntu-24.04-arm
+            architecture: arm64
+    runs-on: ${{ matrix.runner }}
+    env:
+      GOARCH: ${{ matrix.architecture }}
+    timeout-minutes: 30
     steps:
       - uses: actions/checkout@v7
         with:
@@ -193,6 +203,11 @@ jobs:
       - uses: actions/setup-go@v7
         with:
           go-version-file: go.mod
+      - name: Test the native Core installation lifecycle
+        run: go test ./services/core/cmd/oac -count=1 -timeout=3m
+      - uses: ./.github/actions/e2b-provider
+      - name: Build and verify the architecture-matched E2B helper
+        run: bash scripts/build-e2b-provider.sh
       - name: Allocate an isolated Compose project
         run: python3 -c 'import uuid; print("COMPOSE_SMOKE_PROJECT=oac-smoke-" + uuid.uuid4().hex)' >> "$GITHUB_ENV"
       - name: Build the images, start the installation and verify it
diff --git a/.github/workflows/ci-review.yml b/.github/workflows/ci-review.yml
index 0cd33e664..2bc1069bd 100644
--- a/.github/workflows/ci-review.yml
+++ b/.github/workflows/ci-review.yml
@@ -16,12 +16,28 @@ permissions:
 
 jobs:
   review:
+    name: ${{ matrix.name }}
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - kind: code
+            name: Code review
+            instructions: |
+              检查本次代码改动的正确性、仓库设计规则及已有 CI 结果。先读取 AGENTS.md 和 CONTRIBUTING.md，再查看相关实现和测试。
+              用 gh pr checks 查询这个 PR 已有的检查结果，必要时读取 Actions 日志。检查失败、缺失或尚未完成时如实报告，不把合并当作检查通过的证据。
+              报告包括实际行为变化（1–3 条）、代码审查结论和 CI 状态。全部正常时保持简短；有问题时给出文件与行号、证据和最小修改建议。
+          - kind: docs
+            name: Docs review
+            instructions: |
+              每次都检查文档与本次代码变化是否一致，即使 PR 没改文档。读取相关实现、测试和完整文档，核对平台、命令、配置、路径、默认值、接口和操作流程，找出遗漏更新或已经过时的说明。
+              文档有修改（包括新增、删除和重命名）时，再检查文档内部及同主题文档间的矛盾、重复维护的事实、主题归属和中英文含义。按 AGENTS.md 和 CONTRIBUTING.md 的 Documentation ownership 表判断位置。必要的概述加链接、中英文对照和同一来源生成的文档不算重复。
+              分别报告“文档与代码一致性”和“文档矛盾、重复与归属”。未改文档时，第二项写“本次未修改文档”。只报告本次修改引入或使之过时的、有依据的问题，给出文件与行号、对应代码或文档依据，以及最小修改建议。测试或链接检查通过不代表语义一致。只报告影响读者理解或操作的具体问题，不把未穷举实现细节当作文档缺陷。
     if: github.event.pull_request.merged == true
     runs-on: ${{ vars.OAC_USE_GITHUB_RUNNERS == 'true' && 'ubuntu-24.04' || 'blacksmith-2vcpu-ubuntu-2404' }}
     timeout-minutes: 30
     env:
-      # allowed_non_write_users turns on a subprocess secret scrub; opt out so Claude's
-      # commands can read GH_TOKEN and the Feishu webhook.
+      # Keep GH_TOKEN available to read the PR and Actions logs.
       CLAUDE_CODE_SUBPROCESS_ENV_SCRUB: '0'
     steps:
       # The triggering revision is already on main, so its rules and code are trusted.
@@ -30,14 +46,15 @@ jobs:
           ref: ${{ github.event.pull_request.merge_commit_sha }}
           fetch-depth: 2
           persist-credentials: false
-      - name: Review and send Feishu card with Claude Code
-        # Notification is best effort: a failed review or delivery never fails the job.
+      - name: Prepare the report schema
+        id: schema
+        run: python3 scripts/ci_review.py schema "${{ matrix.kind }}" >> "$GITHUB_OUTPUT"
+      - name: Review with Claude Code
+        id: llm
         continue-on-error: true
         timeout-minutes: 25
         uses: anthropics/claude-code-action@12dd8d74c712f5f3669365b2369b558c495b1104 # v1
         env:
-          FEISHU_WEBHOOK_URL: ${{ secrets.FEISHU_WEBHOOK_URL }}
-          FEISHU_WEBHOOK_SECRET: ${{ secrets.FEISHU_WEBHOOK_SECRET }}
           ANTHROPIC_BASE_URL: https://api.minimax.cn/anthropic
           ANTHROPIC_AUTH_TOKEN: ${{ secrets.MINIMAX_API_KEY }}
           CLAUDE_CODE_AUTO_COMPACT_WINDOW: '524288'
@@ -54,29 +71,57 @@ jobs:
           allowed_bots: '*'
           allowed_non_write_users: '*'
           prompt: |
-            你是 CI 的负责人，负责审核 CI 结果并给出结论。
-            仓库 ${{ github.repository }} 的 PR #${{ github.event.pull_request.number }} 已合入 main：
-            - PR：https://github.com/${{ github.repository }}/pull/${{ github.event.pull_request.number }}
-            - 合并 commit：${{ github.event.pull_request.merge_commit_sha }}（已 checkout 到当前目录）
-
-            用 gh pr checks ${{ github.event.pull_request.number }} --repo ${{ github.repository }} 查询这个 PR 已有的检查结果，必要时读取对应 Actions 日志。不要触发新的 CI，也不要把合并本身当作检查通过的证据；管理员可能绕过门禁。检查失败、缺失或尚未完成时如实报告。
+            你负责本次 PR 的 ${{ matrix.name }}，在独立上下文中完成审查。
+            仓库：${{ github.repository }}；PR：#${{ github.event.pull_request.number }}。
+            合并提交：${{ github.event.pull_request.merge_commit_sha }}，已检出到当前目录。
+            先用 gh pr diff ${{ github.event.pull_request.number }} --repo ${{ github.repository }} 读取变更清单与完整差异，再检查相关文件。
 
-            任务：给飞书群发一张中文卡片（Card 2.0）总结这次 CI，尽量在 10 轮以内给出结论，工具调用尽可能的并行。
-            环境里有 gh（已登录，GH_TOKEN）、git、node 和完整的仓库代码。
+            ${{ matrix.instructions }}
 
-            卡片要让手机上的读者快速看懂，如果一切正常，表达的尽可能简单，如果没有问题，尽量简洁：
-            1. 哪个 PR（github id + PR 标题 + 链接）
-              - 如：`github id: jing332, PR 标题: 添加一个新功能, 链接: https://github.com/org/repo/pull/123`
-            2. 改了什么（实际行为变化，1–3 条）
-              - 如：`添加了一个新功能、修改了 web 和 backend 的 CI`
-            3. 是否符合仓库规则（AGENTS.md、CONTRIBUTING.md 及相关文档）：未发现明确违规 / 发现需修复问题 / 信息不足，无法确认
-              - 如：`符合仓库规则`
-            4. CI 哪里失败、可能的原因（可以看日志），全部通过就直接说通过，不要给出细节。如果 CI 失败，则详细说明。
-              - 如：`CI 失败，具体是哪几个失败；全部通过 ✅`
-
-            发送：webhook 地址在环境变量 FEISHU_WEBHOOK_URL。
-            响应 code=0 才算成功，失败就排查并重试，直到发出去。最后用一句中文说明结果，如：`CI 结果已发送至飞书群`。
-            不要在输出里打印 webhook 地址和密钥。
+            按 JSON schema 返回中文报告。status 为 ok（未发现问题）、issues（发现有证据的问题）或 incomplete（审查失败、范围未检查完整或检查结果尚未完成）。有问题且仍有未检查项时，用 issues 并在对应字段中说明缺项。按 schema 把各项结论分别填入字段，不要重复标题；changes 用 1–3 条 Markdown 列表，其他字段无问题时一句话，有问题时保留依据和建议，遵守各字段长度限制。
+            围绕本次 diff 和受影响的文档展开，证据充分后输出结果，避免重复核对同一结论。
+            只读审查，不修改仓库，不触发新的 CI，不发送消息。两份报告会由后续 job 合并发送。
           claude_args: >-
-            --allowedTools Bash Read Write Edit Glob Grep WebFetch WebSearch
-            --max-turns 30
+            --allowedTools Bash Read Glob Grep
+            --json-schema '${{ steps.schema.outputs.schema }}'
+      - name: Save the review result
+        if: always()
+        env:
+          REVIEW_OUTCOME: ${{ steps.llm.outcome }}
+          REVIEW_RESULT: ${{ steps.llm.outputs.structured_output }}
+        run: python3 scripts/ci_review.py collect "${{ matrix.kind }}" "$RUNNER_TEMP/review-${{ matrix.kind }}.json"
+      - uses: actions/upload-artifact@v6
+        if: always()
+        with:
+          name: ci-review-${{ matrix.kind }}
+          path: ${{ runner.temp }}/review-${{ matrix.kind }}.json
+          if-no-files-found: error
+          overwrite: true
+          retention-days: 7
+
+  notify:
+    name: Combined Feishu notification
+    needs: review
+    if: always() && github.event.pull_request.merged == true
+    runs-on: ${{ vars.OAC_USE_GITHUB_RUNNERS == 'true' && 'ubuntu-24.04' || 'blacksmith-2vcpu-ubuntu-2404' }}
+    timeout-minutes: 5
+    permissions:
+      contents: read
+      actions: read
+    steps:
+      - uses: actions/checkout@v7
+        with:
+          ref: ${{ github.event.pull_request.merge_commit_sha }}
+          persist-credentials: false
+      - uses: actions/download-artifact@v6
+        continue-on-error: true
+        with:
+          pattern: ci-review-*
+          merge-multiple: true
+          path: ${{ runner.temp }}/reviews
+      - name: Send one card with both results
+        continue-on-error: true
+        env:
+          FEISHU_WEBHOOK_URL: ${{ secrets.FEISHU_WEBHOOK_URL }}
+          FEISHU_WEBHOOK_SECRET: ${{ secrets.FEISHU_WEBHOOK_SECRET }}
+        run: python3 scripts/ci_review.py notify "$RUNNER_TEMP/reviews"
diff --git a/.github/workflows/native.yml b/.github/workflows/native.yml
index 7be750d35..c901adc6f 100644
--- a/.github/workflows/native.yml
+++ b/.github/workflows/native.yml
@@ -63,6 +63,14 @@ jobs:
         run: |
           go build -ldflags "-X github.com/MiniMax-AI/OpenAgentCore/apps/daemon/internal/cli.Version=$(git rev-parse HEAD)" -o "$RUNNER_TEMP/oac-daemon${{ runner.os == 'Windows' && '.exe' || '' }}" ./apps/daemon/cmd/oac-daemon
           node --test scripts/build-native-installer.test.mjs
+      - name: Build and test the shared Core installer
+        run: |
+          go build -o "$RUNNER_TEMP/oac${{ runner.os == 'Windows' && '.exe' || '' }}" ./services/core/cmd/oac
+          go test ./services/core/cmd/oac -count=1 -timeout=3m
+      - name: Exercise the Windows Core launcher
+        if: runner.os == 'Windows'
+        shell: pwsh
+        run: ./deploy/test_install.ps1 -Binary "$env:RUNNER_TEMP/oac.exe"
       - name: Verify native download bootstrap and recovery
         run: go test ./services/core/internal/nativeinstaller -count=1 -timeout=3m
       - name: Native filesystem, authentication and process lifecycle
@@ -163,3 +171,17 @@ jobs:
           path: ${{ runner.temp }}/native-ci-diagnostics/
           retention-days: 7
           if-no-files-found: ignore
+
+  core-intel-mac:
+    name: Core installer (macOS Intel)
+    runs-on: macos-15-intel
+    timeout-minutes: 10
+    steps:
+      - uses: actions/checkout@v7
+        with:
+          ref: ${{ inputs.ref || github.sha }}
+      - uses: actions/setup-go@v7
+        with:
+          go-version-file: go.mod
+      - run: go test ./services/core/cmd/oac -count=1 -timeout=3m
+      - run: go build -o "$RUNNER_TEMP/oac" ./services/core/cmd/oac
diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
index d798c1976..c8ff4ab28 100644
--- a/.github/workflows/release.yml
+++ b/.github/workflows/release.yml
@@ -114,6 +114,9 @@ jobs:
           path: ${{ runner.temp }}/native-artifacts
       - name: Assemble the native installation catalog
         run: node scripts/build-native-catalog.mjs "$RUNNER_TEMP/native-artifacts" "$RUNNER_TEMP/native-installers"
+      - uses: docker/setup-qemu-action@v3
+        with:
+          platforms: arm64
       - uses: ./.github/actions/e2b-provider
       - name: Build matched artifacts
         env:
@@ -133,8 +136,8 @@ jobs:
           for asset in "$HOME/.oac/build/core-distribution/"*; do
             if [[ -f "$asset" ]]; then ln "$asset" "$HOME/.oac/build/release-upload/"; fi
           done
-          cp deploy/install.sh "$HOME/.oac/build/release-upload/install.sh"
-          (cd "$HOME/.oac/build/release-upload" && sha256sum install.sh > install.sh.sha256)
+          cp deploy/install.sh deploy/install.ps1 "$HOME/.oac/build/release-upload/"
+          (cd "$HOME/.oac/build/release-upload" && sha256sum install.sh > install.sh.sha256 && sha256sum install.ps1 > install.ps1.sha256)
       - name: Sign in to GHCR
         if: github.event_name == 'push' || inputs.draft_release
         env:
diff --git a/AGENTS.md b/AGENTS.md
index 93d98a834..f292b1bb1 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -25,7 +25,7 @@ Do not multiply entities without necessity. The long-term goal is minimal code,
 
 | Boundary | Protocol code | Protocol doc |
 | --- | --- | --- |
-| Application–Core (`/v1`) | Types in `contracts/agents-api/v1/` and route annotations in `services/core/internal/api/`; `make openapi` generates `contracts/agents-api/openapi.yaml` | [Agents API guide](docs/api/public-agent-api.md) |
+| Application–Core (`/v1`) | Official schema pinned by `contracts/agents-api/upstream.json` plus Go-owned `x_agents_core` extensions; `make openapi` generates public Go types and `contracts/agents-api/openapi.yaml` | [Agents API guide](docs/api/public-agent-api.md) |
 | Web and operators–Core (`/core/v1`) | Route annotations in `services/core/internal/api/`; `make openapi` generates `contracts/agents-api/core.openapi.yaml` | [Core administration API](contracts/agents-api/admin-api.md) |
 | Nodes and daemons–Core (`/api/v1` HTTP routes; the node and daemon wire protocols are separate rows) | Route annotations in `services/core/internal/api/`; `make openapi` generates `contracts/agents-api/runtime.openapi.yaml` | [Machine connection API](contracts/agents-api/machine-api.md) |
 | Core–Sandbox Provider | `services/core/internal/sandbox/sandbox_provider.go` | [Sandbox Provider guide](docs/sandbox-provider.md) |
diff --git a/Makefile b/Makefile
index f755dec39..a8825f1ee 100644
--- a/Makefile
+++ b/Makefile
@@ -32,21 +32,28 @@ sqlc-generate:
 
 SWAG ?= go run github.com/swaggo/swag/cmd/swag@$(SWAG_VERSION)
 
-.PHONY: openapi
+.PHONY: openapi check-openapi
+OPENAPI_FLAGS ?=
+check-openapi:
+	$(MAKE) openapi OPENAPI_FLAGS=--check
+	python3 scripts/generate-public-api.test.py
+
 openapi:
 	@set -e; root="$${OAC_DEV_HOME:-$$HOME/.oac}/build"; mkdir -p "$$root"; \
 	output=$$(mktemp -d "$$root/core-openapi.XXXXXX"); trap 'rm -rf "$$output"' EXIT; \
+	python3 scripts/generate-public-api.py $(OPENAPI_FLAGS) --swag-roots "$$output/roots.go"; \
 	$(SWAG) init \
-	    -g cmd/server/main.go --dir ./services/core,./contracts/agents-api/v1 \
+	    -g cmd/server/main.go --dir "./services/core,./contracts/agents-api/v1,$$output" \
 	    --output "$$output" \
 	    --outputTypes yaml --parseInternal; \
 	python3 scripts/patch-agents-openapi.py "$$output/swagger.yaml"; \
-	go run ./scripts/openapi-split "$$output/swagger.yaml" contracts/agents-api/openapi.yaml contracts/agents-api/core.openapi.yaml contracts/agents-api/runtime.openapi.yaml
+	go run ./scripts/openapi-split $(OPENAPI_FLAGS) "$$output/swagger.yaml" "$$output/extensions.json" contracts/agents-api/core.openapi.yaml contracts/agents-api/runtime.openapi.yaml; \
+	python3 scripts/generate-public-api.py $(OPENAPI_FLAGS) --extensions "$$output/extensions.json"
 
 check-sqlc:
 	python3 scripts/check-sqlc.py
 
-check-go:
+check-go: check-openapi
 	go test ./apps/daemon/... ./apps/sandboxio/... ./internal/... ./contracts/agents-api/... ./scripts/openapi-split -count=1
 
 .PHONY: check-runtime-contract
@@ -183,7 +190,7 @@ check-microsandbox-provider:
 .PHONY: check-distribution build-core-distribution
 check-distribution:
 	node --test scripts/build-native-catalog.test.mjs
-	go test ./services/web -count=1
+	go test ./services/web ./services/core/cmd/oac -count=1
 	PYTHONDONTWRITEBYTECODE=1 python3 -m unittest discover -s deploy/node -p 'test_*.py'
 	PYTHONDONTWRITEBYTECODE=1 python3 -m unittest discover -s deploy/compose -p 'test_*.py'
 	PYTHONDONTWRITEBYTECODE=1 python3 -m unittest discover -s scripts/acceptance -p 'test_*.py'
diff --git a/README.md b/README.md
index 5713ac292..d8056f965 100644
--- a/README.md
+++ b/README.md
@@ -42,12 +42,18 @@ Core keeps durable execution state. The Runtime runs the chosen harness inside t
 
 ## Install
 
-On a Linux amd64 host with Docker and Python 3.9+:
+On Linux or macOS with [Docker configured](https://openagentcore.dev/docs/getting-started/install#prerequisites):
 
 ```sh
 curl -fsSL https://github.com/MiniMax-AI/OpenAgentCore/releases/latest/download/install.sh | bash
 ```
 
+Windows PowerShell:
+
+```powershell
+irm https://github.com/MiniMax-AI/OpenAgentCore/releases/latest/download/install.ps1 | iex
+```
+
 Then:
 
 1. **Sign in to Web**, the admin console, with the Core key the installer created, and **configure the domain and HTTPS**.
diff --git a/README.zh-CN.md b/README.zh-CN.md
index 5414cea3c..fb55a62a5 100644
--- a/README.zh-CN.md
+++ b/README.zh-CN.md
@@ -42,12 +42,18 @@ OpenAgentCore 在你自己的基础设施上运行 AI Agent，对外提供 [Open
 
 ## 安装
 
-在已准备 Docker 和 Python 3.9+ 的 Linux amd64 主机上：
+在已按[前置条件](https://openagentcore.dev/zh/docs/getting-started/install#prerequisites)准备 Docker 的 Linux 或 macOS 上：
 
 ```sh
 curl -fsSL https://github.com/MiniMax-AI/OpenAgentCore/releases/latest/download/install.sh | bash
 ```
 
+Windows PowerShell:
+
+```powershell
+irm https://github.com/MiniMax-AI/OpenAgentCore/releases/latest/download/install.ps1 | iex
+```
+
 然后：
 
 1. 用安装器生成的 Core key **登录 Web**（管理控制台），并**配置域名和 HTTPS**。
diff --git a/apps/daemon/internal/agent/claudesdk/cancellation_live_linux_test.go b/apps/daemon/internal/agent/claudesdk/cancellation_live_linux_test.go
index 86f7e0cf0..f64e333b0 100644
--- a/apps/daemon/internal/agent/claudesdk/cancellation_live_linux_test.go
+++ b/apps/daemon/internal/agent/claudesdk/cancellation_live_linux_test.go
@@ -67,7 +67,7 @@ func TestLiveClaudeSDKCancelResume(t *testing.T) {
 		defer cancel()
 		out := make(chan proto.Envelope, 64)
 		request := proto.PromptRequestPayload{RunID: uuid.NewString(), Input: proto.TextInput(prompt), AgentSessionID: resume, ObserveMessages: true, DisableExecutionEnvironment: true, DisableSubagents: true, ExecutionControls: &proto.ExecutionControls{WebSearch: "disabled", TextVerbosity: "medium"}, Model: "MiniMax-M3", ModelProvider: provider, SystemPrompt: "Follow the user's requested format. Preserve the exact verification value in conversation history. Use no tools."}
-		running, err := NewFactory(config)(ctx, request, out)
+		running, err := startSingleTurn(ctx, config, request, out)
 		if err != nil {
 			t.Fatal(err)
 		}
diff --git a/apps/daemon/internal/agent/claudesdk/cancellation_test.go b/apps/daemon/internal/agent/claudesdk/cancellation_test.go
index 8672981b1..5b2c991e7 100644
--- a/apps/daemon/internal/agent/claudesdk/cancellation_test.go
+++ b/apps/daemon/internal/agent/claudesdk/cancellation_test.go
@@ -27,7 +27,7 @@ func TestCancellationWaitsForDrainAndPublishesOutcome(t *testing.T) {
 	defer cancel()
 	// A stopped consumer must not prevent native output draining or cancellation.
 	out := make(chan proto.Envelope)
-	running, err := NewFactory(config)(ctx, cancellationRequest(), out)
+	running, err := startSingleTurn(ctx, config, cancellationRequest(), out)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -89,7 +89,7 @@ func TestFailureKeepsOnlyVerifiedNativeIdentity(t *testing.T) {
 			ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
 			defer cancel()
 			out := make(chan proto.Envelope, 8)
-			running, err := NewFactory(cancellationConfig(root, mode))(ctx, cancellationRequest(), out)
+			running, err := startSingleTurn(ctx, cancellationConfig(root, mode), cancellationRequest(), out)
 			if err != nil {
 				t.Fatal(err)
 			}
@@ -125,7 +125,7 @@ func TestCancellationDrainsIntoReadyConsumer(t *testing.T) {
 	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
 	defer cancel()
 	out := make(chan proto.Envelope, 16)
-	running, err := NewFactory(config)(ctx, cancellationRequest(), out)
+	running, err := startSingleTurn(ctx, config, cancellationRequest(), out)
 	if err != nil {
 		t.Fatal(err)
 	}
diff --git a/apps/daemon/internal/agent/claudesdk/commands_session_test.go b/apps/daemon/internal/agent/claudesdk/commands_session_test.go
index 8ed414dc4..b19a7584e 100644
--- a/apps/daemon/internal/agent/claudesdk/commands_session_test.go
+++ b/apps/daemon/internal/agent/claudesdk/commands_session_test.go
@@ -77,7 +77,7 @@ func TestWorkspaceCommandCancellationAndBridgeFailuresCloseOnlyPendingCalls(t *t
 			req := workspaceRequest()
 			req.AgentSessionID = "native-session"
 			out := make(chan proto.Envelope, 32)
-			s, err := NewFactory(config)(ctx, req, out)
+			s, err := startSingleTurn(ctx, config, req, out)
 			if err != nil {
 				t.Fatal(err)
 			}
diff --git a/apps/daemon/internal/agent/claudesdk/contracts.go b/apps/daemon/internal/agent/claudesdk/contracts.go
index c35ebb6a8..aaf9e92aa 100644
--- a/apps/daemon/internal/agent/claudesdk/contracts.go
+++ b/apps/daemon/internal/agent/claudesdk/contracts.go
@@ -11,8 +11,6 @@ var (
 	_ agent.DurableSteerer           = (*session)(nil)
 	_ agent.Steerer                  = (*session)(nil)
 	_ agent.FunctionResultSubmitter  = (*session)(nil)
-	_ agent.PermissionResponder      = (*session)(nil)
-	_ agent.UserChoiceResponder      = (*session)(nil)
 	_ agent.WorkspaceDirectoryLister = (*session)(nil)
 	_ agent.WorkspaceWriter          = (*session)(nil)
 	_ agent.WorkspaceDirectoryLister = (*executor)(nil)
diff --git a/apps/daemon/internal/agent/claudesdk/declaration.go b/apps/daemon/internal/agent/claudesdk/declaration.go
index 840861b26..c17df1372 100644
--- a/apps/daemon/internal/agent/claudesdk/declaration.go
+++ b/apps/daemon/internal/agent/claudesdk/declaration.go
@@ -22,7 +22,6 @@ const claudeSDKNodeEnv = "OAC_RUNTIME_CLAUDE_SDK_NODE"
 var Declaration = agent.Declaration{Info: proto.SupportedAgentKind{Kind: "claude_sdk", Capabilities: proto.AgentKindCapabilities{
 	SubagentObservations:           proto.CapabilityUnsupported,
 	Streaming:                      proto.CapabilitySupported,
-	Permissions:                    proto.CapabilityUnsupported,
 	Usage:                          proto.CapabilitySupported,
 	Resume:                         proto.CapabilitySupported,
 	NativeSessionRecovery:          proto.CapabilityUnsupported,
@@ -59,9 +58,7 @@ func discoverWithCheck(parent context.Context, options agent.DiscoveryOptions, d
 	if entrypoint == "" {
 		return nil
 	}
-	out := &agent.Runtime{Info: descriptor, Session: func(context.Context, proto.PromptRequestPayload, chan<- proto.Envelope) (agent.Session, error) {
-		return nil, fmt.Errorf("claude_sdk: configured runtime is unavailable")
-	}}
+	out := &agent.Runtime{Info: descriptor}
 	var config Config
 
 	fail := func(err error) *agent.Runtime {
@@ -119,8 +116,8 @@ func discoverWithCheck(parent context.Context, options agent.DiscoveryOptions, d
 		}
 		caps := &out.Info.Capabilities
 		caps.EnvironmentNone, caps.FunctionTools = proto.CapabilityUnsupported, proto.CapabilityFromBool(info.SupportsWorkspaceFunctions())
-		caps.Preparation, caps.LocalEnvironment = proto.CapabilitySupported, proto.CapabilitySupported
-		caps.WorkspaceReadPreparation, caps.NativeSessionRecovery = proto.CapabilitySupported, proto.CapabilitySupported
+		caps.LocalEnvironment, caps.WorkspaceReadPreparation = proto.CapabilitySupported, proto.CapabilitySupported
+		caps.NativeSessionRecovery = proto.CapabilitySupported
 	}
 	out.Info.Available, out.Info.Version = true, info.SDK
 	out.Info.Capabilities.MessageImages = proto.CapabilityFromBool(info.SupportsMessageImages())
@@ -141,7 +138,6 @@ func discoverWithCheck(parent context.Context, options agent.DiscoveryOptions, d
 		out.Info.Capabilities.MCPHTTPTools, out.Info.Capabilities.MCPHTTPBearerAuth = proto.CapabilityUnsupported, proto.CapabilityUnsupported
 		out.Info.Capabilities.MCPHTTPRequired = proto.CapabilityUnsupported
 	}
-	out.Session = NewFactory(config)
 	out.Executor = NewExecutorFactory(config)
 	// The view runs the same install; its probe stays on this host.
 	if view, err := newView(Config{Node: node, Entrypoint: entrypoint}, info); err != nil {
diff --git a/apps/daemon/internal/agent/claudesdk/declaration_test.go b/apps/daemon/internal/agent/claudesdk/declaration_test.go
index e1a3691e3..9181b5454 100644
--- a/apps/daemon/internal/agent/claudesdk/declaration_test.go
+++ b/apps/daemon/internal/agent/claudesdk/declaration_test.go
@@ -125,12 +125,6 @@ func TestRuntimeDiscoveryConfigurationAndRegistration(t *testing.T) {
 			if info.Capabilities.Preparation.IsSupported() != ready {
 				t.Fatal(info)
 			}
-			if !ready {
-				factory, _ := registry.Resolve("claude_sdk")
-				if _, err := factory(t.Context(), proto.PromptRequestPayload{Model: "fixture", ModelProvider: fixtureProvider()}, nil); err == nil || !strings.Contains(err.Error(), "runtime is unavailable") {
-					t.Fatal(err)
-				}
-			}
 		}
 	}
 }
diff --git a/apps/daemon/internal/agent/claudesdk/error_classification_test.go b/apps/daemon/internal/agent/claudesdk/error_classification_test.go
index 3fbd8f8a8..12ed95144 100644
--- a/apps/daemon/internal/agent/claudesdk/error_classification_test.go
+++ b/apps/daemon/internal/agent/claudesdk/error_classification_test.go
@@ -25,7 +25,7 @@ func TestClassifiedBridgeFailurePreservesTerminalEvidence(t *testing.T) {
 			ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
 			defer cancel()
 			out := make(chan proto.Envelope, 16)
-			s, err := NewFactory(config)(ctx, req, out)
+			s, err := startSingleTurn(ctx, config, req, out)
 			if err != nil {
 				t.Fatal(err)
 			}
diff --git a/apps/daemon/internal/agent/claudesdk/execution_controls_test.go b/apps/daemon/internal/agent/claudesdk/execution_controls_test.go
index 4e10c4b7a..0fea3251d 100644
--- a/apps/daemon/internal/agent/claudesdk/execution_controls_test.go
+++ b/apps/daemon/internal/agent/claudesdk/execution_controls_test.go
@@ -50,7 +50,7 @@ func TestExecutionControlsRejectUnsupportedProfilesBeforeLaunch(t *testing.T) {
 			t.Setenv("OAC_RUNTIME_HOME", root)
 			config := Config{Node: "must-not-run", Entrypoint: filepath.Join(root, "worker"), StateDir: filepath.Join(root, "state")}
 			request := proto.PromptRequestPayload{ModelProvider: fixtureProvider(), RunID: "run", Input: proto.TextInput("Original input."), ExecutionControls: &controls, Model: "native-model"}
-			_, err := NewFactory(config)(t.Context(), request, make(chan proto.Envelope, 1))
+			_, err := startSingleTurn(t.Context(), config, request, make(chan proto.Envelope, 1))
 			if err == nil || !strings.Contains(err.Error(), "execution controls require") {
 				t.Fatal("unsupported controls did not fail at admission", err)
 			}
@@ -67,7 +67,7 @@ func TestMCPWithoutEnvironmentNoneRejectedBeforeSetup(t *testing.T) {
 	config := Config{Node: "must-not-run", Entrypoint: filepath.Join(root, "worker"), StateDir: filepath.Join(root, "state")}
 	servers := []proto.MCPHTTPServer{{ConnectionOrigin: "service", ServerLabel: "remote", ServerURL: "https://example.test/mcp"}}
 	request := proto.PromptRequestPayload{RunID: "run", Input: proto.TextInput("Input"), MCPHTTPServers: &servers, Model: "fixture", ModelProvider: fixtureProvider()}
-	_, err := NewFactory(config)(t.Context(), request, make(chan proto.Envelope, 1))
+	_, err := startSingleTurn(t.Context(), config, request, make(chan proto.Envelope, 1))
 	if err == nil || !strings.Contains(err.Error(), "service-origin MCP requires a service execution host") {
 		t.Fatal("MCP reached an unsupported environment", err)
 	}
diff --git a/apps/daemon/internal/agent/claudesdk/executor_fixture_test.go b/apps/daemon/internal/agent/claudesdk/executor_fixture_test.go
index 55768099f..15d683ccf 100644
--- a/apps/daemon/internal/agent/claudesdk/executor_fixture_test.go
+++ b/apps/daemon/internal/agent/claudesdk/executor_fixture_test.go
@@ -4,10 +4,32 @@ package claudesdk
 
 import (
 	"bufio"
+	"context"
 	"encoding/json"
 	"os"
+
+	"github.com/MiniMax-AI/OpenAgentCore/apps/daemon/internal/agent"
+	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
 )
 
+// startSingleTurn prepares an Executor for one Turn and closes it once that
+// Turn settles, so each test observes the complete native lifecycle.
+func startSingleTurn(ctx context.Context, config Config, req proto.PromptRequestPayload, out chan<- proto.Envelope) (agent.Turn, error) {
+	run, input := req.RunID, req.Input
+	req.RunID, req.Input = "", nil
+	resource, err := NewExecutorFactory(config)(ctx, req)
+	if err != nil {
+		return nil, err
+	}
+	turn, err := resource.StartTurn(ctx, run, input, out)
+	if turn == nil {
+		_ = resource.Close(context.Background())
+		return nil, err
+	}
+	go func() { _, _ = turn.AwaitSettlement(context.Background()); _ = resource.Close(context.Background()) }()
+	return turn, err
+}
+
 func helperTurn(scanner *bufio.Scanner, request *startRequest) (func(bridgeEvent), func()) {
 	_ = json.NewEncoder(os.Stdout).Encode(bridgeEvent{Type: "executor_ready", Protocol: 3})
 	if !scanner.Scan() {
diff --git a/apps/daemon/internal/agent/claudesdk/functions_test.go b/apps/daemon/internal/agent/claudesdk/functions_test.go
index b1fe6f442..d0ff4d060 100644
--- a/apps/daemon/internal/agent/claudesdk/functions_test.go
+++ b/apps/daemon/internal/agent/claudesdk/functions_test.go
@@ -26,7 +26,7 @@ func TestFunctionFactoryNativeReceipts(t *testing.T) {
 			ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
 			defer cancel()
 			out := make(chan proto.Envelope, 16)
-			running, err := NewFactory(config)(ctx, request, out)
+			running, err := startSingleTurn(ctx, config, request, out)
 			if err != nil {
 				t.Fatal(err)
 			}
diff --git a/apps/daemon/internal/agent/claudesdk/live_linux_test.go b/apps/daemon/internal/agent/claudesdk/live_linux_test.go
index bda17a491..a1eafaac8 100644
--- a/apps/daemon/internal/agent/claudesdk/live_linux_test.go
+++ b/apps/daemon/internal/agent/claudesdk/live_linux_test.go
@@ -143,7 +143,7 @@ func TestLiveClaudeSDKTextResume(t *testing.T) {
 			request.SystemPrompt = "Call lookup exactly once as requested, then report both result parts and any prior verification value. Never retry a failed tool."
 			request.FunctionTools = []proto.FunctionTool{{Name: "lookup", Description: "Return a synthetic verification value.", Parameters: json.RawMessage(`{"type":"object","properties":{"id":{"type":"string"}},"required":["id"],"additionalProperties":false}`)}}
 		}
-		running, err := NewFactory(config)(ctx, request, out)
+		running, err := startSingleTurn(ctx, config, request, out)
 		if err != nil {
 			t.Fatal(err)
 		}
@@ -269,7 +269,7 @@ func TestLiveClaudeSDKTextResume(t *testing.T) {
 				proof.SessionID, _ = payload.Metadata[proto.DoneMetaAgentSessionID].(string)
 			}
 		}
-		// Done reports the Turn outcome; the direct factory closes its Executor
+		// Done reports the Turn outcome; startSingleTurn closes its Executor
 		// after output settlement. Verify release at that boundary.
 		if _, err := s.AwaitSettlement(ctx); err != nil {
 			t.Fatal(err)
@@ -277,7 +277,7 @@ func TestLiveClaudeSDKTextResume(t *testing.T) {
 		select {
 		case <-s.process.Done():
 		case <-time.After(5 * time.Second):
-			t.Fatal("direct factory retained its process after settlement")
+			t.Fatal("single-Turn Executor retained its process after settlement")
 		}
 		if !steeringAt.IsZero() {
 			receipt := <-steeringReply
diff --git a/apps/daemon/internal/agent/claudesdk/messages_test.go b/apps/daemon/internal/agent/claudesdk/messages_test.go
index 5481adbd7..130bd5fb9 100644
--- a/apps/daemon/internal/agent/claudesdk/messages_test.go
+++ b/apps/daemon/internal/agent/claudesdk/messages_test.go
@@ -24,7 +24,7 @@ func TestMessageObservations(t *testing.T) {
 			ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
 			defer cancel()
 			out := make(chan proto.Envelope, 16)
-			running, err := NewFactory(config)(ctx, request, out)
+			running, err := startSingleTurn(ctx, config, request, out)
 			if err != nil {
 				t.Fatal(err)
 			}
diff --git a/apps/daemon/internal/agent/claudesdk/readiness_test.go b/apps/daemon/internal/agent/claudesdk/readiness_test.go
index e322ed385..286f90799 100644
--- a/apps/daemon/internal/agent/claudesdk/readiness_test.go
+++ b/apps/daemon/internal/agent/claudesdk/readiness_test.go
@@ -25,7 +25,7 @@ func TestRequiredMCPNeedsQualifiedRuntime(t *testing.T) {
 	}}
 	req := proto.PromptRequestPayload{ModelProvider: fixtureProvider(), RunID: "run", Input: proto.TextInput("hello"), DisableExecutionEnvironment: true,
 		Model: "fixture", MCPHTTPServers: &[]proto.MCPHTTPServer{{ConnectionOrigin: "service", ServerLabel: "fixture", ServerURL: "https://example.invalid/mcp", Required: true}}}
-	if _, err := NewFactory(config)(t.Context(), req, make(chan proto.Envelope, 1)); err == nil || err.Error() != "claudesdk: packaged runtime does not support required HTTP MCP" {
+	if _, err := startSingleTurn(t.Context(), config, req, make(chan proto.Envelope, 1)); err == nil || err.Error() != "claudesdk: packaged runtime does not support required HTTP MCP" {
 		t.Fatalf("unqualified runtime executed required MCP: %v", err)
 	}
 }
@@ -46,7 +46,7 @@ func TestHTTPMCPRejectsOldPackagedRuntime(t *testing.T) {
 	}
 	req := proto.PromptRequestPayload{ModelProvider: fixtureProvider(), RunID: "run", Input: proto.TextInput("hello"), DisableExecutionEnvironment: true,
 		Model: "fixture", MCPHTTPServers: &[]proto.MCPHTTPServer{{ConnectionOrigin: "service", ServerLabel: "fixture", ServerURL: "https://example.invalid/mcp"}}}
-	if _, err := NewFactory(config)(t.Context(), req, make(chan proto.Envelope, 1)); err == nil || !strings.Contains(err.Error(), "packaged runtime does not support HTTP MCP") {
+	if _, err := startSingleTurn(t.Context(), config, req, make(chan proto.Envelope, 1)); err == nil || !strings.Contains(err.Error(), "packaged runtime does not support HTTP MCP") {
 		t.Fatalf("old runtime was not rejected before execution: %v", err)
 	}
 }
@@ -83,7 +83,7 @@ func TestMCPBearerRejectsAnonymousOnlyRuntimeWithoutProbeSecrets(t *testing.T) {
 	token := "private-fixture-token"
 	req := proto.PromptRequestPayload{ModelProvider: fixtureProvider(), RunID: "run", Input: proto.TextInput("hello"), DisableExecutionEnvironment: true,
 		Model: "fixture", MCPHTTPServers: &[]proto.MCPHTTPServer{{ConnectionOrigin: "service", ServerLabel: "fixture", ServerURL: "https://example.invalid/mcp", BearerToken: &token}}}
-	if _, err := NewFactory(config)(t.Context(), req, make(chan proto.Envelope, 1)); err == nil || err.Error() != "claudesdk: packaged runtime does not support authenticated HTTP MCP" {
+	if _, err := startSingleTurn(t.Context(), config, req, make(chan proto.Envelope, 1)); err == nil || err.Error() != "claudesdk: packaged runtime does not support authenticated HTTP MCP" {
 		t.Fatalf("old runtime executed authenticated request or readiness received its secret: %v", err)
 	}
 }
diff --git a/apps/daemon/internal/agent/claudesdk/restrictions_test.go b/apps/daemon/internal/agent/claudesdk/restrictions_test.go
index cb080ae77..6fc389905 100644
--- a/apps/daemon/internal/agent/claudesdk/restrictions_test.go
+++ b/apps/daemon/internal/agent/claudesdk/restrictions_test.go
@@ -29,7 +29,7 @@ func TestTextFactoryAcceptsRestrictiveCapabilities(t *testing.T) {
 			ctx, cancel := context.WithTimeout(t.Context(), 5*time.Second)
 			defer cancel()
 			out := make(chan proto.Envelope, 16)
-			running, err := NewFactory(config)(ctx, request, out)
+			running, err := startSingleTurn(ctx, config, request, out)
 			if err != nil {
 				t.Fatal(err)
 			}
diff --git a/apps/daemon/internal/agent/claudesdk/session.go b/apps/daemon/internal/agent/claudesdk/session.go
index 770d212b8..fcf91d376 100644
--- a/apps/daemon/internal/agent/claudesdk/session.go
+++ b/apps/daemon/internal/agent/claudesdk/session.go
@@ -32,27 +32,6 @@ type session struct {
 	outcome     proto.DonePayload
 }
 
-func NewFactory(config Config) agent.Factory {
-	prepareExecutor := NewExecutorFactory(config)
-	return func(ctx context.Context, req proto.PromptRequestPayload, out chan<- proto.Envelope) (agent.Session, error) {
-		run, input := req.RunID, req.Input
-		req.RunID, req.Input = "", nil
-		resource, err := prepareExecutor(ctx, req)
-		if err != nil {
-			return nil, err
-		}
-		turn, err := resource.StartTurn(ctx, run, input, out)
-		if turn == nil {
-			_ = resource.Close(context.Background())
-			return nil, err
-		}
-		// Factory callers own one execution. Both entrypoints use the same
-		// Executor implementation; Runtime pooling uses NewExecutorFactory.
-		go func() { _, _ = turn.AwaitSettlement(context.Background()); _ = resource.Close(context.Background()) }()
-		return turn, err
-	}
-}
-
 type bridgeEvent struct {
 	EngineErrorCode json.RawMessage `json:"engine_error_code"`
 	TurnID          string          `json:"turn_id"`
diff --git a/apps/daemon/internal/agent/claudesdk/session_test.go b/apps/daemon/internal/agent/claudesdk/session_test.go
index 679f156c3..811e8041f 100644
--- a/apps/daemon/internal/agent/claudesdk/session_test.go
+++ b/apps/daemon/internal/agent/claudesdk/session_test.go
@@ -26,7 +26,7 @@ func TestTextFactoryCompletionAndFailures(t *testing.T) {
 			ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
 			defer cancel()
 			out := make(chan proto.Envelope, 16)
-			s, err := NewFactory(config)(ctx, request, out)
+			s, err := startSingleTurn(ctx, config, request, out)
 			if err != nil {
 				t.Fatal(err)
 			}
@@ -88,7 +88,7 @@ func TestTextFactoryRejectsUnsupportedInput(t *testing.T) {
 			case "outside":
 				config.StateDir = filepath.Dir(root)
 			}
-			_, err := NewFactory(config)(context.Background(), request, make(chan proto.Envelope, 1))
+			_, err := startSingleTurn(context.Background(), config, request, make(chan proto.Envelope, 1))
 			if err == nil || !strings.HasPrefix(err.Error(), "claudesdk:") {
 				t.Fatalf("expected pre-launch rejection, got %v", err)
 			}
diff --git a/apps/daemon/internal/agent/claudesdk/steering_test.go b/apps/daemon/internal/agent/claudesdk/steering_test.go
index 4157aeaab..25343a2e2 100644
--- a/apps/daemon/internal/agent/claudesdk/steering_test.go
+++ b/apps/daemon/internal/agent/claudesdk/steering_test.go
@@ -31,7 +31,7 @@ func TestSteeringReceiptsAndLifecycle(t *testing.T) {
 			ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
 			defer cancel()
 			out := make(chan proto.Envelope, 16)
-			running, err := NewFactory(config)(ctx, request, out)
+			running, err := startSingleTurn(ctx, config, request, out)
 			if err != nil {
 				t.Fatal(err)
 			}
diff --git a/apps/daemon/internal/agent/claudesdk/unsupported.go b/apps/daemon/internal/agent/claudesdk/unsupported.go
index 0b4da8274..154d904a4 100644
--- a/apps/daemon/internal/agent/claudesdk/unsupported.go
+++ b/apps/daemon/internal/agent/claudesdk/unsupported.go
@@ -2,19 +2,10 @@ package claudesdk
 
 import (
 	"context"
-	"fmt"
+
 	"github.com/MiniMax-AI/OpenAgentCore/apps/daemon/internal/agent"
-	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
 )
 
-func (s *session) SubmitPermission(context.Context, string, proto.PermissionDecisionPayload) error {
-	return fmt.Errorf("%w: native permission responses are not exposed", agent.ErrUnsupportedOperation)
-}
-
-func (s *session) SubmitPromptForUserChoice(context.Context, string, proto.PromptForUserChoiceDecisionPayload) error {
-	return fmt.Errorf("%w: native user-choice responses are not exposed", agent.ErrUnsupportedOperation)
-}
-
 func (s *executor) WriteWorkspaceFile(context.Context, string, []byte) (agent.WorkspaceWriteResult, error) {
 	return agent.WorkspaceWriteResult{}, agent.ErrWorkspaceWriteUnsupported
 }
diff --git a/apps/daemon/internal/agent/claudesdk/unsupported_test.go b/apps/daemon/internal/agent/claudesdk/unsupported_test.go
index d57a25856..7fe6048c5 100644
--- a/apps/daemon/internal/agent/claudesdk/unsupported_test.go
+++ b/apps/daemon/internal/agent/claudesdk/unsupported_test.go
@@ -7,7 +7,6 @@ import (
 	"testing"
 
 	"github.com/MiniMax-AI/OpenAgentCore/apps/daemon/internal/agent"
-	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
 )
 
 // Nil concrete receivers prove Unsupported needs no native owner, transport,
@@ -25,9 +24,6 @@ func TestUnsupportedExtensionsHaveNoNativeEffects(t *testing.T) {
 			t.Fatal("unsupported error disclosed input")
 		}
 	}
-	var turn *session
-	check(turn.SubmitPermission(ctx, secret, proto.PermissionDecisionPayload{}))
-	check(turn.SubmitPromptForUserChoice(ctx, secret, proto.PromptForUserChoiceDecisionPayload{}))
 	for _, owner := range []agent.WorkspaceWriter{(*executor)(nil), (*session)(nil)} {
 		result, err := owner.WriteWorkspaceFile(ctx, secret, []byte(secret))
 		check(err)
diff --git a/apps/daemon/internal/agent/claudesdk/usage_test.go b/apps/daemon/internal/agent/claudesdk/usage_test.go
index 299078c5e..82b845c05 100644
--- a/apps/daemon/internal/agent/claudesdk/usage_test.go
+++ b/apps/daemon/internal/agent/claudesdk/usage_test.go
@@ -27,7 +27,7 @@ func TestUsageTransportPreservesSnapshotOnFailureAndDone(t *testing.T) {
 			ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
 			defer cancel()
 			out := make(chan proto.Envelope, 16)
-			s, err := NewFactory(config)(ctx, request, out)
+			s, err := startSingleTurn(ctx, config, request, out)
 			if err != nil {
 				t.Fatal(err)
 			}
diff --git a/apps/daemon/internal/agent/claudesdk/view_test.go b/apps/daemon/internal/agent/claudesdk/view_test.go
index ba6a24729..a7123f622 100644
--- a/apps/daemon/internal/agent/claudesdk/view_test.go
+++ b/apps/daemon/internal/agent/claudesdk/view_test.go
@@ -180,7 +180,7 @@ func resolveTestView(t *testing.T) agent.View {
 	loader := viewloader.Fragment{Closure: []agent.ViewMount{lib}, Overlays: []agent.ViewOverlay{{Path: "/lib64/ld-linux-x86-64.so.2", Source: filepath.Join(root, "lib", "ld.so"), Exec: true}}, LibraryPath: lib.Path()}
 	declared := declareView(probe, RuntimeInfo{NativePath: "native/claude"}, probe.Node, filepath.Join(root, "bundle"), "dist/main.js", loader)
 	registry := agent.NewRegistry()
-	registry.Register(Declaration, agent.Runtime{Info: Declaration.Info, Session: NewFactory(probe), View: declared})
+	registry.Register(Declaration, agent.Runtime{Info: Declaration.Info, View: declared})
 	view, err := registry.ResolveView(Declaration.Info.Kind)
 	if err != nil {
 		t.Fatal(err)
diff --git a/apps/daemon/internal/agent/claudesdk/workspace_launch_test.go b/apps/daemon/internal/agent/claudesdk/workspace_launch_test.go
index b95cda8fd..f9b109e90 100644
--- a/apps/daemon/internal/agent/claudesdk/workspace_launch_test.go
+++ b/apps/daemon/internal/agent/claudesdk/workspace_launch_test.go
@@ -41,7 +41,7 @@ esac
 		t.Fatal("readiness did not receive replacement environment", err)
 	}
 	out := make(chan proto.Envelope, 8)
-	s, err := NewFactory(config)(t.Context(), workspaceRequest(), out)
+	s, err := startSingleTurn(t.Context(), config, workspaceRequest(), out)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -64,7 +64,7 @@ esac
 	if err := os.WriteFile(config.Node, []byte(script), 0o700); err != nil {
 		t.Fatal(err)
 	}
-	if _, err := NewFactory(config)(t.Context(), workspaceRequest(), out); err == nil {
+	if _, err := startSingleTurn(t.Context(), config, workspaceRequest(), out); err == nil {
 		t.Fatal("old packaged bridge accepted workspace execution")
 	}
 	if _, err := os.Stat(filepath.Join(config.StateDir, "unexpected-start")); !os.IsNotExist(err) {
diff --git a/apps/daemon/internal/agent/claudesdk/workspace_live_linux_test.go b/apps/daemon/internal/agent/claudesdk/workspace_live_linux_test.go
index c0c65d862..7a93ef048 100644
--- a/apps/daemon/internal/agent/claudesdk/workspace_live_linux_test.go
+++ b/apps/daemon/internal/agent/claudesdk/workspace_live_linux_test.go
@@ -93,7 +93,7 @@ func TestLiveClaudeWorkspaceFactory(t *testing.T) {
 		req.ObserveMessages = true
 		req.Model, req.SystemPrompt = "MiniMax-M3", "Follow the exact verification instructions using the requested native tools. Preserve conversation facts. No other files, network operations or background work."
 		proof := evidence{RunID: req.RunID}
-		running, err := NewFactory(config)(ctx, req, out)
+		running, err := startSingleTurn(ctx, config, req, out)
 		if err != nil {
 			if name == "missing-history" && running == nil && strings.Contains(err.Error(), "history_unavailable") {
 				proof.Failure = err.Error()
diff --git a/apps/daemon/internal/agent/codex/approval_policy.go b/apps/daemon/internal/agent/codex/approval_policy.go
deleted file mode 100644
index 9b084e4da..000000000
--- a/apps/daemon/internal/agent/codex/approval_policy.go
+++ /dev/null
@@ -1,85 +0,0 @@
-package codex
-
-import (
-	"encoding/json"
-	"fmt"
-)
-
-// SilentGranularPolicy disables every granular Codex approval gate.
-func SilentGranularPolicy() AskForApproval {
-	g := GranularAskForApproval{} // zero value = every gate false
-	return AskForApproval{Granular: &g}
-}
-
-// HumanApprovalPolicy lets Codex request sandbox escalation from Core.
-func HumanApprovalPolicy() AskForApproval {
-	return AskForApproval{String: "on-request"}
-}
-
-// IsSilent reports whether p suppresses every approval surface. The
-// daemon logs this distinction when it starts a thread. Server-request
-// handlers are always registered so explicit policy overrides cannot leave
-// Codex waiting on an unhandled request.
-//
-// A nil pointer is treated as silent — the safe default when callers
-// forget to wire a policy.
-func IsSilent(p *AskForApproval) bool {
-	if p == nil {
-		return true
-	}
-	if p.Granular != nil {
-		g := p.Granular
-		return !g.SandboxApproval && !g.Rules && !g.SkillApproval &&
-			!g.RequestPermissions && !g.MCPElicitations
-	}
-	// Bare string variants ("never" is silent; everything else surfaces).
-	return p.String == "never"
-}
-
-// MarshalJSON emits codex-rs's discriminated union — either a bare
-// string or the granular object. Producing both would deserialise to
-// the granular branch on the codex side (it wins precedence in
-// codex-rs/protocol.rs AskForApproval), but the wire would be wrong; we
-// validate exclusivity here.
-func (a AskForApproval) MarshalJSON() ([]byte, error) {
-	hasString := a.String != ""
-	hasGranular := a.Granular != nil
-	if hasString && hasGranular {
-		return nil, fmt.Errorf("codex: AskForApproval must set exactly one of String or Granular, got both")
-	}
-	if hasString {
-		return json.Marshal(a.String)
-	}
-	if hasGranular {
-		return json.Marshal(struct {
-			Granular *GranularAskForApproval `json:"granular"`
-		}{Granular: a.Granular})
-	}
-	// Neither set — preserve the historical zero-value encoding. Production
-	// plans always set a policy explicitly; an empty marshal would
-	// produce `null`, which codex-rs rejects.
-	return json.Marshal(struct {
-		Granular GranularAskForApproval `json:"granular"`
-	}{})
-}
-
-// UnmarshalJSON is the inverse: codex's ThreadStartResult.approvalPolicy
-// echoes back as either a string or {"granular":...}. Provided so tests
-// can round-trip without surprises; production code only marshals.
-func (a *AskForApproval) UnmarshalJSON(data []byte) error {
-	var s string
-	if err := json.Unmarshal(data, &s); err == nil {
-		a.String = s
-		a.Granular = nil
-		return nil
-	}
-	var obj struct {
-		Granular *GranularAskForApproval `json:"granular"`
-	}
-	if err := json.Unmarshal(data, &obj); err != nil {
-		return fmt.Errorf("codex: AskForApproval: %w", err)
-	}
-	a.Granular = obj.Granular
-	a.String = ""
-	return nil
-}
diff --git a/apps/daemon/internal/agent/codex/approval_policy_test.go b/apps/daemon/internal/agent/codex/approval_policy_test.go
deleted file mode 100644
index 7a98f06cd..000000000
--- a/apps/daemon/internal/agent/codex/approval_policy_test.go
+++ /dev/null
@@ -1,142 +0,0 @@
-package codex
-
-import (
-	"encoding/json"
-	"testing"
-)
-
-func TestSilentGranularPolicy_AllFalse(t *testing.T) {
-	p := SilentGranularPolicy()
-	if p.Granular == nil {
-		t.Fatal("SilentGranularPolicy must populate Granular")
-	}
-	g := *p.Granular
-	if g.SandboxApproval || g.Rules || g.SkillApproval || g.RequestPermissions || g.MCPElicitations {
-		t.Fatalf("silent policy must have every gate false, got %+v", g)
-	}
-	if !IsSilent(&p) {
-		t.Fatal("IsSilent must return true for the silent default")
-	}
-}
-
-func TestHumanApprovalPolicy_UsesOnRequest(t *testing.T) {
-	p := HumanApprovalPolicy()
-	if p.String != "on-request" || p.Granular != nil {
-		t.Fatalf("HumanApprovalPolicy = %+v, want on-request string policy", p)
-	}
-	if IsSilent(&p) {
-		t.Fatal("HumanApprovalPolicy must surface app-server requests")
-	}
-}
-
-func TestIsSilent_NilIsSilent(t *testing.T) {
-	if !IsSilent(nil) {
-		t.Fatal("nil policy must be treated as silent (safe default)")
-	}
-}
-
-func TestIsSilent_StringPolicies(t *testing.T) {
-	cases := []struct {
-		name   string
-		policy AskForApproval
-		want   bool
-	}{
-		{"never silences", AskForApproval{String: "never"}, true},
-		{"on-request loud", AskForApproval{String: "on-request"}, false},
-		{"untrusted loud", AskForApproval{String: "untrusted"}, false},
-	}
-	for _, tc := range cases {
-		t.Run(tc.name, func(t *testing.T) {
-			if got := IsSilent(&tc.policy); got != tc.want {
-				t.Fatalf("IsSilent(%+v) = %v, want %v", tc.policy, got, tc.want)
-			}
-		})
-	}
-}
-
-func TestIsSilent_PartialGranularIsLoud(t *testing.T) {
-	// Flipping any single gate true must make IsSilent report false so
-	// the daemon registers the loud server-request handler.
-	for _, flip := range []func(*GranularAskForApproval){
-		func(g *GranularAskForApproval) { g.SandboxApproval = true },
-		func(g *GranularAskForApproval) { g.Rules = true },
-		func(g *GranularAskForApproval) { g.SkillApproval = true },
-		func(g *GranularAskForApproval) { g.RequestPermissions = true },
-		func(g *GranularAskForApproval) { g.MCPElicitations = true },
-	} {
-		g := GranularAskForApproval{}
-		flip(&g)
-		p := AskForApproval{Granular: &g}
-		if IsSilent(&p) {
-			t.Fatalf("IsSilent must be false when any gate is true: %+v", g)
-		}
-	}
-}
-
-func TestAskForApproval_MarshalString(t *testing.T) {
-	p := AskForApproval{String: "never"}
-	raw, err := json.Marshal(p)
-	if err != nil {
-		t.Fatalf("marshal: %v", err)
-	}
-	if string(raw) != `"never"` {
-		t.Fatalf("marshal string variant = %s", raw)
-	}
-}
-
-func TestAskForApproval_MarshalGranular(t *testing.T) {
-	g := GranularAskForApproval{RequestPermissions: true}
-	p := AskForApproval{Granular: &g}
-	raw, err := json.Marshal(p)
-	if err != nil {
-		t.Fatalf("marshal: %v", err)
-	}
-	want := `{"granular":{"sandbox_approval":false,"rules":false,"skill_approval":false,"request_permissions":true,"mcp_elicitations":false}}`
-	if string(raw) != want {
-		t.Fatalf("marshal granular = %s\nwant = %s", raw, want)
-	}
-}
-
-func TestAskForApproval_MarshalEmpty_DefaultsSilent(t *testing.T) {
-	// Neither field set — must not produce `null` (codex rejects it).
-	var p AskForApproval
-	raw, err := json.Marshal(p)
-	if err != nil {
-		t.Fatalf("marshal: %v", err)
-	}
-	if string(raw) == "null" {
-		t.Fatalf("empty AskForApproval must not marshal to null: %s", raw)
-	}
-	if string(raw) != `{"granular":{"sandbox_approval":false,"rules":false,"skill_approval":false,"request_permissions":false,"mcp_elicitations":false}}` {
-		t.Fatalf("empty AskForApproval marshal = %s", raw)
-	}
-}
-
-func TestAskForApproval_MarshalBothErrors(t *testing.T) {
-	g := GranularAskForApproval{}
-	p := AskForApproval{String: "never", Granular: &g}
-	if _, err := json.Marshal(p); err == nil {
-		t.Fatal("setting both String and Granular must error on marshal")
-	}
-}
-
-func TestAskForApproval_RoundTripString(t *testing.T) {
-	var got AskForApproval
-	if err := json.Unmarshal([]byte(`"on-request"`), &got); err != nil {
-		t.Fatalf("unmarshal: %v", err)
-	}
-	if got.String != "on-request" || got.Granular != nil {
-		t.Fatalf("round-trip = %+v", got)
-	}
-}
-
-func TestAskForApproval_RoundTripGranular(t *testing.T) {
-	src := `{"granular":{"sandbox_approval":true,"rules":false,"skill_approval":false,"request_permissions":false,"mcp_elicitations":false}}`
-	var got AskForApproval
-	if err := json.Unmarshal([]byte(src), &got); err != nil {
-		t.Fatalf("unmarshal: %v", err)
-	}
-	if got.Granular == nil || !got.Granular.SandboxApproval || got.String != "" {
-		t.Fatalf("round-trip = %+v", got)
-	}
-}
diff --git a/apps/daemon/internal/agent/codex/contracts.go b/apps/daemon/internal/agent/codex/contracts.go
index 7a19d9eb8..a8b58b88e 100644
--- a/apps/daemon/internal/agent/codex/contracts.go
+++ b/apps/daemon/internal/agent/codex/contracts.go
@@ -11,8 +11,6 @@ var (
 	_ agent.DurableSteerer           = (*Session)(nil)
 	_ agent.Steerer                  = (*Session)(nil)
 	_ agent.FunctionResultSubmitter  = (*Session)(nil)
-	_ agent.PermissionResponder      = (*Session)(nil)
-	_ agent.UserChoiceResponder      = (*Session)(nil)
 	_ agent.WorkspaceDirectoryLister = (*Session)(nil)
 	_ agent.WorkspaceWriter          = (*Session)(nil)
 	_ agent.WorkspaceDirectoryLister = (*Executor)(nil)
diff --git a/apps/daemon/internal/agent/codex/declaration.go b/apps/daemon/internal/agent/codex/declaration.go
index 49f2c528d..2b497b07e 100644
--- a/apps/daemon/internal/agent/codex/declaration.go
+++ b/apps/daemon/internal/agent/codex/declaration.go
@@ -16,7 +16,6 @@ var Declaration = agent.Declaration{Info: proto.SupportedAgentKind{
 	Capabilities: proto.AgentKindCapabilities{
 		SubagentObservations:           proto.CapabilitySupported,
 		Streaming:                      proto.CapabilitySupported,
-		Permissions:                    proto.CapabilitySupported,
 		Usage:                          proto.CapabilitySupported,
 		Resume:                         proto.CapabilitySupported,
 		NativeSessionRecovery:          proto.CapabilityUnsupported,
@@ -50,7 +49,7 @@ func discover(ctx context.Context, options agent.DiscoveryOptions, info proto.Su
 	return discoverWithCheck(ctx, options, info, CheckCLIAvailable)
 }
 func discoverWithCheck(parent context.Context, options agent.DiscoveryOptions, info proto.SupportedAgentKind, check func(context.Context, string) (string, error)) *agent.Runtime {
-	runtime := &agent.Runtime{Info: info, Session: Factory}
+	runtime := &agent.Runtime{Info: info}
 	ctx, cancel := context.WithTimeout(parent, 15*time.Second)
 	defer cancel()
 	version, err := check(ctx, "")
diff --git a/apps/daemon/internal/agent/codex/declaration_test.go b/apps/daemon/internal/agent/codex/declaration_test.go
index b059fef73..65a4460c4 100644
--- a/apps/daemon/internal/agent/codex/declaration_test.go
+++ b/apps/daemon/internal/agent/codex/declaration_test.go
@@ -29,7 +29,7 @@ func TestMCPRequiredDiscoveryRequiresPinnedNative(t *testing.T) {
 
 // The declaration must retain the complete baseline capability descriptor.
 func TestDeclaredCapabilityBaseline(t *testing.T) {
-	expected := map[string]bool{"SubagentObservations": true, "Streaming": true, "Permissions": true, "Usage": true, "Resume": true, "Steering": true, "MessageItems": true, "ToolObservations": true, "EnvironmentNone": true, "ProgrammaticToolCallingDisable": true, "WebSearchControl": true, "MessageImages": true, "FunctionResultImages": true, "SubagentControl": true, "DurableInputReceipts": true, "DurableTurns": true, "FunctionTools": true, "MCPHTTPTools": true, "MCPHTTPBearerAuth": true}
+	expected := map[string]bool{"SubagentObservations": true, "Streaming": true, "Usage": true, "Resume": true, "Steering": true, "MessageItems": true, "ToolObservations": true, "EnvironmentNone": true, "ProgrammaticToolCallingDisable": true, "WebSearchControl": true, "MessageImages": true, "FunctionResultImages": true, "SubagentControl": true, "DurableInputReceipts": true, "DurableTurns": true, "FunctionTools": true, "MCPHTTPTools": true, "MCPHTTPBearerAuth": true}
 	expected["ExecutionControls"], expected["TextVerbosity"] = SupportsTextVerbosity, SupportsTextVerbosity
 	value := reflect.ValueOf(Declaration.Info.Capabilities)
 	for i := 0; i < value.NumField(); i++ {
@@ -49,7 +49,7 @@ func TestDeclaredCapabilityBaseline(t *testing.T) {
 
 func TestUnavailableRuntimeHasNoExecutionFactories(t *testing.T) {
 	runtime := discoverWithCheck(t.Context(), agent.DiscoveryOptions{Stdout: io.Discard, Stderr: io.Discard}, Declaration.Info, func(context.Context, string) (string, error) { return "", errors.New("missing") })
-	if runtime.Info.Available || runtime.Executor != nil || runtime.View != nil || runtime.Session == nil {
+	if runtime.Info.Available || runtime.Executor != nil || runtime.View != nil {
 		t.Fatalf("unavailable runtime: %+v", runtime)
 	}
 }
diff --git a/apps/daemon/internal/agent/codex/execution_controls_test.go b/apps/daemon/internal/agent/codex/execution_controls_test.go
index 182a48fb0..3b9260110 100644
--- a/apps/daemon/internal/agent/codex/execution_controls_test.go
+++ b/apps/daemon/internal/agent/codex/execution_controls_test.go
@@ -14,7 +14,7 @@ func TestExecutionControlsSelectNativeSettings(t *testing.T) {
 		t.Fatal(err)
 	}
 	plan.Cleanup()
-	if len(plan.ExtraConfig) != 1 || plan.ExtraConfig[0][0] != "model_provider" {
+	if want := [][2]string{{"tools.experimental_request_user_input.enabled", "false"}, {"model_provider", `"` + oacProviderSlug + `"`}}; !reflect.DeepEqual(plan.ExtraConfig, want) {
 		t.Fatal("native settings without ExecutionControls", plan.ExtraConfig)
 	}
 	for _, search := range []string{"disabled", "cached", "live"} {
@@ -24,7 +24,7 @@ func TestExecutionControlsSelectNativeSettings(t *testing.T) {
 				t.Fatal(err)
 			}
 			plan.Cleanup()
-			want := [][2]string{{"web_search", `"` + search + `"`}, {"model_verbosity", `"` + verbosity + `"`}, {"model_provider", `"` + oacProviderSlug + `"`}}
+			want := [][2]string{{"tools.experimental_request_user_input.enabled", "false"}, {"web_search", `"` + search + `"`}, {"model_verbosity", `"` + verbosity + `"`}, {"model_provider", `"` + oacProviderSlug + `"`}}
 			if !reflect.DeepEqual(plan.ExtraConfig, want) {
 				t.Fatalf("config = %v, want %v", plan.ExtraConfig, want)
 			}
diff --git a/apps/daemon/internal/agent/codex/executor.go b/apps/daemon/internal/agent/codex/executor.go
index 75403c57d..d8997e525 100644
--- a/apps/daemon/internal/agent/codex/executor.go
+++ b/apps/daemon/internal/agent/codex/executor.go
@@ -72,7 +72,7 @@ func (e *Executor) StartTurn(ctx context.Context, runID string, input proto.Mess
 		functions: functions, observeMessages: base.observeMessages, observeSubagentIdentities: base.observeSubagentIdentities,
 		cfg: base.cfg, rpc: base.rpc, cancelCtx: turnCtx, cancelFn: cancel,
 		waitDone: make(chan struct{}), outputDone: make(chan struct{}), cleanup: func() {},
-		bufs: NewItemBuffers(), resolvedModel: base.resolvedModel, interactions: newPendingCodexInteractions(), runID: runID, out: out}
+		bufs: NewItemBuffers(), resolvedModel: base.resolvedModel, runID: runID, out: out}
 	if previous != nil {
 		s.threadID = previous.currentThreadID()
 		s.retiredTurns = make(map[string]bool, len(previous.retiredTurns)+1)
diff --git a/apps/daemon/internal/agent/codex/executor_native_test.go b/apps/daemon/internal/agent/codex/executor_native_test.go
index 9505d4b50..762ef7389 100644
--- a/apps/daemon/internal/agent/codex/executor_native_test.go
+++ b/apps/daemon/internal/agent/codex/executor_native_test.go
@@ -3,6 +3,7 @@ package codex
 import (
 	"context"
 	"encoding/json"
+	"log/slog"
 	"os"
 	"os/exec"
 	"strings"
@@ -12,7 +13,6 @@ import (
 	"github.com/MiniMax-AI/OpenAgentCore/apps/daemon/internal/agent"
 	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
 	"github.com/MiniMax-AI/OpenAgentCore/internal/modelprovider"
-	obslog "github.com/MiniMax-AI/OpenAgentCore/internal/obs/log"
 )
 
 // This opt-in test uses the real pinned harness and an explicitly configured
@@ -48,7 +48,7 @@ func TestExecutorNativeReuse(t *testing.T) {
 	}
 	cfg := defaultSessionConfig()
 	cfg.codexBinary = binary
-	cfg.logger = obslog.Discard()
+	cfg.logger = slog.New(slog.DiscardHandler)
 	req := proto.PromptRequestPayload{
 		AgentKind: "codex", AgentStateKey: "executor-native",
 		DisableExecutionEnvironment: true, DisableSubagents: true, ObserveMessages: true,
diff --git a/apps/daemon/internal/agent/codex/executor_test.go b/apps/daemon/internal/agent/codex/executor_test.go
index 954f00869..9c88a0579 100644
--- a/apps/daemon/internal/agent/codex/executor_test.go
+++ b/apps/daemon/internal/agent/codex/executor_test.go
@@ -2,8 +2,10 @@ package codex
 
 import (
 	"context"
+	"encoding/json"
 	"errors"
 	"os"
+	"strings"
 	"sync"
 	"sync/atomic"
 	"testing"
@@ -17,22 +19,32 @@ import (
 func executorFixture(t *testing.T, mode string) (*Executor, string) {
 	t.Helper()
 	req, cfg, root := preparationFixture(t)
+	e, err := testExecutor(t, mode, req, cfg)
+	if err != nil {
+		t.Fatal(err)
+	}
+	return e, root
+}
+
+// testExecutor prepares through the production factory and closes the owner at cleanup.
+func testExecutor(t *testing.T, mode string, req proto.PromptRequestPayload, cfg sessionConfig) (*Executor, error) {
+	t.Helper()
 	t.Setenv("OAC_TEST_EXECUTOR_MODE", mode)
 	ownerCtx, cancelOwner := context.WithCancel(context.Background())
 	t.Cleanup(cancelOwner)
 	e, err := newExecutor(ownerCtx, req, cfg)
-	if err != nil {
-		t.Fatal(err)
+	if e != nil {
+		t.Cleanup(func() {
+			ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+			defer cancel()
+			if err := e.Close(ctx); err != nil {
+				t.Error(err)
+			}
+		})
 	}
-	t.Cleanup(func() {
-		ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-		defer cancel()
-		if err := e.Close(ctx); err != nil {
-			t.Error(err)
-		}
-	})
-	return e, root
+	return e, err
 }
+
 func awaitExecutorTurn(t *testing.T, turn agent.Turn, out <-chan proto.Envelope) agent.TurnSettlement {
 	t.Helper()
 	ctx, cancel := context.WithTimeout(t.Context(), 5*time.Second)
@@ -52,6 +64,21 @@ func awaitExecutorTurn(t *testing.T, turn agent.Turn, out <-chan proto.Envelope)
 	}
 	return settlement
 }
+
+// settledFrames waits for a Turn to settle and returns its complete output.
+func settledFrames(t *testing.T, turn agent.Turn, out <-chan proto.Envelope) []proto.Envelope {
+	t.Helper()
+	ctx, cancel := context.WithTimeout(t.Context(), 5*time.Second)
+	defer cancel()
+	if _, err := turn.AwaitSettlement(ctx); errors.Is(err, context.DeadlineExceeded) {
+		t.Fatal("Turn did not settle")
+	}
+	var frames []proto.Envelope
+	for frame := range out {
+		frames = append(frames, frame)
+	}
+	return frames
+}
 func TestExecutorNormalTurnsKeepProcessAndThread(t *testing.T) {
 	e, root := executorFixture(t, "complete")
 	var previous agent.Turn
@@ -84,6 +111,95 @@ func TestExecutorNormalTurnsKeepProcessAndThread(t *testing.T) {
 		t.Fatal("normal completion closed executor")
 	}
 }
+func TestExecutorFreezesPreparedConfiguration(t *testing.T) {
+	for _, resume := range []bool{false, true} {
+		t.Run(map[bool]string{false: "new", true: "resumed"}[resume], func(t *testing.T) {
+			req, cfg, root := preparationFixture(t)
+			expectedThread := "thread/start"
+			if resume {
+				req.AgentSessionID, expectedThread = "fixture-native-thread", "thread/resume"
+			}
+			e, err := testExecutor(t, "complete", req, cfg)
+			if err != nil {
+				t.Fatal(err)
+			}
+			assertPreparationOnly(t, root)
+			cwd := e.prepared.plan.Cwd
+			// Caller-owned data cannot revise the prepared native configuration.
+			req.Model = "different-model"
+			req.AgentSessionID = "different-thread"
+			copy(req.FunctionTools[0].Parameters, strings.ReplaceAll(string(req.FunctionTools[0].Parameters), "integer", "boolean"))
+			out := make(chan proto.Envelope, 20)
+			turn, err := e.StartTurn(t.Context(), "actual-run", proto.TextInput("actual prompt"), out)
+			if err != nil {
+				t.Fatal(err)
+			}
+			awaitExecutorTurn(t, turn, out)
+			counts := map[string]int{}
+			for _, frame := range preparationFrames(t, root) {
+				counts[frame.Method]++
+				var params struct {
+					Model        string                `json:"model"`
+					ThreadID     string                `json:"threadId"`
+					DynamicTools []dynamicFunctionTool `json:"dynamicTools"`
+					Cwd          string                `json:"cwd"`
+					Environments json.RawMessage       `json:"environments"`
+				}
+				if err := json.Unmarshal(frame.Params, &params); err != nil {
+					t.Fatal(err)
+				}
+				if frame.Method == "thread/start" && (params.Model != "fixture-model" || len(params.DynamicTools) != 1 ||
+					!strings.Contains(string(params.DynamicTools[0].InputSchema), "integer") || params.Cwd != cwd) {
+					t.Fatal("prepared configuration changed", string(frame.Params))
+				}
+				if frame.Method == "thread/resume" && params.ThreadID != "fixture-native-thread" {
+					t.Fatal("prepared resume changed")
+				}
+				if len(params.Environments) != 0 {
+					t.Fatal("prepared environment changed")
+				}
+			}
+			if counts["initialize"] != 1 || counts["environment/status"] != 2 || counts[expectedThread] != 1 || counts["turn/start"] != 1 {
+				t.Fatal("unexpected native setup/start count", counts)
+			}
+		})
+	}
+}
+
+func TestExecutorUnavailableOwnerStartsNoTurn(t *testing.T) {
+	for _, reason := range []string{"closed", "owner cancelled", "rpc exited"} {
+		t.Run(reason, func(t *testing.T) {
+			req, cfg, root := preparationFixture(t)
+			owner, cancelOwner := context.WithCancel(context.Background())
+			defer cancelOwner()
+			e, err := newExecutor(owner, req, cfg)
+			if err != nil {
+				t.Fatal(err)
+			}
+			defer e.Close(context.Background())
+			switch reason {
+			case "closed":
+				err = e.Close(t.Context())
+			case "owner cancelled":
+				cancelOwner()
+			case "rpc exited":
+				err = e.prepared.session.rpc.Close()
+			}
+			if err != nil {
+				t.Fatal(err)
+			}
+			out := make(chan proto.Envelope, 1)
+			if turn, err := e.StartTurn(t.Context(), "late-run", proto.TextInput("must not start"), out); turn != nil || err == nil {
+				t.Fatal("unavailable executor started a Turn", err)
+			}
+			if len(out) != 0 {
+				t.Fatal("rejected start emitted output")
+			}
+			assertPreparationOnly(t, root)
+		})
+	}
+}
+
 func TestExecutorCancellationSettlesThenReuses(t *testing.T) {
 	e, root := executorFixture(t, "complete")
 	out := make(chan proto.Envelope, 20)
diff --git a/apps/daemon/internal/agent/codex/executor_turn.go b/apps/daemon/internal/agent/codex/executor_turn.go
index d02eb988c..60746293f 100644
--- a/apps/daemon/internal/agent/codex/executor_turn.go
+++ b/apps/daemon/internal/agent/codex/executor_turn.go
@@ -44,7 +44,6 @@ func (s *Session) settleExecutorTurn(startErr error) {
 	s.operationMu.Unlock()
 	s.stopSteering()
 	s.stopFunctionCalls()
-	s.stopCodexInteractionTimers()
 	if !s.nativeSettled.Load() || startErr != nil || !s.rpc.Alive() {
 		s.cancelFn()
 		s.settlementErr = errors.Join(s.settlementErr, s.rpc.Close())
@@ -120,7 +119,6 @@ func (s *Session) cancelExecutorTurn(ctx context.Context) error {
 			defer close(s.cancelReady)
 			s.stopFunctionCalls()
 			turnID, active := s.stopSteering()
-			s.stopCodexInteractionTimers()
 			if !s.terminal.Load() && active {
 				if turnID == "" {
 					s.cancelErr = errors.New("codex: cancellation has no native turn identity")
@@ -150,9 +148,7 @@ func (s *Session) cancelExecutorTurn(ctx context.Context) error {
 
 var _ agent.Turn = (*Session)(nil)
 
-// Server callbacks retain their originating Turn. MCP elicitation may be a
-// standalone thread-scoped request in the native protocol; a supplied Turn ID
-// must still match exactly.
+// Server callbacks retain their originating Turn, whose ID must match exactly.
 func (s *Session) onServerRequest(method string, handler ServerRequestHandler) {
 	s.rpc.OnServerRequest(method, func(raw json.RawMessage, id any) (any, error) {
 		if s.executor != nil {
@@ -161,8 +157,7 @@ func (s *Session) onServerRequest(method string, handler ServerRequestHandler) {
 				TurnID   string `json:"turnId"`
 			}
 			if json.Unmarshal(raw, &scope) != nil || !s.isRootThread(scope.ThreadID) || s.terminal.Load() ||
-				(scope.TurnID != "" && !s.isRootTurn(scope.ThreadID, scope.TurnID)) ||
-				(scope.TurnID == "" && method != "mcpServer/elicitation/request") {
+				scope.TurnID == "" || !s.isRootTurn(scope.ThreadID, scope.TurnID) {
 				return nil, errors.New("codex: request does not belong to the active turn")
 			}
 		}
diff --git a/apps/daemon/internal/agent/codex/function_receipt_test.go b/apps/daemon/internal/agent/codex/function_receipt_test.go
index decbf235e..fd138a009 100644
--- a/apps/daemon/internal/agent/codex/function_receipt_test.go
+++ b/apps/daemon/internal/agent/codex/function_receipt_test.go
@@ -16,7 +16,7 @@ import (
 func TestFunctionResultWaitsForNativeCompletion(t *testing.T) {
 	client, server, cleanup := NewTestClient()
 	defer cleanup()
-	session, output := newInteractionTestSession(client.JSONRPCClient)
+	session, output := newFunctionTestSession(client.JSONRPCClient)
 	session.setThreadID("thread")
 	session.startSteering("thread", "turn")
 	var err error
@@ -61,7 +61,7 @@ func pendingReceiptContext(t *testing.T, ctx context.Context) (*Session, ServerS
 	t.Helper()
 	client, server, cleanup := NewTestClient()
 	t.Cleanup(cleanup)
-	s, out := newInteractionTestSession(client.JSONRPCClient)
+	s, out := newFunctionTestSession(client.JSONRPCClient)
 	s.cfg.logger = slog.New(slog.NewTextHandler(io.Discard, nil))
 	s.setThreadID("thread")
 	s.startSteering("thread", "turn")
@@ -169,7 +169,7 @@ func TestFunctionReceiptShutdownDoesNotConfirmApplication(t *testing.T) {
 func TestFunctionReceiptDeadlineEndsUncertainExecution(t *testing.T) {
 	client, server, cleanup := NewTestClient()
 	defer cleanup()
-	s, out := newInteractionTestSession(client.JSONRPCClient)
+	s, out := newFunctionTestSession(client.JSONRPCClient)
 	s.setThreadID("thread")
 	s.startSteering("thread", "turn")
 	s.functions, _ = prepareFunctionTools([]proto.FunctionTool{{Name: "lookup", Parameters: json.RawMessage(`{}`)}})
@@ -207,7 +207,7 @@ func TestFunctionReceiptDeadlineEndsUncertainExecution(t *testing.T) {
 func TestFunctionReceiptWinsSimultaneousDeadline(t *testing.T) {
 	for range 100 {
 		client, _, cleanup := NewTestClient()
-		s, _ := newInteractionTestSession(client.JSONRPCClient)
+		s, _ := newFunctionTestSession(client.JSONRPCClient)
 		s.setThreadID("thread")
 		s.startSteering("thread", "turn")
 		s.functions, _ = prepareFunctionTools(nil)
diff --git a/apps/daemon/internal/agent/codex/function_write_receipt_test.go b/apps/daemon/internal/agent/codex/function_write_receipt_test.go
index 49cdc6826..7e6730647 100644
--- a/apps/daemon/internal/agent/codex/function_write_receipt_test.go
+++ b/apps/daemon/internal/agent/codex/function_write_receipt_test.go
@@ -31,7 +31,7 @@ func (w *confirmedResultWriter) Close() error { w.once.Do(func() { close(w.close
 func TestFunctionConfirmedReceiptDuringWriteDeadline(t *testing.T) {
 	client, _, cleanup := NewTestClient()
 	defer cleanup()
-	s, out := newInteractionTestSession(client.JSONRPCClient)
+	s, out := newFunctionTestSession(client.JSONRPCClient)
 	s.setThreadID("thread")
 	s.startSteering("thread", "turn")
 	s.functions, _ = prepareFunctionTools([]proto.FunctionTool{{Name: "lookup", Parameters: json.RawMessage(`{}`)}})
@@ -64,7 +64,7 @@ func TestFunctionConfirmedReceiptDuringWriteDeadline(t *testing.T) {
 func TestFunctionUnconfirmedWriteDeadlineClosesNative(t *testing.T) {
 	client, _, cleanup := NewTestClient()
 	defer cleanup()
-	s, out := newInteractionTestSession(client.JSONRPCClient)
+	s, out := newFunctionTestSession(client.JSONRPCClient)
 	s.setThreadID("thread")
 	s.startSteering("thread", "turn")
 	s.functions, _ = prepareFunctionTools([]proto.FunctionTool{{Name: "lookup", Parameters: json.RawMessage(`{}`)}})
diff --git a/apps/daemon/internal/agent/codex/functions_test.go b/apps/daemon/internal/agent/codex/functions_test.go
index 1fc34979f..a2fd9c752 100644
--- a/apps/daemon/internal/agent/codex/functions_test.go
+++ b/apps/daemon/internal/agent/codex/functions_test.go
@@ -12,12 +12,20 @@ import (
 	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
 )
 
+func newFunctionTestSession(rpc *JSONRPCClient) (*Session, <-chan proto.Envelope) {
+	out := make(chan proto.Envelope, 1)
+	ctx, cancel := context.WithCancel(context.Background())
+	s := &Session{runID: "run-test", out: out, rpc: rpc, cancelCtx: ctx, cancelFn: cancel}
+	s.registerHandlers()
+	return s, out
+}
+
 func TestFunctionCallWaitsAndRepliesOnce(t *testing.T) {
 	for _, success := range []bool{true, false} {
 		t.Run(map[bool]string{true: "success", false: "failure"}[success], func(t *testing.T) {
 			tc, srv, cleanup := NewTestClient()
 			defer cleanup()
-			s, out := newInteractionTestSession(tc.JSONRPCClient)
+			s, out := newFunctionTestSession(tc.JSONRPCClient)
 			var err error
 			s.functions, err = prepareFunctionTools([]proto.FunctionTool{{Name: "lookup", Parameters: json.RawMessage(`{"type":"object"}`)}})
 			if err != nil {
@@ -88,7 +96,7 @@ func TestFunctionCallWaitsAndRepliesOnce(t *testing.T) {
 func TestFunctionCallRejectsUnregisteredAndClosedRuns(t *testing.T) {
 	tc, _, cleanup := NewTestClient()
 	defer cleanup()
-	s, _ := newInteractionTestSession(tc.JSONRPCClient)
+	s, _ := newFunctionTestSession(tc.JSONRPCClient)
 	s.setThreadID("thread")
 	s.startSteering("thread", "turn")
 	s.functions, _ = prepareFunctionTools([]proto.FunctionTool{{Name: "lookup", Parameters: json.RawMessage(`{}`)}})
diff --git a/apps/daemon/internal/agent/codex/mcp_http_preflight_test.go b/apps/daemon/internal/agent/codex/mcp_http_preflight_test.go
index 3ab7ace7d..d3f643744 100644
--- a/apps/daemon/internal/agent/codex/mcp_http_preflight_test.go
+++ b/apps/daemon/internal/agent/codex/mcp_http_preflight_test.go
@@ -1,13 +1,11 @@
 package codex
 
 import (
-	"context"
 	"encoding/json"
 	"os"
 	"path/filepath"
 	"strings"
 	"testing"
-	"time"
 
 	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
 )
@@ -155,9 +153,9 @@ func TestPublicMCPHTTPPreparationChecksBeforeNewAndResumedThread(t *testing.T) {
 			path := filepath.Join(root, "native-config.json")
 			writeMCPHTTPConfigResponse(t, path, response)
 			t.Setenv("OAC_TEST_PREPARATION_MCP_CONFIG", path)
-			p, err := newPreparation(t.Context(), req, cfg)
+			e, err := testExecutor(t, "complete", req, cfg)
 			if strings.HasPrefix(mode, "reject") {
-				if err == nil || p != nil {
+				if err == nil || e != nil {
 					t.Fatal("ambient MCP configuration admitted")
 				}
 				assertPreparationOnly(t, root)
@@ -167,18 +165,18 @@ func TestPublicMCPHTTPPreparationChecksBeforeNewAndResumedThread(t *testing.T) {
 			if err != nil {
 				t.Fatal(err)
 			}
-			defer p.Close()
 			assertPreparationOnly(t, root)
 			home, err := allocCodexHome(req.AgentStateKey)
 			if err != nil {
 				t.Fatal(err)
 			}
-			s, err := p.start(t.Context(), "actual-run", proto.TextInput("actual prompt"), make(chan proto.Envelope, 8))
+			out := make(chan proto.Envelope, 20)
+			turn, err := e.StartTurn(t.Context(), "actual-run", proto.TextInput("actual prompt"), out)
 			if err != nil {
 				t.Fatal(err)
 			}
-			defer s.Cancel(context.Background())
-			frames := waitPreparationMethod(t, root, "turn/start")
+			awaitExecutorTurn(t, turn, out)
+			frames := preparationFrames(t, root)
 			checked, statuses := false, 0
 			for _, frame := range frames {
 				if frame.Method == "environment/status" {
@@ -203,12 +201,6 @@ func TestPublicMCPHTTPPreparationChecksBeforeNewAndResumedThread(t *testing.T) {
 					t.Fatal("preflight started discovery")
 				}
 			}
-			_ = s.Cancel(context.Background())
-			select {
-			case <-s.waitDone:
-			case <-time.After(4 * time.Second):
-				t.Fatal("native fixture did not release")
-			}
 		})
 	}
 }
diff --git a/apps/daemon/internal/agent/codex/mcp_required_test.go b/apps/daemon/internal/agent/codex/mcp_required_test.go
index b488c4aae..cf8860f10 100644
--- a/apps/daemon/internal/agent/codex/mcp_required_test.go
+++ b/apps/daemon/internal/agent/codex/mcp_required_test.go
@@ -1,13 +1,13 @@
 package codex
 
 import (
-	"context"
 	"os"
 	"path/filepath"
 	"strings"
 	"testing"
 	"time"
 
+	"github.com/MiniMax-AI/OpenAgentCore/apps/daemon/internal/agent"
 	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
 )
 
@@ -34,17 +34,20 @@ func TestRequiredMCPWaitsForNativeThreadAndNeverRestartsFailedResume(t *testing.
 			t.Setenv("OAC_TEST_PREPARATION_MCP_CONFIG", config)
 			gate := filepath.Join(root, "required-initialization")
 			t.Setenv("OAC_TEST_PREPARATION_THREAD_GATE", gate)
-			p, err := newPreparation(t.Context(), req, cfg)
+			e, err := testExecutor(t, "complete", req, cfg)
 			if err != nil {
 				t.Fatal(err)
 			}
-			defer p.Close()
 			out := make(chan proto.Envelope, 16)
-			s, err := p.start(t.Context(), "required-run", proto.TextInput("actual prompt"), out)
-			if err != nil {
-				t.Fatal(err)
+			type started struct {
+				turn agent.Turn
+				err  error
 			}
-			defer s.Cancel(context.Background())
+			result := make(chan started, 1)
+			go func() {
+				turn, err := e.StartTurn(t.Context(), "required-run", proto.TextInput("actual prompt"), out)
+				result <- started{turn, err}
+			}()
 			waitPreparationMethod(t, root, method)
 			time.Sleep(100 * time.Millisecond)
 			assertNoTurn := func() {
@@ -67,19 +70,23 @@ func TestRequiredMCPWaitsForNativeThreadAndNeverRestartsFailedResume(t *testing.
 			if err := os.WriteFile(gate, []byte(state), 0o600); err != nil {
 				t.Fatal(err)
 			}
-			if state == "ready" {
-				waitPreparationMethod(t, root, "turn/start")
-				return
-			}
+			var start started
 			select {
-			case <-s.waitDone:
+			case start = <-result:
 			case <-time.After(4 * time.Second):
-				t.Fatal("failed initialization did not terminate")
+				t.Fatal("native initialization did not finish")
+			}
+			if (start.err == nil) != (state == "ready") {
+				t.Fatal("native initialization outcome changed", start.err)
+			}
+			frames := settledFrames(t, start.turn, out)
+			if state == "ready" {
+				return
 			}
 			assertNoTurn()
 			failed := false
-			for len(out) > 0 {
-				failed = (<-out).Type == proto.TypeError || failed
+			for _, frame := range frames {
+				failed = frame.Type == proto.TypeError || failed
 			}
 			if !failed {
 				t.Fatal("native initialization failure was not reported")
diff --git a/apps/daemon/internal/agent/codex/options.go b/apps/daemon/internal/agent/codex/options.go
index a8e904194..c1cde2f10 100644
--- a/apps/daemon/internal/agent/codex/options.go
+++ b/apps/daemon/internal/agent/codex/options.go
@@ -62,18 +62,12 @@ type SessionPlan struct {
 	// ModelReasoningEffort is frozen for launch and every native Turn.
 	ModelReasoningEffort string
 
-	// ApprovalPolicy + Sandbox apply to both new and resumed threads.
-	ApprovalPolicy AskForApproval
-	Sandbox        SandboxMode
-	Permissions    string
-
 	// Cleanup is the deferred housekeeping the session must run after the child exits.
 	Cleanup func()
 }
 
 // BuildSessionPlan derives a SessionPlan from the request's frozen model
 // configuration and ExecutionControls. The codex binary is resolved via PATH.
-// Daemon-managed Codex sessions bypass approvals and the engine sandbox.
 func BuildSessionPlan(req proto.PromptRequestPayload) (SessionPlan, error) {
 	return buildSessionPlan(req, func() (agent.ViewDir, error) {
 		home, err := allocCodexHome(req.AgentStateKey)
@@ -85,9 +79,9 @@ func BuildSessionPlan(req proto.PromptRequestPayload) (SessionPlan, error) {
 // only after the request validates.
 func buildSessionPlan(req proto.PromptRequestPayload, allocHome func() (agent.ViewDir, error)) (SessionPlan, error) {
 	plan := SessionPlan{
-		ApprovalPolicy: AskForApproval{String: "never"},
-		Sandbox:        SandboxDangerFullAcces,
-		Cleanup:        func() {},
+		// Harnesses run unattended: Codex never offers its ask-the-user tool.
+		ExtraConfig: [][2]string{{"tools.experimental_request_user_input.enabled", "false"}},
+		Cleanup:     func() {},
 	}
 	prepared, err := harnessconfiguration.Configuration().Prepare(req)
 	if err != nil {
diff --git a/apps/daemon/internal/agent/codex/options_test.go b/apps/daemon/internal/agent/codex/options_test.go
index f04f77ce9..d8c04c387 100644
--- a/apps/daemon/internal/agent/codex/options_test.go
+++ b/apps/daemon/internal/agent/codex/options_test.go
@@ -1,6 +1,7 @@
 package codex
 
 import (
+	"slices"
 	"strings"
 	"testing"
 
@@ -12,11 +13,8 @@ func TestBuildSessionPlan_DefaultsToBypass(t *testing.T) {
 	if err != nil {
 		t.Fatalf("BuildSessionPlan: %v", err)
 	}
-	if plan.ApprovalPolicy.String != "never" {
-		t.Fatalf("default policy must bypass approvals, got %+v", plan.ApprovalPolicy)
-	}
-	if plan.Sandbox != SandboxDangerFullAcces {
-		t.Fatalf("default sandbox = %s, want danger-full-access", plan.Sandbox)
+	if !slices.Contains(plan.ExtraConfig, [2]string{"tools.experimental_request_user_input.enabled", "false"}) {
+		t.Fatalf("default plan must disable the native ask-the-user tool, got %+v", plan.ExtraConfig)
 	}
 	if plan.Cleanup == nil {
 		t.Fatal("Cleanup must be non-nil")
diff --git a/apps/daemon/internal/agent/codex/permission_profile_test.go b/apps/daemon/internal/agent/codex/permission_profile_test.go
index eed3437f1..642327d50 100644
--- a/apps/daemon/internal/agent/codex/permission_profile_test.go
+++ b/apps/daemon/internal/agent/codex/permission_profile_test.go
@@ -16,9 +16,6 @@ func TestRuntimeUsesHostPermissions(t *testing.T) {
 		if err != nil {
 			t.Fatal(err)
 		}
-		if plan.Sandbox != "danger-full-access" || plan.Permissions != "" || plan.ApprovalPolicy.String != "never" {
-			t.Fatal("Runtime must bypass inner sandbox", plan)
-		}
 		if plan.Cwd != req.LocalEnvironment.WorkspaceRoot {
 			t.Fatal("native cwd is not the bound workspace root", plan.Cwd)
 		}
diff --git a/apps/daemon/internal/agent/codex/preparation.go b/apps/daemon/internal/agent/codex/preparation.go
index 402794dbf..d47acc718 100644
--- a/apps/daemon/internal/agent/codex/preparation.go
+++ b/apps/daemon/internal/agent/codex/preparation.go
@@ -11,20 +11,6 @@ import (
 	obslog "github.com/MiniMax-AI/OpenAgentCore/internal/obs/log"
 )
 
-func newSession(parent context.Context, req proto.PromptRequestPayload, out chan<- proto.Envelope, cfg sessionConfig) (*Session, error) {
-	if out == nil {
-		return nil, errors.New("codex: nil out channel")
-	}
-	runID, prompt := req.RunID, req.Input
-	req.RunID, req.Input = "", nil
-	prepared, err := newPreparation(parent, req, cfg)
-	if err != nil {
-		return nil, err
-	}
-	defer prepared.Close()
-	return prepared.start(parent, runID, prompt, out)
-}
-
 func newPreparation(parent context.Context, req proto.PromptRequestPayload, cfg sessionConfig) (*Prepared, error) {
 	if req.ExecutionControls != nil && req.ExecutionControls.OutputFormat != nil {
 		return nil, errors.New("codex: structured output is not qualified")
@@ -92,7 +78,6 @@ func newPreparation(parent context.Context, req proto.PromptRequestPayload, cfg
 		cleanup:                   sync.OnceFunc(plan.Cleanup),
 		bufs:                      NewItemBuffers(),
 		resolvedModel:             plan.Model,
-		interactions:              newPendingCodexInteractions(),
 	}
 	plan.Cleanup = s.cleanup
 	p := &Prepared{
diff --git a/apps/daemon/internal/agent/codex/preparation_close_test.go b/apps/daemon/internal/agent/codex/preparation_close_test.go
index 4abb0ce68..70cc5d769 100644
--- a/apps/daemon/internal/agent/codex/preparation_close_test.go
+++ b/apps/daemon/internal/agent/codex/preparation_close_test.go
@@ -43,3 +43,32 @@ func TestPreparedCloseWaitsForOwnerCleanup(t *testing.T) {
 	}
 	waitPreparedRelease(t, p, root)
 }
+
+func TestPreparedSessionCancellationDuringReadiness(t *testing.T) {
+	req, cfg, root := preparationFixture(t)
+	t.Setenv("OAC_TEST_PREPARATION_BLOCK", "1")
+	owner, cancel := context.WithCancel(t.Context())
+	defer cancel()
+	result := make(chan error, 1)
+	go func() {
+		p, err := newPreparation(owner, req, cfg)
+		if p != nil {
+			_ = p.Close()
+		}
+		result <- err
+	}()
+	waitPreparationMethod(t, root, "environment/status")
+	cancel()
+	select {
+	case err := <-result:
+		if err == nil {
+			t.Fatal("cancelled readiness succeeded")
+		}
+	case <-time.After(4 * time.Second):
+		t.Fatal("cancelled readiness did not finish")
+	}
+	if len(preparedCatalogs(t, root)) != 0 {
+		t.Fatal("failed readiness leaked model catalog")
+	}
+	assertPreparationOnly(t, root)
+}
diff --git a/apps/daemon/internal/agent/codex/preparation_helpers_test.go b/apps/daemon/internal/agent/codex/preparation_helpers_test.go
index 3c950524f..984f25b7b 100644
--- a/apps/daemon/internal/agent/codex/preparation_helpers_test.go
+++ b/apps/daemon/internal/agent/codex/preparation_helpers_test.go
@@ -29,7 +29,6 @@ func preparationFixture(t *testing.T) (proto.PromptRequestPayload, sessionConfig
 	t.Setenv("OAC_TEST_PREPARATION_FRAMES", filepath.Join(root, "frames.jsonl"))
 	t.Setenv("OAC_TEST_PREPARATION_STATUS", filepath.Join(root, "environment-status"))
 	t.Setenv("OAC_TEST_PREPARATION_BLOCK", "")
-	t.Setenv("OAC_TEST_PREPARATION_OBSERVE", "")
 	for _, key := range []string{"CODEX_EXEC_SERVER_URL", "CODEX_EXEC_SERVER_NOISE_REGISTRY_URL", "CODEX_EXEC_SERVER_NOISE_ENVIRONMENT_ID", "CODEX_EXEC_SERVER_NOISE_AUTH_TOKEN"} {
 		t.Setenv(key, "")
 	}
@@ -257,14 +256,6 @@ func TestPreparationFakeCodexProcess(t *testing.T) {
 		}
 		if frame.Method == "turn/start" {
 			_ = output.Encode(map[string]any{"jsonrpc": "2.0", "method": "turn/started", "params": map[string]any{"threadId": "fixture-native-thread", "turn": map[string]string{"id": "fixture-native-turn"}}})
-			if os.Getenv("OAC_TEST_PREPARATION_OBSERVE") == "1" {
-				for _, raw := range []string{
-					`{"method":"item/completed","params":{"threadId":"fixture-native-thread","turnId":"fixture-native-turn","item":{"type":"agentMessage","id":"message","text":"observed partial answer"}}}`,
-					`{"method":"thread/tokenUsage/updated","params":{"threadId":"fixture-native-thread","turnId":"fixture-native-turn","tokenUsage":{"total":{"inputTokens":30,"cachedInputTokens":4,"outputTokens":10,"reasoningOutputTokens":2,"totalTokens":40}}}}`,
-				} {
-					_ = output.Encode(json.RawMessage(raw))
-				}
-			}
 		}
 	}
 	_ = log.Close()
diff --git a/apps/daemon/internal/agent/codex/preparation_router_test.go b/apps/daemon/internal/agent/codex/preparation_router_test.go
index 2ba23bef6..e965460a2 100644
--- a/apps/daemon/internal/agent/codex/preparation_router_test.go
+++ b/apps/daemon/internal/agent/codex/preparation_router_test.go
@@ -2,7 +2,6 @@ package codex
 
 import (
 	"context"
-	"errors"
 	"os"
 	"path/filepath"
 	"testing"
@@ -58,9 +57,7 @@ func TestPreparationRouterRetainsActualNativeChild(t *testing.T) {
 			req.DisableExecutionEnvironment = false
 			req.LocalEnvironment = &proto.LocalEnvironment{ID: environment, WorkspaceDirectory: "/workspace", NetworkAccess: "enabled", CapabilitySources: &agentcapabilities.Input{}}
 			registry := agent.NewRegistry()
-			registry.RegisterKind(proto.SupportedAgentKind{Kind: "codex", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{LocalEnvironment: proto.CapabilitySupported, FunctionTools: proto.CapabilitySupported})}, harnessconfiguration.Configuration(), func(context.Context, proto.PromptRequestPayload, chan<- proto.Envelope) (agent.Session, error) {
-				return nil, errors.New("ordinary Factory must not run")
-			})
+			registry.RegisterKind(proto.SupportedAgentKind{Kind: "codex", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{LocalEnvironment: proto.CapabilitySupported, FunctionTools: proto.CapabilitySupported})}, harnessconfiguration.Configuration())
 			prepared := make(chan *Prepared, 1)
 			registry.RegisterExecutor("codex", func(ctx context.Context, req proto.PromptRequestPayload) (agent.Executor, error) {
 				e, err := newExecutor(ctx, req, cfg)
diff --git a/apps/daemon/internal/agent/codex/prepared.go b/apps/daemon/internal/agent/codex/prepared.go
index a8a57c30d..d069e9311 100644
--- a/apps/daemon/internal/agent/codex/prepared.go
+++ b/apps/daemon/internal/agent/codex/prepared.go
@@ -1,16 +1,8 @@
 package codex
 
-import (
-	"context"
-	"errors"
-	"strings"
-	"sync"
+import "sync"
 
-	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
-)
-
-// Prepared owns a connected native resource until start transfers it to a Session
-// or an Executor takes it.
+// Prepared owns a connected native resource until an Executor takes it.
 // It observes owner cancellation and RPC exit, not continuous executor readiness.
 type Prepared struct {
 	mu                           sync.Mutex
@@ -18,62 +10,19 @@ type Prepared struct {
 	plan                         SessionPlan
 	resumeID                     string
 	requireExistingNativeSession bool
-	claimed                      bool
-	closed                       bool
 	started                      bool
 	transferred                  chan struct{}
 }
 
-// start consumes the preparation once. ctx bounds only this start operation;
-// cancellation after return does not cancel the transferred Session. The original
-// owner context remains its lifetime context. On success the Session owns out.
-func (p *Prepared) start(ctx context.Context, runID string, prompt proto.MessageInput, out chan<- proto.Envelope) (*Session, error) {
-	if out == nil || strings.TrimSpace(runID) == "" || prompt.Validate() != nil {
-		return nil, errors.New("codex: start requires a run identity, prompt and output channel")
-	}
-	p.mu.Lock()
-	if p.claimed || p.closed {
-		p.mu.Unlock()
-		return nil, errors.New("codex: preparation is no longer available")
-	}
-	p.claimed = true
-	p.mu.Unlock()
-
-	transferred := false
-	defer func() {
-		if !transferred {
-			_ = p.Close()
-		}
-	}()
-	p.mu.Lock()
-	defer p.mu.Unlock()
-	if p.closed || ctx.Err() != nil || p.session.cancelCtx.Err() != nil || !p.session.rpc.Alive() {
-		return nil, errors.New("codex: prepared harness is no longer available")
-	}
-	s := p.session
-	s.runID, s.out = runID, out
-	if s.observeSubagentIdentities {
-		s.startSubagentObservations()
-	}
-	s.registerHandlers()
-	p.started = true
-	close(p.transferred)
-	transferred = true
-	req := proto.PromptRequestPayload{RunID: runID, Input: prompt, AgentSessionID: p.resumeID, RequireExistingNativeSession: p.requireExistingNativeSession}
-	go s.run(p.plan, req)
-	return s, nil
-}
-
 // Close waits for unused teardown and plan cleanup, including another caller's
-// ongoing Close. After a successful start it is inert; use
-// the returned Session's cancellation path to release the transferred resource.
+// ongoing Close. After an Executor takes the resource it is inert; use
+// Executor.Close to release it.
 func (p *Prepared) Close() error {
 	p.mu.Lock()
 	if p.started {
 		p.mu.Unlock()
 		return nil
 	}
-	p.closed = true
 	p.mu.Unlock()
 	p.session.cancelFn()
 	err := p.session.rpc.Close()
diff --git a/apps/daemon/internal/agent/codex/prepared_test.go b/apps/daemon/internal/agent/codex/prepared_test.go
deleted file mode 100644
index 83d63d008..000000000
--- a/apps/daemon/internal/agent/codex/prepared_test.go
+++ /dev/null
@@ -1,234 +0,0 @@
-package codex
-
-import (
-	"context"
-	"encoding/json"
-	"strings"
-	"sync"
-	"testing"
-	"time"
-
-	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
-)
-
-func TestPreparedSessionTransfersSameResourceOnce(t *testing.T) {
-	for _, resume := range []bool{false, true} {
-		t.Run(map[bool]string{false: "new", true: "resumed"}[resume], func(t *testing.T) {
-			req, cfg, root := preparationFixture(t)
-			if resume {
-				req.AgentSessionID = "fixture-native-thread"
-			}
-			p, err := newPreparation(t.Context(), req, cfg)
-			if err != nil {
-				t.Fatal(err)
-			}
-			defer p.Close()
-			assertPreparationOnly(t, root)
-			if len(preparedCatalogs(t, root)) != 1 {
-				t.Fatal("preparation did not retain its model catalog")
-			}
-			pid := p.session.rpc.process.Cmd.Process.Pid
-			cfgPreparedCwd := p.plan.Cwd
-			// Caller-owned data cannot revise the prepared native configuration.
-			req.Model = "different-model"
-			req.AgentSessionID = "different-thread"
-			copy(req.FunctionTools[0].Parameters, strings.ReplaceAll(string(req.FunctionTools[0].Parameters), "integer", "boolean"))
-			out := make(chan proto.Envelope, 8)
-			startCtx, stopStart := context.WithCancel(t.Context())
-			session, err := p.start(startCtx, "actual-run", proto.TextInput("actual prompt"), out)
-			stopStart()
-			if err != nil {
-				t.Fatal(err)
-			}
-			defer session.Cancel(context.Background())
-			if session.rpc != p.session.rpc || session.rpc.process.Cmd.Process.Pid != pid {
-				t.Fatal("start replaced the prepared native resource")
-			}
-			if err := p.Close(); err != nil || !session.rpc.Alive() {
-				t.Fatal("close cancelled transferred resource", err)
-			}
-			if again, err := p.start(t.Context(), "second", proto.TextInput("second prompt"), out); err == nil || again != nil {
-				t.Fatal("preparation started twice", err)
-			}
-			frames := waitPreparationMethod(t, root, "turn/start")
-			counts := map[string]int{}
-			for _, frame := range frames {
-				counts[frame.Method]++
-				if frame.PID != pid {
-					t.Fatal("preparation and start used different children")
-				}
-				var params struct {
-					Model        string                `json:"model"`
-					ThreadID     string                `json:"threadId"`
-					DynamicTools []dynamicFunctionTool `json:"dynamicTools"`
-					Cwd          string                `json:"cwd"`
-					Environments json.RawMessage       `json:"environments"`
-				}
-				if err := json.Unmarshal(frame.Params, &params); err != nil {
-					t.Fatal(err)
-				}
-				if frame.Method == "thread/start" {
-					if params.Model != "fixture-model" || len(params.DynamicTools) != 1 || !strings.Contains(string(params.DynamicTools[0].InputSchema), "integer") {
-						t.Fatal("prepared configuration changed", string(frame.Params))
-					}
-				}
-				if frame.Method == "thread/resume" && params.ThreadID != "fixture-native-thread" {
-					t.Fatal("prepared resume changed")
-				}
-				if len(params.Environments) != 0 || (frame.Method == "thread/start" && params.Cwd != cfgPreparedCwd) || p.plan.Cwd != cfgPreparedCwd {
-					t.Fatal("prepared environment changed")
-				}
-			}
-			expectedThread := "thread/start"
-			if resume {
-				expectedThread = "thread/resume"
-			}
-			if counts["initialize"] != 1 || counts["environment/status"] != 2 || counts[expectedThread] != 1 || counts["turn/start"] != 1 {
-				t.Fatal("unexpected native setup/start count", counts)
-			}
-			if err := session.Cancel(context.Background()); err != nil {
-				t.Fatal(err)
-			}
-			select {
-			case <-session.waitDone:
-			case <-time.After(4 * time.Second):
-				t.Fatal("started session did not release")
-			}
-			waitPreparedRelease(t, p, root)
-		})
-	}
-}
-
-func TestPreparedSessionAbandonmentAndFailedStart(t *testing.T) {
-	for _, reason := range []string{"close", "owner cancelled", "rpc exited", "start cancelled"} {
-		t.Run(reason, func(t *testing.T) {
-			req, cfg, root := preparationFixture(t)
-			owner, cancelOwner := context.WithCancel(t.Context())
-			defer cancelOwner()
-			p, err := newPreparation(owner, req, cfg)
-			if err != nil {
-				t.Fatal(err)
-			}
-			defer p.Close()
-			startCtx := t.Context()
-			switch reason {
-			case "close":
-				if err := p.Close(); err != nil {
-					t.Fatal(err)
-				}
-			case "owner cancelled":
-				cancelOwner()
-			case "rpc exited":
-				if err := p.session.rpc.Close(); err != nil {
-					t.Fatal(err)
-				}
-			case "start cancelled":
-				var cancel context.CancelFunc
-				startCtx, cancel = context.WithCancel(t.Context())
-				cancel()
-			}
-			if reason == "owner cancelled" || reason == "rpc exited" || reason == "close" {
-				// Release must happen without a later Start driving cleanup.
-				waitPreparedRelease(t, p, root)
-			}
-			out := make(chan proto.Envelope, 8)
-			if started, err := p.start(startCtx, "late-run", proto.TextInput("must not start"), out); err == nil || started != nil {
-				t.Fatal("abandoned preparation started", err)
-			}
-			waitPreparedRelease(t, p, root)
-			assertPreparationOnly(t, root)
-			if len(out) != 0 {
-				t.Fatal("failed preparation emitted run output")
-			}
-			count := 0
-			for _, frame := range preparationFrames(t, root) {
-				if frame.Method == "environment/status" {
-					count++
-				}
-			}
-			if count != 2 {
-				t.Fatal("failed start reconnected the native environment", count)
-			}
-		})
-	}
-}
-
-func TestPreparedSessionConcurrentStartAndClose(t *testing.T) {
-	req, cfg, root := preparationFixture(t)
-	p, err := newPreparation(t.Context(), req, cfg)
-	if err != nil {
-		t.Fatal(err)
-	}
-	defer p.Close()
-	begin := make(chan struct{})
-	var wg sync.WaitGroup
-	started := make(chan *Session, 8)
-	for range 8 {
-		wg.Add(1)
-		go func() {
-			defer wg.Done()
-			<-begin
-			s, err := p.start(t.Context(), "run", proto.TextInput("prompt"), make(chan proto.Envelope, 8))
-			if err == nil {
-				started <- s
-			}
-		}()
-	}
-	wg.Add(1)
-	go func() { defer wg.Done(); <-begin; _ = p.Close() }()
-	close(begin)
-	wg.Wait()
-	close(started)
-	count := 0
-	for session := range started {
-		count++
-		_ = session.Cancel(context.Background())
-		select {
-		case <-session.waitDone:
-		case <-time.After(4 * time.Second):
-			t.Fatal("concurrent start retained a session")
-		}
-	}
-	if count > 1 {
-		t.Fatal("multiple ownership transfers", count)
-	}
-	waitPreparedRelease(t, p, root)
-	turns := 0
-	for _, frame := range preparationFrames(t, root) {
-		if frame.Method == "turn/start" {
-			turns++
-		}
-	}
-	if turns > 1 {
-		t.Fatal("multiple native Turns", turns)
-	}
-}
-
-func TestPreparedSessionCancellationDuringReadiness(t *testing.T) {
-	req, cfg, root := preparationFixture(t)
-	t.Setenv("OAC_TEST_PREPARATION_BLOCK", "1")
-	owner, cancel := context.WithCancel(t.Context())
-	defer cancel()
-	result := make(chan error, 1)
-	go func() {
-		p, err := newPreparation(owner, req, cfg)
-		if p != nil {
-			_ = p.Close()
-		}
-		result <- err
-	}()
-	waitPreparationMethod(t, root, "environment/status")
-	cancel()
-	select {
-	case err := <-result:
-		if err == nil {
-			t.Fatal("cancelled readiness succeeded")
-		}
-	case <-time.After(4 * time.Second):
-		t.Fatal("cancelled readiness did not finish")
-	}
-	if len(preparedCatalogs(t, root)) != 0 {
-		t.Fatal("failed readiness leaked model catalog")
-	}
-	assertPreparationOnly(t, root)
-}
diff --git a/apps/daemon/internal/agent/codex/protocol.go b/apps/daemon/internal/agent/codex/protocol.go
index 462c10f3e..2daa4acb7 100644
--- a/apps/daemon/internal/agent/codex/protocol.go
+++ b/apps/daemon/internal/agent/codex/protocol.go
@@ -64,8 +64,8 @@ func (e *JsonRpcError) Error() string { return fmt.Sprintf("%d %s", e.Code, e.Me
 // ---------------------------------------------------------------------------
 
 // InitializeCapabilities mirrors codex-rs/app-server/src/protocol.rs.
-// experimentalApi=true opts into the granular AskForApproval enum and
-// the thread/* notification stream.
+// experimentalApi=true opts into the experimental thread/* fields and
+// notification stream.
 type InitializeCapabilities struct {
 	ExperimentalAPI    bool      `json:"experimentalApi"`
 	RequestAttestation bool      `json:"requestAttestation"`
@@ -93,83 +93,19 @@ type SkillsExtraRootsSetParams struct {
 	ExtraRoots []string `json:"extraRoots"`
 }
 
-// ---------------------------------------------------------------------------
-// Approval / sandbox policies
-// ---------------------------------------------------------------------------
-
-// GranularAskForApproval names each approval gate the codex agent can
-// surface. All-false produces a fully silent run; turning any single
-// field true makes the corresponding ServerRequest reach the daemon for
-// human approval.
-//
-// JSON tags MUST stay snake_case — codex-rs deserialises this struct
-// from a config TOML / RPC param with field names like sandbox_approval,
-// and renaming silently breaks the wire.
-type GranularAskForApproval struct {
-	SandboxApproval    bool `json:"sandbox_approval"`
-	Rules              bool `json:"rules"`
-	SkillApproval      bool `json:"skill_approval"`
-	RequestPermissions bool `json:"request_permissions"`
-	MCPElicitations    bool `json:"mcp_elicitations"`
-}
-
-// AskForApproval is the discriminated union codex accepts on
-// ThreadStartParams.approvalPolicy. The serialiser must emit EITHER
-// {"granular": {...}} OR a bare string ("never" / "on-request" /
-// "on-failure" / "untrusted"). See MarshalJSON in approval_policy.go.
-type AskForApproval struct {
-	String   string                  // "" when granular is set
-	Granular *GranularAskForApproval // nil when string is set
-}
-
-// SandboxMode is the wire-level sandbox setting codex's v2 thread/start
-// API accepts. Serializes to a kebab-case string per
-// codex-rs/app-server-protocol/src/protocol/v2/shared.rs::SandboxMode.
-//
-// Earlier (~0.137-era) the field on ThreadStartParams was named
-// `sandboxPolicy` and took a tagged object `{type: "dangerFullAccess"}`.
-// 0.141.0 renamed it to `sandbox` and flattened it to one of these three
-// strings. Sending the old shape no longer errors loudly — codex just
-// silently falls back to read-only, which makes prompts terminate
-// immediately with no agent output. Keep the constants pinned exactly
-// to the kebab values upstream serializes.
-type SandboxMode string
-
-const (
-	SandboxReadOnly        SandboxMode = "read-only"
-	SandboxWorkspaceWrite  SandboxMode = "workspace-write"
-	SandboxDangerFullAcces SandboxMode = "danger-full-access"
-)
-
-// SandboxPolicy is the legacy compound type kept for internal
-// representation only — codex still echoes it back on some response
-// shapes (turn_context inside rollout files, for example). It is NOT
-// what ThreadStartParams.Sandbox takes on the wire.
-type SandboxPolicy struct {
-	Type                SandboxMode `json:"type"`
-	WritableRoots       []string    `json:"writableRoots,omitempty"`
-	NetworkAccess       bool        `json:"networkAccess,omitempty"`
-	ExcludeTmpdirEnvVar bool        `json:"excludeTmpdirEnvVar,omitempty"`
-	ExcludeSlashTmp     bool        `json:"excludeSlashTmp,omitempty"`
-}
-
 // ---------------------------------------------------------------------------
 // thread/start, thread/resume, thread/list
 // ---------------------------------------------------------------------------
 
 type ThreadStartParams struct {
-	HistoryMode    string         `json:"historyMode,omitempty"`
-	Cwd            string         `json:"cwd"`
-	Model          string         `json:"model,omitempty"`
-	ModelProvider  string         `json:"modelProvider,omitempty"`
-	ApprovalPolicy AskForApproval `json:"approvalPolicy"`
-	// Sandbox is the v0.141+ field name; previously called sandboxPolicy
-	// and took a tagged-enum object. Wire format now is a kebab-case
-	// string: "read-only" / "workspace-write" / "danger-full-access".
-	// Sending the old object shape causes codex to silently default to
-	// read-only, which terminates the turn before the model can reply.
-	Sandbox               SandboxMode           `json:"sandbox,omitempty"`
-	Permissions           string                `json:"permissions,omitempty"`
+	HistoryMode    string `json:"historyMode,omitempty"`
+	Cwd            string `json:"cwd"`
+	Model          string `json:"model,omitempty"`
+	ModelProvider  string `json:"modelProvider,omitempty"`
+	ApprovalPolicy string `json:"approvalPolicy"`
+	// Sandbox is the kebab-case mode string. Codex silently falls back to
+	// read-only for the legacy sandboxPolicy object.
+	Sandbox               string                `json:"sandbox"`
 	DeveloperInstructions string                `json:"developerInstructions,omitempty"`
 	RuntimeWorkspaceRoots []string              `json:"runtimeWorkspaceRoots,omitempty"`
 	DynamicTools          []dynamicFunctionTool `json:"dynamicTools,omitempty"`
@@ -187,19 +123,16 @@ type Thread struct {
 }
 
 type ThreadStartResult struct {
-	Thread         Thread          `json:"thread"`
-	Model          string          `json:"model,omitempty"`
-	ApprovalPolicy *AskForApproval `json:"approvalPolicy,omitempty"`
-	Sandbox        *SandboxPolicy  `json:"sandbox,omitempty"`
+	Thread Thread `json:"thread"`
+	Model  string `json:"model,omitempty"`
 }
 
 type ThreadResumeParams struct {
-	Cwd                   string         `json:"cwd,omitempty"`
-	DeveloperInstructions string         `json:"developerInstructions"`
-	ThreadID              string         `json:"threadId"`
-	ApprovalPolicy        AskForApproval `json:"approvalPolicy"`
-	Sandbox               SandboxMode    `json:"sandbox,omitempty"`
-	Permissions           string         `json:"permissions,omitempty"`
+	Cwd                   string `json:"cwd,omitempty"`
+	DeveloperInstructions string `json:"developerInstructions"`
+	ThreadID              string `json:"threadId"`
+	ApprovalPolicy        string `json:"approvalPolicy"`
+	Sandbox               string `json:"sandbox"`
 }
 
 // ---------------------------------------------------------------------------
@@ -381,84 +314,3 @@ type ErrorNotification struct {
 	Error    *TurnError `json:"error,omitempty"`
 	Message  string     `json:"message,omitempty"`
 }
-
-// ---------------------------------------------------------------------------
-// Approval and user-input ServerRequest params. Explicit requests defer their
-// responses until Web or IM submits the decision, even with bypass defaults.
-// ---------------------------------------------------------------------------
-
-type CommandExecutionRequestApprovalParams struct {
-	ThreadID string  `json:"threadId"`
-	TurnID   string  `json:"turnId"`
-	ItemID   string  `json:"itemId"`
-	Command  *string `json:"command,omitempty"`
-	Cwd      *string `json:"cwd,omitempty"`
-	Reason   *string `json:"reason,omitempty"`
-}
-
-type FileChangeRequestApprovalParams struct {
-	ThreadID  string  `json:"threadId"`
-	TurnID    string  `json:"turnId"`
-	ItemID    string  `json:"itemId"`
-	Reason    *string `json:"reason,omitempty"`
-	GrantRoot *string `json:"grantRoot,omitempty"`
-}
-
-type PermissionsRequestApprovalParams struct {
-	ThreadID    string         `json:"threadId"`
-	TurnID      string         `json:"turnId"`
-	ItemID      string         `json:"itemId"`
-	Cwd         string         `json:"cwd"`
-	Reason      *string        `json:"reason,omitempty"`
-	Permissions map[string]any `json:"permissions,omitempty"`
-}
-
-// CommandExecutionApprovalDecision is the verdict the daemon writes
-// back to a Codex approval ServerRequest. "accept" / "decline" / "cancel"
-// / "acceptForSession".
-type CommandExecutionApprovalDecision = string
-
-// ApprovalDecisionResult is the result body for command-execution and
-// file-change approvals. item/permissions/requestApproval uses the distinct
-// PermissionsRequestApprovalResponse contract below.
-type ApprovalDecisionResult struct {
-	Decision CommandExecutionApprovalDecision `json:"decision"`
-}
-
-// PermissionsRequestApprovalResponse mirrors Codex app-server's dedicated
-// response contract. Approving echoes the requested permission profile;
-// denying returns an empty profile, which grants no additional capability.
-type PermissionsRequestApprovalResponse struct {
-	Permissions map[string]any `json:"permissions"`
-	Scope       string         `json:"scope,omitempty"`
-}
-
-type ToolRequestUserInputOption struct {
-	Label       string `json:"label"`
-	Description string `json:"description"`
-}
-
-type ToolRequestUserInputQuestion struct {
-	ID       string                       `json:"id"`
-	Header   string                       `json:"header"`
-	Question string                       `json:"question"`
-	Options  []ToolRequestUserInputOption `json:"options,omitempty"`
-	IsOther  bool                         `json:"isOther,omitempty"`
-	IsSecret bool                         `json:"isSecret,omitempty"`
-}
-
-type ToolRequestUserInputParams struct {
-	ThreadID         string                         `json:"threadId"`
-	TurnID           string                         `json:"turnId"`
-	ItemID           string                         `json:"itemId"`
-	Questions        []ToolRequestUserInputQuestion `json:"questions"`
-	AutoResolutionMs *uint64                        `json:"autoResolutionMs,omitempty"`
-}
-
-type ToolRequestUserInputAnswer struct {
-	Answers []string `json:"answers"`
-}
-
-type ToolRequestUserInputResponse struct {
-	Answers map[string]ToolRequestUserInputAnswer `json:"answers"`
-}
diff --git a/apps/daemon/internal/agent/codex/protocol_wire_test.go b/apps/daemon/internal/agent/codex/protocol_wire_test.go
index d32590d7c..895888bab 100644
--- a/apps/daemon/internal/agent/codex/protocol_wire_test.go
+++ b/apps/daemon/internal/agent/codex/protocol_wire_test.go
@@ -6,66 +6,12 @@ import (
 	"testing"
 )
 
-// TestThreadStartParams_SandboxIsKebabString pins the v0.141+ wire
-// format reviewer caught the hard way: codex's ThreadStartParams.sandbox
-// is a kebab-case string ("read-only" / "workspace-write" /
-// "danger-full-access"), NOT the legacy {"type":"dangerFullAccess"}
-// tagged object on a sandboxPolicy field.
-//
-// Sending the legacy shape used to terminate every turn in <1s with an
-// empty agent message body, because codex silently fell back to
-// read-only when it didn't recognise the field name.
-func TestThreadStartParams_SandboxIsKebabString(t *testing.T) {
-	cases := []struct {
-		name string
-		mode SandboxMode
-		want string
-	}{
-		{"read-only", SandboxReadOnly, "read-only"},
-		{"workspace-write", SandboxWorkspaceWrite, "workspace-write"},
-		{"danger-full-access", SandboxDangerFullAcces, "danger-full-access"},
-	}
-	for _, tc := range cases {
-		t.Run(tc.name, func(t *testing.T) {
-			params := ThreadStartParams{
-				Cwd:            "/workspace",
-				Model:          "gpt-5.5",
-				ApprovalPolicy: SilentGranularPolicy(),
-				Sandbox:        tc.mode,
-			}
-			raw, err := json.Marshal(params)
-			if err != nil {
-				t.Fatalf("marshal: %v", err)
-			}
-			body := string(raw)
-			if !strings.Contains(body, `"sandbox":"`+tc.want+`"`) {
-				t.Fatalf("wire body missing sandbox=%q: %s", tc.want, body)
-			}
-			// The legacy field name MUST be gone. Even shipping it as
-			// "sandboxPolicy" alongside the new field would confuse
-			// future-version codex servers that strict-deserialise.
-			if strings.Contains(body, `"sandboxPolicy"`) {
-				t.Fatalf("legacy sandboxPolicy field leaked into wire: %s", body)
-			}
-			// And the kebab-case value must NOT collide with the old
-			// camelCase enum names.
-			for _, oldName := range []string{`"readOnly"`, `"workspaceWrite"`, `"dangerFullAccess"`} {
-				if strings.Contains(body, oldName) {
-					t.Fatalf("legacy camelCase enum value %s leaked: %s", oldName, body)
-				}
-			}
-		})
-	}
-}
-
 // TestThreadStartParams_OmitsEmptyOptionalFields pins that model_provider
 // and other optional fields don't leak null/empty values into the wire.
 // codex would reject malformed enum values otherwise.
 func TestThreadStartParams_OmitsEmptyOptionalFields(t *testing.T) {
 	params := ThreadStartParams{
-		Cwd:            "/workspace",
-		ApprovalPolicy: SilentGranularPolicy(),
-		Sandbox:        SandboxDangerFullAcces,
+		Cwd: "/workspace",
 		// Model, ModelProvider, DeveloperInstructions deliberately empty
 	}
 	raw, _ := json.Marshal(params)
@@ -88,11 +34,9 @@ func TestThreadStartParams_OmitsEmptyOptionalFields(t *testing.T) {
 // override. Sending it on both paths is belt + suspenders.
 func TestThreadStartParams_ModelProviderIsCamelCaseField(t *testing.T) {
 	params := ThreadStartParams{
-		Cwd:            "/workspace",
-		Model:          "gpt-5.5",
-		ModelProvider:  "oac",
-		ApprovalPolicy: SilentGranularPolicy(),
-		Sandbox:        SandboxDangerFullAcces,
+		Cwd:           "/workspace",
+		Model:         "gpt-5.5",
+		ModelProvider: "oac",
 	}
 	raw, _ := json.Marshal(params)
 	body := string(raw)
diff --git a/apps/daemon/internal/agent/codex/recovery_test.go b/apps/daemon/internal/agent/codex/recovery_test.go
index 97eff6936..4c9b158db 100644
--- a/apps/daemon/internal/agent/codex/recovery_test.go
+++ b/apps/daemon/internal/agent/codex/recovery_test.go
@@ -161,26 +161,20 @@ func TestPreparedRecoveryCannotStartWithoutExistingHistory(t *testing.T) {
 				req.DisableExecutionEnvironment = false
 				req.LocalEnvironment = &proto.LocalEnvironment{ID: uuid.NewString(), WorkspaceDirectory: "/workspace", NetworkAccess: "enabled", CapabilitySources: &agentcapabilities.Input{}, WorkspaceRoot: cwd}
 			}
-			p, err := newPreparation(t.Context(), req, cfg)
+			e, err := testExecutor(t, "complete", req, cfg)
 			if err != nil {
 				t.Fatal(err)
 			}
-			defer p.Close()
-			if p.plan.Cwd != cwd {
-				t.Fatalf("cwd = %q, want %q", p.plan.Cwd, cwd)
+			if e.prepared.plan.Cwd != cwd {
+				t.Fatalf("cwd = %q, want %q", e.prepared.plan.Cwd, cwd)
 			}
 			assertPreparationOnly(t, root)
 			out := make(chan proto.Envelope, 16)
-			session, err := p.start(t.Context(), "recovery-run", proto.TextInput("continue"), out)
-			if err != nil {
-				t.Fatal(err)
-			}
-			defer session.Cancel(context.Background())
-			select {
-			case <-p.session.waitDone:
-			case <-time.After(4 * time.Second):
-				t.Fatal("recovery did not terminate")
+			turn, err := e.StartTurn(t.Context(), "recovery-run", proto.TextInput("continue"), out)
+			if err == nil {
+				t.Fatal("missing history started a Turn")
 			}
+			settledFrames(t, turn, out)
 			found := false
 			for _, frame := range preparationFrames(t, root) {
 				if frame.Method == "thread/list" {
diff --git a/apps/daemon/internal/agent/codex/rpc_close_test.go b/apps/daemon/internal/agent/codex/rpc_close_test.go
index fbd9c8175..036b1c898 100644
--- a/apps/daemon/internal/agent/codex/rpc_close_test.go
+++ b/apps/daemon/internal/agent/codex/rpc_close_test.go
@@ -80,7 +80,7 @@ func TestJSONRPCClientCloseCanRetryUnreapedChild(t *testing.T) {
 	closeConcurrently(true)
 	ownerCtx, cancelOwner := context.WithCancel(t.Context())
 	s := &Session{rpc: client, cancelCtx: ownerCtx, cancelFn: cancelOwner,
-		cfg: defaultSessionConfig(), interactions: newPendingCodexInteractions(), bufs: NewItemBuffers()}
+		cfg: defaultSessionConfig(), bufs: NewItemBuffers()}
 	ctx, cancelWait := context.WithTimeout(t.Context(), 20*time.Millisecond)
 	defer cancelWait()
 	if err := s.Cancel(ctx); !errors.Is(err, context.DeadlineExceeded) {
diff --git a/apps/daemon/internal/agent/codex/server_requests.go b/apps/daemon/internal/agent/codex/server_requests.go
deleted file mode 100644
index 5e77e3c9d..000000000
--- a/apps/daemon/internal/agent/codex/server_requests.go
+++ /dev/null
@@ -1,362 +0,0 @@
-package codex
-
-import (
-	"crypto/rand"
-	"encoding/hex"
-	"encoding/json"
-	"errors"
-	"fmt"
-	"strings"
-	"sync"
-	"time"
-
-	"github.com/MiniMax-AI/OpenAgentCore/apps/daemon/internal/agent"
-	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
-)
-
-type pendingCodexPermission struct {
-	rpcID       any
-	kind        codexPermissionKind
-	permissions map[string]any
-	timeout     time.Duration
-	timer       *time.Timer
-}
-
-type pendingCodexAsk struct {
-	rpcID       any
-	questionIDs []string
-	timeout     time.Duration
-	timer       *time.Timer
-}
-
-const codexInteractionTimeout = 10 * time.Minute
-
-type codexPermissionKind uint8
-
-const (
-	codexDecisionApproval codexPermissionKind = iota
-	codexPermissionsApproval
-	codexMCPApproval
-)
-
-type pendingCodexInteractions struct {
-	mu          sync.Mutex
-	permissions map[string]pendingCodexPermission
-	asks        map[string]pendingCodexAsk
-}
-
-func newPendingCodexInteractions() *pendingCodexInteractions {
-	return &pendingCodexInteractions{
-		permissions: make(map[string]pendingCodexPermission),
-		asks:        make(map[string]pendingCodexAsk),
-	}
-}
-
-func codexInteractionID(prefix string) string {
-	var bytes [8]byte
-	if _, err := rand.Read(bytes[:]); err == nil {
-		return prefix + "_" + hex.EncodeToString(bytes[:])
-	}
-	return fmt.Sprintf("%s_fallback", prefix)
-}
-
-func (s *Session) handleCodexCommandApproval(raw json.RawMessage, rpcID any) (any, error) {
-	var params CommandExecutionRequestApprovalParams
-	if err := json.Unmarshal(raw, &params); err != nil {
-		return nil, fmt.Errorf("decode command approval: %w", err)
-	}
-	title := stringPointer(params.Command)
-	if title == "" {
-		title = "Run command"
-	}
-	return s.deferCodexPermission(rpcID, codexDecisionApproval, "command_execution", title, stringPointer(params.Reason), raw, nil)
-}
-
-func (s *Session) handleCodexFileApproval(raw json.RawMessage, rpcID any) (any, error) {
-	var params FileChangeRequestApprovalParams
-	if err := json.Unmarshal(raw, &params); err != nil {
-		return nil, fmt.Errorf("decode file approval: %w", err)
-	}
-	title := stringPointer(params.GrantRoot)
-	if title == "" {
-		title = "Apply file changes"
-	}
-	return s.deferCodexPermission(rpcID, codexDecisionApproval, "file_change", title, stringPointer(params.Reason), raw, nil)
-}
-
-func (s *Session) handleCodexPermissionsApproval(raw json.RawMessage, rpcID any) (any, error) {
-	var params PermissionsRequestApprovalParams
-	if err := json.Unmarshal(raw, &params); err != nil {
-		return nil, fmt.Errorf("decode permissions approval: %w", err)
-	}
-	title := strings.TrimSpace(params.Cwd)
-	if title == "" {
-		title = "Grant additional permissions"
-	}
-	return s.deferCodexPermission(rpcID, codexPermissionsApproval, "permission_request", title, stringPointer(params.Reason), raw, params.Permissions)
-}
-
-func (s *Session) deferCodexPermission(rpcID any, kind codexPermissionKind, tool, title, detail string, raw json.RawMessage, permissions map[string]any) (any, error) {
-	requestID := codexInteractionID("perm")
-	payload := map[string]any{}
-	_ = json.Unmarshal(raw, &payload)
-	pending := pendingCodexPermission{
-		rpcID: rpcID, kind: kind, permissions: permissions,
-		timeout: codexInteractionTimeout,
-	}
-	s.interactions.mu.Lock()
-	// Start the timer while holding the table lock. Even a future very short
-	// timeout then blocks in expireCodexPermission until the entry is visible,
-	// rather than firing before insertion and leaving an immortal request.
-	pending.timer = time.AfterFunc(pending.timeout, func() { s.expireCodexPermission(requestID) })
-	s.interactions.permissions[requestID] = pending
-	s.interactions.mu.Unlock()
-	env, err := proto.NewEnvelope(proto.TypePermissionRequest, s.runID, proto.PermissionRequestPayload{
-		RequestID: requestID, Tool: tool, Title: title, Detail: detail, Payload: payload,
-	})
-	if err != nil {
-		s.interactions.mu.Lock()
-		pending, ok := s.interactions.permissions[requestID]
-		if ok {
-			delete(s.interactions.permissions, requestID)
-		}
-		s.interactions.mu.Unlock()
-		if ok && pending.timer != nil {
-			pending.timer.Stop()
-		}
-		return nil, err
-	}
-	s.trySend(env)
-	return DeferReply, nil
-}
-
-func (s *Session) handleCodexUserInput(raw json.RawMessage, rpcID any) (any, error) {
-	var params ToolRequestUserInputParams
-	if err := json.Unmarshal(raw, &params); err != nil {
-		return nil, fmt.Errorf("decode requestUserInput: %w", err)
-	}
-	if len(params.Questions) == 0 {
-		return nil, errors.New("requestUserInput contains no questions")
-	}
-	askID := codexInteractionID("ask")
-	questions := make([]proto.PromptForUserChoiceQuestion, 0, len(params.Questions))
-	questionIDs := make([]string, 0, len(params.Questions))
-	for index, question := range params.Questions {
-		options := make([]proto.PromptForUserChoiceOption, 0, len(question.Options))
-		for _, option := range question.Options {
-			options = append(options, proto.PromptForUserChoiceOption{Label: option.Label, Description: option.Description})
-		}
-		header := strings.TrimSpace(question.Header)
-		if header == "" {
-			header = fmt.Sprintf("q%d", index)
-		}
-		questionID := strings.TrimSpace(question.ID)
-		if questionID == "" {
-			questionID = header
-		}
-		questionIDs = append(questionIDs, questionID)
-		questions = append(questions, proto.PromptForUserChoiceQuestion{
-			ID: questionID, Header: header, Question: question.Question, Options: options,
-			IsOther: question.IsOther, IsSecret: question.IsSecret,
-		})
-	}
-	timeout := codexInteractionTimeout
-	if params.AutoResolutionMs != nil && *params.AutoResolutionMs > 0 {
-		const maxMillis = uint64(^uint64(0)>>1) / uint64(time.Millisecond)
-		if *params.AutoResolutionMs <= maxMillis {
-			timeout = time.Duration(*params.AutoResolutionMs) * time.Millisecond
-		}
-	}
-	pending := pendingCodexAsk{rpcID: rpcID, questionIDs: questionIDs, timeout: timeout}
-	s.interactions.mu.Lock()
-	pending.timer = time.AfterFunc(pending.timeout, func() { s.expireCodexAsk(askID) })
-	s.interactions.asks[askID] = pending
-	s.interactions.mu.Unlock()
-	env, err := proto.NewEnvelope(proto.TypePromptForUserChoice, s.runID, proto.PromptForUserChoicePayload{
-		AskID: askID, Questions: questions, AutoResolutionMs: params.AutoResolutionMs,
-	})
-	if err != nil {
-		s.interactions.mu.Lock()
-		pending, ok := s.interactions.asks[askID]
-		if ok {
-			delete(s.interactions.asks, askID)
-		}
-		s.interactions.mu.Unlock()
-		if ok && pending.timer != nil {
-			pending.timer.Stop()
-		}
-		return nil, err
-	}
-	s.trySend(env)
-	return DeferReply, nil
-}
-
-func (s *Session) submitCodexPermission(requestID string, decision proto.PermissionDecisionPayload) error {
-	if !s.beginOperation() {
-		return agent.ErrSteeringInactive
-	}
-	defer s.endOperation()
-	s.interactions.mu.Lock()
-	pending, ok := s.interactions.permissions[requestID]
-	if ok {
-		delete(s.interactions.permissions, requestID)
-	}
-	s.interactions.mu.Unlock()
-	if !ok {
-		return agent.ErrUnknownPermission
-	}
-	if pending.timer != nil {
-		pending.timer.Stop()
-	}
-	if err := s.sendCodexPermissionReply(pending, decision.Approved); err != nil {
-		s.interactions.mu.Lock()
-		pending.timer = time.AfterFunc(pending.timeout, func() { s.expireCodexPermission(requestID) })
-		s.interactions.permissions[requestID] = pending
-		s.interactions.mu.Unlock()
-		return err
-	}
-	return nil
-}
-
-func (s *Session) sendCodexPermissionReply(pending pendingCodexPermission, approved bool) error {
-	if pending.kind == codexPermissionsApproval {
-		permissions := map[string]any{}
-		if approved && pending.permissions != nil {
-			permissions = pending.permissions
-		}
-		return s.rpc.SendServerReply(pending.rpcID, PermissionsRequestApprovalResponse{
-			Permissions: permissions,
-			Scope:       "turn",
-		})
-	}
-	value := "decline"
-	if approved {
-		value = "accept"
-	}
-	if pending.kind == codexMCPApproval {
-		var content map[string]any
-		if approved {
-			content = map[string]any{}
-		}
-		return s.rpc.SendServerReply(pending.rpcID, mcpElicitationResponse{Action: value, Content: content})
-	}
-	return s.rpc.SendServerReply(pending.rpcID, ApprovalDecisionResult{Decision: value})
-}
-
-func (s *Session) submitCodexUserInput(askID string, decision proto.PromptForUserChoiceDecisionPayload) error {
-	if !s.beginOperation() {
-		return agent.ErrSteeringInactive
-	}
-	defer s.endOperation()
-	s.interactions.mu.Lock()
-	pending, ok := s.interactions.asks[askID]
-	var answers map[string][]string
-	if ok {
-		var err error
-		answers, err = decision.AnswersFor(pending.questionIDs)
-		if err != nil {
-			s.interactions.mu.Unlock()
-			return err
-		}
-		delete(s.interactions.asks, askID)
-	}
-	s.interactions.mu.Unlock()
-	if !ok {
-		return agent.ErrUnknownAsk
-	}
-	if pending.timer != nil {
-		pending.timer.Stop()
-	}
-	if decision.Cancelled {
-		reason := strings.TrimSpace(decision.Reason)
-		if reason == "" {
-			reason = "user cancelled input request"
-		}
-		if err := s.rpc.SendServerError(pending.rpcID, -32001, reason, nil); err != nil {
-			s.interactions.mu.Lock()
-			pending.timer = time.AfterFunc(pending.timeout, func() { s.expireCodexAsk(askID) })
-			s.interactions.asks[askID] = pending
-			s.interactions.mu.Unlock()
-			return err
-		}
-		return nil
-	}
-	result := ToolRequestUserInputResponse{Answers: make(map[string]ToolRequestUserInputAnswer, len(pending.questionIDs))}
-	for _, questionID := range pending.questionIDs {
-		values := answers[questionID]
-		if values == nil {
-			values = []string{}
-		}
-		result.Answers[questionID] = ToolRequestUserInputAnswer{Answers: values}
-	}
-	if err := s.rpc.SendServerReply(pending.rpcID, result); err != nil {
-		s.interactions.mu.Lock()
-		pending.timer = time.AfterFunc(pending.timeout, func() { s.expireCodexAsk(askID) })
-		s.interactions.asks[askID] = pending
-		s.interactions.mu.Unlock()
-		return err
-	}
-	return nil
-}
-
-func (s *Session) expireCodexPermission(requestID string) {
-	if !s.beginOperation() {
-		return
-	}
-	defer s.endOperation()
-	s.interactions.mu.Lock()
-	pending, ok := s.interactions.permissions[requestID]
-	if ok {
-		delete(s.interactions.permissions, requestID)
-	}
-	s.interactions.mu.Unlock()
-	if ok {
-		if pending.timer != nil {
-			pending.timer.Stop()
-		}
-		_ = s.sendCodexPermissionReply(pending, false)
-	}
-}
-
-func (s *Session) expireCodexAsk(askID string) {
-	if !s.beginOperation() {
-		return
-	}
-	defer s.endOperation()
-	s.interactions.mu.Lock()
-	pending, ok := s.interactions.asks[askID]
-	if ok {
-		delete(s.interactions.asks, askID)
-	}
-	s.interactions.mu.Unlock()
-	if ok {
-		if pending.timer != nil {
-			pending.timer.Stop()
-		}
-		_ = s.rpc.SendServerError(pending.rpcID, -32001, "input request timed out", nil)
-	}
-}
-
-func (s *Session) stopCodexInteractionTimers() {
-	s.interactions.mu.Lock()
-	defer s.interactions.mu.Unlock()
-	for id, pending := range s.interactions.permissions {
-		if pending.timer != nil {
-			pending.timer.Stop()
-		}
-		delete(s.interactions.permissions, id)
-	}
-	for id, pending := range s.interactions.asks {
-		if pending.timer != nil {
-			pending.timer.Stop()
-		}
-		delete(s.interactions.asks, id)
-	}
-}
-
-func stringPointer(value *string) string {
-	if value == nil {
-		return ""
-	}
-	return strings.TrimSpace(*value)
-}
diff --git a/apps/daemon/internal/agent/codex/server_requests_mcp.go b/apps/daemon/internal/agent/codex/server_requests_mcp.go
deleted file mode 100644
index 4cb4de00e..000000000
--- a/apps/daemon/internal/agent/codex/server_requests_mcp.go
+++ /dev/null
@@ -1,38 +0,0 @@
-package codex
-
-import (
-	"encoding/json"
-	"errors"
-	"fmt"
-	"strings"
-)
-
-type mcpElicitationParams struct {
-	ServerName string `json:"serverName"`
-	Mode       string `json:"mode"`
-	Message    string `json:"message"`
-	Schema     struct {
-		Type       string                     `json:"type"`
-		Properties map[string]json.RawMessage `json:"properties"`
-		Required   []string                   `json:"required"`
-	} `json:"requestedSchema"`
-}
-
-type mcpElicitationResponse struct {
-	Action  string         `json:"action"`
-	Content map[string]any `json:"content"`
-}
-
-func (s *Session) handleCodexMCPElicitation(raw json.RawMessage, rpcID any) (any, error) {
-	var params mcpElicitationParams
-	if err := json.Unmarshal(raw, &params); err != nil {
-		return nil, fmt.Errorf("decode MCP elicitation: %w", err)
-	}
-	if params.Mode != "form" || params.Schema.Type != "object" || params.Schema.Properties == nil || len(params.Schema.Properties) != 0 || len(params.Schema.Required) != 0 {
-		return nil, errors.New("MCP elicitation requires unsupported input; only empty confirmation forms are supported")
-	}
-	if strings.TrimSpace(params.ServerName) == "" || strings.TrimSpace(params.Message) == "" {
-		return nil, errors.New("MCP confirmation requires a server name and message")
-	}
-	return s.deferCodexPermission(rpcID, codexMCPApproval, "mcp:"+params.ServerName, params.Message, "", raw, nil)
-}
diff --git a/apps/daemon/internal/agent/codex/server_requests_mcp_test.go b/apps/daemon/internal/agent/codex/server_requests_mcp_test.go
deleted file mode 100644
index a72ec3d9e..000000000
--- a/apps/daemon/internal/agent/codex/server_requests_mcp_test.go
+++ /dev/null
@@ -1,100 +0,0 @@
-package codex
-
-import (
-	"encoding/json"
-	"errors"
-	"testing"
-	"time"
-
-	"github.com/MiniMax-AI/OpenAgentCore/apps/daemon/internal/agent"
-	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
-)
-
-func TestCodexMCPConfirmationUsesPermissionLifecycle(t *testing.T) {
-	for _, action := range []string{"approve", "deny", "expire"} {
-		t.Run(action, func(t *testing.T) {
-			tc, srv, cleanup := NewTestClient()
-			defer cleanup()
-			s, out := newInteractionTestSession(tc.JSONRPCClient)
-			defer s.stopCodexInteractionTimers()
-			params := json.RawMessage(`{"threadId":"thread-1","turnId":"turn-1","serverName":"qa-service-desk","mode":"form","message":"Allow get_test_ticket?","requestedSchema":{"type":"object","properties":{}},"_meta":{"codex_approval_kind":"mcp_tool_call","persist":["session","always"]}}`)
-			if err := SendServerRequest(srv, "rpc-mcp", "mcpServer/elicitation/request", params); err != nil {
-				t.Fatal(err)
-			}
-			var env proto.Envelope
-			select {
-			case env = <-out:
-			case <-time.After(2 * time.Second):
-				t.Fatal("MCP confirmation was not surfaced")
-			}
-			var request proto.PermissionRequestPayload
-			if err := env.DecodePayload(&request); err != nil {
-				t.Fatal(err)
-			}
-			if env.Type != proto.TypePermissionRequest || env.ID != "run-test" || request.RequestID == "" || request.Tool != "mcp:qa-service-desk" || request.Title != "Allow get_test_ticket?" {
-				t.Fatalf("incorrect confirmation: %+v / %+v", env, request)
-			}
-			done := make(chan error, 1)
-			go func() {
-				if action == "expire" {
-					s.expireCodexPermission(request.RequestID)
-					done <- nil
-					return
-				}
-				done <- s.SubmitPermission(t.Context(), request.RequestID, proto.PermissionDecisionPayload{Approved: action == "approve"})
-			}()
-			var reply struct {
-				ID     string                     `json:"id"`
-				Result map[string]json.RawMessage `json:"result"`
-			}
-			decodeCodexReply(t, srv, &reply)
-			if err := <-done; err != nil {
-				t.Fatal(err)
-			}
-			wantAction, wantContent := `"decline"`, `null`
-			if action == "approve" {
-				wantAction, wantContent = `"accept"`, `{}`
-			}
-			if reply.ID != "rpc-mcp" || len(reply.Result) != 2 || string(reply.Result["action"]) != wantAction || string(reply.Result["content"]) != wantContent {
-				t.Fatalf("incorrect MCP response: %+v", reply)
-			}
-			if err := s.SubmitPermission(t.Context(), request.RequestID, proto.PermissionDecisionPayload{Approved: true}); !errors.Is(err, agent.ErrUnknownPermission) {
-				t.Fatalf("resolved confirmation accepted again: %v", err)
-			}
-		})
-	}
-}
-
-func TestCodexMCPElicitationRejectsUnsupportedInputWithoutApproval(t *testing.T) {
-	for _, params := range []string{
-		`{"serverName":"qa","mode":"form","message":"Enter name","requestedSchema":{"type":"object","properties":{"name":{"type":"string"}}}}`,
-		`{"serverName":"qa","mode":"url","message":"Sign in","url":"https://example.test/login","elicitationId":"login"}`,
-		`{"serverName":"qa","mode":"form","message":"Confirm","requestedSchema":{"type":"object","properties":{},"required":["name"]}}`,
-		`{"serverName":"qa","mode":"form","message":"Confirm","requestedSchema":{"type":"object"}}`,
-		`{"mode":"form","requestedSchema":{"type":"object","properties":{}}}`,
-	} {
-		t.Run(params, func(t *testing.T) {
-			tc, srv, cleanup := NewTestClient()
-			defer cleanup()
-			s, out := newInteractionTestSession(tc.JSONRPCClient)
-			defer s.stopCodexInteractionTimers()
-			if err := SendServerRequest(srv, "rpc-unsupported", "mcpServer/elicitation/request", json.RawMessage(params)); err != nil {
-				t.Fatal(err)
-			}
-			var reply struct {
-				Error *struct {
-					Code int `json:"code"`
-				} `json:"error"`
-			}
-			decodeCodexReply(t, srv, &reply)
-			if reply.Error == nil || reply.Error.Code != -32603 {
-				t.Fatalf("unsupported input was not rejected: %+v", reply)
-			}
-			select {
-			case env := <-out:
-				t.Fatalf("unsupported input became an approval: %+v", env)
-			default:
-			}
-		})
-	}
-}
diff --git a/apps/daemon/internal/agent/codex/server_requests_test.go b/apps/daemon/internal/agent/codex/server_requests_test.go
deleted file mode 100644
index 4bae35ed0..000000000
--- a/apps/daemon/internal/agent/codex/server_requests_test.go
+++ /dev/null
@@ -1,357 +0,0 @@
-package codex
-
-import (
-	"context"
-	"encoding/json"
-	"errors"
-	"testing"
-	"time"
-
-	"github.com/MiniMax-AI/OpenAgentCore/apps/daemon/internal/agent"
-	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
-)
-
-func newInteractionTestSession(rpc *JSONRPCClient) (*Session, <-chan proto.Envelope) {
-	out := make(chan proto.Envelope, 1)
-	ctx, cancel := context.WithCancel(context.Background())
-	s := &Session{
-		runID:        "run-test",
-		out:          out,
-		rpc:          rpc,
-		cancelCtx:    ctx,
-		cancelFn:     cancel,
-		interactions: newPendingCodexInteractions(),
-	}
-	s.registerHandlers()
-	return s, out
-}
-
-func TestCodexPermissionRequestWaitsForHumanDecision(t *testing.T) {
-	tc, srv, cleanup := NewTestClient()
-	defer cleanup()
-	s, out := newInteractionTestSession(tc.JSONRPCClient)
-
-	command := "go test ./..."
-	reason := "requires process execution"
-	if err := SendServerRequest(srv, "rpc-perm-1", "item/commandExecution/requestApproval", CommandExecutionRequestApprovalParams{
-		ThreadID: "thread-1", TurnID: "turn-1", ItemID: "item-1", Command: &command, Reason: &reason,
-	}); err != nil {
-		t.Fatalf("send server request: %v", err)
-	}
-
-	var env proto.Envelope
-	select {
-	case env = <-out:
-	case <-time.After(2 * time.Second):
-		t.Fatal("permission request was not surfaced to OpenAgentCore")
-	}
-	if env.Type != proto.TypePermissionRequest {
-		t.Fatalf("envelope type = %q, want %q", env.Type, proto.TypePermissionRequest)
-	}
-	var request proto.PermissionRequestPayload
-	if err := env.DecodePayload(&request); err != nil {
-		t.Fatalf("decode permission payload: %v", err)
-	}
-	if env.ID != "run-test" || request.RequestID == "" {
-		t.Fatalf("permission correlation = env.ID %q request.ID %q", env.ID, request.RequestID)
-	}
-	if request.Tool != "command_execution" || request.Title != command || request.Detail != reason {
-		t.Fatalf("permission payload = %+v", request)
-	}
-
-	submitDone := make(chan error, 1)
-	go func() {
-		submitDone <- s.SubmitPermission(context.Background(), request.RequestID, proto.PermissionDecisionPayload{Approved: true})
-	}()
-	reply := readCodexServerReply(t, srv)
-	if err := <-submitDone; err != nil {
-		t.Fatalf("submit permission: %v", err)
-	}
-	if reply.ID != "rpc-perm-1" || reply.Result.Decision != "accept" {
-		t.Fatalf("reply = %+v", reply)
-	}
-}
-
-func TestCodexPermissionsApprovalUsesDedicatedResponseSchema(t *testing.T) {
-	for _, tt := range []struct {
-		name       string
-		approved   bool
-		wantGrants bool
-	}{
-		{name: "approve echoes requested grants", approved: true, wantGrants: true},
-		{name: "deny grants nothing", approved: false, wantGrants: false},
-	} {
-		t.Run(tt.name, func(t *testing.T) {
-			tc, srv, cleanup := NewTestClient()
-			defer cleanup()
-			s, out := newInteractionTestSession(tc.JSONRPCClient)
-			requested := map[string]any{
-				"network":    map[string]any{"enabled": true},
-				"fileSystem": map[string]any{"write": []any{"/workspace"}},
-			}
-			if err := SendServerRequest(srv, "rpc-permissions", "item/permissions/requestApproval", PermissionsRequestApprovalParams{
-				Cwd: "/workspace", Permissions: requested,
-			}); err != nil {
-				t.Fatalf("send permissions request: %v", err)
-			}
-			env := <-out
-			var request proto.PermissionRequestPayload
-			if err := env.DecodePayload(&request); err != nil {
-				t.Fatalf("decode permission payload: %v", err)
-			}
-			done := make(chan error, 1)
-			go func() {
-				done <- s.SubmitPermission(context.Background(), request.RequestID, proto.PermissionDecisionPayload{Approved: tt.approved})
-			}()
-			var reply struct {
-				ID     string `json:"id"`
-				Result struct {
-					Permissions map[string]any `json:"permissions"`
-					Scope       string         `json:"scope"`
-					Decision    string         `json:"decision"`
-				} `json:"result"`
-			}
-			decodeCodexReply(t, srv, &reply)
-			if err := <-done; err != nil {
-				t.Fatalf("submit permissions: %v", err)
-			}
-			if reply.Result.Scope != "turn" || reply.Result.Decision != "" {
-				t.Fatalf("permissions reply = %+v", reply.Result)
-			}
-			_, granted := reply.Result.Permissions["network"]
-			if granted != tt.wantGrants {
-				t.Fatalf("permissions = %+v, want grants=%v", reply.Result.Permissions, tt.wantGrants)
-			}
-		})
-	}
-}
-
-func TestCodexUserInputMapsAnswersByQuestionID(t *testing.T) {
-	tc, srv, cleanup := NewTestClient()
-	defer cleanup()
-	s, out := newInteractionTestSession(tc.JSONRPCClient)
-
-	autoResolutionMs := uint64(120_000)
-	if err := SendServerRequest(srv, "rpc-ask-1", "item/tool/requestUserInput", ToolRequestUserInputParams{
-		ThreadID: "thread-1", TurnID: "turn-1", ItemID: "item-ask",
-		AutoResolutionMs: &autoResolutionMs,
-		Questions: []ToolRequestUserInputQuestion{
-			{ID: "deployment", Header: "Deploy", Question: "Where?", IsOther: true, Options: []ToolRequestUserInputOption{{Label: "Staging"}, {Label: "Production"}}},
-			{ID: "checks", Header: "Checks", Question: "Which checks?", IsSecret: true, Options: []ToolRequestUserInputOption{{Label: "Unit"}, {Label: "E2E"}}},
-		},
-	}); err != nil {
-		t.Fatalf("send server request: %v", err)
-	}
-
-	var env proto.Envelope
-	select {
-	case env = <-out:
-	case <-time.After(2 * time.Second):
-		t.Fatal("requestUserInput was not surfaced to OpenAgentCore")
-	}
-	if env.Type != proto.TypePromptForUserChoice {
-		t.Fatalf("envelope type = %q, want %q", env.Type, proto.TypePromptForUserChoice)
-	}
-	var request proto.PromptForUserChoicePayload
-	if err := env.DecodePayload(&request); err != nil {
-		t.Fatalf("decode user input payload: %v", err)
-	}
-	if len(request.Questions) != 2 || request.Questions[0].ID != "deployment" || request.Questions[1].ID != "checks" || request.Questions[0].Header != "Deploy" {
-		t.Fatalf("user input payload = %+v", request)
-	}
-	if !request.Questions[0].IsOther || !request.Questions[1].IsSecret || request.AutoResolutionMs == nil || *request.AutoResolutionMs != autoResolutionMs {
-		t.Fatalf("user input metadata = %+v", request)
-	}
-	s.interactions.mu.Lock()
-	pending := s.interactions.asks[request.AskID]
-	s.interactions.mu.Unlock()
-	if pending.timeout != 2*time.Minute {
-		t.Fatalf("ask timeout = %v, want 2m", pending.timeout)
-	}
-
-	if err := s.SubmitPromptForUserChoice(context.Background(), request.AskID, proto.PromptForUserChoiceDecisionPayload{
-		QuestionAnswers: []proto.PromptForUserChoiceQuestionAnswer{{QuestionID: "foreign", Answers: []string{"yes"}}},
-	}); err == nil {
-		t.Fatal("accepted a foreign question ID")
-	}
-	// Invalid identity must leave the original native request pending.
-	submitDone := make(chan error, 1)
-	go func() {
-		submitDone <- s.SubmitPromptForUserChoice(context.Background(), request.AskID, proto.PromptForUserChoiceDecisionPayload{
-			QuestionAnswers: []proto.PromptForUserChoiceQuestionAnswer{
-				{QuestionID: "checks", Answers: []string{"Unit", "E2E"}},
-				{QuestionID: "deployment", Answers: []string{"Staging"}},
-			},
-		})
-	}()
-
-	var reply struct {
-		ID     string                       `json:"id"`
-		Result ToolRequestUserInputResponse `json:"result"`
-	}
-	decodeCodexReply(t, srv, &reply)
-	if err := <-submitDone; err != nil {
-		t.Fatalf("submit user input: %v", err)
-	}
-	if reply.ID != "rpc-ask-1" {
-		t.Fatalf("reply id = %q", reply.ID)
-	}
-	if got := reply.Result.Answers["deployment"].Answers; len(got) != 1 || got[0] != "Staging" {
-		t.Fatalf("deployment answers = %v", got)
-	}
-	if got := reply.Result.Answers["checks"].Answers; len(got) != 2 || got[0] != "Unit" || got[1] != "E2E" {
-		t.Fatalf("checks answers = %v", got)
-	}
-}
-
-func TestCodexUserInputCancellationReturnsErrorInsteadOfEmptyAnswers(t *testing.T) {
-	tc, srv, cleanup := NewTestClient()
-	defer cleanup()
-	s, out := newInteractionTestSession(tc.JSONRPCClient)
-
-	if err := SendServerRequest(srv, "rpc-ask-cancel", "item/tool/requestUserInput", ToolRequestUserInputParams{
-		Questions: []ToolRequestUserInputQuestion{{ID: "confirm", Header: "Confirm", Question: "Continue?"}},
-	}); err != nil {
-		t.Fatalf("send server request: %v", err)
-	}
-	var env proto.Envelope
-	select {
-	case env = <-out:
-	case <-time.After(2 * time.Second):
-		t.Fatal("requestUserInput was not surfaced to OpenAgentCore")
-	}
-	var request proto.PromptForUserChoicePayload
-	if err := env.DecodePayload(&request); err != nil {
-		t.Fatalf("decode user input payload: %v", err)
-	}
-	submitDone := make(chan error, 1)
-	go func() {
-		submitDone <- s.SubmitPromptForUserChoice(context.Background(), request.AskID, proto.PromptForUserChoiceDecisionPayload{
-			Cancelled: true, Reason: "cancelled by user",
-		})
-	}()
-
-	var reply struct {
-		ID    string `json:"id"`
-		Error *struct {
-			Code    int    `json:"code"`
-			Message string `json:"message"`
-		} `json:"error"`
-	}
-	decodeCodexReply(t, srv, &reply)
-	if err := <-submitDone; err != nil {
-		t.Fatalf("cancel user input: %v", err)
-	}
-	if reply.ID != "rpc-ask-cancel" || reply.Error == nil || reply.Error.Code != -32001 {
-		t.Fatalf("cancel reply = %+v", reply)
-	}
-}
-
-func TestCodexInteractionExpiryUnblocksRuntime(t *testing.T) {
-	t.Run("permission declines", func(t *testing.T) {
-		tc, srv, cleanup := NewTestClient()
-		defer cleanup()
-		s, out := newInteractionTestSession(tc.JSONRPCClient)
-		command := "deploy"
-		if err := SendServerRequest(srv, "rpc-perm-timeout", "item/commandExecution/requestApproval", CommandExecutionRequestApprovalParams{Command: &command}); err != nil {
-			t.Fatalf("send permission request: %v", err)
-		}
-		env := <-out
-		var request proto.PermissionRequestPayload
-		if err := env.DecodePayload(&request); err != nil {
-			t.Fatalf("decode permission payload: %v", err)
-		}
-		expireDone := make(chan struct{})
-		go func() { s.expireCodexPermission(request.RequestID); close(expireDone) }()
-		reply := readCodexServerReply(t, srv)
-		<-expireDone
-		if reply.Result.Decision != "decline" {
-			t.Fatalf("expiry decision = %q", reply.Result.Decision)
-		}
-		if err := s.SubmitPermission(context.Background(), request.RequestID, proto.PermissionDecisionPayload{Approved: true}); !errors.Is(err, agent.ErrUnknownPermission) {
-			t.Fatalf("late permission error = %v, want ErrUnknownPermission", err)
-		}
-	})
-
-	t.Run("permission profile grants nothing", func(t *testing.T) {
-		tc, srv, cleanup := NewTestClient()
-		defer cleanup()
-		s, out := newInteractionTestSession(tc.JSONRPCClient)
-		if err := SendServerRequest(srv, "rpc-profile-timeout", "item/permissions/requestApproval", PermissionsRequestApprovalParams{
-			Permissions: map[string]any{"network": map[string]any{"enabled": true}},
-		}); err != nil {
-			t.Fatalf("send permission profile request: %v", err)
-		}
-		env := <-out
-		var request proto.PermissionRequestPayload
-		if err := env.DecodePayload(&request); err != nil {
-			t.Fatalf("decode permission payload: %v", err)
-		}
-		done := make(chan struct{})
-		go func() { s.expireCodexPermission(request.RequestID); close(done) }()
-		var reply struct {
-			Result PermissionsRequestApprovalResponse `json:"result"`
-		}
-		decodeCodexReply(t, srv, &reply)
-		<-done
-		if len(reply.Result.Permissions) != 0 || reply.Result.Scope != "turn" {
-			t.Fatalf("expiry permissions response = %+v", reply.Result)
-		}
-	})
-
-	t.Run("user input returns timeout error", func(t *testing.T) {
-		tc, srv, cleanup := NewTestClient()
-		defer cleanup()
-		s, out := newInteractionTestSession(tc.JSONRPCClient)
-		if err := SendServerRequest(srv, "rpc-ask-timeout", "item/tool/requestUserInput", ToolRequestUserInputParams{
-			Questions: []ToolRequestUserInputQuestion{{ID: "q1", Header: "Confirm", Question: "Continue?"}},
-		}); err != nil {
-			t.Fatalf("send input request: %v", err)
-		}
-		var request proto.PromptForUserChoicePayload
-		if err := (<-out).DecodePayload(&request); err != nil {
-			t.Fatalf("decode input request: %v", err)
-		}
-		expireDone := make(chan struct{})
-		go func() { s.expireCodexAsk(request.AskID); close(expireDone) }()
-		var reply struct {
-			Error *struct {
-				Code int `json:"code"`
-			} `json:"error"`
-		}
-		decodeCodexReply(t, srv, &reply)
-		<-expireDone
-		if reply.Error == nil || reply.Error.Code != -32001 {
-			t.Fatalf("expiry reply = %+v", reply)
-		}
-		if err := s.SubmitPromptForUserChoice(context.Background(), request.AskID, proto.PromptForUserChoiceDecisionPayload{QuestionAnswers: []proto.PromptForUserChoiceQuestionAnswer{{QuestionID: "q0", Answers: []string{"yes"}}}}); !errors.Is(err, agent.ErrUnknownAsk) {
-			t.Fatalf("late input error = %v, want ErrUnknownAsk", err)
-		}
-	})
-}
-
-type approvalReply struct {
-	ID     string                 `json:"id"`
-	Result ApprovalDecisionResult `json:"result"`
-}
-
-func readCodexServerReply(t *testing.T, srv ServerSide) approvalReply {
-	t.Helper()
-	var reply approvalReply
-	decodeCodexReply(t, srv, &reply)
-	return reply
-}
-
-func decodeCodexReply(t *testing.T, srv ServerSide, target any) {
-	t.Helper()
-	done := make(chan error, 1)
-	go func() { done <- json.NewDecoder(srv.FromClient).Decode(target) }()
-	select {
-	case err := <-done:
-		if err != nil {
-			t.Fatalf("decode Codex reply: %v", err)
-		}
-	case <-time.After(2 * time.Second):
-		t.Fatal("Codex reply timed out")
-	}
-}
diff --git a/apps/daemon/internal/agent/codex/session.go b/apps/daemon/internal/agent/codex/session.go
index 27ab44063..1a5db1094 100644
--- a/apps/daemon/internal/agent/codex/session.go
+++ b/apps/daemon/internal/agent/codex/session.go
@@ -20,8 +20,8 @@ import (
 // adapter safety net.
 const terminalSendTimeout = 2 * time.Second
 
-// sessionConfig is the cross-cutting knob bag — production callers go
-// through Factory which uses defaults.
+// sessionConfig is the cross-cutting knob bag; production callers use
+// defaultSessionConfig.
 type sessionConfig struct {
 	// codexBinary is the trusted install on this host. Probes run it here.
 	codexBinary string
@@ -39,13 +39,6 @@ func defaultSessionConfig() sessionConfig {
 	}
 }
 
-// Factory implements agent.Factory for agent_kind="codex". Spawns one
-// codex app-server child for one Turn. The run stream closes when the turn
-// completes; the child remains until the caller cancels the Session.
-func Factory(ctx context.Context, req proto.PromptRequestPayload, out chan<- proto.Envelope) (agent.Session, error) {
-	return newSession(ctx, req, out, defaultSessionConfig())
-}
-
 // Session implements agent.Session. State lifecycle:
 //
 //  1. Preparation initializes RPC and verifies the selected environment.
@@ -113,24 +106,11 @@ type Session struct {
 	finalText   string
 	lastErrText string
 
-	interactions *pendingCodexInteractions
-	outcome      cancellationOutcomeState
+	outcome cancellationOutcomeState
 }
 
 var _ agent.Session = (*Session)(nil)
 
-// SubmitPermission completes the deferred Codex app-server request that
-// produced the Core permission envelope.
-func (s *Session) SubmitPermission(_ context.Context, permID string, decision proto.PermissionDecisionPayload) error {
-	return s.submitCodexPermission(permID, decision)
-}
-
-// SubmitPromptForUserChoice maps Core's header/answer pairs back to
-// Codex's question-id keyed requestUserInput response.
-func (s *Session) SubmitPromptForUserChoice(_ context.Context, askID string, decision proto.PromptForUserChoiceDecisionPayload) error {
-	return s.submitCodexUserInput(askID, decision)
-}
-
 // ---------------------------------------------------------------------------
 // notification handlers
 // ---------------------------------------------------------------------------
@@ -152,14 +132,10 @@ func (s *Session) registerHandlers() {
 	rpc.OnNotification("thread/tokenUsage/updated", s.onUsageUpdated)
 	rpc.OnNotification("error", s.onErrorNotif)
 
-	s.onServerRequest("item/commandExecution/requestApproval", s.handleCodexCommandApproval)
-	s.onServerRequest("item/fileChange/requestApproval", s.handleCodexFileApproval)
-	s.onServerRequest("item/permissions/requestApproval", s.handleCodexPermissionsApproval)
-	// Older app-server releases used this unseparated method name.
-	s.onServerRequest("item/permissionsRequestApproval", s.handleCodexPermissionsApproval)
-	s.onServerRequest("item/tool/requestUserInput", s.handleCodexUserInput)
+	// Harnesses run unattended. Approval policy never and the session plan keep
+	// native asks from being raised; any other server request gets the
+	// client's method-not-found reply.
 	s.onServerRequest("item/tool/call", s.handleFunctionCall)
-	s.onServerRequest("mcpServer/elicitation/request", s.handleCodexMCPElicitation)
 }
 
 func (s *Session) onTurnStarted(raw json.RawMessage) {
diff --git a/apps/daemon/internal/agent/codex/session_cancel.go b/apps/daemon/internal/agent/codex/session_cancel.go
index 25024d5b5..091eae119 100644
--- a/apps/daemon/internal/agent/codex/session_cancel.go
+++ b/apps/daemon/internal/agent/codex/session_cancel.go
@@ -42,7 +42,6 @@ func (s *Session) cancelNativeWork() {
 	defer close(s.cancelReady)
 	s.stopFunctionCalls()
 	turnID, active := s.stopSteering()
-	s.stopCodexInteractionTimers()
 	// Best effort: a known Turn must use its native identity. An explicit
 	// empty ID invokes native startup cancellation before turn/started.
 	if threadID := s.currentThreadID(); threadID != "" && active {
diff --git a/apps/daemon/internal/agent/codex/session_cancel_test.go b/apps/daemon/internal/agent/codex/session_cancel_test.go
index b5879197b..32e794b6a 100644
--- a/apps/daemon/internal/agent/codex/session_cancel_test.go
+++ b/apps/daemon/internal/agent/codex/session_cancel_test.go
@@ -116,7 +116,7 @@ func cancellationTestSession(t *testing.T) (*Session, *TestClient, ServerSide) {
 	ctx, cancel := context.WithCancel(context.Background())
 	t.Cleanup(cancel)
 	s := &Session{rpc: client.JSONRPCClient, cancelCtx: ctx, cancelFn: cancel,
-		cfg: defaultSessionConfig(), interactions: newPendingCodexInteractions(), out: make(chan proto.Envelope, 8), bufs: NewItemBuffers()}
+		cfg: defaultSessionConfig(), out: make(chan proto.Envelope, 8), bufs: NewItemBuffers()}
 	return s, client, server
 }
 
diff --git a/apps/daemon/internal/agent/codex/session_cancel_write_test.go b/apps/daemon/internal/agent/codex/session_cancel_write_test.go
index 53cbb1392..bb2abe700 100644
--- a/apps/daemon/internal/agent/codex/session_cancel_write_test.go
+++ b/apps/daemon/internal/agent/codex/session_cancel_write_test.go
@@ -146,7 +146,7 @@ func TestCancelReleasesBlockedNativeProcess(t *testing.T) {
 	ctx, cancel := context.WithCancel(context.Background())
 	defer cancel()
 	s := &Session{rpc: client, cancelCtx: ctx, cancelFn: cancel,
-		cfg: defaultSessionConfig(), interactions: newPendingCodexInteractions(), bufs: NewItemBuffers()}
+		cfg: defaultSessionConfig(), bufs: NewItemBuffers()}
 	s.setThreadID("native-thread")
 	s.onTurnStarted(json.RawMessage(`{"threadId":"native-thread","turn":{"id":"native-turn"}}`))
 	cancelDone := make(chan struct{})
diff --git a/apps/daemon/internal/agent/codex/session_plan.go b/apps/daemon/internal/agent/codex/session_plan.go
index ea99f3174..cb8008cb2 100644
--- a/apps/daemon/internal/agent/codex/session_plan.go
+++ b/apps/daemon/internal/agent/codex/session_plan.go
@@ -31,9 +31,6 @@ func prepareSessionPlan(ctx context.Context, req proto.PromptRequestPayload, cfg
 	disableProgrammaticTools(&plan, req.ExecutionControls)
 	if req.LocalEnvironment != nil {
 		plan.Cwd = req.LocalEnvironment.WorkspaceRoot
-		plan.Sandbox = "danger-full-access"
-		plan.Permissions = ""
-		plan.ApprovalPolicy = AskForApproval{String: "never"}
 	} else {
 		// environment:none has no workspace; the Session's private home is its cwd.
 		plan.Cwd = plan.home.View
diff --git a/apps/daemon/internal/agent/codex/session_run.go b/apps/daemon/internal/agent/codex/session_run.go
index 7517bfb98..3394acf90 100644
--- a/apps/daemon/internal/agent/codex/session_run.go
+++ b/apps/daemon/internal/agent/codex/session_run.go
@@ -9,29 +9,6 @@ import (
 	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
 )
 
-func (s *Session) run(plan SessionPlan, req proto.PromptRequestPayload) {
-	defer close(s.waitDone)
-	defer s.stopCodexInteractionTimers()
-	defer s.stopFunctionCalls()
-	defer s.cleanup()
-	defer s.closeRunOutput()
-
-	if err := s.startNative(s.cancelCtx, plan, req); err != nil {
-		s.emitTerminal(err.Error(), true)
-		return
-	}
-
-	// Block until terminal handlers close the RPC child or cancellation arrives.
-	select {
-	case <-s.rpc.Done():
-		if !s.cancelled.Load() && s.cancelCtx.Err() == nil {
-			s.emitTerminal("codex: connection closed before the run completed", true)
-		}
-	case <-s.cancelCtx.Done():
-		_ = s.rpc.Close()
-	}
-}
-
 func (s *Session) startNative(ctx context.Context, plan SessionPlan, req proto.PromptRequestPayload) error {
 	if s.currentThreadID() == "" {
 		if err := s.resolveThread(req, plan); err != nil {
diff --git a/apps/daemon/internal/agent/codex/session_steering_lifecycle_test.go b/apps/daemon/internal/agent/codex/session_steering_lifecycle_test.go
index 9b2bf38f0..6dc663ea0 100644
--- a/apps/daemon/internal/agent/codex/session_steering_lifecycle_test.go
+++ b/apps/daemon/internal/agent/codex/session_steering_lifecycle_test.go
@@ -83,10 +83,11 @@ func TestBlockedSteeringWriteEndsRunWithTerminalFrames(t *testing.T) {
 	ctx, cancel := context.WithTimeout(context.Background(), 3*time.Second)
 	defer cancel()
 	out := make(chan proto.Envelope, 8)
+	turnCtx, cancelTurn := context.WithCancel(ctx)
 	s := &Session{
-		runID: "run", rpc: client.JSONRPCClient, cancelCtx: ctx, out: out, resolvedModel: "synthetic",
-		cfg: sessionConfig{logger: obslog.Bg()}, waitDone: make(chan struct{}), cleanup: func() {},
-		bufs: NewItemBuffers(), interactions: newPendingCodexInteractions(),
+		executor: &Executor{}, runID: "run", rpc: client.JSONRPCClient, cancelCtx: turnCtx, cancelFn: cancelTurn, out: out, resolvedModel: "synthetic",
+		cfg: sessionConfig{logger: obslog.Bg()}, waitDone: make(chan struct{}), outputDone: make(chan struct{}), cleanup: func() {},
+		bufs: NewItemBuffers(),
 	}
 	s.registerHandlers()
 	ready := make(chan error, 1)
@@ -119,7 +120,8 @@ func TestBlockedSteeringWriteEndsRunWithTerminalFrames(t *testing.T) {
 		}
 		ready <- nil
 	}()
-	go s.run(SessionPlan{Model: "synthetic"}, proto.PromptRequestPayload{Input: proto.TextInput("first")})
+	// Executor.StartTurn starts and settles each Turn through these two steps.
+	go s.settleExecutorTurn(s.startNative(ctx, SessionPlan{Model: "synthetic"}, proto.PromptRequestPayload{Input: proto.TextInput("first")}))
 	if err := <-ready; err != nil {
 		t.Fatal(err)
 	}
diff --git a/apps/daemon/internal/agent/codex/session_thread.go b/apps/daemon/internal/agent/codex/session_thread.go
index 28681b400..35699b8a8 100644
--- a/apps/daemon/internal/agent/codex/session_thread.go
+++ b/apps/daemon/internal/agent/codex/session_thread.go
@@ -5,14 +5,20 @@ import (
 	"fmt"
 )
 
+// Harnesses run unattended with the launching user's permissions: Codex never
+// raises a native approval request and applies no inner sandbox.
+const (
+	approvalPolicyNever     = "never"
+	sandboxDangerFullAccess = "danger-full-access"
+)
+
 func (s *Session) startThread(plan SessionPlan) error {
 	params := ThreadStartParams{
 		Cwd:                   plan.Cwd,
 		Model:                 plan.Model,
 		ModelProvider:         plan.ModelProvider,
-		ApprovalPolicy:        plan.ApprovalPolicy,
-		Sandbox:               plan.Sandbox,
-		Permissions:           plan.Permissions,
+		ApprovalPolicy:        approvalPolicyNever,
+		Sandbox:               sandboxDangerFullAccess,
 		DeveloperInstructions: plan.SystemPrompt,
 	}
 	if s.observeSubagentIdentities {
@@ -26,8 +32,7 @@ func (s *Session) startThread(plan SessionPlan) error {
 		"cwd", params.Cwd,
 		"model", params.Model,
 		"model_provider", params.ModelProvider,
-		"sandbox", string(params.Sandbox),
-		"approval_silent", IsSilent(&params.ApprovalPolicy),
+		"sandbox", params.Sandbox,
 		"developer_instructions_len", len(params.DeveloperInstructions))
 	_, err := s.rpc.requestWithResult(s.cancelCtx, "thread/start", params, func(raw json.RawMessage) error {
 		return s.bindThreadResult(raw, "")
@@ -37,8 +42,7 @@ func (s *Session) startThread(plan SessionPlan) error {
 
 func (s *Session) resumeThread(threadID string, plan SessionPlan) error {
 	params := ThreadResumeParams{
-		ThreadID: threadID, ApprovalPolicy: plan.ApprovalPolicy, Sandbox: plan.Sandbox,
-		Permissions:           plan.Permissions,
+		ThreadID: threadID, ApprovalPolicy: approvalPolicyNever, Sandbox: sandboxDangerFullAccess,
 		DeveloperInstructions: plan.SystemPrompt,
 	}
 	if plan.mcpServers != nil {
diff --git a/apps/daemon/internal/agent/codex/subagent_observations_test.go b/apps/daemon/internal/agent/codex/subagent_observations_test.go
index 7c4b79415..a96258ca7 100644
--- a/apps/daemon/internal/agent/codex/subagent_observations_test.go
+++ b/apps/daemon/internal/agent/codex/subagent_observations_test.go
@@ -75,7 +75,7 @@ func observationSession(t *testing.T, status string) (*Session, *subagentFixture
 		t.Fatal(err)
 	}
 	f.persist(t)
-	s := &Session{runID: "run", nativeHome: agent.ViewDir{Host: f.home, View: f.home}, rpc: client.JSONRPCClient, out: out, cancelCtx: ctx, cancelFn: cancel, cfg: defaultSessionConfig(), bufs: NewItemBuffers(), interactions: newPendingCodexInteractions()}
+	s := &Session{runID: "run", nativeHome: agent.ViewDir{Host: f.home, View: f.home}, rpc: client.JSONRPCClient, out: out, cancelCtx: ctx, cancelFn: cancel, cfg: defaultSessionConfig(), bufs: NewItemBuffers()}
 	s.setThreadID("root")
 	s.beginRootTurn("root", "root-turn")
 	s.startSubagentObservations()
diff --git a/apps/daemon/internal/agent/codex/view.go b/apps/daemon/internal/agent/codex/view.go
index 1f7d85bfa..b64e0c499 100644
--- a/apps/daemon/internal/agent/codex/view.go
+++ b/apps/daemon/internal/agent/codex/view.go
@@ -163,9 +163,6 @@ func prepareViewPlan(ctx context.Context, req proto.PromptRequestPayload, cfg se
 	}
 	disableProgrammaticTools(&plan, req.ExecutionControls)
 	plan.Cwd = cwd
-	plan.Sandbox = SandboxDangerFullAcces
-	plan.Permissions = ""
-	plan.ApprovalPolicy = AskForApproval{String: "never"}
 	if req.DisableSubagents {
 		disableSubagents(&plan)
 	}
diff --git a/apps/daemon/internal/agent/codex/view_test.go b/apps/daemon/internal/agent/codex/view_test.go
index a2a995f34..fda7a6bc3 100644
--- a/apps/daemon/internal/agent/codex/view_test.go
+++ b/apps/daemon/internal/agent/codex/view_test.go
@@ -24,7 +24,7 @@ func TestViewExecutorLaunchesInTheSessionView(t *testing.T) {
 	info := Declaration.Info
 	info.Available = true
 	registry := agent.NewRegistry()
-	registry.Register(Declaration, agent.Runtime{Info: info, Session: Factory, View: &declared})
+	registry.Register(Declaration, agent.Runtime{Info: info, View: &declared})
 	view, err := registry.ResolveView("codex")
 	if err != nil {
 		t.Fatal(err)
diff --git a/apps/daemon/internal/agent/configuration_test.go b/apps/daemon/internal/agent/configuration_test.go
index 2e6455f31..a1ad66749 100644
--- a/apps/daemon/internal/agent/configuration_test.go
+++ b/apps/daemon/internal/agent/configuration_test.go
@@ -18,41 +18,27 @@ func TestEveryRegistryEntryPreparesTheBoundModelConfiguration(t *testing.T) {
 	configuration := harnessconfig.Configuration{Providers: []harnessconfig.Provider{{Protocol: "responses"}}}
 	calls := 0
 	expected := errors.New("native entry reached")
-	registry.RegisterKind(proto.SupportedAgentKind{Kind: "fixture", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, configuration, func(context.Context, proto.PromptRequestPayload, chan<- proto.Envelope) (agent.Session, error) {
-		calls++
-		return nil, expected
-	})
+	registry.RegisterKind(proto.SupportedAgentKind{Kind: "fixture", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, configuration)
 	registry.RegisterExecutor("fixture", func(context.Context, proto.PromptRequestPayload) (agent.Executor, error) {
 		calls++
 		return nil, expected
 	})
 	configuration.Providers[0].Protocol = "anthropic"
-	factory, _ := registry.Resolve("fixture")
 	executor, _ := registry.ResolveExecutor("fixture")
-	entries := []func(proto.PromptRequestPayload) error{
-		func(req proto.PromptRequestPayload) error { _, err := factory(t.Context(), req, nil); return err },
-		func(req proto.PromptRequestPayload) error { _, err := executor(t.Context(), req); return err },
-	}
-	for _, entry := range entries {
-		responses := &modelprovider.Provider{Protocol: modelprovider.Responses, BaseURL: "https://provider.example", APIKey: "private-sentinel"}
-		for _, req := range []proto.PromptRequestPayload{
-			{Model: "fixture", ModelProvider: &modelprovider.Provider{Protocol: modelprovider.Anthropic, BaseURL: "https://provider.example", APIKey: "private-sentinel"}},
-			{ModelProvider: responses},
-			{Model: "fixture"},
-			{HarnessConfig: proto.HarnessConfig(`{"unknown":"private-sentinel"}`)},
-		} {
-			before := calls
-			err := entry(req)
-			if err == nil || errors.Is(err, expected) || calls != before || strings.Contains(err.Error(), "private-sentinel") {
-				t.Fatal("invalid configuration reached native entry or leaked values")
-			}
-		}
-		if err := entry(proto.PromptRequestPayload{Model: "fixture", ModelProvider: responses}); !errors.Is(err, expected) {
-			t.Fatal("bound declaration was lost or mutated", err)
+	responses := &modelprovider.Provider{Protocol: modelprovider.Responses, BaseURL: "https://provider.example", APIKey: "private-sentinel"}
+	for _, req := range []proto.PromptRequestPayload{
+		{Model: "fixture", ModelProvider: &modelprovider.Provider{Protocol: modelprovider.Anthropic, BaseURL: "https://provider.example", APIKey: "private-sentinel"}},
+		{ModelProvider: responses},
+		{Model: "fixture"},
+		{HarnessConfig: proto.HarnessConfig(`{"unknown":"private-sentinel"}`)},
+	} {
+		_, err := executor(t.Context(), req)
+		if err == nil || errors.Is(err, expected) || calls != 0 || strings.Contains(err.Error(), "private-sentinel") {
+			t.Fatal("invalid configuration reached native entry or leaked values")
 		}
 	}
-	if calls != 2 {
-		t.Fatal("unexpected native calls", calls)
+	if _, err := executor(t.Context(), proto.PromptRequestPayload{Model: "fixture", ModelProvider: responses}); !errors.Is(err, expected) || calls != 1 {
+		t.Fatal("bound declaration was lost or mutated", err)
 	}
 }
 
@@ -62,5 +48,5 @@ func TestRegistryRejectsInvalidConfigurationDeclaration(t *testing.T) {
 			t.Fatal("invalid configuration registered")
 		}
 	}()
-	agent.NewRegistry().RegisterKind(proto.SupportedAgentKind{Kind: "fixture", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, harnessconfig.Configuration{Providers: []harnessconfig.Provider{{Protocol: "unknown"}}}, stubFactory("fixture"))
+	agent.NewRegistry().RegisterKind(proto.SupportedAgentKind{Kind: "fixture", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, harnessconfig.Configuration{Providers: []harnessconfig.Provider{{Protocol: "unknown"}}})
 }
diff --git a/apps/daemon/internal/agent/contract_declarations_test.go b/apps/daemon/internal/agent/contract_declarations_test.go
index a07c4e29e..4479f26d4 100644
--- a/apps/daemon/internal/agent/contract_declarations_test.go
+++ b/apps/daemon/internal/agent/contract_declarations_test.go
@@ -22,8 +22,6 @@ func TestPublicHarnessContractDeclarations(t *testing.T) {
 		"DurableSteerer":           {"session"},
 		"Steerer":                  {"session"},
 		"FunctionResultSubmitter":  {"session"},
-		"PermissionResponder":      {"session"},
-		"UserChoiceResponder":      {"session"},
 		"WorkspaceDirectoryLister": {"executor", "session"},
 		"WorkspaceWriter":          {"executor", "session"},
 	}
diff --git a/apps/daemon/internal/agent/contracttest/text.go b/apps/daemon/internal/agent/contracttest/text.go
index 5c0d76e4a..c389163a7 100644
--- a/apps/daemon/internal/agent/contracttest/text.go
+++ b/apps/daemon/internal/agent/contracttest/text.go
@@ -32,7 +32,7 @@ type TextFixture struct {
 
 // TextLifecycle verifies ordinary reuse, exact Turn ownership, durable active
 // input, confirmed cancellation and continuation of a healthy Executor. It asks
-// for no optional tools, images, interactions, workspace or detailed Usage.
+// for no optional tools, images, workspace or detailed Usage.
 // Native fault injection and history recovery have separate adapter tests.
 func TextLifecycle(t *testing.T, fixture TextFixture) {
 	t.Helper()
diff --git a/apps/daemon/internal/agent/harness.go b/apps/daemon/internal/agent/harness.go
index 4f6bc8b26..e3d0b9826 100644
--- a/apps/daemon/internal/agent/harness.go
+++ b/apps/daemon/internal/agent/harness.go
@@ -14,8 +14,8 @@
 // Registration: each adapter exports one Declaration. The Runtime discovers the
 // static declaration list and installs each resulting Runtime through Register.
 // Availability and factory selection belong to the adapter. RegisterKind resets
-// the other factories, so Register installs it first. Preparation capabilities
-// are derived from the declared factories.
+// the factories, so Register installs it first. RegisterExecutor derives the
+// Preparation capability; the adapter declares WorkspaceReadPreparation.
 //
 // Runtime registration and Core service qualification remain separate. A public
 // Harness also needs a profile in services/core/internal/engine; advertising
@@ -48,7 +48,7 @@ import (
 
 // Declaration is the complete startup contract for a Harness implementation.
 // Discover returns nil when the adapter is not configured. An unavailable
-// configured adapter returns a Runtime with Available=false and a session factory.
+// configured adapter returns a Runtime with Available=false and no factories.
 // Discovery owns runtime-specific configuration, readiness and feature gates.
 type Declaration struct {
 	Info          proto.SupportedAgentKind
@@ -65,7 +65,6 @@ type DiscoveryOptions struct {
 // Runtime binds one discovered descriptor to its native factories.
 type Runtime struct {
 	Info     proto.SupportedAgentKind
-	Session  Factory
 	Executor ExecutorFactory
 	// View declares how the Harness runs in an agent-host Session view.
 	// A nil View means the agent host rejects the kind with ErrUnsupportedOperation.
@@ -77,7 +76,10 @@ func (r *Registry) Register(declaration Declaration, runtime Runtime) {
 	if runtime.Info.Kind != declaration.Info.Kind {
 		panic("agent.Registry.Register: discovery kind differs from declaration")
 	}
-	r.RegisterKind(runtime.Info, declaration.Configuration, runtime.Session)
+	if !runtime.Info.Available && runtime.Executor != nil {
+		panic("agent.Registry.Register: unavailable runtime has factories")
+	}
+	r.RegisterKind(runtime.Info, declaration.Configuration)
 	if runtime.Executor != nil {
 		r.RegisterExecutor(runtime.Info.Kind, runtime.Executor)
 	}
@@ -553,8 +555,8 @@ type Executor interface {
 type Turn interface {
 	Session
 	DurableSteerer
-	// Success confirms closed output and settled native input, function,
-	// interaction and child-work obligations. Errors cannot prove cancellation.
+	// Success confirms closed output and settled native input, function and
+	// child-work obligations. Errors cannot prove cancellation.
 	AwaitSettlement(context.Context) (TurnSettlement, error)
 }
 
@@ -565,8 +567,8 @@ type TurnSettlement struct {
 	Reason   string
 }
 
-// Session is the cancellation and outcome surface shared by direct-call
-// sessions and Turns. Every owner exposes observed state.
+// Session is the cancellation and outcome surface of a Turn. Every owner
+// exposes observed state.
 // For Executor-owned Turns, AwaitSettlement and Executor.Close define settlement
 // and resource retirement; Cancel alone does not transfer resource ownership.
 type Session interface {
@@ -602,20 +604,6 @@ type FunctionResultSubmitter interface {
 	SubmitFunctionResult(context.Context, proto.FunctionResultPayload) error
 }
 
-// PermissionResponder accepts decisions for qualified permission requests.
-// An adapter that never supports these interactions returns ErrUnsupportedOperation.
-// Unknown or expired requests return ErrUnknownPermission.
-type PermissionResponder interface {
-	SubmitPermission(context.Context, string, proto.PermissionDecisionPayload) error
-}
-
-// UserChoiceResponder accepts answers for qualified user-choice requests.
-// An adapter that never supports these interactions returns ErrUnsupportedOperation.
-// Unknown or expired requests return ErrUnknownAsk.
-type UserChoiceResponder interface {
-	SubmitPromptForUserChoice(context.Context, string, proto.PromptForUserChoiceDecisionPayload) error
-}
-
 // Workspace extensions, implemented by each owner explicitly. The common
 // Runtime may supply an authorized workspace owner independently of the adapter.
 // A resource without native access returns the corresponding Unsupported error;
@@ -640,25 +628,16 @@ type WorkspaceWriter interface {
 	WriteWorkspaceFile(context.Context, string, []byte) (WorkspaceWriteResult, error)
 }
 
-// Kind registration and the direct-call factory.
-
-// Factory builds a Session that runs req.Input as req.RunID without an
-// Executor; the router starts every Run through RegisterExecutor instead. out
-// is the channel the agent writes into and closes exactly once after terminal
-// output. ctx is cancelled to wind the session down.
-type Factory func(ctx context.Context, req proto.PromptRequestPayload, out chan<- proto.Envelope) (Session, error)
+// Kind registration.
 
-// RegisterKind installs f and the heartbeat descriptor for an
-// agent_kind. Callers may set Available=false when an adapter exists
-// but its underlying CLI is not usable.
-func (r *Registry) RegisterKind(info proto.SupportedAgentKind, configuration harnessconfig.Configuration, f Factory) {
+// RegisterKind installs the heartbeat descriptor and model configuration for an
+// agent_kind. Callers may set Available=false when an adapter exists but its
+// underlying CLI is not usable.
+func (r *Registry) RegisterKind(info proto.SupportedAgentKind, configuration harnessconfig.Configuration) {
 	kind := info.Kind
 	if kind == "" {
 		panic("agent.Registry.Register: empty kind")
 	}
-	if f == nil {
-		panic("agent.Registry.Register: nil factory")
-	}
 	if err := configuration.ValidateDeclaration(); err != nil {
 		panic(err)
 	}
@@ -669,12 +648,6 @@ func (r *Registry) RegisterKind(info proto.SupportedAgentKind, configuration har
 	r.mu.Lock()
 	defer r.mu.Unlock()
 	r.configurations[kind] = configuration
-	r.factories[kind] = func(ctx context.Context, req proto.PromptRequestPayload, out chan<- proto.Envelope) (Session, error) {
-		if _, err := configuration.Prepare(req); err != nil {
-			return nil, err
-		}
-		return f(ctx, req, out)
-	}
 	delete(r.executors, kind)
 	delete(r.views, kind)
 	info.Capabilities.Preparation = proto.CapabilityUnsupported
diff --git a/apps/daemon/internal/agent/installroot/lock.go b/apps/daemon/internal/agent/installroot/lock.go
deleted file mode 100644
index 19d9295e4..000000000
--- a/apps/daemon/internal/agent/installroot/lock.go
+++ /dev/null
@@ -1,69 +0,0 @@
-// Package installroot coordinates adapter installations within one daemon process.
-package installroot
-
-import (
-	"context"
-	"os"
-	"sync"
-)
-
-type installRootLock struct {
-	info  os.FileInfo
-	token chan struct{}
-	users int
-}
-
-var installRoots = struct {
-	sync.Mutex
-	entries map[*installRootLock]struct{}
-}{entries: make(map[*installRootLock]struct{})}
-
-// Lock creates the install root if needed and holds its filesystem identity
-// until the returned function is called once.
-// Waiting callers may cancel without interrupting the current installation.
-func Lock(ctx context.Context, root string) (func(), error) {
-	if err := ctx.Err(); err != nil {
-		return nil, err
-	}
-	if err := os.MkdirAll(root, 0o755); err != nil {
-		return nil, err
-	}
-	info, err := os.Stat(root)
-	if err != nil {
-		return nil, err
-	}
-	installRoots.Lock()
-	var entry *installRootLock
-	for candidate := range installRoots.entries {
-		if os.SameFile(candidate.info, info) {
-			entry = candidate
-			break
-		}
-	}
-	if entry == nil {
-		entry = &installRootLock{info: info, token: make(chan struct{}, 1)}
-		entry.token <- struct{}{}
-		installRoots.entries[entry] = struct{}{}
-	}
-	entry.users++
-	installRoots.Unlock()
-
-	release := func() {
-		installRoots.Lock()
-		entry.users--
-		if entry.users == 0 {
-			delete(installRoots.entries, entry)
-		}
-		installRoots.Unlock()
-	}
-	select {
-	case <-ctx.Done():
-		release()
-		return nil, ctx.Err()
-	case <-entry.token:
-		return func() {
-			entry.token <- struct{}{}
-			release()
-		}, nil
-	}
-}
diff --git a/apps/daemon/internal/agent/installroot/lock_test.go b/apps/daemon/internal/agent/installroot/lock_test.go
deleted file mode 100644
index 4359af299..000000000
--- a/apps/daemon/internal/agent/installroot/lock_test.go
+++ /dev/null
@@ -1,39 +0,0 @@
-package installroot
-
-import (
-	"context"
-	"os"
-	"path/filepath"
-	"strings"
-	"testing"
-	"time"
-)
-
-func TestLockCaseAliases(t *testing.T) {
-	parent := t.TempDir()
-	alias := strings.ToUpper(parent)
-	realInfo, err := os.Stat(parent)
-	if err != nil {
-		t.Fatal(err)
-	}
-	aliasInfo, err := os.Stat(alias)
-	if err != nil || !os.SameFile(realInfo, aliasInfo) {
-		t.Skip("filesystem does not expose this case alias")
-	}
-	root := filepath.Join(parent, "new-root")
-	unlock, err := Lock(context.Background(), root)
-	if err != nil {
-		t.Fatal(err)
-	}
-	defer unlock()
-	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Millisecond)
-	defer cancel()
-	release, err := Lock(ctx, filepath.Join(alias, "NEW-ROOT"))
-	if err == nil {
-		release()
-		t.Fatal("case alias acquired an independent lock")
-	}
-	if err != context.DeadlineExceeded {
-		t.Fatalf("lock error = %v", err)
-	}
-}
diff --git a/apps/daemon/internal/agent/installroot/probe.go b/apps/daemon/internal/agent/installroot/probe.go
index 21f50ed47..d2932e3f8 100644
--- a/apps/daemon/internal/agent/installroot/probe.go
+++ b/apps/daemon/internal/agent/installroot/probe.go
@@ -1,3 +1,4 @@
+// Package installroot probes native adapter installations.
 package installroot
 
 import (
diff --git a/apps/daemon/internal/agent/mcode/contracts.go b/apps/daemon/internal/agent/mcode/contracts.go
index 3df9bbe3d..f58d8ca5e 100644
--- a/apps/daemon/internal/agent/mcode/contracts.go
+++ b/apps/daemon/internal/agent/mcode/contracts.go
@@ -11,8 +11,6 @@ var (
 	_ agent.DurableSteerer           = (*Session)(nil)
 	_ agent.Steerer                  = (*Session)(nil)
 	_ agent.FunctionResultSubmitter  = (*Session)(nil)
-	_ agent.PermissionResponder      = (*Session)(nil)
-	_ agent.UserChoiceResponder      = (*Session)(nil)
 	_ agent.WorkspaceDirectoryLister = (*Session)(nil)
 	_ agent.WorkspaceWriter          = (*Session)(nil)
 	_ agent.WorkspaceDirectoryLister = (*executor)(nil)
diff --git a/apps/daemon/internal/agent/mcode/declaration.go b/apps/daemon/internal/agent/mcode/declaration.go
index ff79fd25f..461cd53ed 100644
--- a/apps/daemon/internal/agent/mcode/declaration.go
+++ b/apps/daemon/internal/agent/mcode/declaration.go
@@ -14,7 +14,6 @@ import (
 var Declaration = agent.Declaration{Info: proto.SupportedAgentKind{Kind: "mcode", Capabilities: proto.AgentKindCapabilities{
 	SubagentObservations:           proto.CapabilityUnsupported,
 	Streaming:                      proto.CapabilitySupported,
-	Permissions:                    proto.CapabilitySupported,
 	Usage:                          proto.CapabilityUnsupported,
 	Resume:                         proto.CapabilitySupported,
 	NativeSessionRecovery:          proto.CapabilityUnsupported,
@@ -47,7 +46,7 @@ func discover(ctx context.Context, options agent.DiscoveryOptions, info proto.Su
 	return discoverWithCheck(ctx, options, info, CheckCLIAvailable)
 }
 func discoverWithCheck(parent context.Context, options agent.DiscoveryOptions, result proto.SupportedAgentKind, check func(context.Context, string) (string, error)) *agent.Runtime {
-	runtime := &agent.Runtime{Info: result, Session: Factory}
+	runtime := &agent.Runtime{Info: result}
 
 	ctx, cancel := context.WithTimeout(parent, 15*time.Second)
 	defer cancel()
@@ -57,27 +56,23 @@ func discoverWithCheck(parent context.Context, options agent.DiscoveryOptions, r
 		return runtime
 	}
 	result.Available, result.Version = true, version
-	if SupportsExecution(version) {
-		result.Capabilities.Steering = proto.CapabilitySupported
-		result.Capabilities.DurableTurns = proto.CapabilitySupported
-		result.Capabilities.DurableInputReceipts = proto.CapabilitySupported
-		result.Capabilities.ExecutionControls = proto.CapabilitySupported
-		result.Capabilities.ProgrammaticToolCallingDisable = proto.CapabilitySupported
-		result.Capabilities.ToolObservations = proto.CapabilitySupported
-		result.Capabilities.SubagentControl = proto.CapabilitySupported
-		// Native preparation verifies the applied admission/tool profile before input.
-		result.Capabilities.SubagentObservations = proto.CapabilitySupported
-		result.Capabilities.EnvironmentNone = proto.CapabilitySupported
-		result.Capabilities.MCPHTTPTools = proto.CapabilitySupported
-		result.Capabilities.MCPHTTPBearerAuth = proto.CapabilitySupported
-	}
+	result.Capabilities.Steering = proto.CapabilitySupported
+	result.Capabilities.DurableTurns = proto.CapabilitySupported
+	result.Capabilities.DurableInputReceipts = proto.CapabilitySupported
+	result.Capabilities.ExecutionControls = proto.CapabilitySupported
+	result.Capabilities.ProgrammaticToolCallingDisable = proto.CapabilitySupported
+	result.Capabilities.ToolObservations = proto.CapabilitySupported
+	result.Capabilities.SubagentControl = proto.CapabilitySupported
+	// Native preparation verifies the applied admission/tool profile before input.
+	result.Capabilities.SubagentObservations = proto.CapabilitySupported
+	result.Capabilities.EnvironmentNone = proto.CapabilitySupported
+	result.Capabilities.MCPHTTPTools = proto.CapabilitySupported
+	result.Capabilities.MCPHTTPBearerAuth = proto.CapabilitySupported
 	runtime.Info = result
 	workspace := discoverWorkspace(parent, options, runtime)
 	if runtime.Info.Available {
 		runtime.Executor = NewExecutorFactory(workspace)
-		if SupportsExecution(version) {
-			runtime.View = discoverView(options)
-		}
+		runtime.View = discoverView(options)
 	}
 	fmt.Fprintf(options.Stdout, "mcode preflight ok (%s)\n", version)
 	return runtime
diff --git a/apps/daemon/internal/agent/mcode/declaration_test.go b/apps/daemon/internal/agent/mcode/declaration_test.go
index 229d6192e..386c4df2d 100644
--- a/apps/daemon/internal/agent/mcode/declaration_test.go
+++ b/apps/daemon/internal/agent/mcode/declaration_test.go
@@ -2,6 +2,7 @@ package mcode
 
 import (
 	"context"
+	"errors"
 	"io"
 	"reflect"
 	"testing"
@@ -10,20 +11,20 @@ import (
 	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
 )
 
-func TestMCodeExecutionOptInIsVersionBound(t *testing.T) {
+// An available runtime is execution-capable; a rejected native version is unavailable.
+func TestMCodeExecutionFollowsAvailability(t *testing.T) {
 	for _, tc := range []struct {
-		enabled, version string
-		qualified        bool
-	}{{"", "0.4.12", false}, {"1", "0.3.11", false}, {"1", "0.4.12", true}} {
-		t.Run(tc.enabled+"/"+tc.version, func(t *testing.T) {
-			t.Setenv("OAC_RUNTIME_MCODE_AGENTS_API", tc.enabled)
+		version string
+		check   error
+	}{{SupportedVersion, nil}, {"0.3.11", errors.New("mcode: unsupported version 0.3.11")}} {
+		t.Run(tc.version, func(t *testing.T) {
 			rc := agent.DiscoveryOptions{Stdout: io.Discard, Stderr: io.Discard}
-			runtime := discoverWithCheck(t.Context(), rc, Declaration.Info, func(context.Context, string) (string, error) { return tc.version, nil })
-			if runtime.Executor == nil || runtime.Info.Capabilities.WorkspaceReadPreparation.IsSupported() {
+			runtime := discoverWithCheck(t.Context(), rc, Declaration.Info, func(context.Context, string) (string, error) { return tc.version, tc.check })
+			info, available := runtime.Info, tc.check == nil
+			if (runtime.Executor != nil) != available || info.Capabilities.WorkspaceReadPreparation.IsSupported() {
 				t.Fatalf("factories: %+v", runtime)
 			}
-			info := runtime.Info
-			if !info.Available || info.Capabilities.EnvironmentNone.IsSupported() != tc.qualified || info.Capabilities.DurableInputReceipts.IsSupported() != tc.qualified || info.Capabilities.SubagentObservations.IsSupported() != tc.qualified {
+			if info.Available != available || info.Capabilities.EnvironmentNone.IsSupported() != available || info.Capabilities.DurableInputReceipts.IsSupported() != available || info.Capabilities.SubagentObservations.IsSupported() != available {
 				t.Fatalf("capabilities=%+v", info.Capabilities)
 			}
 			if info.Capabilities.NativeSessionRecovery.IsSupported() || info.Capabilities.LocalEnvironment.IsSupported() || info.Capabilities.FunctionTools.IsSupported() {
@@ -35,7 +36,7 @@ func TestMCodeExecutionOptInIsVersionBound(t *testing.T) {
 
 // The declaration must retain the complete baseline capability descriptor.
 func TestDeclaredCapabilityBaseline(t *testing.T) {
-	expected := map[string]bool{"Streaming": true, "Permissions": true, "Resume": true}
+	expected := map[string]bool{"Streaming": true, "Resume": true}
 	value := reflect.ValueOf(Declaration.Info.Capabilities)
 	for i := 0; i < value.NumField(); i++ {
 		name := value.Type().Field(i).Name
diff --git a/apps/daemon/internal/agent/mcode/discovery_workspace.go b/apps/daemon/internal/agent/mcode/discovery_workspace.go
index 9f6060436..6ee8d78e7 100644
--- a/apps/daemon/internal/agent/mcode/discovery_workspace.go
+++ b/apps/daemon/internal/agent/mcode/discovery_workspace.go
@@ -27,10 +27,6 @@ func discoverWorkspace(parent context.Context, options agent.DiscoveryOptions, r
 	if binding == nil {
 		return nil
 	}
-	if !runtime.Info.Available || !SupportsExecution(runtime.Info.Version) {
-		fail(fmt.Errorf("local execution requires the qualified native version"))
-		return nil
-	}
 	root, err := paths.Root()
 	if err != nil {
 		fail(err)
@@ -52,8 +48,7 @@ func discoverWorkspace(parent context.Context, options agent.DiscoveryOptions, r
 
 	caps := &runtime.Info.Capabilities
 	caps.EnvironmentNone = proto.CapabilityUnsupported
-	caps.Preparation, caps.LocalEnvironment = proto.CapabilitySupported, proto.CapabilitySupported
-	caps.WorkspaceReadPreparation = proto.CapabilitySupported
+	caps.LocalEnvironment, caps.WorkspaceReadPreparation = proto.CapabilitySupported, proto.CapabilitySupported
 	return &c
 }
 
diff --git a/apps/daemon/internal/agent/mcode/events.go b/apps/daemon/internal/agent/mcode/events.go
index 97bd1f8cd..a41789fd1 100644
--- a/apps/daemon/internal/agent/mcode/events.go
+++ b/apps/daemon/internal/agent/mcode/events.go
@@ -7,18 +7,18 @@ import (
 	"net/url"
 
 	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
-	"github.com/google/uuid"
 )
 
 func decodeComponent(value string) (string, error) { return url.PathUnescape(value) }
 
 func (s *Session) handle(frame rpcFrame) error {
 	if len(frame.ID) > 0 {
-		if frame.Method == "session/request_permission" && s.active {
-			return s.askPermission(frame)
-		}
-		if frame.Method == "elicitation/create" && s.active {
-			return s.askQuestion(frame)
+		// Harnesses run unattended, so no client method other than the
+		// permission answer is offered. Pinned mcode 0.4.12 maps the ACP
+		// cancelled outcome to deny: the tool call is blocked and the Turn
+		// continues.
+		if frame.Method == "session/request_permission" {
+			return s.write(rpcFrame{JSONRPC: "2.0", ID: frame.ID, Result: json.RawMessage(`{"outcome":{"outcome":"cancelled"}}`)})
 		}
 		return s.write(rpcFrame{JSONRPC: "2.0", ID: frame.ID, Error: &rpcError{Code: -32601, Message: "ACP method not supported by OpenAgentCore"}})
 	}
@@ -95,35 +95,3 @@ func (s *Session) emitTool(update toolUpdate) error {
 	}
 	return nil
 }
-
-func (s *Session) askPermission(frame rpcFrame) error {
-	var request permissionRequest
-	if err := json.Unmarshal(frame.Params, &request); err != nil {
-		return fmt.Errorf("mcode: invalid permission request")
-	}
-	if request.SessionID != s.sessionID {
-		return fmt.Errorf("mcode: permission request belongs to another session")
-	}
-	pending := pendingPermission{RPCID: frame.ID}
-	for _, option := range request.Options {
-		switch option.Kind {
-		case "allow_once":
-			pending.Allow = option.ID
-		case "reject_once":
-			pending.Deny = option.ID
-		}
-	}
-	if pending.Allow == "" || pending.Deny == "" {
-		return fmt.Errorf("mcode: permission request has no one-time allow/deny options")
-	}
-	id := "perm_" + uuid.NewString()
-	s.mu.Lock()
-	s.permissions[id] = pending
-	s.mu.Unlock()
-	tool := request.ToolCall.Name
-	if tool == "" {
-		tool = request.ToolCall.Title
-	}
-	s.emit(proto.TypePermissionRequest, proto.PermissionRequestPayload{RequestID: id, Tool: tool, Title: request.ToolCall.Title, Payload: request.ToolCall.RawInput})
-	return nil
-}
diff --git a/apps/daemon/internal/agent/mcode/execution.go b/apps/daemon/internal/agent/mcode/execution.go
index 7b2a93d93..c8438e680 100644
--- a/apps/daemon/internal/agent/mcode/execution.go
+++ b/apps/daemon/internal/agent/mcode/execution.go
@@ -7,13 +7,6 @@ import (
 	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
 )
 
-// SupportsExecution reports whether the daemon advertises MiniMax Code execution:
-// the operator sets OAC_RUNTIME_MCODE_AGENTS_API=1 and the native version is the
-// qualified one. Otherwise discovery reports only availability.
-func SupportsExecution(version string) bool {
-	return os.Getenv("OAC_RUNTIME_MCODE_AGENTS_API") == "1" && version == SupportedVersion
-}
-
 func validateExecutionRequest(req proto.PromptRequestPayload) error {
 	if !req.DisableExecutionEnvironment || req.AgentStateKey == "" || req.LocalEnvironment != nil || req.RequireExistingNativeSession || len(req.FunctionTools) != 0 || (req.MCPHTTPServers != nil && len(*req.MCPHTTPServers) != 0) {
 		return fmt.Errorf("mcode: unsupported execution configuration")
diff --git a/apps/daemon/internal/agent/mcode/executor.go b/apps/daemon/internal/agent/mcode/executor.go
index ac22cced5..d40b8964c 100644
--- a/apps/daemon/internal/agent/mcode/executor.go
+++ b/apps/daemon/internal/agent/mcode/executor.go
@@ -70,7 +70,7 @@ func startExecutor(ctx context.Context, req proto.PromptRequestPayload, binary s
 }
 
 func newExecutor(ctx context.Context, req proto.PromptRequestPayload, opts launchOptions, binary string) (*executor, error) {
-	bootstrap, err := launch(ctx, req, opts, binary, nil)
+	bootstrap, err := launch(ctx, req, opts, binary)
 	if err != nil {
 		return nil, err
 	}
@@ -133,14 +133,14 @@ func (e *executor) StartTurn(ctx context.Context, runID string, input proto.Mess
 	default:
 	}
 	req := e.req
-	req.RunID, req.Input = runID, proto.TextInput(text)
+	req.RunID = runID
 	s := newTurnSession(e.connection.process.Context(), req, e.opts, e.connection, out)
 	s.executor, s.sessionID, s.nativeModel = e, e.nativeSession, e.model
 	s.settled, s.inputDone = make(chan struct{}), make(chan struct{})
 	s.outputContext, s.outputCancel = context.WithCancel(context.Background())
 	e.active = s
 	e.connection.setCurrent(s)
-	go s.runExecutorTurn()
+	go s.runExecutorTurn(text)
 	go func() {
 		select {
 		case <-ctx.Done():
diff --git a/apps/daemon/internal/agent/mcode/executor_test.go b/apps/daemon/internal/agent/mcode/executor_test.go
index a7aba62ed..59a1f5d60 100644
--- a/apps/daemon/internal/agent/mcode/executor_test.go
+++ b/apps/daemon/internal/agent/mcode/executor_test.go
@@ -209,12 +209,21 @@ func TestExecutorCancellationRetiresOwnerAndLateCancelCannotRetarget(t *testing.
 func TestExecutorStartFailureOwnership(t *testing.T) {
 	t.Run("validation", func(t *testing.T) {
 		e, record := executorFixture(t, "executor-reuse", true)
-		out := make(chan proto.Envelope, 1)
-		turn, err := e.StartTurn(t.Context(), "", proto.TextInput("invalid"), out)
-		if err == nil || turn != nil {
-			t.Fatal("invalid Start acquired output")
+		image := "data:image/png;base64,iVBORw0KGgo="
+		for _, invalid := range []struct {
+			id, reason string
+			input      proto.MessageInput
+		}{
+			{"", "requires live context, identity", proto.TextInput("invalid")},
+			{"attachment", "does not support image input", proto.MessageInput{{Content: []proto.InputContent{{Type: "input_image", ImageURL: &image}}}}},
+		} {
+			out := make(chan proto.Envelope, 1)
+			turn, err := e.StartTurn(t.Context(), invalid.id, invalid.input, out)
+			if err == nil || turn != nil || !strings.Contains(err.Error(), invalid.reason) {
+				t.Fatal("invalid Start acquired output", err)
+			}
+			close(out)
 		}
-		close(out)
 		raw, _ := os.ReadFile(record)
 		if strings.Contains(string(raw), "session/prompt") {
 			t.Fatal("invalid input was sent")
diff --git a/apps/daemon/internal/agent/mcode/executor_turn.go b/apps/daemon/internal/agent/mcode/executor_turn.go
index 1633f5f18..dc24cd17a 100644
--- a/apps/daemon/internal/agent/mcode/executor_turn.go
+++ b/apps/daemon/internal/agent/mcode/executor_turn.go
@@ -10,10 +10,10 @@ import (
 	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
 )
 
-func (s *Session) runExecutorTurn() {
+func (s *Session) runExecutorTurn(prompt string) {
 	err := s.captureSubagentBaseline()
 	if err == nil {
-		err = s.executePrompt()
+		err = s.executePrompt(prompt)
 	}
 	if errors.Is(err, errTurnCancelled) {
 		err = nil
@@ -26,11 +26,7 @@ func (s *Session) runExecutorTurn() {
 	// prompt completion. No successor starts until all callers have settled.
 	s.operations.Wait()
 	if !s.req.DisableSubagents && s.subagentHistoryReady {
-		childErr := s.settleSubagents()
-		s.mu.Lock()
-		s.subagentSettlementError = childErr
-		s.mu.Unlock()
-		if childErr != nil {
+		if childErr := s.settleSubagents(); childErr != nil {
 			err = childErr
 		}
 	}
@@ -42,7 +38,7 @@ func (s *Session) runExecutorTurn() {
 	s.mu.Lock()
 	// ACP and native history cancellation do not prove detached tool cleanup.
 	// Retire the owner and settle its workers before acknowledging cancellation.
-	if s.cancelled || s.inputUncertain || len(s.permissions) != 0 || len(s.questions) != 0 {
+	if s.cancelled || s.inputUncertain {
 		reusable = false
 	}
 	if s.inputUncertain && err == nil {
@@ -51,7 +47,6 @@ func (s *Session) runExecutorTurn() {
 	metadata := map[string]any{proto.DoneMetaAgentSessionType: "mcode", proto.DoneMetaAgentSessionID: s.sessionID}
 	s.outcome = proto.DonePayload{Content: s.content.String(), Metadata: metadata, SourceCompletedAtMS: s.rootCompletedAtMS}
 	outcome := s.outcome
-	s.permissions, s.questions = map[string]pendingPermission{}, map[string]pendingQuestion{}
 	s.mu.Unlock()
 	if !reusable {
 		// Unknown quiescence invalidates this owner. A successful settlement
@@ -99,9 +94,6 @@ func (s *Session) captureSubagentBaseline() error {
 }
 
 func (s *Session) AwaitSettlement(ctx context.Context) (agent.TurnSettlement, error) {
-	if s.settled == nil {
-		return agent.TurnSettlement{}, fmt.Errorf("mcode: Turn has no Executor owner")
-	}
 	select {
 	case <-s.settled:
 		return s.settlement, s.settlementErr
@@ -110,7 +102,7 @@ func (s *Session) AwaitSettlement(ctx context.Context) (agent.TurnSettlement, er
 	}
 }
 
-func (s *Session) cancelTurn(ctx context.Context) error {
+func (s *Session) Cancel(ctx context.Context) error {
 	e := s.executor
 	e.mu.Lock()
 	if e.active != s {
diff --git a/apps/daemon/internal/agent/mcode/installation.go b/apps/daemon/internal/agent/mcode/installation.go
index fe75d9258..5f6937fc1 100644
--- a/apps/daemon/internal/agent/mcode/installation.go
+++ b/apps/daemon/internal/agent/mcode/installation.go
@@ -12,7 +12,7 @@ import (
 func Installation() agent.Installation {
 	return agent.Installation{AgentKind: "mcode", Version: SupportedVersion, Supported: func() bool { return runtime.GOOS == "linux" || runtime.GOOS == "darwin" },
 		Environment: func(dir, node string) map[string]string {
-			return map[string]string{"OAC_RUNTIME_MCODE_BIN": filepath.Join(dir, "native", "cli.js"), "OAC_RUNTIME_MCODE_NODE": node, "OAC_RUNTIME_MCODE_WORKSPACE_BRIDGE": filepath.Join(dir, "bridge.mjs"), "OAC_RUNTIME_MCODE_AGENTS_API": "1"}
+			return map[string]string{"OAC_RUNTIME_MCODE_BIN": filepath.Join(dir, "native", "cli.js"), "OAC_RUNTIME_MCODE_NODE": node, "OAC_RUNTIME_MCODE_WORKSPACE_BRIDGE": filepath.Join(dir, "bridge.mjs")}
 		},
 		Check: func(ctx context.Context, dir, node string, env []string) error {
 			got, err := installroot.Probe(ctx, node, []string{filepath.Join(dir, "native", "cli.js"), "--version"}, env, dir)
diff --git a/apps/daemon/internal/agent/mcode/mcp_observations_test.go b/apps/daemon/internal/agent/mcode/mcp_observations_test.go
index 78c94b467..dba30bf7a 100644
--- a/apps/daemon/internal/agent/mcode/mcp_observations_test.go
+++ b/apps/daemon/internal/agent/mcode/mcp_observations_test.go
@@ -15,7 +15,7 @@ import (
 func mcpObservationSession(t *testing.T) (*Session, chan proto.Envelope) {
 	t.Helper()
 	out := make(chan proto.Envelope, 16)
-	s := &Session{ctx: context.Background(), opts: launchOptions{DataDir: t.TempDir()},
+	s := &Session{ctx: context.Background(), outputContext: context.Background(), opts: launchOptions{DataDir: t.TempDir()},
 		req: proto.PromptRequestPayload{RunID: "run",
 			LocalEnvironment: &proto.LocalEnvironment{NetworkAccess: "enabled", MCP: []proto.EnvironmentMCP{environmentMCPFixture()}}},
 		out: out, tools: map[string]toolUpdate{}, completedTools: map[string]bool{}, active: true, sessionID: "native-session"}
diff --git a/apps/daemon/internal/agent/mcode/native_history_test.go b/apps/daemon/internal/agent/mcode/native_history_test.go
index 98c7c6a29..e438e2ff7 100644
--- a/apps/daemon/internal/agent/mcode/native_history_test.go
+++ b/apps/daemon/internal/agent/mcode/native_history_test.go
@@ -7,12 +7,11 @@ import (
 	"strings"
 	"testing"
 	"time"
-
-	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
 )
 
 // A successful public real-model run supplies an actual foreign native ID.
-// Neither that history nor a missing ID may silently become a new session.
+// Neither that history nor a missing ID may prepare an Executor, so no Turn can
+// run against it or silently replace it with a new session.
 func TestNativeMCodeHistoryIsolation(t *testing.T) {
 	binary, options, foreign := os.Getenv("OAC_RUNTIME_MCODE_BIN"), os.Getenv("OAC_TEST_MCODE_REAL_OPTIONS"), os.Getenv("OAC_TEST_MCODE_FOREIGN_NATIVE_ID")
 	if binary == "" || options == "" || foreign == "" {
@@ -28,37 +27,11 @@ func TestNativeMCodeHistoryIsolation(t *testing.T) {
 			if json.Unmarshal(raw, &req) != nil {
 				t.Fatal("invalid private options")
 			}
-			req.AgentSessionID, req.Input = id, proto.TextInput("This input must never execute.")
+			req.AgentSessionID = id
 			ctx, cancel := context.WithTimeout(t.Context(), 90*time.Second)
 			defer cancel()
-			out := make(chan proto.Envelope, 64)
-			session, err := newSession(ctx, req, out, binary)
-			if err != nil {
-				t.Fatal(err)
-			}
-			defer func() {
-				cleanup, stop := context.WithTimeout(context.Background(), 10*time.Second)
-				defer stop()
-				if err := session.Cancel(cleanup); err != nil {
-					t.Error(err)
-				}
-			}()
-			rejected := false
-			for event := range out {
-				if event.Type == proto.TypeError {
-					var failure proto.ErrorPayload
-					_ = json.Unmarshal(event.Payload, &failure)
-					rejected = strings.Contains(failure.Error, "session/load:") && !strings.Contains(failure.Error, "deadline exceeded")
-				}
-				if event.Type == proto.TypeDone {
-					var done proto.DonePayload
-					_ = json.Unmarshal(event.Payload, &done)
-					if done.Content != "" || done.Metadata[proto.DoneMetaAgentSessionID] != nil {
-						t.Fatal("unowned history executed or silently replaced")
-					}
-				}
-			}
-			if !rejected {
+			e, err := prepareExecutor(t, ctx, req)
+			if e != nil || err == nil || !strings.Contains(err.Error(), "session/load:") || strings.Contains(err.Error(), "deadline exceeded") {
 				t.Fatal("native history was not explicitly rejected")
 			}
 		})
diff --git a/apps/daemon/internal/agent/mcode/native_test.go b/apps/daemon/internal/agent/mcode/native_test.go
index f23a0b65a..eb43e7cf3 100644
--- a/apps/daemon/internal/agent/mcode/native_test.go
+++ b/apps/daemon/internal/agent/mcode/native_test.go
@@ -23,6 +23,7 @@ func TestNativeMCodeACP(t *testing.T) {
 		t.Skip("set OAC_TEST_MCODE_INTEGRATION_BIN to run native ACP smoke test")
 	}
 	req := testRequest(t)
+	t.Setenv("OAC_RUNTIME_MCODE_BIN", binary)
 	var mu sync.Mutex
 	var requests []string
 	model := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
@@ -45,18 +46,9 @@ func TestNativeMCodeACP(t *testing.T) {
 		ctx, cancel := context.WithTimeout(context.Background(), 60*time.Second)
 		t.Cleanup(cancel)
 		out := make(chan proto.Envelope, 64)
-		session, err := newSession(ctx, req, out, binary)
-		if err != nil {
+		if _, err := startTurn(t, ctx, req, out); err != nil {
 			t.Fatal(err)
 		}
-		t.Cleanup(func() {
-			_ = session.Cancel(context.Background())
-			select {
-			case <-session.exited:
-			case <-time.After(5 * time.Second):
-				t.Error("native CLI did not stop")
-			}
-		})
 		var done proto.DonePayload
 		for event := range out {
 			if event.Type == proto.TypeError {
diff --git a/apps/daemon/internal/agent/mcode/options.go b/apps/daemon/internal/agent/mcode/options.go
index cd5da0d56..2f3f93414 100644
--- a/apps/daemon/internal/agent/mcode/options.go
+++ b/apps/daemon/internal/agent/mcode/options.go
@@ -90,9 +90,6 @@ func validateOptions(req proto.PromptRequestPayload) (harnessconfig.PreparedConf
 	if err := validateExecutionRequest(req); err != nil {
 		return prepared, err
 	}
-	if req.Input.HasImages() {
-		return prepared, fmt.Errorf("mcode: ACP does not support attachments")
-	}
 	return prepared, nil
 }
 
diff --git a/apps/daemon/internal/agent/mcode/options_test.go b/apps/daemon/internal/agent/mcode/options_test.go
index 13099f019..59a8ea559 100644
--- a/apps/daemon/internal/agent/mcode/options_test.go
+++ b/apps/daemon/internal/agent/mcode/options_test.go
@@ -68,9 +68,6 @@ func TestOptionsRejectDroppedContext(t *testing.T) {
 		edit func(*proto.PromptRequestPayload)
 	}{
 		{"oversized instructions", func(r *proto.PromptRequestPayload) { r.SystemPrompt = strings.Repeat("x", 32*1024+1) }},
-		{"attachment", func(r *proto.PromptRequestPayload) {
-			r.Input = proto.MessageInput{{Content: []proto.InputContent{{Type: "input_image"}}}}
-		}},
 		{"missing model", func(r *proto.PromptRequestPayload) { r.Model = "" }},
 		{"missing provider", func(r *proto.PromptRequestPayload) { r.ModelProvider = nil }},
 	}
@@ -85,25 +82,6 @@ func TestOptionsRejectDroppedContext(t *testing.T) {
 	}
 }
 
-func TestQuestionContentPreservesTypesAndValidates(t *testing.T) {
-	pending := pendingQuestion{Properties: map[string]formProperty{"text": {Type: "string"}, "choice": {Type: "string", Options: []formOption{{Value: "eu", Title: "Europe"}}}}, Required: []string{"choice"}}
-	if _, err := questionContent(pending, proto.PromptForUserChoiceDecisionPayload{}); err == nil {
-		t.Fatal("required answer accepted empty")
-	}
-	decision := proto.PromptForUserChoiceDecisionPayload{QuestionAnswers: []proto.PromptForUserChoiceQuestionAnswer{{QuestionID: "text", Answers: []string{"custom"}}, {QuestionID: "choice", Answers: []string{"Europe"}}}}
-	content, err := questionContent(pending, decision)
-	if err != nil {
-		t.Fatal(err)
-	}
-	if content["choice"] != "eu" || content["text"] != "custom" {
-		t.Fatalf("answers=%v", content)
-	}
-	decision.QuestionAnswers[1].Answers = []string{"unoffered"}
-	if _, err := questionContent(pending, decision); err == nil {
-		t.Fatal("unoffered choice accepted")
-	}
-}
-
 func TestDataDirectoryRequiresAgentState(t *testing.T) {
 	home := t.TempDir()
 	t.Setenv("OAC_RUNTIME_HOME", home)
diff --git a/apps/daemon/internal/agent/mcode/protocol.go b/apps/daemon/internal/agent/mcode/protocol.go
index 95c9f629a..116d8c024 100644
--- a/apps/daemon/internal/agent/mcode/protocol.go
+++ b/apps/daemon/internal/agent/mcode/protocol.go
@@ -50,18 +50,3 @@ type sessionUpdate struct {
 		toolUpdate
 	} `json:"update"`
 }
-
-type permissionRequest struct {
-	SessionID string     `json:"sessionId"`
-	ToolCall  toolUpdate `json:"toolCall"`
-	Options   []struct {
-		ID   string `json:"optionId"`
-		Kind string `json:"kind"`
-	} `json:"options"`
-}
-
-type pendingPermission struct {
-	RPCID json.RawMessage
-	Allow string
-	Deny  string
-}
diff --git a/apps/daemon/internal/agent/mcode/questions.go b/apps/daemon/internal/agent/mcode/questions.go
deleted file mode 100644
index b61721d97..000000000
--- a/apps/daemon/internal/agent/mcode/questions.go
+++ /dev/null
@@ -1,217 +0,0 @@
-package mcode
-
-import (
-	"context"
-	"encoding/json"
-	"fmt"
-	"sort"
-	"strings"
-
-	"github.com/MiniMax-AI/OpenAgentCore/apps/daemon/internal/agent"
-	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
-	"github.com/google/uuid"
-)
-
-type formOption struct {
-	Value       string `json:"const"`
-	Title       string `json:"title"`
-	Description string `json:"description"`
-}
-
-type formProperty struct {
-	Type        string       `json:"type"`
-	Title       string       `json:"title"`
-	Description string       `json:"description"`
-	Options     []formOption `json:"oneOf"`
-	Items       struct {
-		Options []formOption `json:"anyOf"`
-	} `json:"items"`
-}
-
-type pendingQuestion struct {
-	RPCID       json.RawMessage
-	Properties  map[string]formProperty
-	Required    []string
-	OtherFields map[string]string
-}
-
-func (s *Session) askQuestion(frame rpcFrame) error {
-	var request struct {
-		SessionID string `json:"sessionId"`
-		Mode      string `json:"mode"`
-		Schema    struct {
-			Type       string                  `json:"type"`
-			Properties map[string]formProperty `json:"properties"`
-			Required   []string                `json:"required"`
-		} `json:"requestedSchema"`
-	}
-	if err := json.Unmarshal(frame.Params, &request); err != nil {
-		return fmt.Errorf("mcode: invalid input request")
-	}
-	if request.SessionID != s.sessionID {
-		return fmt.Errorf("mcode: input request belongs to another session")
-	}
-	if request.Mode != "form" || request.Schema.Type != "object" || len(request.Schema.Properties) == 0 {
-		return s.write(rpcFrame{JSONRPC: "2.0", ID: frame.ID, Error: &rpcError{Code: -32602, Message: "OpenAgentCore requires a nonempty input form"}})
-	}
-	otherFields := questionnaireOtherFields(request.Schema.Properties)
-	for _, key := range otherFields {
-		delete(request.Schema.Properties, key)
-	}
-	keys := make([]string, 0, len(request.Schema.Properties))
-	for key := range request.Schema.Properties {
-		keys = append(keys, key)
-	}
-	sort.Strings(keys)
-	questions := make([]proto.PromptForUserChoiceQuestion, 0, len(keys))
-	for _, key := range keys {
-		property := request.Schema.Properties[key]
-		if property.Type != "string" && property.Type != "array" {
-			return s.write(rpcFrame{JSONRPC: "2.0", ID: frame.ID, Error: &rpcError{Code: -32602, Message: "OpenAgentCore supports text and choice input fields"}})
-		}
-		question := proto.PromptForUserChoiceQuestion{ID: key, Question: property.Title, MultiSelect: property.Type == "array", Options: []proto.PromptForUserChoiceOption{}}
-		if question.Question == "" {
-			question.Question = key
-		}
-		if property.Description != "" {
-			question.Question += "\n" + property.Description
-		}
-		options := property.Options
-		if question.MultiSelect {
-			options = property.Items.Options
-		}
-		labels := map[string]bool{}
-		for _, option := range options {
-			label := option.Title
-			if label == "" {
-				label = option.Value
-			}
-			if labels[label] {
-				return fmt.Errorf("mcode: input choices have ambiguous labels")
-			}
-			labels[label] = true
-			question.Options = append(question.Options, proto.PromptForUserChoiceOption{Label: label, Description: option.Description})
-		}
-		question.IsOther = len(options) == 0 || otherFields[key] != ""
-		questions = append(questions, question)
-	}
-	id := "ask_" + uuid.NewString()
-	s.mu.Lock()
-	s.questions[id] = pendingQuestion{RPCID: frame.ID, Properties: request.Schema.Properties, Required: request.Schema.Required, OtherFields: otherFields}
-	s.mu.Unlock()
-	s.emit(proto.TypePromptForUserChoice, proto.PromptForUserChoicePayload{AskID: id, Questions: questions})
-	return nil
-}
-
-// Native questionnaires encode Other as a companion field, not a second question.
-func questionnaireOtherFields(properties map[string]formProperty) map[string]string {
-	fields := map[string]string{}
-	for key, property := range properties {
-		if len(property.Options) == 0 && len(property.Items.Options) == 0 {
-			continue
-		}
-		for candidate, other := range properties {
-			if strings.HasPrefix(candidate, key+"__other") && strings.Trim(strings.TrimPrefix(candidate, key+"__other"), "_") == "" && other.Type == "string" && len(other.Options) == 0 && other.Title == property.Title+" — Other" {
-				fields[key] = candidate
-				break
-			}
-		}
-	}
-	return fields
-}
-
-func (s *Session) SubmitPromptForUserChoice(_ context.Context, id string, decision proto.PromptForUserChoiceDecisionPayload) error {
-	s.mu.Lock()
-	defer s.mu.Unlock()
-	pending, ok := s.questions[id]
-	if !ok {
-		return agent.ErrUnknownAsk
-	}
-	if err := decision.Validate(); err != nil {
-		return err
-	}
-	response := map[string]any{"action": "cancel"}
-	if !decision.Cancelled {
-		content, err := questionContent(pending, decision)
-		if err != nil {
-			return err
-		}
-		response = map[string]any{"action": "accept", "content": content}
-	}
-	raw, _ := json.Marshal(response)
-	if err := s.write(rpcFrame{JSONRPC: "2.0", ID: pending.RPCID, Result: raw}); err != nil {
-		return err
-	}
-	delete(s.questions, id)
-	return nil
-}
-
-func questionContent(pending pendingQuestion, decision proto.PromptForUserChoiceDecisionPayload) (map[string]any, error) {
-	ids := make([]string, 0, len(pending.Properties))
-	for id := range pending.Properties {
-		ids = append(ids, id)
-	}
-	if _, err := decision.AnswersFor(ids); err != nil {
-		return nil, err
-	}
-	content := map[string]any{}
-	for _, answer := range decision.QuestionAnswers {
-		property, ok := pending.Properties[answer.QuestionID]
-		if !ok {
-			return nil, fmt.Errorf("mcode: unknown input field")
-		}
-		values := append([]string{}, answer.Answers...)
-		if len(values) == 0 {
-			continue
-		}
-		options := property.Options
-		if property.Type == "array" {
-			options = property.Items.Options
-		} else if len(values) != 1 {
-			return nil, fmt.Errorf("mcode: input field requires a single answer")
-		}
-		selected := make([]string, 0, len(values))
-		for _, value := range values {
-			if len(options) == 0 {
-				selected = append(selected, value)
-				continue
-			}
-			found := false
-			for _, option := range options {
-				label := option.Title
-				if label == "" {
-					label = option.Value
-				}
-				if value == label {
-					selected = append(selected, option.Value)
-					found = true
-					break
-				}
-			}
-			if !found {
-				other := pending.OtherFields[answer.QuestionID]
-				if other == "" {
-					return nil, fmt.Errorf("mcode: answer is not an offered choice")
-				}
-				if _, exists := content[other]; exists {
-					return nil, fmt.Errorf("mcode: input field requires a single custom answer")
-				}
-				content[other] = value
-			}
-		}
-		if len(selected) == 0 {
-			continue
-		}
-		if property.Type == "array" {
-			content[answer.QuestionID] = selected
-		} else {
-			content[answer.QuestionID] = selected[0]
-		}
-	}
-	for _, key := range pending.Required {
-		if _, ok := content[key]; !ok {
-			return nil, fmt.Errorf("mcode: required input is missing")
-		}
-	}
-	return content, nil
-}
diff --git a/apps/daemon/internal/agent/mcode/questions_test.go b/apps/daemon/internal/agent/mcode/questions_test.go
deleted file mode 100644
index c46562977..000000000
--- a/apps/daemon/internal/agent/mcode/questions_test.go
+++ /dev/null
@@ -1,55 +0,0 @@
-package mcode
-
-import (
-	"encoding/json"
-	"reflect"
-	"testing"
-
-	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
-)
-
-func TestQuestionnaireOtherUsesOneQuestion(t *testing.T) {
-	for _, multiple := range []bool{false, true} {
-		property := formProperty{Type: "string", Title: "Region?", Options: []formOption{{Value: "eu", Title: "Europe"}}}
-		if multiple {
-			property.Type = "array"
-			property.Items.Options = property.Options
-			property.Options = nil
-		}
-		properties := map[string]formProperty{"region": property, "region__other": {Type: "string", Title: "Region? — Other"}}
-		params, _ := json.Marshal(map[string]any{"sessionId": "native-1", "mode": "form", "requestedSchema": map[string]any{"type": "object", "properties": properties}})
-		out := make(chan proto.Envelope, 1)
-		session := &Session{ctx: t.Context(), sessionID: "native-1", out: out, questions: map[string]pendingQuestion{}}
-		if err := session.askQuestion(rpcFrame{ID: json.RawMessage(`1`), Params: params}); err != nil {
-			t.Fatal(err)
-		}
-		var request proto.PromptForUserChoicePayload
-		_ = json.Unmarshal((<-out).Payload, &request)
-		if len(request.Questions) != 1 || !request.Questions[0].IsOther || request.Questions[0].MultiSelect != multiple {
-			t.Fatalf("unexpected questions: %#v", request.Questions)
-		}
-		pending := session.questions[request.AskID]
-		for _, custom := range []bool{false, true} {
-			answer := "Europe"
-			want := map[string]any{"region": "eu"}
-			if multiple {
-				want["region"] = []string{"eu"}
-			}
-			if custom {
-				answer = "Asia"
-				want = map[string]any{"region__other": "Asia"}
-			}
-			got, err := questionContent(pending, proto.PromptForUserChoiceDecisionPayload{QuestionAnswers: []proto.PromptForUserChoiceQuestionAnswer{{QuestionID: "region", Answers: []string{answer}}}})
-			if err != nil || !reflect.DeepEqual(got, want) {
-				t.Fatalf("multiple=%t custom=%t: got=%v err=%v", multiple, custom, got, err)
-			}
-		}
-		if multiple {
-			got, err := questionContent(pending, proto.PromptForUserChoiceDecisionPayload{QuestionAnswers: []proto.PromptForUserChoiceQuestionAnswer{{QuestionID: "region", Answers: []string{"Europe", "Asia"}}}})
-			want := map[string]any{"region": []string{"eu"}, "region__other": "Asia"}
-			if err != nil || !reflect.DeepEqual(got, want) {
-				t.Fatalf("combined choice and custom: got=%v err=%v", got, err)
-			}
-		}
-	}
-}
diff --git a/apps/daemon/internal/agent/mcode/session.go b/apps/daemon/internal/agent/mcode/session.go
index 91766f1d5..ec43b1482 100644
--- a/apps/daemon/internal/agent/mcode/session.go
+++ b/apps/daemon/internal/agent/mcode/session.go
@@ -3,7 +3,6 @@ package mcode
 import (
 	"context"
 	"encoding/json"
-	"errors"
 	"fmt"
 	"net/url"
 	"slices"
@@ -21,65 +20,39 @@ type Session struct {
 	req  proto.PromptRequestPayload
 	opts launchOptions
 	*connection
-	executor                *executor
-	settlement              agent.TurnSettlement
-	settlementErr           error
-	settled                 chan struct{}
-	inputDone               chan struct{}
-	outputCancel            context.CancelFunc
-	operations              sync.WaitGroup
-	closing                 bool
-	cancelled               bool
-	inputUncertain          bool
-	out                     chan<- proto.Envelope
-	frames                  chan rpcFrame
-	finished                chan struct{}
-	mu                      sync.Mutex
-	sessionID               string
-	nativeModel             string
-	outputContext           context.Context
-	outcome                 proto.DonePayload
-	permissions             map[string]pendingPermission
-	questions               map[string]pendingQuestion
-	steeringReady           bool
-	steeringTurn            string
-	sequence                uint64
-	active                  bool
-	content                 strings.Builder
-	tools                   map[string]toolUpdate
-	completedTools          map[string]bool
-	previousNativeTurns     map[string]bool
-	subagentSettlementError error
-	rootCompletedAtMS       *int64
-	subagentHistoryReady    bool
+	executor             *executor
+	settlement           agent.TurnSettlement
+	settlementErr        error
+	settled              chan struct{}
+	inputDone            chan struct{}
+	outputCancel         context.CancelFunc
+	operations           sync.WaitGroup
+	closing              bool
+	cancelled            bool
+	inputUncertain       bool
+	out                  chan<- proto.Envelope
+	frames               chan rpcFrame
+	finished             chan struct{}
+	mu                   sync.Mutex
+	sessionID            string
+	nativeModel          string
+	outputContext        context.Context
+	outcome              proto.DonePayload
+	steeringReady        bool
+	steeringTurn         string
+	sequence             uint64
+	active               bool
+	content              strings.Builder
+	tools                map[string]toolUpdate
+	completedTools       map[string]bool
+	previousNativeTurns  map[string]bool
+	rootCompletedAtMS    *int64
+	subagentHistoryReady bool
 }
 
 var _ agent.Session = (*Session)(nil)
 
-func Factory(ctx context.Context, req proto.PromptRequestPayload, out chan<- proto.Envelope) (agent.Session, error) {
-	return newSession(ctx, req, out, defaultBinary())
-}
-
-func newSession(ctx context.Context, req proto.PromptRequestPayload, out chan<- proto.Envelope, binary string) (*Session, error) {
-	if ctx == nil {
-		ctx = context.Background()
-	}
-	if out == nil {
-		return nil, fmt.Errorf("mcode: output channel is required")
-	}
-	opts, err := prepareOptions(req)
-	if err != nil {
-		return nil, err
-	}
-	s, err := launch(ctx, req, opts, binary, out)
-	if err != nil {
-		return nil, err
-	}
-	go s.run()
-	return s, nil
-}
-
-func launch(ctx context.Context, req proto.PromptRequestPayload, opts launchOptions, binary string, out chan<- proto.Envelope) (*Session, error) {
+func launch(ctx context.Context, req proto.PromptRequestPayload, opts launchOptions, binary string) (*Session, error) {
 	start, args := opts.start, []string{"acp"}
 	if start == nil {
 		start = clirunner.Start
@@ -92,77 +65,14 @@ func launch(ctx context.Context, req proto.PromptRequestPayload, opts launchOpti
 		return nil, err
 	}
 	c := &connection{process: process, exited: make(chan struct{}), responses: map[string]chan rpcFrame{}}
-	s := newTurnSession(ctx, req, opts, c, out)
+	s := newTurnSession(ctx, req, opts, c, nil)
 	c.current = s
 	go c.read()
 	return s, nil
 }
 
 func newTurnSession(ctx context.Context, req proto.PromptRequestPayload, opts launchOptions, c *connection, out chan<- proto.Envelope) *Session {
-	return &Session{ctx: ctx, req: req, opts: opts, connection: c, out: out, frames: make(chan rpcFrame, 32), finished: make(chan struct{}), permissions: map[string]pendingPermission{}, questions: map[string]pendingQuestion{}, tools: map[string]toolUpdate{}, completedTools: map[string]bool{}}
-}
-
-func (s *Session) run() {
-	defer func() {
-		if s.out != nil {
-			close(s.out)
-		}
-	}()
-	defer close(s.finished)
-	err := s.prepareNative()
-	if err == nil {
-		if !s.req.DisableSubagents {
-			var snapshot nativeSubagentSnapshot
-			snapshot, err = s.readSubagents(s.ctx)
-			s.subagentHistoryReady = err == nil
-			s.previousNativeTurns = map[string]bool{}
-			for _, session := range snapshot.Sessions {
-				if session.ID == s.sessionID {
-					for _, turn := range session.Turns {
-						s.previousNativeTurns[turn.ID] = true
-					}
-				}
-			}
-		}
-	}
-	if err == nil {
-		err = s.executePrompt()
-	}
-	if !s.req.DisableSubagents && s.subagentHistoryReady && s.out != nil {
-		observationErr := s.settleSubagents()
-		s.mu.Lock()
-		s.subagentSettlementError = observationErr
-		s.mu.Unlock()
-		if observationErr != nil {
-			err = observationErr
-		}
-	}
-	if err != nil {
-		s.process.Cancel()
-		<-s.exited
-	}
-	s.finishEnvironmentMCP()
-	if s.out == nil {
-		return
-	}
-	s.mu.Lock()
-	s.steeringReady = false
-	s.mu.Unlock()
-	if err != nil {
-		s.process.Cancel()
-		s.emit(proto.TypeError, proto.ErrorPayload{Error: err.Error()})
-	}
-	s.mu.Lock()
-	sessionID := s.sessionID
-	s.permissions = map[string]pendingPermission{}
-	s.questions = map[string]pendingQuestion{}
-	s.mu.Unlock()
-	metadata := map[string]any{proto.DoneMetaAgentSessionType: "mcode"}
-	if sessionID != "" {
-		metadata[proto.DoneMetaAgentSessionID] = sessionID
-	}
-	// ACP context usage is not per-turn token usage; do not record it as spend.
-	s.emit(proto.TypeDone, proto.DonePayload{Content: s.content.String(), Metadata: metadata, SourceCompletedAtMS: s.rootCompletedAtMS})
+	return &Session{ctx: ctx, req: req, opts: opts, connection: c, out: out, frames: make(chan rpcFrame, 32), finished: make(chan struct{}), tools: map[string]toolUpdate{}, completedTools: map[string]bool{}}
 }
 
 func (s *Session) prepareNative() error {
@@ -175,7 +85,7 @@ func (s *Session) prepareNative() error {
 			} `json:"oac/subagents"`
 		} `json:"_meta"`
 	}
-	if err := s.call("initialize", map[string]any{"protocolVersion": 1, "clientInfo": map[string]string{"name": "oac", "version": "1"}, "clientCapabilities": map[string]any{"elicitation": map[string]any{"form": map[string]any{}}}}, &initialized, false); err != nil {
+	if err := s.call("initialize", map[string]any{"protocolVersion": 1, "clientInfo": map[string]string{"name": "oac", "version": "1"}}, &initialized, false); err != nil {
 		return err
 	}
 	if initialized.ProtocolVersion != 1 {
@@ -219,16 +129,12 @@ func (s *Session) prepareNative() error {
 	return nil
 }
 
-func (s *Session) executePrompt() error {
-	prompt, err := s.req.Input.TextOnly()
-	if err != nil {
-		return err
-	}
+func (s *Session) executePrompt(prompt string) error {
 	s.active = true
 	var result struct {
 		StopReason string `json:"stopReason"`
 	}
-	err = s.call("session/prompt", map[string]any{"sessionId": s.sessionID, "prompt": promptContent(prompt)}, &result, true)
+	err := s.call("session/prompt", map[string]any{"sessionId": s.sessionID, "prompt": promptContent(prompt)}, &result, true)
 	s.active = false
 	s.mu.Lock()
 	s.steeringReady = false
@@ -282,7 +188,7 @@ func (s *Session) call(method string, params any, result any, prompt bool) error
 	if err != nil {
 		return err
 	}
-	if prompt && s.executor != nil {
+	if prompt {
 		// Serialize the admission check with the wire, but release the owner
 		// mutex before a pipe write so cancellation and Close can stop it.
 		s.connection.writeMu.Lock()
@@ -344,10 +250,6 @@ func (s *Session) call(method string, params any, result any, prompt bool) error
 }
 
 func (s *Session) emit(kind string, payload any) {
-	ctx := s.ctx
-	if s.outputContext != nil {
-		ctx = s.outputContext
-	}
 	env, err := proto.NewEnvelope(kind, s.req.RunID, payload)
 	if err != nil {
 		return
@@ -359,55 +261,6 @@ func (s *Session) emit(kind string, payload any) {
 	}
 	select {
 	case s.out <- env:
-	case <-ctx.Done():
-	}
-}
-
-func (s *Session) Cancel(ctx context.Context) error {
-	if s.executor != nil {
-		return s.cancelTurn(ctx)
-	}
-	if !s.req.DisableSubagents {
-		if err := s.cancelSubagents(ctx); err != nil {
-			s.process.Cancel()
-			return err
-		}
+	case <-s.outputContext.Done():
 	}
-	s.process.Cancel()
-	select {
-	case <-s.exited:
-	case <-ctx.Done():
-		return ctx.Err()
-	}
-	select {
-	case <-s.finished:
-		return nil
-	case <-ctx.Done():
-		return ctx.Err()
-	}
-}
-
-func (s *Session) SubmitPermission(_ context.Context, id string, decision proto.PermissionDecisionPayload) error {
-	s.mu.Lock()
-	defer s.mu.Unlock()
-	pending, ok := s.permissions[id]
-	if !ok {
-		return agent.ErrUnknownPermission
-	}
-	choice := pending.Deny
-	if decision.Approved {
-		choice = pending.Allow
-	}
-	if choice == "" {
-		return errors.New("mcode: ACP permission option is unavailable")
-	}
-	if len(decision.UpdatedInput) > 0 {
-		return errors.New("mcode: edited permission input is not supported")
-	}
-	raw, _ := json.Marshal(map[string]any{"outcome": map[string]string{"outcome": "selected", "optionId": choice}})
-	if err := s.write(rpcFrame{JSONRPC: "2.0", ID: pending.RPCID, Result: raw}); err != nil {
-		return err
-	}
-	delete(s.permissions, id)
-	return nil
 }
diff --git a/apps/daemon/internal/agent/mcode/session_test.go b/apps/daemon/internal/agent/mcode/session_test.go
index 7e72086b8..40d3b443d 100644
--- a/apps/daemon/internal/agent/mcode/session_test.go
+++ b/apps/daemon/internal/agent/mcode/session_test.go
@@ -4,14 +4,12 @@ import (
 	"bufio"
 	"context"
 	"encoding/json"
-	"errors"
 	"os"
 	"path/filepath"
 	"strings"
 	"testing"
 	"time"
 
-	"github.com/MiniMax-AI/OpenAgentCore/apps/daemon/internal/agent"
 	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
 	"github.com/MiniMax-AI/OpenAgentCore/internal/modelprovider"
 )
@@ -25,7 +23,8 @@ func testRequest(t *testing.T) proto.PromptRequestPayload {
 		DisableExecutionEnvironment: true, DisableSubagents: true, ExecutionControls: &proto.ExecutionControls{WebSearch: "disabled", TextVerbosity: "medium"}}
 }
 
-func helperSession(t *testing.T, scenario string, resume bool) (*Session, <-chan proto.Envelope) {
+// helperRequest selects a protocol fixture scenario as the native CLI.
+func helperRequest(t *testing.T, scenario string, resume bool) proto.PromptRequestPayload {
 	t.Helper()
 	req := testRequest(t)
 	if resume {
@@ -41,21 +40,54 @@ func helperSession(t *testing.T, scenario string, resume bool) (*Session, <-chan
 	if err := os.WriteFile(binary, []byte(script), 0700); err != nil {
 		t.Fatal(err)
 	}
+	t.Setenv("OAC_RUNTIME_MCODE_BIN", binary)
+	return req
+}
+
+// prepareExecutor prepares req without its Turn input; cleanup closes the
+// Executor and reaps its CLI.
+func prepareExecutor(t *testing.T, ctx context.Context, req proto.PromptRequestPayload) (*executor, error) {
+	t.Helper()
+	req.RunID, req.Input = "", nil
+	value, err := NewExecutorFactory(nil)(ctx, req)
+	if value == nil {
+		return nil, err
+	}
+	e := value.(*executor)
+	t.Cleanup(func() {
+		cleanup, cancel := context.WithTimeout(context.Background(), 3*time.Second)
+		defer cancel()
+		if err := e.Close(cleanup); err != nil {
+			t.Error("CLI was not reaped:", err)
+		}
+	})
+	return e, err
+}
+
+// startTurn prepares an Executor for req and starts req.Input as its Turn.
+func startTurn(t *testing.T, ctx context.Context, req proto.PromptRequestPayload, out chan<- proto.Envelope) (*Session, error) {
+	t.Helper()
+	e, err := prepareExecutor(t, ctx, req)
+	if err != nil {
+		return nil, err
+	}
+	turn, err := e.StartTurn(ctx, req.RunID, req.Input, out)
+	if err != nil {
+		return nil, err
+	}
+	return turn.(*Session), nil
+}
+
+func helperSession(t *testing.T, scenario string, resume bool) (*Session, <-chan proto.Envelope) {
+	t.Helper()
+	req := helperRequest(t, scenario, resume)
 	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
 	t.Cleanup(cancel)
 	out := make(chan proto.Envelope, 32)
-	session, err := newSession(ctx, req, out, binary)
+	session, err := startTurn(t, ctx, req, out)
 	if err != nil {
 		t.Fatal(err)
 	}
-	t.Cleanup(func() {
-		_ = session.Cancel(context.Background())
-		select {
-		case <-session.exited:
-		case <-time.After(3 * time.Second):
-			t.Error("CLI was not reaped")
-		}
-	})
 	return session, out
 }
 
@@ -97,39 +129,20 @@ func TestSessionStreamsCurrentTurnAndResumes(t *testing.T) {
 	}
 }
 
-func TestSessionInteractionRoundTrip(t *testing.T) {
-	for _, approved := range []bool{true, false} {
-		t.Run(map[bool]string{true: "allow", false: "deny"}[approved], func(t *testing.T) {
-			session, out := helperSession(t, "interaction", false)
-			permissions, questions := 0, 0
-			for event := range out {
-				switch event.Type {
-				case proto.TypeError:
-					t.Fatalf("error: %s", event.Payload)
-				case proto.TypePermissionRequest:
-					permissions++
-					var p proto.PermissionRequestPayload
-					_ = json.Unmarshal(event.Payload, &p)
-					if err := session.SubmitPermission(context.Background(), p.RequestID, proto.PermissionDecisionPayload{Approved: approved}); err != nil {
-						t.Fatal(err)
-					}
-					if err := session.SubmitPermission(context.Background(), p.RequestID, proto.PermissionDecisionPayload{Approved: true}); !errors.Is(err, agent.ErrUnknownPermission) {
-						t.Fatalf("duplicate approval: %v", err)
-					}
-				case proto.TypePromptForUserChoice:
-					questions++
-					var p proto.PromptForUserChoicePayload
-					_ = json.Unmarshal(event.Payload, &p)
-					decision := proto.PromptForUserChoiceDecisionPayload{QuestionAnswers: []proto.PromptForUserChoiceQuestionAnswer{{QuestionID: "region", Answers: []string{"Europe"}}}}
-					if err := session.SubmitPromptForUserChoice(context.Background(), p.AskID, decision); err != nil {
-						t.Fatal(err)
-					}
-				}
-			}
-			if permissions != 1 || questions != 1 {
-				t.Fatalf("permissions=%d questions=%d", permissions, questions)
-			}
-		})
+// Harnesses run unattended: native asks are declined in the adapter and the turn completes.
+func TestSessionDeclinesNativeAsks(t *testing.T) {
+	_, out := helperSession(t, "unattended", false)
+	done := 0
+	for event := range out {
+		switch event.Type {
+		case proto.TypeError:
+			t.Fatalf("error: %s", event.Payload)
+		case proto.TypeDone:
+			done++
+		}
+	}
+	if done != 1 {
+		t.Fatalf("done=%d", done)
 	}
 }
 
@@ -150,34 +163,41 @@ func TestResumeSelectsModelWhenNativeSelectorIsMissing(t *testing.T) {
 }
 
 func TestSessionFailuresAreReported(t *testing.T) {
-	for _, scenario := range []string{"malformed", "exit", "rpc-error", "unknown-model"} {
+	for _, scenario := range []string{"malformed", "exit", "unknown-model"} {
 		t.Run(scenario, func(t *testing.T) {
-			_, out := helperSession(t, scenario, false)
-			reported := false
-			for event := range out {
-				if event.Type == proto.TypeError {
-					reported = true
-				}
-			}
-			if !reported {
-				t.Fatal("failure was not emitted")
+			ctx, cancel := context.WithTimeout(t.Context(), 10*time.Second)
+			defer cancel()
+			if e, err := prepareExecutor(t, ctx, helperRequest(t, scenario, false)); err == nil || e != nil {
+				t.Fatal("preparation failure was not reported", err)
 			}
 		})
 	}
+	t.Run("rpc-error", func(t *testing.T) {
+		_, out := helperSession(t, "rpc-error", false)
+		reported := false
+		for event := range out {
+			if event.Type == proto.TypeError {
+				reported = true
+			}
+		}
+		if !reported {
+			t.Fatal("failure was not emitted")
+		}
+	})
 }
 
-func TestCancelStopsWaitingCLI(t *testing.T) {
-	session, out := helperSession(t, "hang", false)
-	if err := session.Cancel(context.Background()); err != nil {
-		t.Fatal(err)
+func TestPreparationCancellationStopsWaitingCLI(t *testing.T) {
+	req := helperRequest(t, "hang", false)
+	ctx, cancel := context.WithCancel(t.Context())
+	defer cancel()
+	time.AfterFunc(100*time.Millisecond, cancel)
+	started := time.Now()
+	if e, err := prepareExecutor(t, ctx, req); err == nil || e != nil {
+		t.Fatal("cancelled preparation retained the CLI", err)
 	}
-	select {
-	case <-session.exited:
-	case <-time.After(3 * time.Second):
+	if time.Since(started) > 3*time.Second {
 		t.Fatal("cancel hung")
 	}
-	for range out {
-	}
 }
 
 func TestMCodeProcess(t *testing.T) {
@@ -233,6 +253,9 @@ func TestMCodeProcess(t *testing.T) {
 		result := any(map[string]any{})
 		switch frame.Method {
 		case "initialize":
+			if scenario == "unattended" && strings.Contains(string(frame.Params), "elicitation") {
+				os.Exit(7)
+			}
 			result = map[string]int{"protocolVersion": 1}
 		case "session/new", "session/load":
 			if scenario == "prepared-mcp-cancel" {
@@ -317,9 +340,9 @@ func TestMCodeProcess(t *testing.T) {
 				send(rpcFrame{JSONRPC: "2.0", ID: frame.ID, Error: &rpcError{Code: -32603, Message: "Fixture provider unavailable"}})
 				continue
 			}
-			if scenario == "interaction" {
+			if scenario == "unattended" {
 				promptID = frame.ID
-				send(map[string]any{"jsonrpc": "2.0", "id": "permission-1", "method": "session/request_permission", "params": map[string]any{"sessionId": "native-1", "toolCall": map[string]any{"toolCallId": "tool-1", "name": "Bash", "title": "Run fixture", "rawInput": map[string]any{"command": "echo fixture"}}, "options": []map[string]string{{"optionId": "once", "kind": "allow_once"}, {"optionId": "always", "kind": "allow_always"}, {"optionId": "deny", "kind": "reject_once"}}}})
+				send(map[string]any{"jsonrpc": "2.0", "id": "permission-1", "method": "session/request_permission", "params": map[string]any{"sessionId": "native-1", "toolCall": map[string]any{"toolCallId": "tool-1", "name": "Bash", "title": "Run fixture", "rawInput": map[string]any{"command": "echo fixture"}}, "options": []map[string]string{{"optionId": "once", "kind": "allow_once"}, {"optionId": "deny", "kind": "reject_once"}}}})
 				continue
 			}
 			update("agent_message_chunk", map[string]any{"content": map[string]string{"type": "text", "text": "Hello "}})
@@ -358,21 +381,15 @@ func TestMCodeProcess(t *testing.T) {
 			if string(frame.ID) == `"permission-1"` {
 				var reply struct {
 					Outcome struct {
-						Option string `json:"optionId"`
+						Outcome string `json:"outcome"`
 					} `json:"outcome"`
 				}
-				_ = json.Unmarshal(frame.Result, &reply)
-				if reply.Outcome.Option != "once" && reply.Outcome.Option != "deny" {
+				if json.Unmarshal(frame.Result, &reply) != nil || reply.Outcome.Outcome != "cancelled" {
 					os.Exit(5)
 				}
-				send(map[string]any{"jsonrpc": "2.0", "id": "question-1", "method": "elicitation/create", "params": map[string]any{"sessionId": "native-1", "mode": "form", "requestedSchema": map[string]any{"type": "object", "required": []string{"region"}, "properties": map[string]any{"region": map[string]any{"type": "string", "title": "Region?", "oneOf": []map[string]string{{"const": "eu", "title": "Europe"}, {"const": "us", "title": "America"}}}}}}})
+				send(map[string]any{"jsonrpc": "2.0", "id": "question-1", "method": "elicitation/create", "params": map[string]any{"sessionId": "native-1", "mode": "form", "requestedSchema": map[string]any{"type": "object", "properties": map[string]any{"region": map[string]any{"type": "string"}}}}})
 			} else {
-				var reply struct {
-					Action  string            `json:"action"`
-					Content map[string]string `json:"content"`
-				}
-				_ = json.Unmarshal(frame.Result, &reply)
-				if reply.Action != "accept" || reply.Content["region"] != "eu" {
+				if frame.Error == nil || frame.Error.Code != -32601 {
 					os.Exit(6)
 				}
 				raw, _ := json.Marshal(map[string]string{"stopReason": "end_turn"})
diff --git a/apps/daemon/internal/agent/mcode/steering.go b/apps/daemon/internal/agent/mcode/steering.go
index bff6f079f..005f5c859 100644
--- a/apps/daemon/internal/agent/mcode/steering.go
+++ b/apps/daemon/internal/agent/mcode/steering.go
@@ -18,16 +18,14 @@ func (s *Session) Steer(ctx context.Context, input proto.PromptSteerPayload) err
 
 // Native acceptance belongs to the active ACP Turn; it does not promise model consumption.
 func (s *Session) SteerWithReceipt(ctx context.Context, input proto.PromptSteerPayload, written func()) error {
-	if s.executor != nil {
-		s.mu.Lock()
-		if s.closing || s.cancelled {
-			s.mu.Unlock()
-			return agent.ErrSteeringInactive
-		}
-		s.operations.Add(1)
+	s.mu.Lock()
+	if s.closing || s.cancelled {
 		s.mu.Unlock()
-		defer s.operations.Done()
+		return agent.ErrSteeringInactive
 	}
+	s.operations.Add(1)
+	s.mu.Unlock()
+	defer s.operations.Done()
 	text, err := input.Input.TextOnly()
 	if strings.TrimSpace(input.InputID) == "" || err != nil {
 		return agent.ErrSteeringRejected
@@ -62,7 +60,7 @@ func (s *Session) SteerWithReceipt(ctx context.Context, input proto.PromptSteerP
 	var stopped error
 	select {
 	case frame = <-response:
-	case <-s.inputSettlementDone():
+	case <-s.inputDone:
 		stopped = fmt.Errorf("mcode: run ended with unknown input outcome")
 	case <-s.exited:
 		stopped = fmt.Errorf("mcode: input transport closed")
@@ -103,13 +101,6 @@ func (s *Session) SteerWithReceipt(ctx context.Context, input proto.PromptSteerP
 	return nil
 }
 
-func (s *Session) inputSettlementDone() <-chan struct{} {
-	if s.inputDone != nil {
-		return s.inputDone
-	}
-	return s.finished
-}
-
 func (s *Session) CancellationOutcome() proto.DonePayload {
 	s.mu.Lock()
 	defer s.mu.Unlock()
diff --git a/apps/daemon/internal/agent/mcode/subagent_cancel.go b/apps/daemon/internal/agent/mcode/subagent_cancel.go
index bd1b88e68..5efa5a031 100644
--- a/apps/daemon/internal/agent/mcode/subagent_cancel.go
+++ b/apps/daemon/internal/agent/mcode/subagent_cancel.go
@@ -6,21 +6,6 @@ import (
 	"fmt"
 )
 
-func (s *Session) cancelSubagents(ctx context.Context) error {
-	if err := s.stopSubagents(ctx); err != nil {
-		return err
-	}
-	select {
-	case <-s.finished:
-		s.mu.Lock()
-		err := s.subagentSettlementError
-		s.mu.Unlock()
-		return err
-	case <-ctx.Done():
-		return ctx.Err()
-	}
-}
-
 func (s *Session) stopSubagents(ctx context.Context) error {
 	select {
 	case <-s.finished:
diff --git a/apps/daemon/internal/agent/mcode/subagents_test.go b/apps/daemon/internal/agent/mcode/subagents_test.go
index bccb15597..25a1773af 100644
--- a/apps/daemon/internal/agent/mcode/subagents_test.go
+++ b/apps/daemon/internal/agent/mcode/subagents_test.go
@@ -27,7 +27,7 @@ func childSnapshot(t *testing.T) nativeSubagentSnapshot {
 func TestSubagentSnapshotsKeepOwnHistoryAndStableNativeIdentity(t *testing.T) {
 	project := func(snapshot nativeSubagentSnapshot) []proto.Envelope {
 		out := make(chan proto.Envelope, 32)
-		s := &Session{ctx: context.Background(), out: out, previousNativeTurns: map[string]bool{}}
+		s := &Session{ctx: context.Background(), outputContext: context.Background(), out: out, previousNativeTurns: map[string]bool{}}
 		if err := s.projectSubagents(snapshot); err != nil {
 			t.Fatal(err)
 		}
@@ -63,7 +63,7 @@ func TestSubagentSnapshotsKeepOwnHistoryAndStableNativeIdentity(t *testing.T) {
 func TestSubagentSnapshotRejectsMissingParentProvenance(t *testing.T) {
 	snapshot := childSnapshot(t)
 	snapshot.Sessions[0].Tasks = nil
-	s := &Session{ctx: context.Background(), out: make(chan proto.Envelope, 32)}
+	s := &Session{ctx: context.Background(), outputContext: context.Background(), out: make(chan proto.Envelope, 32)}
 	if err := s.projectSubagents(snapshot); err == nil {
 		t.Fatal("accepted child without original spawning provenance")
 	}
diff --git a/apps/daemon/internal/agent/mcode/tool_observations_test.go b/apps/daemon/internal/agent/mcode/tool_observations_test.go
index c7d1fa6da..703e3cb90 100644
--- a/apps/daemon/internal/agent/mcode/tool_observations_test.go
+++ b/apps/daemon/internal/agent/mcode/tool_observations_test.go
@@ -12,7 +12,7 @@ func TestWorkspaceCommandObservationsWaitForArgumentsAndRetainOutcome(t *testing
 	for _, status := range []string{"completed", "failed"} {
 		t.Run(status, func(t *testing.T) {
 			out := make(chan proto.Envelope, 8)
-			s := &Session{ctx: context.Background(), req: proto.PromptRequestPayload{RunID: "run"}, out: out, tools: map[string]toolUpdate{}, completedTools: map[string]bool{}}
+			s := &Session{ctx: context.Background(), outputContext: context.Background(), req: proto.PromptRequestPayload{RunID: "run"}, out: out, tools: map[string]toolUpdate{}, completedTools: map[string]bool{}}
 			s.emitTool(toolUpdate{ID: "call", Name: "mcp__oac_workspace__workspace_bash"})
 			if len(out) != 0 {
 				t.Fatal("command item emitted before native arguments")
diff --git a/apps/daemon/internal/agent/mcode/view_test.go b/apps/daemon/internal/agent/mcode/view_test.go
index 7b6d3a953..f21a17dcb 100644
--- a/apps/daemon/internal/agent/mcode/view_test.go
+++ b/apps/daemon/internal/agent/mcode/view_test.go
@@ -48,7 +48,7 @@ func viewFixture(t *testing.T) (viewInstall, agent.View, proto.PromptRequestPayl
 	registry := agent.NewRegistry()
 	info := Declaration.Info
 	info.Available = true
-	registry.Register(Declaration, agent.Runtime{Info: info, Session: Factory, View: &declared})
+	registry.Register(Declaration, agent.Runtime{Info: info, View: &declared})
 	view, err := registry.ResolveView("mcode")
 	if err != nil {
 		t.Fatal(err)
diff --git a/apps/daemon/internal/agent/registry.go b/apps/daemon/internal/agent/registry.go
index f64f74fa3..19265955b 100644
--- a/apps/daemon/internal/agent/registry.go
+++ b/apps/daemon/internal/agent/registry.go
@@ -10,23 +10,12 @@ import (
 	"github.com/MiniMax-AI/OpenAgentCore/internal/harnessconfig"
 )
 
-// ErrUnknownPermission is returned by PermissionResponder.SubmitPermission when
-// the permID doesn't match any outstanding request. The router uses
-// this to distinguish a benign race from a real forwarding failure.
-var ErrUnknownPermission = errors.New("agent: unknown permission id")
-
-// ErrUnknownAsk is returned by UserChoiceResponder.SubmitPromptForUserChoice when
-// the askID doesn't match any outstanding ask. Same race semantics as
-// ErrUnknownPermission.
-var ErrUnknownAsk = errors.New("agent: unknown ask id")
-
 var ErrUnsupportedKind = errors.New("agent: unsupported agent_kind")
 
-// Registry maps agent_kind → Factory and keeps the daemon-advertised
-// capability descriptor for each kind. Safe for concurrent use.
+// Registry keeps the daemon-advertised capability descriptor and execution
+// factories for each agent_kind. Safe for concurrent use.
 type Registry struct {
 	mu             sync.RWMutex
-	factories      map[string]Factory
 	executors      map[string]ExecutorFactory
 	views          map[string]View
 	kinds          map[string]proto.SupportedAgentKind
@@ -35,7 +24,6 @@ type Registry struct {
 
 func NewRegistry() *Registry {
 	return &Registry{
-		factories:      make(map[string]Factory),
 		executors:      make(map[string]ExecutorFactory),
 		views:          make(map[string]View),
 		kinds:          make(map[string]proto.SupportedAgentKind),
@@ -43,37 +31,13 @@ func NewRegistry() *Registry {
 	}
 }
 
-// Resolve returns the factory for kind, or wraps ErrUnsupportedKind.
-func (r *Registry) Resolve(kind string) (Factory, error) {
-	r.mu.RLock()
-	defer r.mu.RUnlock()
-	f, ok := r.factories[kind]
-	if !ok {
-		return nil, fmt.Errorf("%w: %q", ErrUnsupportedKind, kind)
-	}
-	return f, nil
-}
-
-// Kinds returns the list of registered kinds sorted lexicographically.
-func (r *Registry) Kinds() []string {
-	r.mu.RLock()
-	defer r.mu.RUnlock()
-	out := make([]string, 0, len(r.factories))
-	for k := range r.factories {
-		out = append(out, k)
-	}
-	slices.Sort(out)
-	return out
-}
-
 // SupportedAgentKinds returns the daemon-advertised capability
 // descriptors sorted by kind so heartbeat payloads are stable.
 func (r *Registry) SupportedAgentKinds() []proto.SupportedAgentKind {
 	r.mu.RLock()
 	defer r.mu.RUnlock()
-	out := make([]proto.SupportedAgentKind, 0, len(r.factories))
-	for kind := range r.factories {
-		info := r.kinds[kind]
+	out := make([]proto.SupportedAgentKind, 0, len(r.kinds))
+	for _, info := range r.kinds {
 		out = append(out, info)
 	}
 	slices.SortFunc(out, func(a, b proto.SupportedAgentKind) int {
diff --git a/apps/daemon/internal/agent/registry_test.go b/apps/daemon/internal/agent/registry_test.go
index 9614a7f7e..e2538065a 100644
--- a/apps/daemon/internal/agent/registry_test.go
+++ b/apps/daemon/internal/agent/registry_test.go
@@ -1,10 +1,11 @@
 package agent_test
 
+import "github.com/MiniMax-AI/OpenAgentCore/internal/harnessconfig"
+
 import (
 	"context"
 	"errors"
 	"reflect"
-	"slices"
 	"testing"
 
 	"github.com/MiniMax-AI/OpenAgentCore/apps/daemon/internal/agent"
@@ -12,77 +13,14 @@ import (
 	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto/prototest"
 )
 
-func stubFactory(marker string) agent.Factory {
-	return func(_ context.Context, _ proto.PromptRequestPayload, _ chan<- proto.Envelope) (agent.Session, error) {
-		return stubSession{marker: marker}, nil
-	}
-}
-
-type stubSession struct{ marker string }
-
-func (stubSession) CancellationOutcome() proto.DonePayload { return proto.DonePayload{} }
-
-func (stubSession) Cancel(context.Context) error { return nil }
-func (stubSession) SubmitPermission(context.Context, string, proto.PermissionDecisionPayload) error {
-	return nil
-}
-func (stubSession) SubmitPromptForUserChoice(context.Context, string, proto.PromptForUserChoiceDecisionPayload) error {
-	return nil
-}
-
-func TestRegistryResolveReturnsRegisteredFactory(t *testing.T) {
-	reg := agent.NewRegistry()
-	reg.RegisterKind(proto.SupportedAgentKind{Kind: "fake_alpha", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, prototest.ModelConfiguration(), stubFactory("cc"))
-
-	f, err := reg.Resolve("fake_alpha")
-	if err != nil {
-		t.Fatalf("Resolve: %v", err)
-	}
-	sess, err := f(context.Background(), prototest.WithModel(proto.PromptRequestPayload{AgentKind: "fake_alpha"}), nil)
-	if err != nil {
-		t.Fatalf("factory: %v", err)
-	}
-	stub, ok := sess.(stubSession)
-	if !ok || stub.marker != "cc" {
-		t.Errorf("resolved factory returned %#v, want stubSession{marker:\"cc\"}", sess)
-	}
-}
-
-func TestRegistryResolveUnknownKindReturnsTypedError(t *testing.T) {
+func TestRegistryRegisterOverwritesDescriptor(t *testing.T) {
 	reg := agent.NewRegistry()
-	reg.RegisterKind(proto.SupportedAgentKind{Kind: "fake_alpha", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, prototest.ModelConfiguration(), stubFactory("cc"))
+	reg.RegisterKind(proto.SupportedAgentKind{Kind: "k", Available: true, Version: "v1", Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, harnessconfig.Configuration{})
+	reg.RegisterKind(proto.SupportedAgentKind{Kind: "k", Available: true, Version: "v2", Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, harnessconfig.Configuration{})
 
-	_, err := reg.Resolve("fake_beta")
-	if !errors.Is(err, agent.ErrUnsupportedKind) {
-		t.Errorf("Resolve unknown = %v, want ErrUnsupportedKind chain", err)
-	}
-}
-
-func TestRegistryRegisterOverwrites(t *testing.T) {
-	reg := agent.NewRegistry()
-	reg.RegisterKind(proto.SupportedAgentKind{Kind: "k", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, prototest.ModelConfiguration(), stubFactory("v1"))
-	reg.RegisterKind(proto.SupportedAgentKind{Kind: "k", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, prototest.ModelConfiguration(), stubFactory("v2"))
-
-	f, err := reg.Resolve("k")
-	if err != nil {
-		t.Fatalf("Resolve: %v", err)
-	}
-	sess, _ := f(context.Background(), prototest.WithModel(proto.PromptRequestPayload{}), nil)
-	if got := sess.(stubSession).marker; got != "v2" {
-		t.Errorf("overwrite: marker = %q, want v2", got)
-	}
-}
-
-func TestRegistryKindsReportsRegistered(t *testing.T) {
-	reg := agent.NewRegistry()
-	reg.RegisterKind(proto.SupportedAgentKind{Kind: "fake_alpha", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, prototest.ModelConfiguration(), stubFactory("cc"))
-	reg.RegisterKind(proto.SupportedAgentKind{Kind: "fake_beta", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, prototest.ModelConfiguration(), stubFactory("oc"))
-
-	got := reg.Kinds()
-	slices.Sort(got)
-	want := []string{"fake_alpha", "fake_beta"}
-	if !slices.Equal(got, want) {
-		t.Errorf("Kinds = %v, want %v", got, want)
+	got := reg.SupportedAgentKinds()
+	if len(got) != 1 || got[0].Version != "v2" {
+		t.Errorf("overwrite: descriptors = %#v, want one v2 descriptor", got)
 	}
 }
 
@@ -92,16 +30,22 @@ func TestRegistryRegisterPanicsOnEmptyKind(t *testing.T) {
 			t.Fatal("Register(\"\", ...) did not panic")
 		}
 	}()
-	agent.NewRegistry().RegisterKind(proto.SupportedAgentKind{Kind: "", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, prototest.ModelConfiguration(), stubFactory("x"))
+	agent.NewRegistry().RegisterKind(proto.SupportedAgentKind{Kind: "", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, harnessconfig.Configuration{})
 }
 
-func TestRegistryRegisterPanicsOnNilFactory(t *testing.T) {
+func TestRegistryRegisterRejectsFactoriesForUnavailableRuntime(t *testing.T) {
+	info := proto.SupportedAgentKind{Kind: "k", Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{LocalEnvironment: proto.CapabilitySupported})}
+	executor := func(context.Context, proto.PromptRequestPayload) (agent.Executor, error) { return nil, nil }
+	registry := agent.NewRegistry()
 	defer func() {
-		if r := recover(); r == nil {
-			t.Fatal("Register(kind, nil) did not panic")
+		if recover() == nil {
+			t.Fatal("unavailable runtime registered factories")
+		}
+		if len(registry.SupportedAgentKinds()) != 0 {
+			t.Fatal("rejected runtime changed registry")
 		}
 	}()
-	agent.NewRegistry().RegisterKind(proto.SupportedAgentKind{Kind: "k", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, prototest.ModelConfiguration(), nil)
+	registry.Register(agent.Declaration{Info: info}, agent.Runtime{Info: info, Executor: executor})
 }
 
 func TestRegistrySupportedAgentKindsReportsDescriptors(t *testing.T) {
@@ -113,18 +57,17 @@ func TestRegistrySupportedAgentKindsReportsDescriptors(t *testing.T) {
 		Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{
 			Streaming: proto.CapabilitySupported,
 		}),
-	}, prototest.ModelConfiguration(), stubFactory("oc"))
+	}, harnessconfig.Configuration{})
 	reg.RegisterKind(proto.SupportedAgentKind{
 		Kind:      "fake_alpha",
 		Available: true,
 		Version:   "1.2.3",
 		Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{
-			Streaming:   proto.CapabilitySupported,
-			Permissions: proto.CapabilitySupported,
-			Usage:       proto.CapabilitySupported,
-			Resume:      proto.CapabilitySupported,
+			Streaming: proto.CapabilitySupported,
+			Usage:     proto.CapabilitySupported,
+			Resume:    proto.CapabilitySupported,
 		}),
-	}, prototest.ModelConfiguration(), stubFactory("cc"))
+	}, harnessconfig.Configuration{})
 
 	got := reg.SupportedAgentKinds()
 	if len(got) != 2 {
@@ -133,7 +76,7 @@ func TestRegistrySupportedAgentKindsReportsDescriptors(t *testing.T) {
 	if got[0].Kind != "fake_alpha" || got[1].Kind != "fake_beta" {
 		t.Fatalf("SupportedAgentKinds sort = %#v, want fake_alpha then fake_beta", got)
 	}
-	if !got[0].Available || got[0].Version != "1.2.3" || !got[0].Capabilities.Permissions.IsSupported() || !got[0].Capabilities.Resume.IsSupported() {
+	if !got[0].Available || got[0].Version != "1.2.3" || !got[0].Capabilities.Usage.IsSupported() || !got[0].Capabilities.Resume.IsSupported() {
 		t.Fatalf("fake_alpha descriptor not preserved: %#v", got[0])
 	}
 	if got[1].Available || got[1].Version != "missing" || !got[1].Capabilities.Streaming.IsSupported() {
@@ -143,9 +86,9 @@ func TestRegistrySupportedAgentKindsReportsDescriptors(t *testing.T) {
 
 func TestRegistryExecutorRequiresExplicitRegistration(t *testing.T) {
 	registry := agent.NewRegistry()
-	registry.RegisterKind(proto.SupportedAgentKind{Kind: "native", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, prototest.ModelConfiguration(), stubFactory("native"))
+	registry.RegisterKind(proto.SupportedAgentKind{Kind: "native", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, prototest.ModelConfiguration())
 	if _, err := registry.ResolveExecutor("native"); err == nil {
-		t.Fatal("legacy factory implied reusable execution")
+		t.Fatal("kind registration implied reusable execution")
 	}
 	expected := errors.New("executor factory")
 	registry.RegisterExecutor("native", func(context.Context, proto.PromptRequestPayload) (agent.Executor, error) { return nil, expected })
@@ -156,7 +99,7 @@ func TestRegistryExecutorRequiresExplicitRegistration(t *testing.T) {
 	if _, err := factory(t.Context(), prototest.WithModel(proto.PromptRequestPayload{})); !errors.Is(err, expected) {
 		t.Fatal(err)
 	}
-	registry.RegisterKind(proto.SupportedAgentKind{Kind: "native", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, prototest.ModelConfiguration(), stubFactory("replacement"))
+	registry.RegisterKind(proto.SupportedAgentKind{Kind: "native", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, harnessconfig.Configuration{})
 	if _, err := registry.ResolveExecutor("native"); err == nil {
 		t.Fatal("replacing a kind retained its old executor capability")
 	}
@@ -167,7 +110,10 @@ func TestRegistryRejectsEveryOmittedCapabilityBeforeReplacement(t *testing.T) {
 	for i := 0; i < reflect.TypeOf(valid).NumField(); i++ {
 		t.Run(reflect.TypeOf(valid).Field(i).Name, func(t *testing.T) {
 			registry := agent.NewRegistry()
-			registry.RegisterKind(proto.SupportedAgentKind{Kind: "fixture", Available: true, Capabilities: valid}, prototest.ModelConfiguration(), stubFactory("original"))
+			original := proto.SupportedAgentKind{Kind: "fixture", Available: true, Capabilities: valid}
+			registry.RegisterKind(original, harnessconfig.Configuration{})
+			registry.RegisterExecutor("fixture", func(context.Context, proto.PromptRequestPayload) (agent.Executor, error) { return nil, nil })
+			original.Capabilities.Preparation = proto.CapabilitySupported
 			missing := valid
 			reflect.ValueOf(&missing).Elem().Field(i).Set(reflect.ValueOf(proto.CapabilityUnspecified))
 			func() {
@@ -176,14 +122,9 @@ func TestRegistryRejectsEveryOmittedCapabilityBeforeReplacement(t *testing.T) {
 						t.Error("incomplete declaration registered")
 					}
 				}()
-				registry.RegisterKind(proto.SupportedAgentKind{Kind: "fixture", Available: false, Capabilities: missing}, prototest.ModelConfiguration(), stubFactory("replacement"))
+				registry.RegisterKind(proto.SupportedAgentKind{Kind: "fixture", Available: false, Capabilities: missing}, harnessconfig.Configuration{})
 			}()
-			factory, err := registry.Resolve("fixture")
-			if err != nil {
-				t.Fatal(err)
-			}
-			session, err := factory(t.Context(), prototest.WithModel(proto.PromptRequestPayload{}), nil)
-			if err != nil || session.(stubSession).marker != "original" {
+			if _, err := registry.ResolveExecutor("fixture"); err != nil || !reflect.DeepEqual(registry.SupportedAgentKinds(), []proto.SupportedAgentKind{original}) {
 				t.Fatal("failed declaration changed registry")
 			}
 		})
diff --git a/apps/daemon/internal/agent/view_test.go b/apps/daemon/internal/agent/view_test.go
index 70f5ae267..04f1332e9 100644
--- a/apps/daemon/internal/agent/view_test.go
+++ b/apps/daemon/internal/agent/view_test.go
@@ -54,7 +54,7 @@ func TestRegistryResolvesOnlyDeclaredViews(t *testing.T) {
 	declared := validView(t)
 	for kind, view := range map[string]*agent.View{"with_view": &declared, "without_view": nil} {
 		info := proto.SupportedAgentKind{Kind: kind, Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}
-		reg.Register(agent.Declaration{Info: info}, agent.Runtime{Info: info, Session: stubFactory(kind), View: view})
+		reg.Register(agent.Declaration{Info: info}, agent.Runtime{Info: info, View: view})
 	}
 	if _, err := reg.ResolveView("without_view"); !errors.Is(err, agent.ErrUnsupportedOperation) {
 		t.Fatalf("ResolveView without a view = %v, want ErrUnsupportedOperation", err)
@@ -76,7 +76,7 @@ func TestViewExecutorReceivesOnlyGatewayConnections(t *testing.T) {
 		Info:          info,
 		Configuration: harnessconfig.Configuration{Providers: []harnessconfig.Provider{{Protocol: string(modelprovider.Responses)}}},
 	}
-	reg.Register(declaration, agent.Runtime{Info: info, Session: stubFactory("viewed"), View: &declared})
+	reg.Register(declaration, agent.Runtime{Info: info, View: &declared})
 	view, err := reg.ResolveView("viewed")
 	if err != nil {
 		t.Fatal(err)
diff --git a/apps/daemon/internal/agenthost/agenthost_linux_test.go b/apps/daemon/internal/agenthost/agenthost_linux_test.go
index 09655db85..2cce3512f 100644
--- a/apps/daemon/internal/agenthost/agenthost_linux_test.go
+++ b/apps/daemon/internal/agenthost/agenthost_linux_test.go
@@ -74,10 +74,7 @@ func register(reg *agent.Registry, kind string, view *agent.View) {
 		MCPHTTPTools: proto.CapabilitySupported, MCPHTTPBearerAuth: proto.CapabilitySupported, WorkspaceReadPreparation: proto.CapabilitySupported})}
 	declaration := agent.Declaration{Info: info,
 		Configuration: harnessconfig.Configuration{Providers: []harnessconfig.Provider{{Protocol: string(modelprovider.Anthropic)}}}}
-	reg.Register(declaration, agent.Runtime{Info: info, View: view,
-		Session: func(context.Context, proto.PromptRequestPayload, chan<- proto.Envelope) (agent.Session, error) {
-			return nil, errors.New("not used")
-		}})
+	reg.Register(declaration, agent.Runtime{Info: info, View: view})
 }
 
 // declared declares every view capability as s.
diff --git a/apps/daemon/internal/agenthost/executor_linux.go b/apps/daemon/internal/agenthost/executor_linux.go
index e6a156746..ce6555c9c 100644
--- a/apps/daemon/internal/agenthost/executor_linux.go
+++ b/apps/daemon/internal/agenthost/executor_linux.go
@@ -30,8 +30,7 @@ type deps struct {
 // with Info that describes how views run it. Its Executor factory prepares an
 // Executor of the Session that bind binds the request to, as the package
 // documentation describes, and bind's error fails the preparation. The Router
-// that runs it sets dispatch.Config.SessionEnvironments. A direct prompt run
-// is unsupported.
+// that runs it sets dispatch.Config.SessionEnvironments.
 func (h *Host) Registry(bind func(proto.PromptRequestPayload) (Binding, Environment, error)) *agent.Registry {
 	d := deps{dial: relayDial(h.cfg), tasks: taskUIDs}
 	return registry(h.cfg.Harnesses, func(ctx context.Context, req proto.PromptRequestPayload) (agent.Executor, error) {
@@ -49,9 +48,7 @@ func registry(harnesses *agent.Registry, factory agent.ExecutorFactory) *agent.R
 		if err != nil || viewErr != nil {
 			continue
 		}
-		reg.RegisterKind(viewInfo(info, view.Capabilities), configuration, func(context.Context, proto.PromptRequestPayload, chan<- proto.Envelope) (agent.Session, error) {
-			return nil, unsupported("a direct prompt run")
-		})
+		reg.RegisterKind(viewInfo(info, view.Capabilities), configuration)
 		reg.RegisterExecutor(info.Kind, factory)
 	}
 	return reg
diff --git a/apps/daemon/internal/agenthostqualify/qualify_linux_test.go b/apps/daemon/internal/agenthostqualify/qualify_linux_test.go
index f7e4b915d..c6b21f4ca 100644
--- a/apps/daemon/internal/agenthostqualify/qualify_linux_test.go
+++ b/apps/daemon/internal/agenthostqualify/qualify_linux_test.go
@@ -326,12 +326,11 @@ func withMCP(t *testing.T, reg *agent.Registry, mcp []proto.EnvironmentMCP) *age
 	wrapped := agent.NewRegistry()
 	for _, info := range reg.SupportedAgentKinds() {
 		configuration, err := reg.Configuration(info.Kind)
-		direct, directErr := reg.Resolve(info.Kind)
 		factory, factoryErr := reg.ResolveExecutor(info.Kind)
-		if err := errors.Join(err, directErr, factoryErr); err != nil {
+		if err := errors.Join(err, factoryErr); err != nil {
 			t.Fatal(err)
 		}
-		wrapped.RegisterKind(info, configuration, direct)
+		wrapped.RegisterKind(info, configuration)
 		wrapped.RegisterExecutor(info.Kind, func(ctx context.Context, req proto.PromptRequestPayload) (agent.Executor, error) {
 			local := *req.LocalEnvironment
 			local.MCP = mcp
diff --git a/apps/daemon/internal/cli/claude_sdk_live_linux_test.go b/apps/daemon/internal/cli/claude_sdk_live_linux_test.go
index 19741a255..c2e8dd5a7 100644
--- a/apps/daemon/internal/cli/claude_sdk_live_linux_test.go
+++ b/apps/daemon/internal/cli/claude_sdk_live_linux_test.go
@@ -16,6 +16,7 @@ import (
 	"github.com/MiniMax-AI/OpenAgentCore/apps/daemon/internal/dispatch"
 	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
 	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto/prototest"
+	"github.com/MiniMax-AI/OpenAgentCore/internal/modelprovider"
 	"github.com/google/uuid"
 )
 
@@ -49,10 +50,10 @@ func TestLiveRegisteredClaudeSDK(t *testing.T) {
 	if err != nil {
 		t.Fatal(err)
 	}
+	provider := &modelprovider.Provider{Protocol: modelprovider.Anthropic, BaseURL: "https://api.minimax.cn/anthropic", APIKey: strings.TrimSpace(string(key))}
 	for name, value := range map[string]string{
-		"ANTHROPIC_BASE_URL": "https://api.minimax.cn/anthropic", "ANTHROPIC_AUTH_TOKEN": strings.TrimSpace(string(key)),
-		"ANTHROPIC_API_KEY": "", "CLAUDE_CODE_OAUTH_TOKEN": "", "CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS": "1",
-		"ANTHROPIC_DEFAULT_SONNET_MODEL": "MiniMax-M3", "ANTHROPIC_DEFAULT_OPUS_MODEL": "MiniMax-M3", "ANTHROPIC_DEFAULT_HAIKU_MODEL": "MiniMax-M3",
+		"CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS": "1",
+		"ANTHROPIC_DEFAULT_SONNET_MODEL":         "MiniMax-M3", "ANTHROPIC_DEFAULT_OPUS_MODEL": "MiniMax-M3", "ANTHROPIC_DEFAULT_HAIKU_MODEL": "MiniMax-M3",
 	} {
 		t.Setenv(name, value)
 	}
@@ -89,7 +90,7 @@ func TestLiveRegisteredClaudeSDK(t *testing.T) {
 		ctx, cancel := context.WithTimeout(t.Context(), 120*time.Second)
 		defer cancel()
 		id := uuid.NewString()
-		request := proto.PromptRequestPayload{AgentKind: "claude_sdk", AgentStateKey: prototest.StateKey, AgentSessionID: resume, RequireExistingNativeSession: resume != "", ObserveMessages: true, DisableExecutionEnvironment: true, DisableSubagents: true, ExecutionControls: &proto.ExecutionControls{WebSearch: "disabled", TextVerbosity: "medium"}, Model: "MiniMax-M3"}
+		request := proto.PromptRequestPayload{AgentKind: "claude_sdk", AgentStateKey: prototest.StateKey, AgentSessionID: resume, RequireExistingNativeSession: resume != "", ObserveMessages: true, DisableExecutionEnvironment: true, DisableSubagents: true, ExecutionControls: &proto.ExecutionControls{WebSearch: "disabled", TextVerbosity: "medium"}, Model: "MiniMax-M3", ModelProvider: provider}
 		if callFunction {
 			request.FunctionTools = []proto.FunctionTool{{Name: "lookup", Description: "Return a verification value.", Parameters: json.RawMessage(`{"type":"object","properties":{"id":{"type":"string"}},"required":["id"],"additionalProperties":false}`)}}
 		}
diff --git a/apps/daemon/internal/cli/connect.go b/apps/daemon/internal/cli/connect.go
index f920318b3..afdea1a96 100644
--- a/apps/daemon/internal/cli/connect.go
+++ b/apps/daemon/internal/cli/connect.go
@@ -151,7 +151,7 @@ func spawnBackground(ctx context.Context, rc *runContext, profile string, argv [
 	} else if !errors.Is(err, os.ErrNotExist) && !errors.Is(err, daemonize.ErrStaleOrCorrupt) {
 		return fmt.Errorf("connect: check pidfile: %w", err)
 	}
-	// Stale pidfile → remove so WritePIDFile starts clean.
+	// Stale pidfile → remove so Spawn starts clean.
 	_ = daemonize.RemovePIDFile(pidPath)
 
 	if err := daemonize.EnsureLogFile(logPath); err != nil {
diff --git a/apps/daemon/internal/cli/connect_cleanup_test.go b/apps/daemon/internal/cli/connect_cleanup_test.go
index e7d44e052..3a20c2e16 100644
--- a/apps/daemon/internal/cli/connect_cleanup_test.go
+++ b/apps/daemon/internal/cli/connect_cleanup_test.go
@@ -113,10 +113,7 @@ func testDisconnectedPumpCleanup(t *testing.T, suspend bool) {
 	}
 	owner := &cleanupExecutor{retry: make(chan struct{}), confirm: make(chan struct{})}
 	registry := agent.NewRegistry()
-	registry.RegisterKind(proto.SupportedAgentKind{Kind: "cleanup", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{EnvironmentNone: proto.CapabilitySupported})},
-		prototest.ModelConfiguration(), func(context.Context, proto.PromptRequestPayload, chan<- proto.Envelope) (agent.Session, error) {
-			return nil, errors.New("unexpected legacy factory")
-		})
+	registry.RegisterKind(proto.SupportedAgentKind{Kind: "cleanup", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{EnvironmentNone: proto.CapabilitySupported})}, prototest.ModelConfiguration())
 	var factories atomic.Int32
 	registry.RegisterExecutor("cleanup", func(context.Context, proto.PromptRequestPayload) (agent.Executor, error) {
 		factories.Add(1)
diff --git a/apps/daemon/internal/cli/connect_environment_binding.go b/apps/daemon/internal/cli/connect_environment_binding.go
index 9fa651798..b661092e0 100644
--- a/apps/daemon/internal/cli/connect_environment_binding.go
+++ b/apps/daemon/internal/cli/connect_environment_binding.go
@@ -95,17 +95,6 @@ func bindEnvironmentRuntime(remote string, bound environmentEnrollment, credenti
 	return nil
 }
 
-// Neither selecting private state nor selecting its parent grants workspace access.
-func environmentPathsOverlap(first, second string) bool {
-	for _, pair := range [][2]string{{first, second}, {second, first}} {
-		relative, err := filepath.Rel(pair[0], pair[1])
-		if err == nil && (relative == "." || filepath.IsLocal(relative)) {
-			return true
-		}
-	}
-	return false
-}
-
 func saveEnvironmentBinding(root string, want environmentBinding) error {
 	// Store the binding with the other daemon state.
 	dir := filepath.Join(root, "daemon")
diff --git a/apps/daemon/internal/cli/native_discovery_test.go b/apps/daemon/internal/cli/native_discovery_test.go
index e6d9e0dee..5f3592c9d 100644
--- a/apps/daemon/internal/cli/native_discovery_test.go
+++ b/apps/daemon/internal/cli/native_discovery_test.go
@@ -21,9 +21,7 @@ func TestDiscoveryAndRegistration(t *testing.T) {
 					called = append(called, info.Kind)
 					info.Available = true
 					info.Version = "test"
-					return &agent.Runtime{Info: info, Session: func(context.Context, proto.PromptRequestPayload, chan<- proto.Envelope) (agent.Session, error) {
-						return nil, errors.New("test")
-					}}
+					return &agent.Runtime{Info: info}
 				}
 			}
 			rc := &runContext{stdout: io.Discard, stderr: io.Discard}
@@ -41,10 +39,11 @@ func TestDiscoveryAndRegistration(t *testing.T) {
 			}
 			registry := agent.NewRegistry()
 			registerAgentKinds(registry, discovery)
-			if len(registry.Kinds()) != len(expected) {
-				t.Fatal(registry.Kinds())
+			kinds := registry.SupportedAgentKinds()
+			if len(kinds) != len(expected) {
+				t.Fatal(kinds)
 			}
-			for _, info := range registry.SupportedAgentKinds() {
+			for _, info := range kinds {
 				if !info.Available || info.Version != "test" {
 					t.Fatal(info)
 				}
diff --git a/apps/daemon/internal/daemonize/logfile.go b/apps/daemon/internal/daemonize/logfile.go
index 80124e1fc..a74f0dcfd 100644
--- a/apps/daemon/internal/daemonize/logfile.go
+++ b/apps/daemon/internal/daemonize/logfile.go
@@ -1,14 +1,14 @@
 package daemonize
 
 import (
-	"bufio"
 	"errors"
 	"fmt"
-	"github.com/MiniMax-AI/OpenAgentCore/internal/runtimefs"
 	"io"
 	"os"
 	"path/filepath"
 	"time"
+
+	"github.com/MiniMax-AI/OpenAgentCore/internal/runtimefs"
 )
 
 // TailOptions configures Tail.
@@ -149,27 +149,6 @@ func EnsureLogFile(path string) error {
 	return f.Close()
 }
 
-// MustWriteLine appends one line to path with 0o600 mode, adding a
-// trailing newline if missing. Returns errors despite the name —
-// kept short because it's used in startup hot paths.
-func MustWriteLine(path string, line string) error {
-	f, err := openPrivateLog(path)
-	if err != nil {
-		return err
-	}
-	defer f.Close()
-	bw := bufio.NewWriter(f)
-	if _, err := bw.WriteString(line); err != nil {
-		return err
-	}
-	if len(line) == 0 || line[len(line)-1] != '\n' {
-		if _, err := bw.WriteString("\n"); err != nil {
-			return err
-		}
-	}
-	return bw.Flush()
-}
-
 func openPrivateLog(path string) (*os.File, error) {
 	root, err := os.OpenRoot(filepath.Dir(path))
 	if err != nil {
diff --git a/apps/daemon/internal/daemonize/logfile_test.go b/apps/daemon/internal/daemonize/logfile_test.go
index a13bdca48..5d1caeb6e 100644
--- a/apps/daemon/internal/daemonize/logfile_test.go
+++ b/apps/daemon/internal/daemonize/logfile_test.go
@@ -182,21 +182,6 @@ func TestEnsureLogFileCreatesMissingParentDir(t *testing.T) {
 	}
 }
 
-func TestMustWriteLineAppendsTrailingNewline(t *testing.T) {
-	dir := privateTempDir(t)
-	path := filepath.Join(dir, "ml.log")
-	if err := MustWriteLine(path, "no-newline"); err != nil {
-		t.Fatalf("MustWriteLine: %v", err)
-	}
-	if err := MustWriteLine(path, "has-newline\n"); err != nil {
-		t.Fatalf("MustWriteLine: %v", err)
-	}
-	body, _ := os.ReadFile(path)
-	if string(body) != "no-newline\nhas-newline\n" {
-		t.Errorf("body = %q", string(body))
-	}
-}
-
 // safeBuf wraps bytes.Buffer with a mutex so concurrent reads/writes
 // during Tail's poll loop don't race.
 type safeBuf struct {
diff --git a/apps/daemon/internal/daemonize/pidfile.go b/apps/daemon/internal/daemonize/pidfile.go
index 2224c8542..b6ad008c1 100644
--- a/apps/daemon/internal/daemonize/pidfile.go
+++ b/apps/daemon/internal/daemonize/pidfile.go
@@ -19,15 +19,6 @@ type processIdentity struct {
 	StopEvent string `json:"stop_event,omitempty"`
 }
 
-func WritePIDFile(path string, pid int) error {
-	identity, err := identifyProcess(pid)
-	if err != nil {
-		return err
-	}
-	identity.StopEvent = os.Getenv(stopEventEnv)
-	return writeIdentity(path, identity)
-}
-
 func writeIdentity(path string, identity processIdentity) error {
 	if path == "" {
 		return errors.New("daemonize: process record path required")
@@ -71,8 +62,6 @@ func ReadPIDFile(path string) (int, error) {
 	return identity.PID, err
 }
 
-func IsAlive(pid int) error { _, err := identifyProcess(pid); return err }
-
 // StopPIDFile never removes ownership before the exact process has exited.
 // A cleanup timeout leaves the record available for observation and a later stop.
 func StopPIDFile(path string, timeout time.Duration) error {
diff --git a/apps/daemon/internal/daemonize/pidfile_test.go b/apps/daemon/internal/daemonize/pidfile_test.go
index 4aec5a769..5f83362d0 100644
--- a/apps/daemon/internal/daemonize/pidfile_test.go
+++ b/apps/daemon/internal/daemonize/pidfile_test.go
@@ -11,7 +11,11 @@ import (
 
 func TestProcessRecordIdentity(t *testing.T) {
 	path := filepath.Join(privateTempDir(t), "connect.pid")
-	if err := WritePIDFile(path, os.Getpid()); err != nil {
+	record, err := identifyProcess(os.Getpid())
+	if err == nil {
+		err = writeIdentity(path, record)
+	}
+	if err != nil {
 		t.Fatal(err)
 	}
 	pid, err := ReadPIDFile(path)
@@ -34,7 +38,7 @@ func TestProcessRecordIdentity(t *testing.T) {
 	if err = StopPIDFile(path, time.Second); !errors.Is(err, ErrStaleOrCorrupt) {
 		t.Fatal("stale identity was accepted", err)
 	}
-	if err = IsAlive(os.Getpid()); err != nil {
+	if _, err = identifyProcess(os.Getpid()); err != nil {
 		t.Fatal("unrelated process was affected", err)
 	}
 	if _, err = os.Stat(path); err != nil {
diff --git a/apps/daemon/internal/dispatch/assignment.go b/apps/daemon/internal/dispatch/assignment.go
index ae5b82b41..de307618b 100644
--- a/apps/daemon/internal/dispatch/assignment.go
+++ b/apps/daemon/internal/dispatch/assignment.go
@@ -120,7 +120,7 @@ func (r *Router) handleAssignmentRelease(ctx context.Context, env proto.Envelope
 	go func() {
 		defer r.shutdownWG.Done()
 		for _, p := range preparations {
-			r.releasePreparation(p, "failed", proto.AssignmentStale, true, false)
+			r.releasePreparation(p, "failed", proto.AssignmentStale, true)
 		}
 		work.Wait()
 		state, code := proto.AssignmentReleased, ""
@@ -154,7 +154,7 @@ func (r *Router) fenceSessionWorkLocked(sessionID string) []*preparationState {
 	}
 	var preparations []*preparationState
 	for _, p := range r.preparations {
-		if p.executor == nil && p.workspaceReadOnly && p.owns && p.request.Assignment.SessionID == sessionID {
+		if p.executor == nil && p.owns && p.request.Assignment.SessionID == sessionID {
 			preparations = append(preparations, p)
 		}
 	}
diff --git a/apps/daemon/internal/dispatch/capability_admission_test.go b/apps/daemon/internal/dispatch/capability_admission_test.go
index 8cdb2240d..823aa22d3 100644
--- a/apps/daemon/internal/dispatch/capability_admission_test.go
+++ b/apps/daemon/internal/dispatch/capability_admission_test.go
@@ -52,50 +52,3 @@ func TestSteeringUsesAdmittedDeclarationAndDoesNotReplayUnsupportedImplementatio
 		})
 	}
 }
-
-func TestInteractionDeclarationPrecedesResponderMethods(t *testing.T) {
-	for _, supported := range []bool{false, true} {
-		for _, ask := range []bool{false, true} {
-			t.Run(fmt.Sprintf("supported=%v/ask=%v", supported, ask), func(t *testing.T) {
-				h := newHarness(t)
-				defer h.router.Shutdown(context.Background())
-				var session *fakeSession
-				info := proto.SupportedAgentKind{Kind: "fixture", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{Permissions: proto.CapabilityFromBool(supported)})}
-				registerSession(h.reg, info, func(_ context.Context, _ proto.PromptRequestPayload, out chan<- proto.Envelope) (agent.Session, error) {
-					session = &fakeSession{out: out, closeOutOnCancel: true, submitErr: agent.ErrUnsupportedOperation, askErr: agent.ErrUnsupportedOperation}
-					return session, nil
-				})
-				startRun(t, h.router, h.sender, "fixture", "run")
-				event := mustEnv(t, proto.TypePermissionRequest, "run", proto.PermissionRequestPayload{RequestID: "interaction", Tool: "fixture"})
-				decision := scoped(t, "run", proto.TypePermissionDecision, "interaction", proto.PermissionDecisionPayload{DeliveryID: "decision", Approved: true})
-				if ask {
-					event = mustEnv(t, proto.TypePromptForUserChoice, "run", proto.PromptForUserChoicePayload{AskID: "interaction"})
-					decision = scoped(t, "run", proto.TypePromptForUserChoiceDecision, "interaction", proto.PromptForUserChoiceDecisionPayload{DeliveryID: "decision"})
-				}
-				session.out <- event
-				waitFor(t, func() bool { return hasFrame(h.sender, event.Type, "run") }, "interaction indexed")
-				if err := h.router.Handle(t.Context(), decision); err != nil {
-					t.Fatal(err)
-				}
-				code := "unsupported"
-				if supported {
-					code = "contract_violation"
-				}
-				assertDecisionAck(t, h.sender, "decision", false, code)
-				count := len(session.submissions())
-				if ask {
-					session.askMu.Lock()
-					count = len(session.askCalls)
-					session.askMu.Unlock()
-				}
-				want := 0
-				if supported {
-					want = 1
-				}
-				if count != want {
-					t.Fatalf("native calls %d, want %d", count, want)
-				}
-			})
-		}
-	}
-}
diff --git a/apps/daemon/internal/dispatch/executor.go b/apps/daemon/internal/dispatch/executor.go
index 9bf45b9e6..2fd2a18f5 100644
--- a/apps/daemon/internal/dispatch/executor.go
+++ b/apps/daemon/internal/dispatch/executor.go
@@ -161,7 +161,7 @@ func (r *Router) handleExecutorPrepare(ctx context.Context, env proto.Envelope,
 	p.status = proto.PreparationStatusPayload{Handle: uuid.NewString(), ExecutorID: owner.id, Revision: 1, State: state, Reused: reused, ExpiresAt: p.deadline.UnixMilli()}
 	owner.admission = p
 	r.preparations[p.status.Handle], r.preparationRequests[env.ID] = p, p
-	p.timer = time.AfterFunc(r.preparationTimeout, func() { r.releasePreparation(p, "expired", "", true, true) })
+	p.timer = time.AfterFunc(r.preparationTimeout, func() { r.releasePreparation(p, "expired", "", true) })
 	if !reused {
 		r.shutdownWG.Add(1)
 	}
diff --git a/apps/daemon/internal/dispatch/executor_cancel_receipt_test.go b/apps/daemon/internal/dispatch/executor_cancel_receipt_test.go
index 496e4dd4b..590d8bc0b 100644
--- a/apps/daemon/internal/dispatch/executor_cancel_receipt_test.go
+++ b/apps/daemon/internal/dispatch/executor_cancel_receipt_test.go
@@ -125,9 +125,7 @@ func TestExecutorCancellationReachesNativeBeforeDurableReceiptJoin(t *testing.T)
 			sender := &receiptCancelSender{recSender: &recSender{}, entered: make(chan struct{}), release: make(chan struct{})}
 			owner := &receiptCancelExecutor{turn: make(chan *receiptCancelTurn, 2), cancelFails: mode == "cancel_failure" || mode == "close_failure_retry", closeFailsFirst: mode == "close_failure_retry", closeEntered: make(chan struct{}), closeRelease: make(chan struct{})}
 			reg := agent.NewRegistry()
-			reg.RegisterKind(proto.SupportedAgentKind{Kind: "reusable", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{EnvironmentNone: proto.CapabilitySupported, DurableInputReceipts: proto.CapabilitySupported})}, prototest.ModelConfiguration(), func(context.Context, proto.PromptRequestPayload, chan<- proto.Envelope) (agent.Session, error) {
-				return nil, errors.New("legacy factory forbidden")
-			})
+			reg.RegisterKind(proto.SupportedAgentKind{Kind: "reusable", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{EnvironmentNone: proto.CapabilitySupported, DurableInputReceipts: proto.CapabilitySupported})}, prototest.ModelConfiguration())
 			reg.RegisterExecutor("reusable", func(context.Context, proto.PromptRequestPayload) (agent.Executor, error) { return owner, nil })
 			r, err := dispatch.New(dispatch.Config{Registry: reg, Sender: sender, IdleTimeout: time.Hour})
 			if err != nil {
diff --git a/apps/daemon/internal/dispatch/executor_handoff_test.go b/apps/daemon/internal/dispatch/executor_handoff_test.go
index 3db03edad..b7f89a573 100644
--- a/apps/daemon/internal/dispatch/executor_handoff_test.go
+++ b/apps/daemon/internal/dispatch/executor_handoff_test.go
@@ -91,10 +91,7 @@ func TestPreparedDonePublishesAfterExecutorHandoff(t *testing.T) {
 			}
 			owner := &terminalHandoffExecutor{turns: make(chan *terminalHandoffTurn, 3)}
 			registry := agent.NewRegistry()
-			registry.RegisterKind(proto.SupportedAgentKind{Kind: "handoff", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{EnvironmentNone: proto.CapabilitySupported})},
-				prototest.ModelConfiguration(), func(context.Context, proto.PromptRequestPayload, chan<- proto.Envelope) (agent.Session, error) {
-					return nil, errors.New("legacy path forbidden")
-				})
+			registry.RegisterKind(proto.SupportedAgentKind{Kind: "handoff", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{EnvironmentNone: proto.CapabilitySupported})}, prototest.ModelConfiguration())
 			var creates atomic.Int32
 			registry.RegisterExecutor("handoff", func(context.Context, proto.PromptRequestPayload) (agent.Executor, error) {
 				creates.Add(1)
diff --git a/apps/daemon/internal/dispatch/executor_test.go b/apps/daemon/internal/dispatch/executor_test.go
index 0a8080804..52941687b 100644
--- a/apps/daemon/internal/dispatch/executor_test.go
+++ b/apps/daemon/internal/dispatch/executor_test.go
@@ -79,9 +79,7 @@ func executorRequest() proto.ExecutionPreparePayload {
 
 // registerExecutorKind registers info for prepared execution only.
 func registerExecutorKind(reg *agent.Registry, info proto.SupportedAgentKind, factory agent.ExecutorFactory) {
-	reg.RegisterKind(info, prototest.ModelConfiguration(), func(context.Context, proto.PromptRequestPayload, chan<- proto.Envelope) (agent.Session, error) {
-		return nil, errors.New("prepared execution must not use the direct Session factory")
-	})
+	reg.RegisterKind(info, prototest.ModelConfiguration())
 	reg.RegisterExecutor(info.Kind, factory)
 }
 func executorRouter(t *testing.T, owner *reusableExecutor, idle time.Duration) (*dispatch.Router, *recSender, *atomic.Int32) {
@@ -230,9 +228,7 @@ func TestExecutorPreInputFailureConfirmsCloseBeforeRetrySignal(t *testing.T) {
 func poolRouter(t *testing.T, factory agent.ExecutorFactory) (*dispatch.Router, *recSender) {
 	t.Helper()
 	registry := agent.NewRegistry()
-	registry.RegisterKind(proto.SupportedAgentKind{Kind: "reusable", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{EnvironmentNone: proto.CapabilitySupported, DurableInputReceipts: proto.CapabilitySupported})}, prototest.ModelConfiguration(), func(context.Context, proto.PromptRequestPayload, chan<- proto.Envelope) (agent.Session, error) {
-		return nil, errors.New("unexpected legacy factory")
-	})
+	registry.RegisterKind(proto.SupportedAgentKind{Kind: "reusable", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{EnvironmentNone: proto.CapabilitySupported, DurableInputReceipts: proto.CapabilitySupported})}, prototest.ModelConfiguration())
 	registry.RegisterExecutor("reusable", factory)
 	sender := &recSender{}
 	router, err := dispatch.New(dispatch.Config{Registry: registry, Sender: sender, IdleTimeout: time.Minute})
diff --git a/apps/daemon/internal/dispatch/export_test.go b/apps/daemon/internal/dispatch/export_test.go
index 05d7011d7..6ee90d36e 100644
--- a/apps/daemon/internal/dispatch/export_test.go
+++ b/apps/daemon/internal/dispatch/export_test.go
@@ -7,29 +7,6 @@ func (r *Router) PreparationOwnershipForTest(handle string) (bool, bool) {
 	return p != nil && p.owns, p != nil && p.busy
 }
 
-// Test-only re-exports so router_test.go (package dispatch_test) can
-// peek into internal state without widening the public surface.
-
-// AskIndexLenForTest returns the number of asks still indexed at the
-// router level. Used to assert cleanup paths.
-func (r *Router) AskIndexLenForTest() int {
-	r.mu.Lock()
-	defer r.mu.Unlock()
-	return len(r.askIndex)
-}
-
-// PendingAsksLenForTest reports how many asks the named run still has
-// outstanding. Returns -1 if the run is unknown.
-func (r *Router) PendingAsksLenForTest(runID string) int {
-	r.mu.Lock()
-	defer r.mu.Unlock()
-	s, ok := r.sessions[runID]
-	if !ok {
-		return -1
-	}
-	return len(s.pendingAsks)
-}
-
 func (r *Router) SteeringClosedForTest(runID string) bool {
 	r.mu.Lock()
 	defer r.mu.Unlock()
diff --git a/apps/daemon/internal/dispatch/functions.go b/apps/daemon/internal/dispatch/functions.go
index 6aed14c06..569a26aaf 100644
--- a/apps/daemon/internal/dispatch/functions.go
+++ b/apps/daemon/internal/dispatch/functions.go
@@ -5,6 +5,8 @@ import (
 	"crypto/sha256"
 	"encoding/json"
 	"errors"
+	"fmt"
+	"time"
 
 	"github.com/MiniMax-AI/OpenAgentCore/apps/daemon/internal/agent"
 	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
@@ -29,9 +31,19 @@ func (r *Router) handleFunctionResult(ctx context.Context, env proto.Envelope) e
 	}
 	fingerprint := sha256.Sum256(encoded)
 	// Scope receipt replay to both identities, even when native call IDs repeat across Runs.
-	kind := proto.TypeFunctionResult + "\x00" + result.CallID
-	if handled, err := r.replayAppliedInteractionDecision(ctx, env, result.DeliveryID, kind, fingerprint); handled {
-		return err
+	key := env.ID + "\x00" + result.CallID
+	r.mu.Lock()
+	applied, replay := r.applied[key]
+	r.mu.Unlock()
+	if replay {
+		// The receipt answers only the assignment that applied the result.
+		if applied.assignment != env.Assignment {
+			return r.sendInteractionDecisionAck(ctx, env, result.DeliveryID, false, proto.AssignmentConflict, "The result was applied under another assignment.")
+		}
+		if applied.fingerprint != fingerprint {
+			return r.sendInteractionDecisionAck(ctx, env, result.DeliveryID, false, "decision_conflict", "request was already applied with a different decision")
+		}
+		return r.sendInteractionDecisionAck(ctx, env, result.DeliveryID, true, "", "")
 	}
 	r.mu.Lock()
 	state := r.sessions[env.ID]
@@ -75,6 +87,43 @@ func (r *Router) handleFunctionResult(ctx context.Context, env proto.Envelope) e
 		}
 		return r.sendInteractionDecisionAck(ctx, env, result.DeliveryID, false, code, "function result was not applied")
 	}
-	r.rememberAppliedInteractionDecision(env, kind, fingerprint)
+	r.rememberAppliedFunctionResult(key, env.Assignment, fingerprint)
 	return r.sendInteractionDecisionAck(ctx, env, result.DeliveryID, true, "", "")
 }
+
+func (r *Router) rememberAppliedFunctionResult(key string, assignment proto.AssignmentRef, fingerprint [32]byte) {
+	now := time.Now().UTC()
+	r.mu.Lock()
+	if len(r.applied) >= 1024 {
+		cutoff := now.Add(-time.Hour)
+		for id, entry := range r.applied {
+			if entry.recordedAt.Before(cutoff) {
+				delete(r.applied, id)
+			}
+		}
+	}
+	if len(r.applied) >= 1024 {
+		for id := range r.applied {
+			delete(r.applied, id)
+			break
+		}
+	}
+	r.applied[key] = appliedFunctionResult{fingerprint: fingerprint, assignment: assignment, recordedAt: now}
+	r.mu.Unlock()
+}
+
+func (r *Router) sendInteractionDecisionAck(ctx context.Context, request proto.Envelope, deliveryID string, applied bool, errorCode, message string) error {
+	env, err := request.Reply(proto.TypeInteractionDecisionAck, proto.InteractionDecisionAckPayload{
+		DeliveryID: deliveryID,
+		Applied:    applied,
+		ErrorCode:  errorCode,
+		Error:      message,
+	})
+	if err != nil {
+		return fmt.Errorf("dispatch: build interaction decision ack: %w", err)
+	}
+	if err := r.sender.Send(ctx, env); err != nil {
+		return fmt.Errorf("dispatch: send interaction decision ack: %w", err)
+	}
+	return nil
+}
diff --git a/apps/daemon/internal/dispatch/interaction_decisions.go b/apps/daemon/internal/dispatch/interaction_decisions.go
deleted file mode 100644
index 8bfb3337d..000000000
--- a/apps/daemon/internal/dispatch/interaction_decisions.go
+++ /dev/null
@@ -1,340 +0,0 @@
-package dispatch
-
-import (
-	"context"
-	"crypto/sha256"
-	"encoding/json"
-	"errors"
-	"fmt"
-	"strings"
-	"time"
-
-	"github.com/MiniMax-AI/OpenAgentCore/apps/daemon/internal/agent"
-	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
-)
-
-func (r *Router) handlePermissionDecision(ctx context.Context, env proto.Envelope) error {
-	if env.ID == "" {
-		return errors.New("dispatch: permission_decision missing perm id (Envelope.ID empty)")
-	}
-	var payload proto.PermissionDecisionPayload
-	if err := env.DecodeRequest(&payload); err != nil {
-		return fmt.Errorf("dispatch: decode permission_decision: %w", err)
-	}
-	if payload.DeliveryID == "" {
-		return errors.New("dispatch: permission_decision missing delivery_id")
-	}
-	fingerprint, err := interactionDecisionFingerprint(payload)
-	if err != nil {
-		return fmt.Errorf("dispatch: fingerprint permission_decision: %w", err)
-	}
-	if handled, err := r.replayAppliedInteractionDecision(ctx, env, payload.DeliveryID, proto.TypePermissionDecision, fingerprint); handled {
-		return err
-	}
-
-	r.mu.Lock()
-	runID, known := r.permIndex[env.ID]
-	var state *sessionState
-	var session agent.Session
-	var finishOperation func()
-	if known {
-		state = r.sessions[runID]
-	}
-	if state != nil {
-		if code := r.admitRunLocked(env.Assignment, state); code != "" {
-			r.mu.Unlock()
-			return r.sendInteractionDecisionAck(ctx, env, payload.DeliveryID, false, code, "The run's assignment does not admit this decision.")
-		}
-		session, finishOperation, _ = r.preparedOperationLocked(state)
-	}
-	r.mu.Unlock()
-
-	if !known || state == nil {
-		// Server's perm timeout / cancel race; common enough that info
-		// is right.
-		r.log.InfoContext(ctx, "permission_decision for unknown perm (run gone)", "perm_id", env.ID)
-		return r.sendInteractionDecisionAck(ctx, env, payload.DeliveryID, false, "not_pending", "permission request is no longer pending")
-	}
-	if session == nil {
-		return r.sendInteractionDecisionAck(ctx, env, payload.DeliveryID, false, "not_ready", "permission request is waiting for the native session")
-	}
-	defer finishOperation()
-	ctx, stop := r.shutdownContext(ctx)
-	defer stop()
-
-	if !state.capabilities.Permissions.IsSupported() {
-		return r.sendInteractionDecisionAck(ctx, env, payload.DeliveryID, false, "unsupported", "The runtime declaration does not support interaction decisions.")
-	}
-	responder, supported := session.(agent.PermissionResponder)
-	if !supported {
-		r.dropPermission(state, env.ID)
-		return r.sendInteractionDecisionAck(ctx, env, payload.DeliveryID, false, "contract_violation", "Declared runtime capability does not implement permission responses")
-	}
-	if err := responder.SubmitPermission(ctx, env.ID, payload); err != nil {
-		if errors.Is(err, agent.ErrUnsupportedOperation) {
-			return r.sendInteractionDecisionAck(ctx, env, payload.DeliveryID, false, "contract_violation", "Declared permission capability has no implementation.")
-		}
-		if errors.Is(err, agent.ErrUnknownPermission) {
-			r.log.InfoContext(ctx, "agent reports unknown perm (race with cancel)", "perm_id", env.ID, "run_id", runID)
-			r.dropPermission(state, env.ID)
-			return r.sendInteractionDecisionAck(ctx, env, payload.DeliveryID, false, "not_pending", err.Error())
-		}
-		r.log.WarnContext(ctx, "agent rejected permission decision", "perm_id", env.ID, "run_id", runID, "err", err)
-		return r.sendInteractionDecisionAck(ctx, env, payload.DeliveryID, false, "runtime_error", err.Error())
-	}
-	r.dropPermission(state, env.ID)
-	r.rememberAppliedInteractionDecision(env, proto.TypePermissionDecision, fingerprint)
-	return r.sendInteractionDecisionAck(ctx, env, payload.DeliveryID, true, "", "")
-}
-
-func (r *Router) dropPermission(s *sessionState, permissionID string) {
-	r.mu.Lock()
-	delete(r.permIndex, permissionID)
-	delete(s.pendingIDs, permissionID)
-	r.mu.Unlock()
-}
-
-// handlePromptForUserChoiceDecision is the ask-side twin of
-// handlePermissionDecision. The server forwards the human's answer
-// here; we look up the owning session via askIndex and ask the agent
-// to write a matching tool_result back into its CLI.
-//
-// On both success and ErrUnknownAsk we drop the ask from askIndex /
-// pendingAsks so a stale retry can't waste cycles. Timer-fired cancels
-// inside the session don't currently call back into the router, so
-// those entries linger until cleanupSession — acceptable because they
-// can't double-fire (the session's own pendingAskTable.Take already
-// guards that); cleanupSession removes the routing entry when the run
-// stream closes.
-func (r *Router) handlePromptForUserChoiceDecision(ctx context.Context, env proto.Envelope) error {
-	if env.ID == "" {
-		return errors.New("dispatch: prompt_for_user_choice_decision missing ask id (Envelope.ID empty)")
-	}
-	var payload proto.PromptForUserChoiceDecisionPayload
-	if err := env.DecodeRequest(&payload); err != nil {
-		return fmt.Errorf("dispatch: decode prompt_for_user_choice_decision: %w", err)
-	}
-	if payload.DeliveryID == "" {
-		return errors.New("dispatch: prompt_for_user_choice_decision missing delivery_id")
-	}
-	fingerprint, err := interactionDecisionFingerprint(payload)
-	if err != nil {
-		return fmt.Errorf("dispatch: fingerprint prompt_for_user_choice_decision: %w", err)
-	}
-	if handled, err := r.replayAppliedInteractionDecision(ctx, env, payload.DeliveryID, proto.TypePromptForUserChoiceDecision, fingerprint); handled {
-		return err
-	}
-
-	r.mu.Lock()
-	runID, known := r.askIndex[env.ID]
-	var state *sessionState
-	var session agent.Session
-	var finishOperation func()
-	if known {
-		state = r.sessions[runID]
-	}
-	if state != nil {
-		if code := r.admitRunLocked(env.Assignment, state); code != "" {
-			r.mu.Unlock()
-			return r.sendInteractionDecisionAck(ctx, env, payload.DeliveryID, false, code, "The run's assignment does not admit this decision.")
-		}
-		session, finishOperation, _ = r.preparedOperationLocked(state)
-	}
-	r.mu.Unlock()
-
-	if !known || state == nil {
-		r.log.InfoContext(ctx, "prompt_for_user_choice_decision for unknown ask (run gone)", "ask_id", env.ID)
-		return r.sendInteractionDecisionAck(ctx, env, payload.DeliveryID, false, "not_pending", "user-input request is no longer pending")
-	}
-	if session == nil {
-		return r.sendInteractionDecisionAck(ctx, env, payload.DeliveryID, false, "not_ready", "user-input request is waiting for the native session")
-	}
-	defer finishOperation()
-	ctx, stop := r.shutdownContext(ctx)
-	defer stop()
-
-	if !state.capabilities.Permissions.IsSupported() {
-		return r.sendInteractionDecisionAck(ctx, env, payload.DeliveryID, false, "unsupported", "The runtime declaration does not support interaction decisions.")
-	}
-	responder, supported := session.(agent.UserChoiceResponder)
-	if !supported {
-		r.dropAsk(state, env.ID)
-		return r.sendInteractionDecisionAck(ctx, env, payload.DeliveryID, false, "contract_violation", "Declared runtime capability does not implement user-choice responses")
-	}
-	err = responder.SubmitPromptForUserChoice(ctx, env.ID, payload)
-	if err != nil {
-		if errors.Is(err, agent.ErrUnsupportedOperation) {
-			return r.sendInteractionDecisionAck(ctx, env, payload.DeliveryID, false, "contract_violation", "Declared user-choice capability has no implementation.")
-		}
-		if errors.Is(err, agent.ErrUnknownAsk) {
-			r.log.InfoContext(ctx, "agent reports unknown ask (race with cancel)", "ask_id", env.ID, "run_id", runID)
-			r.dropAsk(state, env.ID)
-			return r.sendInteractionDecisionAck(ctx, env, payload.DeliveryID, false, "not_pending", err.Error())
-		}
-		// Keep the routing entry for transient runtime failures. Codex, for
-		// example, restores its pending request when a JSON-RPC reply write
-		// fails, so dropping the ask here would turn a retryable error into a
-		// permanent not_pending response on the next attempt.
-		r.log.WarnContext(ctx, "agent rejected user-input decision", "ask_id", env.ID, "run_id", runID, "err", err)
-		return r.sendInteractionDecisionAck(ctx, env, payload.DeliveryID, false, "runtime_error", err.Error())
-	}
-	r.dropAsk(state, env.ID)
-	r.rememberAppliedInteractionDecision(env, proto.TypePromptForUserChoiceDecision, fingerprint)
-	return r.sendInteractionDecisionAck(ctx, env, payload.DeliveryID, true, "", "")
-}
-
-func (r *Router) replayAppliedInteractionDecision(ctx context.Context, env proto.Envelope, deliveryID, kind string, fingerprint [32]byte) (bool, error) {
-	key := appliedInteractionDecisionKey(env.ID, kind)
-	r.mu.Lock()
-	applied, ok := r.applied[key]
-	r.mu.Unlock()
-	if !ok {
-		return false, nil
-	}
-	// The receipt answers only the assignment that applied the decision.
-	if applied.assignment != env.Assignment {
-		return true, r.sendInteractionDecisionAck(ctx, env, deliveryID, false, proto.AssignmentConflict, "The decision was applied under another assignment.")
-	}
-	if applied.requestID != env.ID || applied.kind != kind || applied.fingerprint != fingerprint {
-		return true, r.sendInteractionDecisionAck(ctx, env, deliveryID, false, "decision_conflict", "request was already applied with a different decision")
-	}
-	return true, r.sendInteractionDecisionAck(ctx, env, deliveryID, true, "", "")
-}
-
-func (r *Router) rememberAppliedInteractionDecision(env proto.Envelope, kind string, fingerprint [32]byte) {
-	now := time.Now().UTC()
-	key := appliedInteractionDecisionKey(env.ID, kind)
-	r.mu.Lock()
-	if len(r.applied) >= 1024 {
-		cutoff := now.Add(-time.Hour)
-		for id, entry := range r.applied {
-			if entry.recordedAt.Before(cutoff) {
-				delete(r.applied, id)
-			}
-		}
-	}
-	if len(r.applied) >= 1024 {
-		for id := range r.applied {
-			delete(r.applied, id)
-			break
-		}
-	}
-	r.applied[key] = appliedInteractionDecision{
-		requestID: env.ID, kind: kind, fingerprint: fingerprint, assignment: env.Assignment, recordedAt: now,
-	}
-	r.mu.Unlock()
-}
-
-func appliedInteractionDecisionKey(requestID, kind string) string {
-	return kind + "\x00" + requestID
-}
-
-// interactionDecisionFingerprint excludes the transport delivery id. Each
-// retry gets a fresh delivery id so a late ack cannot satisfy a newer waiter,
-// while the request plus decision content remains stable for daemon replay.
-func interactionDecisionFingerprint(payload any) ([32]byte, error) {
-	switch decision := payload.(type) {
-	case proto.PermissionDecisionPayload:
-		decision.DeliveryID = ""
-		encoded, err := json.Marshal(decision)
-		if err != nil {
-			return [32]byte{}, err
-		}
-		return sha256.Sum256(encoded), nil
-	case proto.PromptForUserChoiceDecisionPayload:
-		decision.DeliveryID = ""
-		encoded, err := json.Marshal(decision)
-		if err != nil {
-			return [32]byte{}, err
-		}
-		return sha256.Sum256(encoded), nil
-	default:
-		return [32]byte{}, fmt.Errorf("unsupported interaction decision %T", payload)
-	}
-}
-
-func (r *Router) sendInteractionDecisionAck(ctx context.Context, request proto.Envelope, deliveryID string, applied bool, errorCode, message string) error {
-	env, err := request.Reply(proto.TypeInteractionDecisionAck, proto.InteractionDecisionAckPayload{
-		DeliveryID: deliveryID,
-		Applied:    applied,
-		ErrorCode:  errorCode,
-		Error:      message,
-	})
-	if err != nil {
-		return fmt.Errorf("dispatch: build interaction decision ack: %w", err)
-	}
-	if err := r.sender.Send(ctx, env); err != nil {
-		return fmt.Errorf("dispatch: send interaction decision ack: %w", err)
-	}
-	return nil
-}
-
-// dropAsk clears askID from both the router-level askIndex and the
-// session's pendingAsks set. Safe to call with an askID that's already
-// gone — both deletes are no-ops then.
-func (r *Router) dropAsk(s *sessionState, askID string) {
-	r.mu.Lock()
-	delete(r.askIndex, askID)
-	delete(s.pendingAsks, askID)
-	r.mu.Unlock()
-}
-
-// indexPermissionFrame records interaction identities before forwarding them.
-// Prepared output may arrive before successful Session publication; decisions
-// remain retryable until state.session becomes available.
-func (r *Router) indexPermissionFrame(s *sessionState, env proto.Envelope) {
-	switch env.Type {
-	case proto.TypePermissionRequest:
-		var p proto.PermissionRequestPayload
-		if err := env.DecodePayload(&p); err != nil {
-			return
-		}
-		requestID := strings.TrimSpace(p.RequestID)
-		if requestID == "" {
-			return
-		}
-		r.mu.Lock()
-		if r.interactionRouteOpenLocked(s) {
-			r.permIndex[requestID] = s.runID
-			s.pendingIDs[requestID] = struct{}{}
-		}
-		r.mu.Unlock()
-	case proto.TypePermissionCancel:
-		if env.ID == "" {
-			return
-		}
-		r.mu.Lock()
-		delete(r.permIndex, env.ID)
-		delete(s.pendingIDs, env.ID)
-		r.mu.Unlock()
-	case proto.TypePromptForUserChoice:
-		// env.ID is the run id (so the server-side dispatch can fan
-		// this frame to the run's subscriber); the ask id rides on
-		// the payload. Decode just enough to seed the index.
-		var p proto.PromptForUserChoicePayload
-		if err := env.DecodePayload(&p); err != nil || p.AskID == "" {
-			return
-		}
-		r.mu.Lock()
-		if r.interactionRouteOpenLocked(s) {
-			r.askIndex[p.AskID] = s.runID
-			s.pendingAsks[p.AskID] = struct{}{}
-		}
-		r.mu.Unlock()
-	}
-}
-
-func (r *Router) clearInteractionRoutesLocked(s *sessionState) {
-	for permissionID := range s.pendingIDs {
-		delete(r.permIndex, permissionID)
-		delete(s.pendingIDs, permissionID)
-	}
-	for askID := range s.pendingAsks {
-		delete(r.askIndex, askID)
-		delete(s.pendingAsks, askID)
-	}
-}
-
-// drain consumes everything left on ch until the agent closes it.
-// Events are dropped — by the time we're draining, either transport
-// is dead or the router is shutting down.
diff --git a/apps/daemon/internal/dispatch/local_directory.go b/apps/daemon/internal/dispatch/local_directory.go
deleted file mode 100644
index 57e72d8e9..000000000
--- a/apps/daemon/internal/dispatch/local_directory.go
+++ /dev/null
@@ -1,7 +0,0 @@
-package dispatch
-
-// localDirectoryPreparation is a ready read-only preparation. The bound local
-// workspace serves its reads, so it holds no native resource.
-type localDirectoryPreparation struct{}
-
-func (localDirectoryPreparation) Close() error { return nil }
diff --git a/apps/daemon/internal/dispatch/local_directory_test.go b/apps/daemon/internal/dispatch/local_directory_test.go
index e354b668b..d042e7854 100644
--- a/apps/daemon/internal/dispatch/local_directory_test.go
+++ b/apps/daemon/internal/dispatch/local_directory_test.go
@@ -22,16 +22,13 @@ func TestLocalDirectoryPreparationNeedsNoHarnessAndRejectsOtherOwners(t *testing
 	workspace := t.TempDir()
 
 	environment, session := uuid.NewString(), preparationSessionID
-	binding, err := localworkspace.New(environment, session, workspace)
+	binding, err := localworkspace.NewWithCapabilityDirectory(environment, session, workspace, t.TempDir())
 	if err != nil {
 		t.Fatal(err)
 	}
 	var harnessCalls atomic.Int32
 	reg := agent.NewRegistry()
-	reg.RegisterKind(proto.SupportedAgentKind{Kind: "native", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{LocalEnvironment: proto.CapabilitySupported, WorkspaceReadPreparation: proto.CapabilitySupported})}, harnessconfig.Configuration{}, func(context.Context, proto.PromptRequestPayload, chan<- proto.Envelope) (agent.Session, error) {
-		harnessCalls.Add(1)
-		return nil, errors.New("must not start a model")
-	})
+	reg.RegisterKind(proto.SupportedAgentKind{Kind: "native", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{LocalEnvironment: proto.CapabilitySupported, WorkspaceReadPreparation: proto.CapabilitySupported})}, harnessconfig.Configuration{})
 	reg.RegisterExecutor("native", func(context.Context, proto.PromptRequestPayload) (agent.Executor, error) {
 		harnessCalls.Add(1)
 		return nil, errors.New("must not prepare a harness")
@@ -98,14 +95,12 @@ func TestLocalDirectoryKeepsNotDirectorySeparateFromFailures(t *testing.T) {
 		t.Fatal(err)
 	}
 	environment, session := uuid.NewString(), preparationSessionID
-	binding, err := localworkspace.New(environment, session, workspace)
+	binding, err := localworkspace.NewWithCapabilityDirectory(environment, session, workspace, t.TempDir())
 	if err != nil {
 		t.Fatal(err)
 	}
 	reg := agent.NewRegistry()
-	reg.RegisterKind(proto.SupportedAgentKind{Kind: "native", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{LocalEnvironment: proto.CapabilitySupported, WorkspaceReadPreparation: proto.CapabilitySupported})}, harnessconfig.Configuration{}, func(context.Context, proto.PromptRequestPayload, chan<- proto.Envelope) (agent.Session, error) {
-		return nil, errors.New("must not start a model")
-	})
+	reg.RegisterKind(proto.SupportedAgentKind{Kind: "native", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{LocalEnvironment: proto.CapabilitySupported, WorkspaceReadPreparation: proto.CapabilitySupported})}, harnessconfig.Configuration{})
 	reg.RegisterExecutor("native", func(context.Context, proto.PromptRequestPayload) (agent.Executor, error) {
 		return nil, errors.New("must not prepare a harness")
 	})
diff --git a/apps/daemon/internal/dispatch/mcp_http_test.go b/apps/daemon/internal/dispatch/mcp_http_test.go
index f0e8b9112..0d8b8cadd 100644
--- a/apps/daemon/internal/dispatch/mcp_http_test.go
+++ b/apps/daemon/internal/dispatch/mcp_http_test.go
@@ -111,10 +111,7 @@ func TestLocalMCPOriginAndCapabilityAdmission(t *testing.T) {
 				req.Configuration.MCPHTTPServers = nil
 			}
 			entered := make(chan struct{}, 1)
-			h.reg.RegisterKind(proto.SupportedAgentKind{Kind: "prepared", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{LocalEnvironment: proto.CapabilitySupported, MCPHTTPTools: proto.CapabilityFromBool(mode != "environment missing capability"), MCPHTTPBearerAuth: proto.CapabilitySupported, MCPHTTPRequired: proto.CapabilitySupported})}, prototest.ModelConfiguration(), func(context.Context, proto.PromptRequestPayload, chan<- proto.Envelope) (agent.Session, error) {
-				t.Error("ordinary factory called")
-				return nil, errors.New("unexpected")
-			})
+			h.reg.RegisterKind(proto.SupportedAgentKind{Kind: "prepared", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{LocalEnvironment: proto.CapabilitySupported, MCPHTTPTools: proto.CapabilityFromBool(mode != "environment missing capability"), MCPHTTPBearerAuth: proto.CapabilitySupported, MCPHTTPRequired: proto.CapabilitySupported})}, prototest.ModelConfiguration())
 			h.reg.RegisterExecutor("prepared", func(context.Context, proto.PromptRequestPayload) (agent.Executor, error) {
 				entered <- struct{}{}
 				return nil, errors.New("controlled stop")
diff --git a/apps/daemon/internal/dispatch/optional_interactions_test.go b/apps/daemon/internal/dispatch/optional_interactions_test.go
deleted file mode 100644
index b799480bc..000000000
--- a/apps/daemon/internal/dispatch/optional_interactions_test.go
+++ /dev/null
@@ -1,43 +0,0 @@
-package dispatch_test
-
-import (
-	"context"
-	"testing"
-
-	"github.com/MiniMax-AI/OpenAgentCore/apps/daemon/internal/agent"
-	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
-	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto/prototest"
-)
-
-// Wrapping Session proves that no responder stubs are required for a Session.
-type lifecycleOnly struct{ agent.Session }
-
-func TestOptionalInteractionResponders(t *testing.T) {
-	for _, ask := range []bool{false, true} {
-		t.Run(map[bool]string{false: "permission", true: "user choice"}[ask], func(t *testing.T) {
-			h := newHarness(t)
-			defer h.router.Shutdown(context.Background())
-			var output chan<- proto.Envelope
-			registerSession(h.reg, proto.SupportedAgentKind{Kind: "minimal", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, func(_ context.Context, _ proto.PromptRequestPayload, out chan<- proto.Envelope) (agent.Session, error) {
-				output = out
-				s := &fakeSession{out: out, closeOutOnCancel: true}
-				return lifecycleOnly{Session: s}, nil
-			})
-			startRun(t, h.router, h.sender, "minimal", "run")
-			event := mustEnv(t, proto.TypePermissionRequest, "run", proto.PermissionRequestPayload{RequestID: "interaction", Tool: "fixture"})
-			decision := scoped(t, "run", proto.TypePermissionDecision, "interaction", proto.PermissionDecisionPayload{DeliveryID: "decision", Approved: true})
-			if ask {
-				event = mustEnv(t, proto.TypePromptForUserChoice, "run", proto.PromptForUserChoicePayload{AskID: "interaction"})
-				decision = scoped(t, "run", proto.TypePromptForUserChoiceDecision, "interaction", proto.PromptForUserChoiceDecisionPayload{DeliveryID: "decision"})
-			}
-			// An inconsistent adapter emitted an interaction it cannot answer: reject it,
-			// never acknowledge application or call a fabricated responder.
-			output <- event
-			waitFor(t, func() bool { return hasFrame(h.sender, event.Type, "run") }, "interaction indexed")
-			if err := h.router.Handle(t.Context(), decision); err != nil {
-				t.Fatal(err)
-			}
-			assertDecisionAck(t, h.sender, "decision", false, "unsupported")
-		})
-	}
-}
diff --git a/apps/daemon/internal/dispatch/preparation.go b/apps/daemon/internal/dispatch/preparation.go
index 3dea80ef8..81e51fabc 100644
--- a/apps/daemon/internal/dispatch/preparation.go
+++ b/apps/daemon/internal/dispatch/preparation.go
@@ -5,7 +5,6 @@ import (
 	"crypto/sha256"
 	"encoding/json"
 	"errors"
-	"io"
 	"strings"
 	"time"
 
@@ -23,21 +22,19 @@ type preparationState struct {
 	executor     *executorState
 	// request is the execution_prepare's ID, trace and assignment, which
 	// every status echoes.
-	request           proto.Envelope
-	fingerprint       [32]byte
-	startFingerprint  [32]byte
-	status            proto.PreparationStatusPayload
-	deadline          time.Time
-	timer             *time.Timer
-	ctx               context.Context
-	cancel            context.CancelFunc
-	prepared          io.Closer
-	environmentID     string
-	busy              bool
-	owns              bool
-	closeErr          error
-	workspaceReadOnly bool
-	handoff           *preparedHandoff
+	request          proto.Envelope
+	fingerprint      [32]byte
+	startFingerprint [32]byte
+	status           proto.PreparationStatusPayload
+	deadline         time.Time
+	timer            *time.Timer
+	ctx              context.Context
+	cancel           context.CancelFunc
+	environmentID    string
+	busy             bool
+	owns             bool
+	closeErr         error
+	handoff          *preparedHandoff
 }
 
 func (r *Router) handleExecutionPrepare(ctx context.Context, env proto.Envelope) error {
@@ -109,10 +106,10 @@ func (r *Router) handleExecutionPrepare(ctx context.Context, env proto.Envelope)
 		return r.rejectPreparation(env, "preparation_capacity")
 	}
 	owner, cancel := context.WithCancel(context.WithoutCancel(ctx))
-	p := &preparationState{capabilities: caps, request: proto.Envelope{ID: env.ID, Trace: env.Trace, Assignment: env.Assignment}, fingerprint: fingerprint, ctx: owner, cancel: cancel, environmentID: req.EnvironmentID(), workspaceReadOnly: req.WorkspaceReadOnly, busy: true, owns: true, deadline: time.Now().Add(r.preparationTimeout)}
+	p := &preparationState{capabilities: caps, request: proto.Envelope{ID: env.ID, Trace: env.Trace, Assignment: env.Assignment}, fingerprint: fingerprint, ctx: owner, cancel: cancel, environmentID: req.EnvironmentID(), busy: true, owns: true, deadline: time.Now().Add(r.preparationTimeout)}
 	p.status = proto.PreparationStatusPayload{Handle: uuid.NewString(), Revision: 1, State: "preparing", ExpiresAt: p.deadline.UnixMilli()}
 	r.preparations[p.status.Handle], r.preparationRequests[p.request.ID] = p, p
-	p.timer = time.AfterFunc(r.preparationTimeout, func() { r.releasePreparation(p, "expired", "", true, true) })
+	p.timer = time.AfterFunc(r.preparationTimeout, func() { r.releasePreparation(p, "expired", "", true) })
 	r.shutdownWG.Add(1)
 	r.mu.Unlock()
 	go r.prepareExecution(p)
@@ -123,30 +120,30 @@ func (r *Router) handleExecutionPrepare(ctx context.Context, env proto.Envelope)
 func (r *Router) prepareExecution(p *preparationState) {
 	defer r.shutdownWG.Done()
 	if !r.sendPreparation(p.request, proto.PreparationStatusPayload{Handle: p.status.Handle, Revision: 1, State: "preparing", ExpiresAt: p.deadline.UnixMilli()}) {
-		r.releasePreparation(p, "failed", "status_delivery_failed", false, false)
+		r.releasePreparation(p, "failed", "status_delivery_failed", false)
 	}
 	r.mu.Lock()
 	p.busy = false
 	ready := p.status.State == "preparing" && p.ctx.Err() == nil && !r.closed
 	if ready {
-		p.prepared = localDirectoryPreparation{}
 		p.status.State, p.status.Revision = "ready", p.status.Revision+1
-	} else if p.status.State == "preparing" {
-		p.status.State, p.status.ErrorCode, p.status.Revision = "failed", "preparation_failed", p.status.Revision+1
-	}
-	status := p.status
-	if !ready {
-		p.busy = true
+	} else {
+		if p.status.State == "preparing" {
+			p.status.State, p.status.ErrorCode, p.status.Revision = "failed", "preparation_failed", p.status.Revision+1
+		}
+		// A release or shutdown during readiness left ownership to this return.
+		p.owns = false
 		p.cancel()
 		p.timer.Stop()
 	}
+	status := p.status
 	r.mu.Unlock()
 	if !ready {
-		r.closePreparationResource(p)
+		r.publishPreparation(p, status)
 		return
 	}
 	if !r.sendPreparation(p.request, status) {
-		r.releasePreparation(p, "failed", "status_delivery_failed", false, false)
+		r.releasePreparation(p, "failed", "status_delivery_failed", false)
 	}
 }
 
@@ -162,11 +159,11 @@ func (r *Router) handleExecutionRelease(_ context.Context, env proto.Envelope) e
 	if !valid {
 		return r.rejectPreparation(env, "unknown_preparation")
 	}
-	r.releasePreparation(p, "released", "", true, true)
+	r.releasePreparation(p, "released", "", true)
 	return nil
 }
 
-func (r *Router) releasePreparation(p *preparationState, state, code string, publish, retryHandoff bool) {
+func (r *Router) releasePreparation(p *preparationState, state, code string, publish bool) {
 	r.mu.Lock()
 	if r.closed || r.suspension != nil {
 		r.mu.Unlock()
@@ -177,48 +174,21 @@ func (r *Router) releasePreparation(p *preparationState, state, code string, pub
 		r.abandonExecutorAdmission(p, state, code, publish)
 		return
 	}
-	if p.handoff != nil {
-		if active := r.sessions[p.status.RunID]; active != nil && active.preparedHandoff == p.handoff {
-			if state == "expired" && p.handoff.published {
-				r.mu.Unlock()
-				return
-			}
-			switch p.status.State {
-			case "preparing", "ready", "starting", "started":
-				p.status.State, p.status.ErrorCode, p.status.Revision = state, code, p.status.Revision+1
-				p.timer.Stop()
-			}
-			r.claimPreparedReleaseLocked(active, true, "", retryHandoff)
-			status := p.status
-			r.mu.Unlock()
-			if publish {
-				r.publishPreparation(p, status)
-			}
-			return
-		}
-	}
-	closeResource := false
 	switch p.status.State {
-	case "preparing", "ready", "starting":
+	case "preparing", "ready":
 		p.status.State, p.status.ErrorCode, p.status.Revision = state, code, p.status.Revision+1
 		p.cancel()
 		p.timer.Stop()
 	}
-	if p.owns && !p.busy {
-		if p.workspaceReadOnly && state == "released" && p.status.ErrorCode == "cleanup_unconfirmed" {
-			p.status.State, p.status.ErrorCode, p.status.Revision = state, "", p.status.Revision+1
-		}
-		p.busy = true
-		closeResource = true
-		r.shutdownWG.Add(1)
+	// A busy preparation drops ownership and reports when readiness returns.
+	// Dropping ownership here always reports it.
+	report := !p.busy && (publish || p.owns)
+	if !p.busy {
+		p.owns = false
 	}
 	status := p.status
-	settled := !p.owns && !p.busy
 	r.mu.Unlock()
-	if closeResource {
-		go func() { defer r.shutdownWG.Done(); r.closePreparationResource(p) }()
-	}
-	if publish && (!p.workspaceReadOnly || settled) {
+	if report {
 		r.publishPreparation(p, status)
 	}
 }
@@ -244,11 +214,9 @@ func (r *Router) prunePreparationsLocked() {
 
 func (r *Router) publishPreparation(p *preparationState, status proto.PreparationStatusPayload) {
 	r.mu.Lock()
-	if p.workspaceReadOnly {
-		if status.Revision != p.status.Revision || (p.owns && (p.busy || status.State == "released" || status.State == "expired") && status.State != "preparing" && status.State != "ready") {
-			r.mu.Unlock()
-			return
-		}
+	if p.executor == nil && status.Revision != p.status.Revision {
+		r.mu.Unlock()
+		return
 	}
 	if r.closed || r.suspension != nil {
 		r.mu.Unlock()
@@ -259,8 +227,8 @@ func (r *Router) publishPreparation(p *preparationState, status proto.Preparatio
 	go func() {
 		defer r.shutdownWG.Done()
 		// A failed terminal notification must not restart incomplete cleanup.
-		if !r.sendPreparation(p.request, status) && (!p.workspaceReadOnly || status.State == "preparing" || status.State == "ready") {
-			r.releasePreparation(p, "failed", "status_delivery_failed", false, false)
+		if !r.sendPreparation(p.request, status) && (p.executor != nil || status.State == "preparing" || status.State == "ready") {
+			r.releasePreparation(p, "failed", "status_delivery_failed", false)
 		}
 	}()
 }
diff --git a/apps/daemon/internal/dispatch/preparation_cancel_test.go b/apps/daemon/internal/dispatch/preparation_cancel_test.go
index 5ee5e3cf3..5804650cb 100644
--- a/apps/daemon/internal/dispatch/preparation_cancel_test.go
+++ b/apps/daemon/internal/dispatch/preparation_cancel_test.go
@@ -86,8 +86,6 @@ func TestPreparedCancellationWaitsForOutputAndCleanup(t *testing.T) {
 		session = &fakeSession{out: out, closeOutOnCancel: true,
 			postCancelEnvelopes: []proto.Envelope{mustEnv(t, proto.TypeDone, id, p.outcome)}}
 		out <- mustEnv(t, proto.TypeDelta, id, proto.DeltaPayload{Delta: "observed"})
-		out <- mustEnv(t, proto.TypePermissionRequest, id, proto.PermissionRequestPayload{RequestID: "permission"})
-		out <- mustEnv(t, proto.TypePromptForUserChoice, id, proto.PromptForUserChoicePayload{AskID: "ask"})
 		out <- mustEnv(t, proto.TypeUsage, id, proto.UsagePayload{Usage: p.outcome.Usage})
 		close(startEntered)
 		<-startReturn
@@ -124,16 +122,6 @@ func TestPreparedCancellationWaitsForOutputAndCleanup(t *testing.T) {
 	if len(cancellationAcks(sender.recSender)) != 0 || r.ActiveRuns() != 1 {
 		t.Fatal("cleanup released ownership early")
 	}
-	for _, decision := range []proto.Envelope{
-		mustEnv(t, proto.TypePermissionDecision, "permission", proto.PermissionDecisionPayload{DeliveryID: "permission-reply", Approved: true}),
-		mustEnv(t, proto.TypePromptForUserChoiceDecision, "ask", proto.PromptForUserChoiceDecisionPayload{DeliveryID: "ask-reply", QuestionAnswers: []proto.PromptForUserChoiceQuestionAnswer{{QuestionID: "q0", Answers: []string{"yes"}}}}),
-	} {
-		if err := r.Handle(t.Context(), decision); err != nil {
-			t.Fatal(err)
-		}
-	}
-	assertDecisionAck(t, sender.recSender, "permission-reply", false, "not_pending")
-	assertDecisionAck(t, sender.recSender, "ask-reply", false, "not_pending")
 	close(cleanupReturn)
 	waitFor(t, func() bool { return len(cancellationAcks(sender.recSender)) == 2 && r.ActiveRuns() == 0 }, "prepared cancellation receipts")
 	if p.calls.Load() != 1 || session.cancels() != 1 {
@@ -145,7 +133,7 @@ func TestPreparedCancellationWaitsForOutputAndCleanup(t *testing.T) {
 		}
 	}
 	got := sender.typesFor("run")
-	want := []string{proto.TypeDelta, proto.TypePermissionRequest, proto.TypePromptForUserChoice, proto.TypeUsage, proto.TypeDone, proto.TypeInteractionDecisionAck, proto.TypeInteractionDecisionAck}
+	want := []string{proto.TypeDelta, proto.TypeUsage, proto.TypeDone, proto.TypeInteractionDecisionAck, proto.TypeInteractionDecisionAck}
 	if !reflect.DeepEqual(got, want) {
 		t.Fatalf("output/receipt order = %v", got)
 	}
diff --git a/apps/daemon/internal/dispatch/preparation_cleanup.go b/apps/daemon/internal/dispatch/preparation_cleanup.go
index 2a51c0e8c..97b77dbc6 100644
--- a/apps/daemon/internal/dispatch/preparation_cleanup.go
+++ b/apps/daemon/internal/dispatch/preparation_cleanup.go
@@ -1,35 +1,6 @@
 package dispatch
 
-func (r *Router) closePreparationResource(p *preparationState) error {
-	// Only the operation that owns busy calls this; other paths cancel its owner.
-	var err error
-	if p.prepared != nil {
-		err = p.prepared.Close()
-	}
-	r.mu.Lock()
-	p.busy, p.closeErr = false, err
-	if err == nil {
-		p.prepared, p.owns = nil, false
-	}
-	if p.workspaceReadOnly {
-		p.status.Revision++
-		if err != nil {
-			p.status.State, p.status.ErrorCode = "failed", "cleanup_unconfirmed"
-		}
-	}
-	status := p.status
-	r.mu.Unlock()
-	if p.workspaceReadOnly {
-		r.publishPreparation(p, status)
-	}
-	if err != nil {
-		r.log.Warn("preparation cleanup incomplete", "handle", p.status.Handle)
-	}
-	return err
-}
-
-func (r *Router) closePendingPreparationsLocked() []*preparationState {
-	var closeNow []*preparationState
+func (r *Router) closePendingPreparationsLocked() {
 	for _, p := range r.preparations {
 		p.timer.Stop()
 		if p.executor != nil {
@@ -38,19 +9,14 @@ func (r *Router) closePendingPreparationsLocked() []*preparationState {
 		if !p.owns {
 			continue
 		}
-		if p.handoff != nil {
-			continue
-		}
 		p.cancel()
 		switch p.status.State {
-		case "preparing", "ready", "starting":
+		case "preparing", "ready":
 			p.status.State, p.status.ErrorCode, p.status.Revision = "failed", "connection_closed", p.status.Revision+1
 		}
+		// A busy preparation drops ownership when readiness returns.
 		if !p.busy {
-			p.busy = true
-			r.shutdownWG.Add(1)
-			closeNow = append(closeNow, p)
+			p.owns = false
 		}
 	}
-	return closeNow
 }
diff --git a/apps/daemon/internal/dispatch/preparation_executor_fixture_test.go b/apps/daemon/internal/dispatch/preparation_executor_fixture_test.go
index a5966ce69..5e9e778d2 100644
--- a/apps/daemon/internal/dispatch/preparation_executor_fixture_test.go
+++ b/apps/daemon/internal/dispatch/preparation_executor_fixture_test.go
@@ -122,15 +122,3 @@ func (t *preparationTurn) SteerWithReceipt(ctx context.Context, p proto.PromptSt
 	}
 	return agent.ErrSteeringInactive
 }
-func (t *preparationTurn) SubmitPermission(ctx context.Context, id string, p proto.PermissionDecisionPayload) error {
-	if target, ok := t.Session.(agent.PermissionResponder); ok {
-		return target.SubmitPermission(ctx, id, p)
-	}
-	return agent.ErrUnknownPermission
-}
-func (t *preparationTurn) SubmitPromptForUserChoice(ctx context.Context, id string, p proto.PromptForUserChoiceDecisionPayload) error {
-	if target, ok := t.Session.(agent.UserChoiceResponder); ok {
-		return target.SubmitPromptForUserChoice(ctx, id, p)
-	}
-	return agent.ErrUnknownAsk
-}
diff --git a/apps/daemon/internal/dispatch/preparation_start.go b/apps/daemon/internal/dispatch/preparation_start.go
index 2c09428c0..dd803d938 100644
--- a/apps/daemon/internal/dispatch/preparation_start.go
+++ b/apps/daemon/internal/dispatch/preparation_start.go
@@ -41,12 +41,12 @@ func (r *Router) handleExecutionStart(_ context.Context, env proto.Envelope) err
 		r.mu.Unlock()
 		return r.rejectPreparation(env, code)
 	}
-	if p.workspaceReadOnly {
+	if p.executor == nil {
 		r.mu.Unlock()
 		return r.rejectPreparation(env, "read_only_preparation")
 	}
 	owner := p.executor
-	if owner == nil || owner.id != input.ExecutorID {
+	if owner.id != input.ExecutorID {
 		r.mu.Unlock()
 		return r.rejectPreparation(env, "unknown_executor")
 	}
@@ -69,7 +69,7 @@ func (r *Router) handleExecutionStart(_ context.Context, env proto.Envelope) err
 	}
 	if !time.Now().Before(p.deadline) {
 		r.mu.Unlock()
-		r.releasePreparation(p, "expired", "", true, true)
+		r.releasePreparation(p, "expired", "", true)
 		return nil
 	}
 	if r.sessions[input.RunID] != nil {
@@ -78,7 +78,7 @@ func (r *Router) handleExecutionStart(_ context.Context, env proto.Envelope) err
 	}
 	p.status.State, p.status.RunID, p.status.Revision = "starting", input.RunID, p.status.Revision+1
 	p.startFingerprint, p.busy = fingerprint, true
-	state := &sessionState{assignment: env.Assignment, capabilities: p.capabilities, runID: input.RunID, environmentID: p.environmentID, out: make(chan proto.Envelope, 64), ctx: p.ctx, pendingIDs: make(map[string]struct{}), pendingAsks: make(map[string]struct{}), traceparent: env.Trace}
+	state := &sessionState{assignment: env.Assignment, capabilities: p.capabilities, runID: input.RunID, environmentID: p.environmentID, out: make(chan proto.Envelope, 64), ctx: p.ctx, traceparent: env.Trace}
 	state.preparedHandoff = newPreparedHandoff(p, owner.native)
 	p.handoff, owner.run = state.preparedHandoff, state
 	r.sessions[input.RunID] = state
diff --git a/apps/daemon/internal/dispatch/preparation_test.go b/apps/daemon/internal/dispatch/preparation_test.go
index bd4fbe3ea..bb39c151f 100644
--- a/apps/daemon/internal/dispatch/preparation_test.go
+++ b/apps/daemon/internal/dispatch/preparation_test.go
@@ -121,9 +121,7 @@ func preparationRequest() proto.ExecutionPreparePayload {
 func preparationRouter(t *testing.T, sender dispatch.Sender, timeout time.Duration, factory preparationFactory) *dispatch.Router {
 	t.Helper()
 	reg := agent.NewRegistry()
-	reg.RegisterKind(proto.SupportedAgentKind{Kind: "prepared", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{LocalEnvironment: proto.CapabilitySupported, WorkspaceReadPreparation: proto.CapabilitySupported, Permissions: proto.CapabilitySupported, FunctionTools: proto.CapabilitySupported, Steering: proto.CapabilitySupported, DurableInputReceipts: proto.CapabilitySupported})}, prototest.ModelConfiguration(), func(context.Context, proto.PromptRequestPayload, chan<- proto.Envelope) (agent.Session, error) {
-		return nil, errors.New("ordinary Factory must not be used for preparation")
-	})
+	reg.RegisterKind(proto.SupportedAgentKind{Kind: "prepared", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{LocalEnvironment: proto.CapabilitySupported, WorkspaceReadPreparation: proto.CapabilitySupported, FunctionTools: proto.CapabilitySupported, Steering: proto.CapabilitySupported, DurableInputReceipts: proto.CapabilitySupported})}, prototest.ModelConfiguration())
 	reg.RegisterExecutor("prepared", preparationExecutorFixture(factory))
 	r, err := dispatch.New(dispatch.Config{Registry: reg, Sender: sender, PreparationTimeout: timeout, LocalWorkspace: preparationWorkspace(t)})
 	if err != nil {
diff --git a/apps/daemon/internal/dispatch/prepared_handoff.go b/apps/daemon/internal/dispatch/prepared_handoff.go
index 16bed1669..772cce4a5 100644
--- a/apps/daemon/internal/dispatch/prepared_handoff.go
+++ b/apps/daemon/internal/dispatch/prepared_handoff.go
@@ -89,7 +89,7 @@ func (r *Router) preparedOperationLocked(state *sessionState) (agent.Turn, func(
 	return state.session, handoff.operations.RUnlock, true
 }
 
-func (r *Router) interactionRouteOpenLocked(state *sessionState) bool {
+func (r *Router) runRouteOpenLocked(state *sessionState) bool {
 	return state != nil && !r.closed && state.ctx.Err() == nil && !state.steeringClosed && state.preparedHandoff.release == nil
 }
 
@@ -104,7 +104,6 @@ func (r *Router) claimPreparedReleaseLocked(state *sessionState, abort bool, fai
 		handoff.release = release
 		state.steeringClosed = true
 		state.session = nil
-		r.clearInteractionRoutesLocked(state)
 	}
 	if abort && !release.aborted() {
 		close(release.abort)
@@ -328,10 +327,6 @@ func (r *Router) forwardPreparedOutput(state *sessionState) {
 			if drainOnly {
 				continue
 			}
-			switch env.Type {
-			case proto.TypePermissionRequest, proto.TypePermissionCancel, proto.TypePromptForUserChoice:
-				r.indexPermissionFrame(state, env)
-			}
 			if err := r.sendSessionOutput(pumpCtx, state, env); err != nil {
 				r.mu.Lock()
 				if r.closed {
diff --git a/apps/daemon/internal/dispatch/prepared_handoff_mutation_test.go b/apps/daemon/internal/dispatch/prepared_handoff_mutation_test.go
index 7689961ed..0a04ea8e2 100644
--- a/apps/daemon/internal/dispatch/prepared_handoff_mutation_test.go
+++ b/apps/daemon/internal/dispatch/prepared_handoff_mutation_test.go
@@ -71,7 +71,7 @@ func (s *blockingPreparedReceiptSender) matches(env proto.Envelope) bool {
 }
 
 func TestPreparedHandoffReleaseWaitsForMutationReceipt(t *testing.T) {
-	for _, operation := range []string{"function", "permission", "choice", "steering"} {
+	for _, operation := range []string{"function", "steering"} {
 		t.Run(operation, func(t *testing.T) {
 			sender := &blockingPreparedReceiptSender{
 				recSender: &recSender{}, deliveryID: operation + "-delivery", inputID: operation + "-input",
@@ -91,14 +91,6 @@ func TestPreparedHandoffReleaseWaitsForMutationReceipt(t *testing.T) {
 			switch operation {
 			case "function":
 				mutation = mustEnv(t, proto.TypeFunctionResult, "run", proto.FunctionResultPayload{CallID: "call", Success: true, Content: functionResultContent("answer"), DeliveryID: sender.deliveryID})
-			case "permission":
-				session.out <- mustEnv(t, proto.TypePermissionRequest, "run", proto.PermissionRequestPayload{RequestID: "permission"})
-				waitFor(t, func() bool { return hasFrame(sender.recSender, proto.TypePermissionRequest, "run") }, "permission request")
-				mutation = mustEnv(t, proto.TypePermissionDecision, "permission", proto.PermissionDecisionPayload{DeliveryID: sender.deliveryID, Approved: true})
-			case "choice":
-				session.out <- mustEnv(t, proto.TypePromptForUserChoice, "run", proto.PromptForUserChoicePayload{AskID: "ask"})
-				waitFor(t, func() bool { return hasFrame(sender.recSender, proto.TypePromptForUserChoice, "run") }, "choice request")
-				mutation = mustEnv(t, proto.TypePromptForUserChoiceDecision, "ask", proto.PromptForUserChoiceDecisionPayload{DeliveryID: sender.deliveryID, QuestionAnswers: []proto.PromptForUserChoiceQuestionAnswer{{QuestionID: "q0", Answers: []string{"yes"}}}})
 			case "steering":
 				mutation = mustEnv(t, proto.TypePromptSteer, "run", proto.PromptSteerPayload{InputID: sender.inputID, Input: proto.TextInput("continue")})
 			}
@@ -119,28 +111,6 @@ func TestPreparedHandoffReleaseWaitsForMutationReceipt(t *testing.T) {
 					t.Fatal(err)
 				}
 				assertDecisionAck(t, sender.recSender, "late-function", false, "not_ready")
-			case "permission":
-				late := mustEnv(t, proto.TypePermissionDecision, "permission", proto.PermissionDecisionPayload{DeliveryID: "late-permission", Approved: true})
-				if err := r.Handle(t.Context(), late); err != nil {
-					t.Fatal(err)
-				}
-				assertDecisionAck(t, sender.recSender, "late-permission", true, "")
-				newRequest := mustEnv(t, proto.TypePermissionDecision, "new-permission", proto.PermissionDecisionPayload{DeliveryID: "new-permission", Approved: true})
-				if err := r.Handle(t.Context(), newRequest); err != nil {
-					t.Fatal(err)
-				}
-				assertDecisionAck(t, sender.recSender, "new-permission", false, "not_pending")
-			case "choice":
-				late := mustEnv(t, proto.TypePromptForUserChoiceDecision, "ask", proto.PromptForUserChoiceDecisionPayload{DeliveryID: "late-choice", QuestionAnswers: []proto.PromptForUserChoiceQuestionAnswer{{QuestionID: "q0", Answers: []string{"yes"}}}})
-				if err := r.Handle(t.Context(), late); err != nil {
-					t.Fatal(err)
-				}
-				assertDecisionAck(t, sender.recSender, "late-choice", true, "")
-				newRequest := mustEnv(t, proto.TypePromptForUserChoiceDecision, "new-choice", proto.PromptForUserChoiceDecisionPayload{DeliveryID: "new-choice", QuestionAnswers: []proto.PromptForUserChoiceQuestionAnswer{{QuestionID: "q0", Answers: []string{"yes"}}}})
-				if err := r.Handle(t.Context(), newRequest); err != nil {
-					t.Fatal(err)
-				}
-				assertDecisionAck(t, sender.recSender, "new-choice", false, "not_pending")
 			case "steering":
 				late := mustEnv(t, proto.TypePromptSteer, "run", proto.PromptSteerPayload{InputID: "late-steering", Input: proto.TextInput("late")})
 				if err := r.Handle(t.Context(), late); err != nil {
@@ -181,17 +151,6 @@ func TestPreparedHandoffReleaseWaitsForMutationReceipt(t *testing.T) {
 				if session.functions.Load() != 1 {
 					t.Fatalf("function native calls = %d, want 1", session.functions.Load())
 				}
-			case "permission":
-				if len(session.submissions()) != 1 {
-					t.Fatalf("permission native calls = %d, want 1", len(session.submissions()))
-				}
-			case "choice":
-				session.askMu.Lock()
-				calls := len(session.askCalls)
-				session.askMu.Unlock()
-				if calls != 1 {
-					t.Fatalf("choice native calls = %d, want 1", calls)
-				}
 			case "steering":
 				if session.steers.Load() != 1 {
 					t.Fatalf("steering native calls = %d, want 1", session.steers.Load())
@@ -228,7 +187,7 @@ func assertReceiptBeforeDone(t *testing.T, sender *recSender, operation string)
 }
 
 func TestPreparedHandoffRouterShutdownWaitsForReceiptAttempt(t *testing.T) {
-	for _, operation := range []string{"function", "permission", "choice", "steering"} {
+	for _, operation := range []string{"function", "steering"} {
 		t.Run(operation, func(t *testing.T) {
 			sender := &blockingPreparedReceiptSender{recSender: &recSender{}, deliveryID: operation + "-delivery", inputID: operation + "-input", entered: make(chan struct{}), release: make(chan struct{}), exited: make(chan struct{})}
 			defer close(sender.release)
@@ -246,14 +205,6 @@ func TestPreparedHandoffRouterShutdownWaitsForReceiptAttempt(t *testing.T) {
 			switch operation {
 			case "function":
 				mutation = mustEnv(t, proto.TypeFunctionResult, "run", proto.FunctionResultPayload{CallID: "call", Success: true, Content: functionResultContent("answer"), DeliveryID: sender.deliveryID})
-			case "permission":
-				session.out <- mustEnv(t, proto.TypePermissionRequest, "run", proto.PermissionRequestPayload{RequestID: "permission"})
-				waitFor(t, func() bool { return hasFrame(sender.recSender, proto.TypePermissionRequest, "run") }, "permission request")
-				mutation = mustEnv(t, proto.TypePermissionDecision, "permission", proto.PermissionDecisionPayload{DeliveryID: sender.deliveryID, Approved: true})
-			case "choice":
-				session.out <- mustEnv(t, proto.TypePromptForUserChoice, "run", proto.PromptForUserChoicePayload{AskID: "ask"})
-				waitFor(t, func() bool { return hasFrame(sender.recSender, proto.TypePromptForUserChoice, "run") }, "choice request")
-				mutation = mustEnv(t, proto.TypePromptForUserChoiceDecision, "ask", proto.PromptForUserChoiceDecisionPayload{DeliveryID: sender.deliveryID, QuestionAnswers: []proto.PromptForUserChoiceQuestionAnswer{{QuestionID: "q0", Answers: []string{"yes"}}}})
 			case "steering":
 				mutation = mustEnv(t, proto.TypePromptSteer, "run", proto.PromptSteerPayload{InputID: sender.inputID, Input: proto.TextInput("continue")})
 			}
diff --git a/apps/daemon/internal/dispatch/prepared_handoff_test.go b/apps/daemon/internal/dispatch/prepared_handoff_test.go
index c4cf45c91..3a76fbac6 100644
--- a/apps/daemon/internal/dispatch/prepared_handoff_test.go
+++ b/apps/daemon/internal/dispatch/prepared_handoff_test.go
@@ -161,8 +161,6 @@ func TestPreparedHandoffDuplicateStartDoesNotReexecuteDuringPublication(t *testi
 	p := &controlledPreparation{closed: make(chan struct{})}
 	p.start = func(_ context.Context, _ string, _ proto.MessageInput, out chan<- proto.Envelope) (agent.Session, error) {
 		session.out = out
-		out <- mustEnv(t, proto.TypePermissionRequest, "run", proto.PermissionRequestPayload{RequestID: "publication-permission"})
-		out <- mustEnv(t, proto.TypePromptForUserChoice, "run", proto.PromptForUserChoicePayload{AskID: "publication-choice"})
 		return session, nil
 	}
 	r := preparationRouter(t, sender, time.Minute, func(context.Context, proto.PromptRequestPayload) (preparedFixture, error) { return p, nil })
@@ -172,21 +170,11 @@ func TestPreparedHandoffDuplicateStartDoesNotReexecuteDuringPublication(t *testi
 	case <-time.After(2 * time.Second):
 		t.Fatal("started status did not reach publication boundary")
 	}
-	waitFor(t, func() bool {
-		return hasFrame(sender.recSender, proto.TypePermissionRequest, "run") && hasFrame(sender.recSender, proto.TypePromptForUserChoice, "run")
-	}, "pre-publication interaction routes")
-	for _, mutation := range []proto.Envelope{
-		mustEnv(t, proto.TypeFunctionResult, "run", proto.FunctionResultPayload{CallID: "call", Success: true, Content: functionResultContent("answer"), DeliveryID: "publication-function"}),
-		mustEnv(t, proto.TypePermissionDecision, "publication-permission", proto.PermissionDecisionPayload{DeliveryID: "publication-permission", Approved: true}),
-		mustEnv(t, proto.TypePromptForUserChoiceDecision, "publication-choice", proto.PromptForUserChoiceDecisionPayload{DeliveryID: "publication-choice", QuestionAnswers: []proto.PromptForUserChoiceQuestionAnswer{{QuestionID: "q0", Answers: []string{"yes"}}}}),
-	} {
-		if err := r.Handle(t.Context(), mutation); err != nil {
-			t.Fatal(err)
-		}
+	result := mustEnv(t, proto.TypeFunctionResult, "run", proto.FunctionResultPayload{CallID: "call", Success: true, Content: functionResultContent("answer"), DeliveryID: "publication-function"})
+	if err := r.Handle(t.Context(), result); err != nil {
+		t.Fatal(err)
 	}
 	assertDecisionAck(t, sender.recSender, "publication-function", false, "not_ready")
-	assertDecisionAck(t, sender.recSender, "publication-permission", false, "not_ready")
-	assertDecisionAck(t, sender.recSender, "publication-choice", false, "not_ready")
 	if err := r.Handle(t.Context(), mustEnv(t, proto.TypePromptSteer, "run", proto.PromptSteerPayload{InputID: "publication-steering", Input: proto.TextInput("continue")})); err != nil {
 		t.Fatal(err)
 	}
@@ -202,10 +190,7 @@ func TestPreparedHandoffDuplicateStartDoesNotReexecuteDuringPublication(t *testi
 	if len(frames) == 0 || frames[len(frames)-1].Type != proto.TypeWorkspaceReadResult || frames[len(frames)-1].DecodePayload(&readResult) != nil || readResult.ErrorCode != "resource_unavailable" {
 		t.Fatalf("pre-publication workspace read = %+v", frames)
 	}
-	session.askMu.Lock()
-	askCalls := len(session.askCalls)
-	session.askMu.Unlock()
-	if session.functions.Load() != 0 || session.steers.Load() != 0 || len(session.submissions()) != 0 || askCalls != 0 {
+	if session.functions.Load() != 0 || session.steers.Load() != 0 {
 		t.Fatal("private Session accepted work before started publication")
 	}
 	duplicate := mustEnv(t, proto.TypeExecutionStart, "request", proto.ExecutionStartPayload{Handle: ready.Handle, ExecutorID: ready.ExecutorID, RunID: "run", Input: proto.TextInput("input")})
diff --git a/apps/daemon/internal/dispatch/router.go b/apps/daemon/internal/dispatch/router.go
index a9c59e368..39cbf3065 100644
--- a/apps/daemon/internal/dispatch/router.go
+++ b/apps/daemon/internal/dispatch/router.go
@@ -1,8 +1,7 @@
 // Package dispatch wires inbound WebSocket frames to the agent layer.
 // It owns the Session assignments of its connection, one Turn per active
-// RunID with a goroutine that forwards the Turn's events to the transport,
-// and a permission_id → run_id index so permission_decision frames route
-// back to the right run.
+// RunID and a per-Turn output goroutine that forwards the agent's events to
+// the transport.
 //
 // Concurrency: Handle is safe for one goroutine (typically the read
 // loop). Each run has its own goroutines. Internal state is
@@ -38,11 +37,9 @@ type Router struct {
 	suspension          *proto.EnvironmentSuspendPayload
 	suspendedBy         proto.AssignmentRef // the assignment that quiesced
 	mu                  sync.Mutex
-	assignments         map[string]*assignmentState // SessionID → assignment
-	sessions            map[string]*sessionState    // RunID → state
-	permIndex           map[string]string           // permID  → RunID
-	askIndex            map[string]string           // askID   → RunID
-	applied             map[string]appliedInteractionDecision
+	assignments         map[string]*assignmentState      // SessionID → assignment
+	sessions            map[string]*sessionState         // RunID → state
+	applied             map[string]appliedFunctionResult // RunID and call ID → applied result
 	shutdownAttempt     *shutdownAttempt
 	shutdownCh          chan struct{} // closed by Shutdown
 	shutdownWG          dispatchWork  // waits for all pump goroutines
@@ -61,9 +58,7 @@ type Router struct {
 	removeHome          func(sessionID string) error
 }
 
-type appliedInteractionDecision struct {
-	requestID   string
-	kind        string
+type appliedFunctionResult struct {
 	fingerprint [32]byte
 	assignment  proto.AssignmentRef
 	recordedAt  time.Time
@@ -82,8 +77,6 @@ type sessionState struct {
 	session         agent.Turn
 	out             chan proto.Envelope
 	ctx             context.Context
-	pendingIDs      map[string]struct{}
-	pendingAsks     map[string]struct{}
 	traceparent     string
 	steering        map[string]steeringReceipt
 	steerBusy       bool
@@ -141,9 +134,7 @@ func New(cfg Config) (*Router, error) {
 		log:                 log,
 		assignments:         make(map[string]*assignmentState),
 		sessions:            make(map[string]*sessionState),
-		permIndex:           make(map[string]string),
-		askIndex:            make(map[string]string),
-		applied:             make(map[string]appliedInteractionDecision),
+		applied:             make(map[string]appliedFunctionResult),
 		shutdownCh:          make(chan struct{}),
 		idleTimeout:         idleTimeout,
 		executors:           make(map[string]*executorState),
@@ -204,10 +195,6 @@ func (r *Router) Handle(ctx context.Context, env proto.Envelope) error {
 		return r.handleFunctionResult(ctx, env)
 	case proto.TypePromptSteer:
 		return r.handlePromptSteer(ctx, env)
-	case proto.TypePermissionDecision:
-		return r.handlePermissionDecision(ctx, env)
-	case proto.TypePromptForUserChoiceDecision:
-		return r.handlePromptForUserChoiceDecision(ctx, env)
 	default:
 		r.log.WarnContext(ctx, "unsupported envelope type", "type", env.Type, "id", env.ID)
 		return r.reply(ctx, env, proto.TypeProtocolError, proto.ProtocolErrorPayload{Type: env.Type, ErrorCode: proto.UnsupportedOperation})
@@ -223,7 +210,7 @@ func adoptEnvelopeTrace(ctx context.Context, env proto.Envelope) context.Context
 			return obslog.WithTrace(ctx, carrier)
 		}
 	}
-	ctx, _ = obslog.StartBackgroundTrace(ctx, "daemon.envelope")
+	ctx, _ = obslog.StartBackgroundTrace(ctx)
 	return ctx
 }
 
@@ -251,11 +238,5 @@ func (r *Router) drain(ch <-chan proto.Envelope) {
 func (r *Router) cleanupSession(s *sessionState) {
 	r.mu.Lock()
 	delete(r.sessions, s.runID)
-	for permID := range s.pendingIDs {
-		delete(r.permIndex, permID)
-	}
-	for askID := range s.pendingAsks {
-		delete(r.askIndex, askID)
-	}
 	r.mu.Unlock()
 }
diff --git a/apps/daemon/internal/dispatch/router_test.go b/apps/daemon/internal/dispatch/router_test.go
index 1d755905b..5b19337a9 100644
--- a/apps/daemon/internal/dispatch/router_test.go
+++ b/apps/daemon/internal/dispatch/router_test.go
@@ -62,12 +62,7 @@ func (s *recSender) typesFor(runID string) []string {
 // channel and manipulates outbound traffic / cancel observability.
 type fakeSession struct {
 	cancelCalls         int
-	submitCalls         []permCall
-	askCalls            []askCall
-	submitErr           error
-	askErr              error
-	cancelMu, submitMu  sync.Mutex
-	askMu               sync.Mutex
+	cancelMu            sync.Mutex
 	closeOutOnCancel    bool
 	out                 chan<- proto.Envelope
 	closeOutOnCancelMu  sync.Once
@@ -75,16 +70,6 @@ type fakeSession struct {
 	ctx                 context.Context
 }
 
-type permCall struct {
-	id       string
-	decision proto.PermissionDecisionPayload
-}
-
-type askCall struct {
-	id       string
-	decision proto.PromptForUserChoiceDecisionPayload
-}
-
 func (s *fakeSession) CancellationOutcome() proto.DonePayload { return proto.DonePayload{} }
 
 func (s *fakeSession) Cancel(context.Context) error {
@@ -102,34 +87,12 @@ func (s *fakeSession) Cancel(context.Context) error {
 	return nil
 }
 
-func (s *fakeSession) SubmitPermission(_ context.Context, permID string, dec proto.PermissionDecisionPayload) error {
-	s.submitMu.Lock()
-	s.submitCalls = append(s.submitCalls, permCall{id: permID, decision: dec})
-	s.submitMu.Unlock()
-	return s.submitErr
-}
-
-func (s *fakeSession) SubmitPromptForUserChoice(_ context.Context, askID string, dec proto.PromptForUserChoiceDecisionPayload) error {
-	s.askMu.Lock()
-	s.askCalls = append(s.askCalls, askCall{id: askID, decision: dec})
-	s.askMu.Unlock()
-	return s.askErr
-}
-
 func (s *fakeSession) cancels() int {
 	s.cancelMu.Lock()
 	defer s.cancelMu.Unlock()
 	return s.cancelCalls
 }
 
-func (s *fakeSession) submissions() []permCall {
-	s.submitMu.Lock()
-	defer s.submitMu.Unlock()
-	out := make([]permCall, len(s.submitCalls))
-	copy(out, s.submitCalls)
-	return out
-}
-
 // ---------------------------------------------------------------------
 // helpers
 // ---------------------------------------------------------------------
@@ -151,7 +114,7 @@ func newHarness(t *testing.T) *harness {
 		gotReq:  make(chan proto.PromptRequestPayload, 16),
 		gotSess: make(chan *fakeSession, 16),
 	}
-	registerSession(h.reg, proto.SupportedAgentKind{Kind: "fake_alpha", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{Permissions: proto.CapabilitySupported})}, func(ctx context.Context, req proto.PromptRequestPayload, out chan<- proto.Envelope) (agent.Session, error) {
+	registerSession(h.reg, proto.SupportedAgentKind{Kind: "fake_alpha", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{})}, func(ctx context.Context, req proto.PromptRequestPayload, out chan<- proto.Envelope) (agent.Session, error) {
 		sess := &fakeSession{out: out, ctx: ctx, closeOutOnCancel: true}
 		h.gotReq <- req
 		h.gotSess <- sess
@@ -167,9 +130,9 @@ func newHarness(t *testing.T) *harness {
 
 // registerSession declares info, without an Environment, and starts each
 // Turn of the kind with factory.
-func registerSession(reg *agent.Registry, info proto.SupportedAgentKind, factory agent.Factory) {
+func registerSession(reg *agent.Registry, info proto.SupportedAgentKind, factory func(context.Context, proto.PromptRequestPayload, chan<- proto.Envelope) (agent.Session, error)) {
 	info.Capabilities.EnvironmentNone = proto.CapabilitySupported
-	reg.RegisterKind(info, prototest.ModelConfiguration(), factory)
+	reg.RegisterKind(info, prototest.ModelConfiguration())
 	reg.RegisterExecutor(info.Kind, preparationExecutorFixture(func(_ context.Context, req proto.PromptRequestPayload) (preparedFixture, error) {
 		return &controlledPreparation{start: func(ctx context.Context, id string, input proto.MessageInput, out chan<- proto.Envelope) (agent.Session, error) {
 			req.RunID, req.Input = id, input
@@ -332,187 +295,6 @@ func TestHandlePromptCancelUnknownRunIsNoop(t *testing.T) {
 	}
 }
 
-func TestPermissionRequestIsIndexedAndDecisionRoutes(t *testing.T) {
-	h := newHarness(t)
-	defer h.router.Shutdown(context.Background())
-
-	startRun(t, h.router, h.sender, "fake_alpha", "run_p")
-	<-h.gotReq
-	sess := <-h.gotSess
-
-	// Session emits a permission_request; the Router indexes it before it forwards it.
-	sess.out <- mustEnv(t, proto.TypePermissionRequest, "run_p", proto.PermissionRequestPayload{
-		RequestID: "perm_abcd1234", Tool: "Bash", Title: "rm -rf /",
-	})
-	waitFor(t, func() bool { return hasFrame(h.sender, proto.TypePermissionRequest, "run_p") }, "permission_request to be forwarded")
-
-	dec := scoped(t, "run_p", proto.TypePermissionDecision, "perm_abcd1234", proto.PermissionDecisionPayload{DeliveryID: "delivery-perm-1", Approved: true})
-	if err := h.router.Handle(context.Background(), dec); err != nil {
-		t.Fatalf("permission_decision: %v", err)
-	}
-	calls := sess.submissions()
-	if len(calls) != 1 || calls[0].id != "perm_abcd1234" || !calls[0].decision.Approved {
-		t.Errorf("submissions = %+v, want one approved perm_abcd1234", calls)
-	}
-	assertDecisionAck(t, h.sender, "delivery-perm-1", true, "")
-	retry := scoped(t, "run_p", proto.TypePermissionDecision, "perm_abcd1234", proto.PermissionDecisionPayload{DeliveryID: "delivery-perm-2", Approved: true})
-	if err := h.router.Handle(context.Background(), retry); err != nil {
-		t.Fatalf("idempotent permission replay: %v", err)
-	}
-	if calls := sess.submissions(); len(calls) != 1 {
-		t.Fatalf("idempotent replay reached agent twice: %+v", calls)
-	}
-	assertDecisionAck(t, h.sender, "delivery-perm-2", true, "")
-	conflict := scoped(t, "run_p", proto.TypePermissionDecision, "perm_abcd1234", proto.PermissionDecisionPayload{DeliveryID: "delivery-perm-3", Approved: false})
-	if err := h.router.Handle(context.Background(), conflict); err != nil {
-		t.Fatalf("conflicting permission replay: %v", err)
-	}
-	assertDecisionAck(t, h.sender, "delivery-perm-3", false, "decision_conflict")
-}
-
-func TestPermissionDecisionUnknownPermIsNoop(t *testing.T) {
-	h := newHarness(t)
-	defer h.router.Shutdown(context.Background())
-
-	if err := h.router.Handle(context.Background(), mustEnv(t, proto.TypePermissionDecision, "perm_unknown", proto.PermissionDecisionPayload{DeliveryID: "delivery-unknown-perm"})); err != nil {
-		t.Errorf("decision for unknown perm = %v, want nil", err)
-	}
-	assertDecisionAck(t, h.sender, "delivery-unknown-perm", false, "not_pending")
-}
-
-func TestPromptForUserChoiceDecisionRoutesToSession(t *testing.T) {
-	h := newHarness(t)
-	defer h.router.Shutdown(context.Background())
-
-	startRun(t, h.router, h.sender, "fake_alpha", "run_ask")
-	<-h.gotReq
-	sess := <-h.gotSess
-
-	// Envelope.ID is the run id (server-side dispatch fans on it); the
-	// ask id rides on the payload. Daemon's indexPermissionFrame reads
-	// payload.AskID to seed askIndex.
-	sess.out <- mustEnv(t, proto.TypePromptForUserChoice, "run_ask", proto.PromptForUserChoicePayload{
-		AskID:     "ask_abcd1234",
-		Questions: []proto.PromptForUserChoiceQuestion{{Question: "?", Options: []proto.PromptForUserChoiceOption{{Label: "yes"}, {Label: "no"}}}},
-		ToolUseID: "toolu_42",
-	})
-	waitFor(t, func() bool { return hasFrame(h.sender, proto.TypePromptForUserChoice, "run_ask") }, "prompt_for_user_choice forwarded")
-
-	dec := scoped(t, "run_ask", proto.TypePromptForUserChoiceDecision, "ask_abcd1234", proto.PromptForUserChoiceDecisionPayload{
-		DeliveryID: "delivery-ask-1", QuestionAnswers: []proto.PromptForUserChoiceQuestionAnswer{{QuestionID: "q0", Answers: []string{"yes"}}},
-	})
-	if err := h.router.Handle(context.Background(), dec); err != nil {
-		t.Fatalf("prompt_for_user_choice_decision: %v", err)
-	}
-
-	sess.askMu.Lock()
-	calls := append([]askCall(nil), sess.askCalls...)
-	sess.askMu.Unlock()
-	if len(calls) != 1 || calls[0].id != "ask_abcd1234" {
-		t.Fatalf("askCalls = %+v, want one ask_abcd1234", calls)
-	}
-	if len(calls[0].decision.QuestionAnswers[0].Answers) != 1 || calls[0].decision.QuestionAnswers[0].Answers[0] != "yes" {
-		t.Errorf("answer payload mismatch: %+v", calls[0].decision)
-	}
-	assertDecisionAck(t, h.sender, "delivery-ask-1", true, "")
-
-	// Cleanup contract: a successful decision drops the ask from both
-	// the router-level index and the session's pendingAsks set, so a
-	// stale retry short-circuits as "run gone".
-	if got := h.router.AskIndexLenForTest(); got != 0 {
-		t.Errorf("askIndex len = %d, want 0 after decision", got)
-	}
-	if got := h.router.PendingAsksLenForTest("run_ask"); got != 0 {
-		t.Errorf("pendingAsks len = %d, want 0 after decision", got)
-	}
-}
-
-// TestPromptForUserChoiceDecisionClearsIndexOnAgentUnknown locks in the
-// cleanup branch: when the session returns ErrUnknownAsk (timer already
-// consumed the entry), the router still drops the index so a retry doesn't
-// loop into Submit again.
-func TestPromptForUserChoiceDecisionClearsIndexOnAgentUnknown(t *testing.T) {
-	h := newHarness(t)
-	defer h.router.Shutdown(context.Background())
-
-	startRun(t, h.router, h.sender, "fake_alpha", "run_ask_u")
-	<-h.gotReq
-	sess := <-h.gotSess
-	sess.askErr = agent.ErrUnknownAsk
-
-	sess.out <- mustEnv(t, proto.TypePromptForUserChoice, "run_ask_u", proto.PromptForUserChoicePayload{
-		AskID:     "ask_xxxxxxxx",
-		Questions: []proto.PromptForUserChoiceQuestion{{Question: "?", Options: []proto.PromptForUserChoiceOption{{Label: "yes"}}}},
-		ToolUseID: "toolu_y",
-	})
-	waitFor(t, func() bool { return hasFrame(h.sender, proto.TypePromptForUserChoice, "run_ask_u") }, "prompt_for_user_choice forwarded")
-
-	dec := scoped(t, "run_ask_u", proto.TypePromptForUserChoiceDecision, "ask_xxxxxxxx", proto.PromptForUserChoiceDecisionPayload{
-		DeliveryID: "delivery-ask-gone", QuestionAnswers: []proto.PromptForUserChoiceQuestionAnswer{{QuestionID: "q0", Answers: []string{"yes"}}},
-	})
-	if err := h.router.Handle(context.Background(), dec); err != nil {
-		t.Fatalf("prompt_for_user_choice_decision: %v", err)
-	}
-
-	if got := h.router.AskIndexLenForTest(); got != 0 {
-		t.Errorf("askIndex len = %d, want 0 after ErrUnknownAsk", got)
-	}
-	if got := h.router.PendingAsksLenForTest("run_ask_u"); got != 0 {
-		t.Errorf("pendingAsks len = %d, want 0 after ErrUnknownAsk", got)
-	}
-	assertDecisionAck(t, h.sender, "delivery-ask-gone", false, "not_pending")
-}
-
-func TestPromptForUserChoiceDecisionKeepsIndexOnTransientAgentError(t *testing.T) {
-	h := newHarness(t)
-	defer h.router.Shutdown(context.Background())
-
-	startRun(t, h.router, h.sender, "fake_alpha", "run_ask_retry")
-	<-h.gotReq
-	sess := <-h.gotSess
-	sess.askErr = errors.New("temporary stdin failure")
-
-	sess.out <- mustEnv(t, proto.TypePromptForUserChoice, "run_ask_retry", proto.PromptForUserChoicePayload{
-		AskID: "ask_retry", Questions: []proto.PromptForUserChoiceQuestion{{ID: "q0", Question: "Retry?"}},
-	})
-	waitFor(t, func() bool { return hasFrame(h.sender, proto.TypePromptForUserChoice, "run_ask_retry") }, "prompt_for_user_choice forwarded")
-
-	decision := scoped(t, "run_ask_retry", proto.TypePromptForUserChoiceDecision, "ask_retry", proto.PromptForUserChoiceDecisionPayload{
-		DeliveryID: "delivery-ask-retry", QuestionAnswers: []proto.PromptForUserChoiceQuestionAnswer{{QuestionID: "q0", Answers: []string{"yes"}}},
-	})
-	if err := h.router.Handle(context.Background(), decision); err != nil {
-		t.Fatalf("first decision: %v", err)
-	}
-	assertDecisionAck(t, h.sender, "delivery-ask-retry", false, "runtime_error")
-	if got := h.router.AskIndexLenForTest(); got != 1 {
-		t.Fatalf("askIndex len = %d, want 1 after transient error", got)
-	}
-	if got := h.router.PendingAsksLenForTest("run_ask_retry"); got != 1 {
-		t.Fatalf("pendingAsks len = %d, want 1 after transient error", got)
-	}
-
-	sess.askMu.Lock()
-	sess.askErr = nil
-	sess.askMu.Unlock()
-	if err := h.router.Handle(context.Background(), decision); err != nil {
-		t.Fatalf("retry decision: %v", err)
-	}
-	assertDecisionAck(t, h.sender, "delivery-ask-retry", true, "")
-	if got := h.router.AskIndexLenForTest(); got != 0 {
-		t.Fatalf("askIndex len = %d, want 0 after successful retry", got)
-	}
-}
-
-func TestPromptForUserChoiceDecisionUnknownAskIsNoop(t *testing.T) {
-	h := newHarness(t)
-	defer h.router.Shutdown(context.Background())
-
-	if err := h.router.Handle(context.Background(), mustEnv(t, proto.TypePromptForUserChoiceDecision, "ask_unknown", proto.PromptForUserChoiceDecisionPayload{DeliveryID: "delivery-unknown-ask"})); err != nil {
-		t.Errorf("decision for unknown ask = %v, want nil", err)
-	}
-	assertDecisionAck(t, h.sender, "delivery-unknown-ask", false, "not_pending")
-}
-
 func assertDecisionAck(t *testing.T, sender *recSender, deliveryID string, applied bool, errorCode string) {
 	t.Helper()
 	frames := sender.snapshot()
diff --git a/apps/daemon/internal/dispatch/runtime_preparation_test.go b/apps/daemon/internal/dispatch/runtime_preparation_test.go
index 6dde480cd..ca4497430 100644
--- a/apps/daemon/internal/dispatch/runtime_preparation_test.go
+++ b/apps/daemon/internal/dispatch/runtime_preparation_test.go
@@ -36,7 +36,7 @@ var capabilityRef = proto.AssignmentRef{SessionID: "0b6f1f3e-6f0a-4d38-9c1e-2f5d
 func capabilitiesTestRouter(t *testing.T) (*Router, *capabilitiesTestSender, string, string) {
 	t.Helper()
 	environment, session := uuid.NewString(), capabilityRef.SessionID
-	binding, err := localworkspace.New(environment, session, t.TempDir())
+	binding, err := localworkspace.NewWithCapabilityDirectory(environment, session, t.TempDir(), t.TempDir())
 	if err != nil {
 		t.Fatal(err)
 	}
diff --git a/apps/daemon/internal/dispatch/shutdown.go b/apps/daemon/internal/dispatch/shutdown.go
index ef27133b4..b09de4c70 100644
--- a/apps/daemon/internal/dispatch/shutdown.go
+++ b/apps/daemon/internal/dispatch/shutdown.go
@@ -37,7 +37,7 @@ func (r *Router) Shutdown(ctx context.Context) error {
 		// Prepared release claims exist before this signal can interrupt output.
 		close(r.shutdownCh)
 	}
-	preparations := r.closePendingPreparationsLocked()
+	r.closePendingPreparationsLocked()
 	executors := r.closeIdleExecutorsLocked()
 	attempt := &shutdownAttempt{done: make(chan struct{})}
 	r.shutdownAttempt = attempt
@@ -46,9 +46,6 @@ func (r *Router) Shutdown(ctx context.Context) error {
 	r.mu.Unlock()
 
 	r.closeIdleExecutors(executors)
-	for _, p := range preparations {
-		go func() { defer r.shutdownWG.Done(); r.closePreparationResource(p) }()
-	}
 	go r.runShutdownAttempt(attempt, victims)
 	return waitShutdown(ctx, attempt)
 }
@@ -116,7 +113,6 @@ func waitShutdown(ctx context.Context, attempt *shutdownAttempt) error {
 
 type sessionCancellation struct {
 	runID   string
-	handoff *preparedHandoff
 	release *preparedRelease
 	attempt *preparedReleaseAttempt
 }
@@ -127,7 +123,7 @@ func (r *Router) sessionCancellationsLocked() []sessionCancellation {
 	victims := make([]sessionCancellation, 0, len(r.sessions))
 	for _, state := range r.sessions {
 		release, attempt := r.claimPreparedReleaseLocked(state, true, "", true)
-		victims = append(victims, sessionCancellation{runID: state.runID, handoff: state.preparedHandoff, release: release, attempt: attempt})
+		victims = append(victims, sessionCancellation{runID: state.runID, release: release, attempt: attempt})
 	}
 	return victims
 }
diff --git a/apps/daemon/internal/dispatch/suspend.go b/apps/daemon/internal/dispatch/suspend.go
index 9220b7c6a..fccb8d4ee 100644
--- a/apps/daemon/internal/dispatch/suspend.go
+++ b/apps/daemon/internal/dispatch/suspend.go
@@ -42,7 +42,7 @@ func (r *Router) Quiesce(ctx context.Context, ref proto.AssignmentRef, request p
 		r.mu.Unlock()
 		return AssignmentError(code)
 	}
-	if r.runtimePreparation != nil || len(r.sessions) != 0 || len(r.workspaceReads) != 0 || r.workspaceWrite != nil || r.workspaceExport != nil || len(r.permIndex) != 0 || len(r.askIndex) != 0 {
+	if r.runtimePreparation != nil || len(r.sessions) != 0 || len(r.workspaceReads) != 0 || r.workspaceWrite != nil || r.workspaceExport != nil {
 		r.mu.Unlock()
 		return ErrRouterBusy
 	}
diff --git a/apps/daemon/internal/dispatch/suspend_test.go b/apps/daemon/internal/dispatch/suspend_test.go
index b71577e7a..db35925ff 100644
--- a/apps/daemon/internal/dispatch/suspend_test.go
+++ b/apps/daemon/internal/dispatch/suspend_test.go
@@ -49,14 +49,12 @@ func suspensionRouter(t *testing.T, sender Sender) *Router {
 
 func TestQuiesceRejectsEveryUnsettledResource(t *testing.T) {
 	cases := map[string]func(*Router){
-		"active":     func(r *Router) { r.sessions["run"] = &sessionState{} },
-		"preparing":  func(r *Router) { r.preparations["p"] = &preparationState{owns: true} },
-		"receipt":    func(r *Router) { r.preparations["p"] = &preparationState{busy: true} },
-		"read":       func(r *Router) { r.workspaceReads = map[string]struct{}{"read": {}} },
-		"write":      func(r *Router) { r.workspaceWrite = &workspaceUpload{} },
-		"export":     func(r *Router) { r.workspaceExport = &workspaceExport{} },
-		"permission": func(r *Router) { r.permIndex["permission"] = "run" },
-		"choice":     func(r *Router) { r.askIndex["choice"] = "run" },
+		"active":    func(r *Router) { r.sessions["run"] = &sessionState{} },
+		"preparing": func(r *Router) { r.preparations["p"] = &preparationState{owns: true} },
+		"receipt":   func(r *Router) { r.preparations["p"] = &preparationState{busy: true} },
+		"read":      func(r *Router) { r.workspaceReads = map[string]struct{}{"read": {}} },
+		"write":     func(r *Router) { r.workspaceWrite = &workspaceUpload{} },
+		"export":    func(r *Router) { r.workspaceExport = &workspaceExport{} },
 	}
 	for name, setup := range cases {
 		t.Run(name, func(t *testing.T) {
diff --git a/apps/daemon/internal/dispatch/workspace_export.go b/apps/daemon/internal/dispatch/workspace_export.go
index ca9ebc2c1..724b84841 100644
--- a/apps/daemon/internal/dispatch/workspace_export.go
+++ b/apps/daemon/internal/dispatch/workspace_export.go
@@ -49,7 +49,7 @@ func (r *Router) handleWorkspaceExport(ctx context.Context, env proto.Envelope)
 	}
 	_, code := r.workspaceResourceLocked(env.Assignment, proto.WorkspaceReadPayload{Handle: request.Handle, EnvironmentID: request.EnvironmentID})
 	p := r.preparations[request.Handle]
-	if code == "" && (u != nil || r.workspaceWrite != nil || !r.localWorkspace.CanExport() || p == nil || !p.workspaceReadOnly) {
+	if code == "" && (u != nil || r.workspaceWrite != nil || !r.localWorkspace.CanExport() || p == nil || p.executor != nil) {
 		code = "resource_unavailable"
 	}
 	if code != "" {
diff --git a/apps/daemon/internal/dispatch/workspace_export_test.go b/apps/daemon/internal/dispatch/workspace_export_test.go
index 7a1e2e5b7..cb142173f 100644
--- a/apps/daemon/internal/dispatch/workspace_export_test.go
+++ b/apps/daemon/internal/dispatch/workspace_export_test.go
@@ -51,7 +51,7 @@ func exporterRouter(t *testing.T, program string) (*Router, exportSender, proto.
 		f.Close()
 	}
 	environment, session := uuid.NewString(), capabilityRef.SessionID
-	binding, err := localworkspace.New(environment, session, workspace)
+	binding, err := localworkspace.NewWithCapabilityDirectory(environment, session, workspace, t.TempDir())
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -62,7 +62,7 @@ func exporterRouter(t *testing.T, program string) (*Router, exportSender, proto.
 	}
 	bindAssignment(r, capabilityRef, environment)
 	handle := uuid.NewString()
-	r.preparations[handle] = &preparationState{request: proto.Envelope{Assignment: capabilityRef}, workspaceReadOnly: true, environmentID: environment, owns: true, ctx: context.Background(), deadline: time.Now().Add(time.Hour), status: proto.PreparationStatusPayload{State: "ready"}}
+	r.preparations[handle] = &preparationState{request: proto.Envelope{Assignment: capabilityRef}, environmentID: environment, owns: true, ctx: context.Background(), deadline: time.Now().Add(time.Hour), status: proto.PreparationStatusPayload{State: "ready"}}
 	t.Cleanup(func() {
 		r.mu.Lock()
 		delete(r.preparations, handle)
diff --git a/apps/daemon/internal/dispatch/workspace_preparation_status_test.go b/apps/daemon/internal/dispatch/workspace_preparation_status_test.go
index 3e0bbcc25..d748b5bbe 100644
--- a/apps/daemon/internal/dispatch/workspace_preparation_status_test.go
+++ b/apps/daemon/internal/dispatch/workspace_preparation_status_test.go
@@ -2,14 +2,10 @@ package dispatch
 
 import (
 	"context"
-	"errors"
-	"sync"
-	"sync/atomic"
 	"testing"
 	"time"
 
 	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
-	obslog "github.com/MiniMax-AI/OpenAgentCore/internal/obs/log"
 )
 
 type workspaceStatusSender chan proto.Envelope
@@ -19,115 +15,23 @@ func (s workspaceStatusSender) Send(_ context.Context, envelope proto.Envelope)
 	return nil
 }
 
-type offlineWorkspaceStatusSender struct{}
-
-func (offlineWorkspaceStatusSender) Send(context.Context, proto.Envelope) error {
-	return errors.New("observer disconnected")
-}
-
-type unsettledWorkspacePreparation struct {
-	calls   atomic.Int32
-	settled atomic.Bool
-}
-
-func (p *unsettledWorkspacePreparation) Close() error {
-	// Bound a regression so a recursive retry cannot hang the test.
-	if p.calls.Add(1) >= 100 || p.settled.Load() {
-		return nil
-	}
-	return errors.New("cleanup incomplete")
-}
-
-func TestReadPreparationOfflineStatusDoesNotRetryCleanup(t *testing.T) {
-	prepared := &unsettledWorkspacePreparation{}
+func TestReadPreparationRetryCannotPublishStaleStatus(t *testing.T) {
+	sender := make(workspaceStatusSender, 4)
 	ctx, cancel := context.WithCancel(context.Background())
 	defer cancel()
 	timer := time.NewTimer(time.Hour)
 	defer timer.Stop()
-	r := &Router{sender: offlineWorkspaceStatusSender{}, shutdownCh: make(chan struct{}), log: obslog.Bg()}
-	p := &preparationState{workspaceReadOnly: true, owns: true, prepared: prepared,
-		ctx: ctx, cancel: cancel, timer: timer,
-		status: proto.PreparationStatusPayload{Handle: "reader", Revision: 1, State: "ready"}}
-	for attempt := int32(1); attempt <= 2; attempt++ {
-		r.releasePreparation(p, "released", "", true, true)
-		r.shutdownWG.Wait()
-		if got := prepared.calls.Load(); got != attempt {
-			t.Fatalf("explicit release %d caused %d cleanup attempts", attempt, got)
-		}
-		if !p.owns || p.busy || p.prepared != prepared || p.status.ErrorCode != "cleanup_unconfirmed" {
-			t.Fatal("unconfirmed cleanup lost its resource ownership")
-		}
-	}
-	prepared.settled.Store(true)
-	r.releasePreparation(p, "released", "", true, true)
-	r.shutdownWG.Wait()
-	if prepared.calls.Load() != 3 || p.owns || p.prepared != nil || p.status.State != "released" {
-		t.Fatal("explicit retry did not settle resource ownership")
-	}
-}
-
-func TestReadPreparationRetryCannotPublishStaleRelease(t *testing.T) {
-	sender := make(workspaceStatusSender, 4)
 	r := &Router{sender: sender, shutdownCh: make(chan struct{})}
-	p := &preparationState{workspaceReadOnly: true, owns: true, busy: true,
-		status: proto.PreparationStatusPayload{Handle: "reader", Revision: 2, State: "released"}}
-	// A prepare retry captures this snapshot while Close is still running.
+	p := &preparationState{owns: true, ctx: ctx, cancel: cancel, timer: timer,
+		status: proto.PreparationStatusPayload{Handle: "reader", Revision: 2, State: "ready"}}
+	// A prepare retry captures this snapshot before the release settles.
 	snapshot := p.status
-	// Close fails before the retry reaches publication.
-	p.busy = false
-	p.status = proto.PreparationStatusPayload{Handle: "reader", Revision: 3, State: "failed", ErrorCode: "cleanup_unconfirmed"}
-	r.publishPreparation(p, snapshot)
-	r.shutdownWG.Wait()
-	if len(sender) != 0 {
-		t.Fatal("stale release success escaped after failed Close")
-	}
-	r.publishPreparation(p, p.status)
+	r.releasePreparation(p, "released", "", true)
 	r.shutdownWG.Wait()
-	var failed proto.PreparationStatusPayload
-	if len(sender) != 1 || (<-sender).DecodePayload(&failed) != nil || failed.State != "failed" {
-		t.Fatal("confirmed cleanup failure was suppressed")
-	}
-}
-
-// Local read-only preparation uses no native factory. Keep the shared close
-// settlement regression at its owner boundary instead of a retired remote fixture.
-type blockingWorkspacePreparation struct {
-	entered, release chan struct{}
-}
-
-func (p *blockingWorkspacePreparation) Close() error {
-	close(p.entered)
-	<-p.release
-	return nil
-}
-
-func TestReadPreparationReleaseWaitsForClose(t *testing.T) {
-	sender := make(workspaceStatusSender, 4)
-	prepared := &blockingWorkspacePreparation{entered: make(chan struct{}), release: make(chan struct{})}
-	var release sync.Once
-	defer release.Do(func() { close(prepared.release) })
-	ctx, cancel := context.WithCancel(context.Background())
-	defer cancel()
-	timer := time.NewTimer(time.Hour)
-	defer timer.Stop()
-	r := &Router{sender: sender, shutdownCh: make(chan struct{}), log: obslog.Bg()}
-	p := &preparationState{workspaceReadOnly: true, owns: true, prepared: prepared,
-		ctx: ctx, cancel: cancel, timer: timer,
-		status: proto.PreparationStatusPayload{Handle: "reader", Revision: 1, State: "ready"}}
-	r.releasePreparation(p, "released", "", true, true)
-	select {
-	case <-prepared.entered:
-	case <-time.After(time.Second):
-		t.Fatal("close did not start")
-	}
-	r.publishPreparation(p, p.status)
-	if len(sender) != 0 || !p.owns {
-		t.Fatal("release acknowledged before close settled")
-	}
-	release.Do(func() { close(prepared.release) })
+	r.publishPreparation(p, snapshot)
 	r.shutdownWG.Wait()
-	var status proto.PreparationStatusPayload
-	if p.owns || len(sender) != 1 || (<-sender).DecodePayload(&status) != nil || status.State != "released" {
-		t.Fatal("settled close did not release ownership and publish status")
+	var released proto.PreparationStatusPayload
+	if p.owns || len(sender) != 1 || (<-sender).DecodePayload(&released) != nil || released.State != "released" {
+		t.Fatal("stale ready snapshot escaped or settled release was not published")
 	}
 }
diff --git a/apps/daemon/internal/dispatch/workspace_read.go b/apps/daemon/internal/dispatch/workspace_read.go
index 4ef393ae4..d2ef331c7 100644
--- a/apps/daemon/internal/dispatch/workspace_read.go
+++ b/apps/daemon/internal/dispatch/workspace_read.go
@@ -79,7 +79,7 @@ func (r *Router) workspaceResourceLocked(ref proto.AssignmentRef, request proto.
 	}
 	s := r.sessions[request.RunID]
 	if s == nil || s.assignment != ref || s.environmentID != request.EnvironmentID || s.session == nil ||
-		!r.interactionRouteOpenLocked(s) {
+		!r.runRouteOpenLocked(s) {
 		return nil, "resource_unavailable"
 	}
 	if r.localWorkspace != nil {
diff --git a/apps/daemon/internal/dispatch/workspace_write_test.go b/apps/daemon/internal/dispatch/workspace_write_test.go
index 85e74bbd0..7ee243ed0 100644
--- a/apps/daemon/internal/dispatch/workspace_write_test.go
+++ b/apps/daemon/internal/dispatch/workspace_write_test.go
@@ -21,7 +21,7 @@ func localWriterRouter(t *testing.T) (*dispatch.Router, *recSender, proto.Worksp
 	t.Helper()
 	workspace := t.TempDir()
 	environment, session := uuid.NewString(), preparationSessionID
-	binding, err := localworkspace.New(environment, session, workspace)
+	binding, err := localworkspace.NewWithCapabilityDirectory(environment, session, workspace, t.TempDir())
 	if err != nil {
 		t.Fatal(err)
 	}
diff --git a/apps/daemon/internal/localworkspace/binding.go b/apps/daemon/internal/localworkspace/binding.go
index 5ee7fbf31..0ead8710a 100644
--- a/apps/daemon/internal/localworkspace/binding.go
+++ b/apps/daemon/internal/localworkspace/binding.go
@@ -3,11 +3,9 @@ package localworkspace
 import (
 	"errors"
 	"os"
-	"path/filepath"
 	"strings"
 	"sync"
 
-	"github.com/MiniMax-AI/OpenAgentCore/apps/daemon/internal/paths"
 	"github.com/MiniMax-AI/OpenAgentCore/internal/agentcapabilities"
 
 	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
@@ -26,14 +24,6 @@ type Binding struct {
 	capabilityRoot string
 }
 
-func New(environment, session, workspace string) (*Binding, error) {
-	root, err := paths.Root()
-	if err != nil {
-		return nil, err
-	}
-	return newNativeBinding(environment, session, workspace, filepath.Join(root, "capabilities"))
-}
-
 // NewWithCapabilityDirectory freezes paths selected by the Runtime operator.
 func NewWithCapabilityDirectory(environment, session, workspace, directory string) (*Binding, error) {
 	return newNativeBinding(environment, session, workspace, directory)
diff --git a/apps/daemon/internal/localworkspace/binding_test.go b/apps/daemon/internal/localworkspace/binding_test.go
index 6d5bc80a5..b23ea8c0f 100644
--- a/apps/daemon/internal/localworkspace/binding_test.go
+++ b/apps/daemon/internal/localworkspace/binding_test.go
@@ -20,12 +20,11 @@ func testBinding(t *testing.T) (*Binding, proto.PromptRequestPayload) {
 	t.Setenv("OAC_RUNTIME_HOME", private)
 	root := t.TempDir()
 	environment, session := uuid.NewString(), uuid.NewString()
-	b, err := New(environment, session, root)
+	b, err := NewWithCapabilityDirectory(environment, session, root, t.TempDir())
 	if err != nil {
 		t.Fatal(err)
 	}
 	b.networkAccess = "disabled"
-	b.capabilityRoot = t.TempDir()
 	return b, proto.PromptRequestPayload{LocalEnvironment: &proto.LocalEnvironment{ID: environment, NetworkAccess: "disabled", WorkspaceDirectory: "/workspace", CapabilitySources: &agentcapabilities.Input{}}, AgentStateKey: "agents-api-" + session}
 }
 
diff --git a/apps/daemon/internal/localworkspace/capability_preparation_test.go b/apps/daemon/internal/localworkspace/capability_preparation_test.go
index 0d226d55e..dc061b085 100644
--- a/apps/daemon/internal/localworkspace/capability_preparation_test.go
+++ b/apps/daemon/internal/localworkspace/capability_preparation_test.go
@@ -40,12 +40,11 @@ func TestPreparationFreezesLocalContentsAcrossReconnect(t *testing.T) {
 		t.Fatalf("first preparation: %v", err)
 	}
 	writeSourceSkill(t, source, "second")
-	reconnect, err := New(b.environment, b.capabilityIdentity().SessionID, b.workspace)
+	reconnect, err := NewWithCapabilityDirectory(b.environment, b.capabilityIdentity().SessionID, b.workspace, b.capabilityRoot)
 	if err != nil {
 		t.Fatal(err)
 	}
 	reconnect.networkAccess = b.networkAccess
-	reconnect.capabilityRoot = b.capabilityRoot
 	again, err := reconnect.Prepare(t.Context(), configured)
 	if err != nil || len(again.LocalEnvironment.Skills) != 1 {
 		t.Fatalf("reconnection: %v", err)
@@ -206,11 +205,11 @@ func TestPreparationFreezesToolOnlyEnvironmentAcrossReconnect(t *testing.T) {
 			if err := os.WriteFile(source, []byte(`{"LOCAL_ONLY":"changed"}`), 0600); err != nil {
 				t.Fatal(err)
 			}
-			reconnect, err := New(b.environment, b.capabilityIdentity().SessionID, b.workspace)
+			reconnect, err := NewWithCapabilityDirectory(b.environment, b.capabilityIdentity().SessionID, b.workspace, b.capabilityRoot)
 			if err != nil {
 				t.Fatal(err)
 			}
-			reconnect.networkAccess, reconnect.capabilityRoot = b.networkAccess, b.capabilityRoot
+			reconnect.networkAccess = b.networkAccess
 			if _, err := reconnect.Prepare(t.Context(), configured); err != nil {
 				t.Fatal(err)
 			}
diff --git a/apps/daemon/internal/paths/paths.go b/apps/daemon/internal/paths/paths.go
index 6c835ae3d..accdd85c6 100644
--- a/apps/daemon/internal/paths/paths.go
+++ b/apps/daemon/internal/paths/paths.go
@@ -88,12 +88,3 @@ func LogFile(profile string) (string, error) {
 	}
 	return filepath.Join(dir, "connect.log"), nil
 }
-
-// SessionsFile returns the absolute path to sessions.json.
-func SessionsFile(profile string) (string, error) {
-	dir, err := ProfileDir(profile)
-	if err != nil {
-		return "", err
-	}
-	return filepath.Join(dir, "sessions.json"), nil
-}
diff --git a/apps/daemon/internal/paths/paths_test.go b/apps/daemon/internal/paths/paths_test.go
index 7f4d8fa9e..cd6fc605f 100644
--- a/apps/daemon/internal/paths/paths_test.go
+++ b/apps/daemon/internal/paths/paths_test.go
@@ -75,10 +75,9 @@ func TestProfileDirAndFiles(t *testing.T) {
 	}
 
 	cases := map[string]func(string) (string, error){
-		"auth.json":     paths.AuthFile,
-		"connect.pid":   paths.PIDFile,
-		"connect.log":   paths.LogFile,
-		"sessions.json": paths.SessionsFile,
+		"auth.json":   paths.AuthFile,
+		"connect.pid": paths.PIDFile,
+		"connect.log": paths.LogFile,
 	}
 	for filename, fn := range cases {
 		got, err := fn("test")
diff --git a/apps/daemon/internal/wireconformance/wire_test.go b/apps/daemon/internal/wireconformance/wire_test.go
index 22667ed26..6e9bb9394 100644
--- a/apps/daemon/internal/wireconformance/wire_test.go
+++ b/apps/daemon/internal/wireconformance/wire_test.go
@@ -156,10 +156,7 @@ func connectRuntime(t *testing.T, peer *corePeer, setupErr error) *runtimeSide {
 	peer.accept(t)
 	rt := &runtimeSide{conn: conn, executor: &controlledExecutor{turn: make(chan *controlledTurn, 1)}, stopped: make(chan struct{})}
 	kinds := agent.NewRegistry()
-	kinds.RegisterKind(proto.SupportedAgentKind{Kind: prototest.HarnessKind, Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{EnvironmentNone: proto.CapabilitySupported})},
-		prototest.ModelConfiguration(), func(context.Context, proto.PromptRequestPayload, chan<- proto.Envelope) (agent.Session, error) {
-			return nil, errors.New("prepared execution must not use the direct Session factory")
-		})
+	kinds.RegisterKind(proto.SupportedAgentKind{Kind: prototest.HarnessKind, Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{EnvironmentNone: proto.CapabilitySupported})}, prototest.ModelConfiguration())
 	kinds.RegisterExecutor(prototest.HarnessKind, func(context.Context, proto.PromptRequestPayload) (agent.Executor, error) {
 		return rt.executor, setupErr
 	})
diff --git a/apps/daemon/testdata/onboarding/main.go b/apps/daemon/testdata/onboarding/main.go
index 5dbb2bdc3..783c5220e 100644
--- a/apps/daemon/testdata/onboarding/main.go
+++ b/apps/daemon/testdata/onboarding/main.go
@@ -164,9 +164,7 @@ func run() error {
 	h := &harness{history: map[string]string{}}
 	registry.RegisterKind(proto.SupportedAgentKind{Kind: "mcode", Available: true, Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{
 		Streaming: proto.CapabilitySupported, Steering: proto.CapabilitySupported, DurableTurns: proto.CapabilitySupported, DurableInputReceipts: proto.CapabilitySupported, ExecutionControls: proto.CapabilitySupported, ToolObservations: proto.CapabilitySupported, SubagentControl: proto.CapabilitySupported, EnvironmentNone: proto.CapabilitySupported,
-	})}, mcode.Configuration(), func(context.Context, proto.PromptRequestPayload, chan<- proto.Envelope) (agent.Session, error) {
-		return nil, errors.New("fixture execution requires an Executor")
-	})
+	})}, mcode.Configuration())
 	registry.RegisterExecutor("mcode", h.prepare)
 	sink := &sender{encoder: json.NewEncoder(os.Stdout)}
 	router, err := dispatch.New(dispatch.Config{Registry: registry, Sender: sink, Log: slog.New(slog.NewTextHandler(io.Discard, nil))})
diff --git a/apps/web/DESIGN.md b/apps/web/DESIGN.md
index 64bb19dd3..86c08ae95 100644
--- a/apps/web/DESIGN.md
+++ b/apps/web/DESIGN.md
@@ -402,7 +402,7 @@ A failed action whose outcome needs a decision (a sandbox change with no answer,
 A local-only installation has the same amber notice on Overview, Nodes and System: other machines cannot connect, followed by Core's configuration path and apply command as copyable values. If Core has no configuration snapshot, state that those instructions are unavailable; never fill in a path or command. Add node is disabled with its reason beside the action, and Getting started leaves its first step to do with the address fix visible. A pending or failed installation read cannot complete that step; a failed read shows Unknown and Retry.
 
 ### Onboarding
-Signing in and the console tour share one frame: a dark stage on the left (always dark, whatever the theme) and the task panel on the right, which follows the theme. The stage is the product's one authored moment: a flickering indigo dot grid under slow light rays (Magic UI's flickering grid and light rays), Core as the OpenAgentCore mark on a tile with a travelling border beam, and two orbits of Agents, Sessions, Skills, Vaults, files, templates and machines around it; the OpenAgentCore mark is itself nodes on a ring. Brand copy sits bottom-left in solid ink; it is a paragraph, not a heading, because the panel's title names the task. Signing in asks for one thing, the deployment's Core key, in a single password field; the default key location and a copyable read command stay visible beneath it, with a reminder to substitute a custom installation directory. The key’s authority stays in a help tip. A refused key, too many attempts or an unavailable console is an error beside the field. Signing in opens the console on the Overview. The optional tour has three chapters — Monitor, Resources, Platform — whose stage shows a real dark screenshot of those pages, tilted towards the panel; it takes the place of the console until its last button, Skip or Escape, and then returns the focus to the control that opened it. Entering the console or the tour, and leaving the tour, happen inside a View Transition: the old page dissolves forward and the new one is revealed in a circle growing from the pressed button. With reduced motion the orbits hold their places, the grid is a still frame and no transition runs.
+Signing in and the console tour share one frame: a dark stage on the left (always dark, whatever the theme) and the task panel on the right, which follows the theme. The stage is the product's one authored moment: a flickering indigo dot grid under slow light rays (Magic UI's flickering grid and light rays), Core as the OpenAgentCore mark on a tile with a travelling border beam, and two orbits of Agents, Sessions, Skills, Vaults, files, templates and machines around it; the OpenAgentCore mark is itself nodes on a ring. Brand copy sits bottom-left in solid ink; it is a paragraph, not a heading, because the panel's title names the task. Signing in asks for one thing, the deployment's Core key, in a single password field; a copyable Docker Compose command to read the key stays visible beneath it, with a reminder to substitute a custom installation directory. The key’s authority stays in a help tip. A refused key, too many attempts or an unavailable console is an error beside the field. Signing in opens the console on the Overview. The optional tour has three chapters — Monitor, Resources, Platform — whose stage shows a real dark screenshot of those pages, tilted towards the panel; it takes the place of the console until its last button, Skip or Escape, and then returns the focus to the control that opened it. Entering the console or the tour, and leaving the tour, happen inside a View Transition: the old page dissolves forward and the new one is revealed in a circle growing from the pressed button. With reduced motion the orbits hold their places, the grid is a still frame and no transition runs.
 
 ### Getting started
 The first card on the Overview while any step is to do: a card header ("Getting started", "n of 4 done", a help tip, then a ghost Take the tour button and an icon button that hides it) over four rows split by Faint Rules. Each row has a 22px numbered ring (a check on the tile wash when done), a 13px/600 title over one 12.5px Graphite line, a status dot (Done in green, To do in Pencil, Checking pending, Unknown for a failed read) and one outline action while the step is to do: Set up sandboxes, Add node, Open Nodes or Open sandbox backend; Open System; Create project (which continues to the new project's first key) or Issue key; See how to call (the newest active project, preferring one with an active key), or Projects and keys without an active project. Add node, Create project and Issue key open their page with the dialog already open; Open System brings the Default model provider section to the top of the page body and focuses the default harness's Set or Replace; See how to call opens the project and, once its keys, usage and address are read, brings its How to call heading to the top of the page body, focused. Only the page body scrolls; the page header stays. Every step done turns it into one line, "You're set", with Take the tour and Dismiss; it stays, through the tour, until dismissed, and the checklist does not come back on its own. The choice is kept per installation in the browser, also while the deployment cannot be read; Show Getting started, a quiet row above the sidebar's account controls, opens it again at any time.
diff --git a/apps/web/PRODUCT.md b/apps/web/PRODUCT.md
index 2aa72c28c..090ca06fd 100644
--- a/apps/web/PRODUCT.md
+++ b/apps/web/PRODUCT.md
@@ -22,7 +22,7 @@ The console runs beside the administrator's own Core, with execution, files and
 
 ## Operating Context
 
-- Paired console (`services/web`): the administrator signs in with the deployment's Core key, the administration credential the installer writes to `secrets/core.key` under the installation directory (by default `~/.oac/core/secrets/core.key`; keeping and rotating it is described in [Core key](../../docs/getting-started/operations.md#core-key)). There are no console accounts or usernames. Sign-in shows the default file location and a copyable `cat ~/.oac/core/secrets/core.key` command for the Core host, with a reminder to substitute a custom installation directory. The browser sends the key only to sign in and keeps only the session cookie; the console server holds the Core key and forwards the Web API (`/core/v1/**`, including sandbox administration under `/core/v1/sandbox/**`). The console never calls `/v1`.
+- Paired console (`services/web`): the administrator signs in with the deployment's [Core key](../../docs/getting-started/operations.md#core-key). Sign-in shows a copyable Docker Compose command to read the key on the Core host, with a reminder to substitute a custom installation directory. The browser sends the key only to sign in and keeps only the session cookie; the console server holds the Core key and forwards the Web API (`/core/v1/**`, including sandbox administration under `/core/v1/sandbox/**`). The console never calls `/v1`.
 - The Core key is not an Agents API identity and cannot call `/v1`. An administrator who wants to call the Agents API issues a project API key like any other caller.
 - `/console/config` reports the node installer (`node_installer`, `node_installer_sha256`), offered only with a 64-hex digest. Native self-hosted installation does not depend on this endpoint. It also lists the providers it has node files for (`node_artifacts`); without the deployment's provider, Add node says so and issues no command. Signing in grants administration, sandbox administration included.
 - Chinese and English UI; light and dark themes; reduced motion honored.
diff --git a/apps/web/e2e/access.spec.ts b/apps/web/e2e/access.spec.ts
index 41149ef97..f8d48a28d 100644
--- a/apps/web/e2e/access.spec.ts
+++ b/apps/web/e2e/access.spec.ts
@@ -18,11 +18,11 @@ test("signs in with the Core key, keeps it out of the browser, and signs out and
   await page.goto("/");
 
   await expect(page.getByRole("heading", { name: "Sign in to OpenAgentCore" })).toBeVisible();
-  await expect(page.getByText("cat ~/.oac/core/secrets/core.key", { exact: true })).toBeVisible();
+  await expect(page.getByText('docker compose -f "$HOME/.oac/core/compose.yaml" exec -T web oac-web core-key', { exact: true })).toBeVisible();
   await expect(page.getByText("For a custom installation directory, replace the path in this command.")).toBeVisible();
   await page.context().grantPermissions(["clipboard-read", "clipboard-write"]);
   await page.getByRole("button", { name: "Copy key read command" }).click();
-  expect(await page.evaluate(() => navigator.clipboard.readText())).toBe("cat ~/.oac/core/secrets/core.key");
+  expect(await page.evaluate(() => navigator.clipboard.readText())).toBe('docker compose -f "$HOME/.oac/core/compose.yaml" exec -T web oac-web core-key');
   await signIn(page, "not-the-core-key");
   await expect(page.getByRole("alert")).toHaveText("This Core key is not correct. Check it and try again.");
   await signIn(page, FIXTURE_CORE_KEY);
diff --git a/apps/web/src/features/first-run/ConsoleAccess.tsx b/apps/web/src/features/first-run/ConsoleAccess.tsx
index d9ef1f408..5e561f330 100644
--- a/apps/web/src/features/first-run/ConsoleAccess.tsx
+++ b/apps/web/src/features/first-run/ConsoleAccess.tsx
@@ -12,13 +12,6 @@ import { withTransition } from "../onboarding/view-transition";
 import { changeConsoleAuth, ConsoleAuthError, readConsoleAuth, type ConsoleAuth } from "./auth";
 import "./console-access.css";
 
-/**
- * Where the installer writes the Core key: its file inside the installation
- * directory, and that file under the default installation directory. The
- * visible sign-in instructions name both; the actual custom path is not public.
- */
-const CORE_KEY_LOCATION = { file: "secrets/core.key", defaultPath: "~/.oac/core/secrets/core.key" } as const;
-
 const ConsoleAccountContext = createContext<{ logout: () => Promise<void> } | null>(null);
 export const useConsoleAccount = () => useContext(ConsoleAccountContext);
 
@@ -146,8 +139,8 @@ function CoreKeyForm({ onAuthenticated }: {
         readOnly={busy} aria-invalid={error ? true : undefined} aria-describedby={`${id}-location${error ? ` ${id}-error` : ""}`} />
     </div>
     <div className="console-key-location" id={`${id}-location`}>
-      <p>{t("The installer saved the key in {{file}} inside the installation directory. On the Core host, read the default location with:", CORE_KEY_LOCATION)}</p>
-      <CopyableId id={`cat ${CORE_KEY_LOCATION.defaultPath}`} label={t("Copy key read command")} />
+      <p>{t("On the Core host, run this command to read the Core key:")}</p>
+      <CopyableId id={'docker compose -f "$HOME/.oac/core/compose.yaml" exec -T web oac-web core-key'} label={t("Copy key read command")} />
       <p>{t("For a custom installation directory, replace the path in this command.")}</p>
     </div>
     {error ? <p className="console-auth-error" id={`${id}-error`} role="alert">{error}</p> : null}
diff --git a/apps/web/src/i18n/locales/en/core-errors.ts b/apps/web/src/i18n/locales/en/core-errors.ts
index 3c78ff8a6..802d3768f 100644
--- a/apps/web/src/i18n/locales/en/core-errors.ts
+++ b/apps/web/src/i18n/locales/en/core-errors.ts
@@ -1,5 +1,5 @@
 export const coreErrors = {
-  "invalid_admin_key": "The console's Core key was rejected. Update secrets/core.key on the Core host and run oac apply.",
+  "invalid_admin_key": "The console's Core key was rejected. Rotate it on the Core host, then sign in again.",
   "console_sign_in_required": "Sign in to the console again.",
   "console_origin_rejected": "Open the console at its configured address.",
   "console_request_invalid": "The console request was rejected. Reload the page.",
diff --git a/apps/web/src/i18n/locales/zh-CN/core-errors.ts b/apps/web/src/i18n/locales/zh-CN/core-errors.ts
index 1d7fe0ade..fb30419dd 100644
--- a/apps/web/src/i18n/locales/zh-CN/core-errors.ts
+++ b/apps/web/src/i18n/locales/zh-CN/core-errors.ts
@@ -1,5 +1,5 @@
 export const coreErrors = {
-  "invalid_admin_key": "控制台的 Core Key 被拒绝。请更新 Core 主机上的 secrets/core.key，再运行 oac apply。",
+  "invalid_admin_key": "控制台的 Core Key 被拒绝。请在 Core 主机上轮换密钥，然后重新登录。",
   "console_sign_in_required": "请重新登录控制台。",
   "console_origin_rejected": "请通过配置的地址打开控制台。",
   "console_request_invalid": "控制台请求被拒绝，请重新加载页面。",
diff --git a/apps/web/src/lib/console-auth-strings.ts b/apps/web/src/lib/console-auth-strings.ts
index c2c8afdf1..c6490daef 100644
--- a/apps/web/src/lib/console-auth-strings.ts
+++ b/apps/web/src/lib/console-auth-strings.ts
@@ -4,8 +4,8 @@ export const consoleAuthChinese = {
   "Core key": "Core Key",
   "The Core key is an administration credential: it cannot call the /v1 Agents API, and the console never keeps it in your browser.":
     "Core Key 是管理凭据：不能调用 /v1 Agents API，控制台也不会把它保存在你的浏览器里。",
-  "The installer saved the key in {{file}} inside the installation directory. On the Core host, read the default location with:":
-    "安装器将 key 保存在安装目录下的 {{file}} 中。在 Core 主机上运行以下命令可读取默认位置：",
+  "On the Core host, run this command to read the Core key:":
+    "在 Core 主机上运行以下命令，读取 Core Key：",
   "Copy key read command": "复制 key 读取命令",
   "For a custom installation directory, replace the path in this command.": "如果使用了自定义安装目录，请替换命令中的路径。",
   "Sign in": "登录",
diff --git a/contracts/agents-api/core-errors.md b/contracts/agents-api/core-errors.md
index b8eddd89d..00be4d1c5 100644
--- a/contracts/agents-api/core-errors.md
+++ b/contracts/agents-api/core-errors.md
@@ -96,7 +96,7 @@ The [Session and Turn diagnostics reads](./session-diagnostics.md) return these
 | `execution_interrupted` | Core execution interrupted |
 | `delivery_unconfirmed` | `delivery_unknown`, `input_outcome_unknown`, `cancel_unconfirmed`, `cancel_outcome_unavailable`, `function_result_unconfirmed` |
 | `input_rejected` | `invalid_input`, `input_not_applied`, `message_input_unsupported`, and the exact steering outcomes `input_invalid_input`, `input_run_inactive`, `input_input_conflict`, `input_input_limit`, `input_unsupported`, `input_rejected`, `input_not_ready`, `input_busy` |
-| `executor_protocol_error` | `invalid_executor_result`, `interaction_not_supported`, `execution_state_unavailable`, `execution_state_changed`, `function_call_invalid`, `function_result_invalid` |
+| `executor_protocol_error` | `invalid_executor_result`, `execution_state_unavailable`, `execution_state_changed`, `function_call_invalid`, `function_result_invalid` |
 | `core_storage_failed` | `event_persistence_failed`, `artifact_capture_failed` |
 | `internal_error` | Unknown or malformed outcome; no raw value is returned |
 | `environment_connection_timeout` | Initial input connection deadline expired |
diff --git a/contracts/agents-api/core.openapi.yaml b/contracts/agents-api/core.openapi.yaml
index 9a74d1381..c3412ffd4 100644
--- a/contracts/agents-api/core.openapi.yaml
+++ b/contracts/agents-api/core.openapi.yaml
@@ -1458,6 +1458,10 @@ definitions:
       service_tier:
         enum:
           - auto
+          - default
+          - flex
+          - priority
+          - fast
         type: string
       text:
         $ref: '#/definitions/v1.TextConfig'
@@ -1466,13 +1470,13 @@ definitions:
           type: object
         type: array
       x_agents_core:
-        allOf:
-          - $ref: '#/definitions/v1.AgentsCore'
-        x-nullable: true
+        $ref: '#/definitions/v1.AgentsCore'
     required:
       - id
+      - instructions
       - model
       - multi_agent
+      - name
       - reasoning
       - service_tier
       - text
@@ -1481,8 +1485,6 @@ definitions:
   v1.AgentDeleted:
     properties:
       deleted:
-        enum:
-          - true
         type: boolean
       id:
         type: string
@@ -1546,8 +1548,8 @@ definitions:
         x-nullable: true
       type:
         enum:
-          - static_bearer
           - mcp_oauth
+          - static_bearer
         type: string
     required:
       - mcp_server_url
@@ -1588,7 +1590,9 @@ definitions:
         type: string
     required:
       - data
+      - first_id
       - has_more
+      - last_id
       - object
     type: object
   v1.EnvironmentInstallation:
@@ -1684,6 +1688,7 @@ definitions:
       - created_at
       - files
       - id
+      - name
       - network
       - object
       - packages
@@ -1726,7 +1731,9 @@ definitions:
         type: string
     required:
       - data
+      - first_id
       - has_more
+      - last_id
       - object
     type: object
   v1.ExecutionHarnessConfigSelection:
@@ -1794,7 +1801,9 @@ definitions:
   v1.Item:
     properties:
       action:
-        $ref: '#/definitions/v1.WebSearchAction'
+        allOf:
+          - $ref: '#/definitions/v1.WebSearchAction'
+        x-nullable: true
       agent_id:
         type: string
       arguments: {}
@@ -1808,18 +1817,25 @@ definitions:
         type: array
       cwd:
         type: string
+        x-nullable: true
       duration_ms:
         type: integer
-      error: {}
+        x-nullable: true
+      error:
+        x-nullable: true
       exit_code:
         type: integer
+        x-nullable: true
       id:
         type: string
+        x-nullable: true
       model:
         type: string
+        x-nullable: true
       name:
         type: string
-      output: {}
+      output:
+        x-nullable: true
       phase:
         enum:
           - commentary
@@ -1828,6 +1844,7 @@ definitions:
         x-nullable: true
       reasoning_effort:
         type: string
+        x-nullable: true
       recipient_agent_id:
         type: string
       recipient_agent_ids:
@@ -1847,9 +1864,10 @@ definitions:
         enum:
           - in_progress
           - completed
-          - failed
           - incomplete
+          - failed
         type: string
+        x-nullable: true
       summary:
         items:
           $ref: '#/definitions/v1.SummaryText'
@@ -1859,13 +1877,13 @@ definitions:
       type:
         enum:
           - message
-          - command_execution
-          - mcp_call
+          - reasoning
           - function_call
           - function_call_output
-          - web_search_call
-          - reasoning
           - agent_message
+          - mcp_call
+          - web_search_call
+          - command_execution
           - create_subagent_call
           - send_subagent_input_call
           - resume_subagent_call
@@ -1889,8 +1907,8 @@ definitions:
       type:
         enum:
           - input_text
-          - output_text
           - input_image
+          - output_text
           - encrypted_content
         type: string
     required:
@@ -1916,7 +1934,9 @@ definitions:
         type: string
     required:
       - data
+      - first_id
       - has_more
+      - last_id
       - object
     type: object
   v1.ModelConfigurationInput:
@@ -1997,6 +2017,7 @@ definitions:
         x-nullable: true
     required:
       - enabled
+      - max_concurrent_subagents
     type: object
   v1.OAuthCredentialRefresh:
     properties:
@@ -2014,6 +2035,8 @@ definitions:
         $ref: '#/definitions/v1.OAuthEndpointAuth'
     required:
       - client_id
+      - resource
+      - scope
       - token_endpoint
       - token_endpoint_auth
     type: object
@@ -2038,9 +2061,21 @@ definitions:
   v1.Reasoning:
     properties:
       effort:
+        enum:
+          - none
+          - minimal
+          - low
+          - medium
+          - high
+          - xhigh
+          - max
         type: string
         x-nullable: true
       summary:
+        enum:
+          - concise
+          - detailed
+          - auto
         type: string
         x-nullable: true
     type: object
@@ -2552,7 +2587,7 @@ definitions:
           - fast
         type: string
       text:
-        $ref: '#/definitions/v1.SavedAgentText'
+        $ref: '#/definitions/v1.TextConfig'
       tools:
         items:
           type: object
@@ -2560,15 +2595,15 @@ definitions:
       updated_at:
         type: integer
       x_agents_core:
-        allOf:
-          - $ref: '#/definitions/v1.SavedAgentCore'
-        x-nullable: true
+        $ref: '#/definitions/v1.SavedAgentCore'
     required:
       - created_at
       - id
+      - instructions
       - metadata
       - model
       - multi_agent
+      - name
       - object
       - reasoning
       - service_tier
@@ -2609,35 +2644,11 @@ definitions:
         type: string
     required:
       - data
+      - first_id
       - has_more
+      - last_id
       - object
     type: object
-  v1.SavedAgentText:
-    properties:
-      format:
-        $ref: '#/definitions/v1.SavedAgentTextFormat'
-      verbosity:
-        enum:
-          - low
-          - medium
-          - high
-        type: string
-    required:
-      - format
-      - verbosity
-    type: object
-  v1.SavedAgentTextFormat:
-    properties:
-      schema:
-        type: object
-      type:
-        enum:
-          - text
-          - json_schema
-        type: string
-    required:
-      - type
-    type: object
   v1.Session:
     properties:
       agent:
@@ -2686,12 +2697,14 @@ definitions:
       - agent
       - created_at
       - environment
+      - error
       - id
       - last_active_at
       - metadata
       - object
       - required_actions
       - status
+      - usage
       - vault_ids
     type: object
   v1.SessionArtifact:
@@ -2759,7 +2772,9 @@ definitions:
         type: string
     required:
       - data
+      - first_id
       - has_more
+      - last_id
       - object
     type: object
   v1.SessionCore:
@@ -2811,8 +2826,8 @@ definitions:
       type:
         enum:
           - none
-          - self_hosted
           - openai_hosted
+          - self_hosted
         type: string
       workspace_directory:
         type: string
@@ -2868,7 +2883,9 @@ definitions:
         type: string
     required:
       - data
+      - first_id
       - has_more
+      - last_id
       - object
     type: object
   v1.Skill:
@@ -2933,7 +2950,9 @@ definitions:
         type: string
     required:
       - data
+      - first_id
       - has_more
+      - last_id
       - object
     type: object
   v1.SkillVersion:
@@ -3001,19 +3020,19 @@ definitions:
         type: string
     required:
       - data
+      - first_id
       - has_more
+      - last_id
       - object
     type: object
   v1.SourceFile:
     properties:
       bytes:
-        minimum: 0
         type: integer
       created_at:
         type: integer
       expires_at:
         type: integer
-        x-nullable: true
       filename:
         type: string
       id:
@@ -3024,15 +3043,23 @@ definitions:
         type: string
       purpose:
         enum:
+          - assistants
+          - assistants_output
+          - batch
+          - batch_output
+          - fine-tune
+          - fine-tune-results
+          - vision
           - user_data
         type: string
       status:
         enum:
+          - uploaded
           - processed
+          - error
         type: string
       status_details:
         type: string
-        x-nullable: true
     required:
       - bytes
       - created_at
@@ -3065,19 +3092,17 @@ definitions:
         type: array
       first_id:
         type: string
-        x-nullable: true
       has_more:
         type: boolean
       last_id:
         type: string
-        x-nullable: true
       object:
-        enum:
-          - list
         type: string
     required:
       - data
+      - first_id
       - has_more
+      - last_id
       - object
     type: object
   v1.SummaryText:
@@ -3179,11 +3204,16 @@ definitions:
         x-nullable: true
     required:
       - agent_id
+      - completed_at
       - created_at
+      - error
       - id
       - object
       - session_id
+      - started_at
       - status
+      - subagent_id
+      - usage
     type: object
   v1.TurnError:
     properties:
@@ -3232,7 +3262,9 @@ definitions:
         type: string
     required:
       - data
+      - first_id
       - has_more
+      - last_id
       - object
     type: object
   v1.Vault:
@@ -3256,6 +3288,7 @@ definitions:
       - created_at
       - id
       - metadata
+      - name
       - object
     type: object
   v1.VaultDeleted:
@@ -3293,19 +3326,24 @@ definitions:
         type: string
     required:
       - data
+      - first_id
       - has_more
+      - last_id
       - object
     type: object
   v1.WebSearchAction:
     properties:
       pattern:
         type: string
+        x-nullable: true
       queries:
         items:
           type: string
         type: array
+        x-nullable: true
       query:
         type: string
+        x-nullable: true
       type:
         enum:
           - search
@@ -3315,6 +3353,7 @@ definitions:
         type: string
       url:
         type: string
+        x-nullable: true
     required:
       - type
     type: object
diff --git a/contracts/agents-api/go-bindings.json b/contracts/agents-api/go-bindings.json
new file mode 100644
index 000000000..5b5d9253e
--- /dev/null
+++ b/contracts/agents-api/go-bindings.json
@@ -0,0 +1,536 @@
+{
+  "APIError": {
+    "sources": ["#/components/schemas/Error"],
+    "order": ["message", "type", "code", "param"]
+  },
+  "Agent": {
+    "sources": ["#/components/schemas/SessionAgentResource"],
+    "fields": {
+      "x_agents_core": {"type": "*AgentsCore"},
+      "reasoning": {"type": "Reasoning"}
+    },
+    "order": ["x_agents_core", "id", "instructions", "model", "multi_agent", "name", "reasoning", "service_tier", "text", "tools"]
+  },
+  "AgentContent": {
+    "sources": ["#/components/schemas/AgentContentResource"]
+  },
+  "AgentDeleted": {
+    "sources": ["#/components/schemas/DeletedAgentResource"]
+  },
+  "AgentMessageItem": {
+    "sources": ["#/components/schemas/AgentMessageItemResource"]
+  },
+  "CreateAgentRequest": {
+    "sources": ["#/components/schemas/CreateAgentParams"],
+    "fields": {
+      "x_agents_core": {"type": "*SavedAgentCoreInput"},
+      "model": {"type": "*string"},
+      "metadata": {"type": "map[string]*string"},
+      "reasoning": {"type": "*Reasoning"},
+      "text": {"type": "*TextConfigInput"}
+    },
+    "order": ["x_agents_core", "model", "name", "instructions", "metadata", "multi_agent", "reasoning", "service_tier", "text", "tools"]
+  },
+  "CreateSessionRequest": {
+    "sources": ["#/components/schemas/CreateAgentSessionParams"],
+    "fields": {
+      "x_agents_core": {"type": "*SessionExecutionInput"},
+      "environment": {"type": "*Environment"},
+      "input": {"type": "any"},
+      "stream": {"type": "bool"}
+    },
+    "order": ["x_agents_core", "agent", "agent_id", "environment", "input", "metadata", "stream", "vault_ids"]
+  },
+  "CreateSubagentCallItem": {
+    "sources": ["#/components/schemas/CreateSubagentCallItemResource"],
+    "order": ["id", "turn_id", "type", "status", "agent_id", "content", "model", "reasoning_effort"]
+  },
+  "Credential": {
+    "sources": ["#/components/schemas/VaultCredentialResource"],
+    "order": ["id", "vault_id", "name", "object", "auth", "created_at", "updated_at"]
+  },
+  "CredentialAuth": {
+    "sources": ["#/components/schemas/VaultCredentialAuthResource"],
+    "fields": {
+      "expires_at": {"omit": false},
+      "refresh": {"type": "*OAuthCredentialRefresh", "omit": false}
+    }
+  },
+  "CredentialAuthInput": {
+    "sources": ["#/components/schemas/CreateVaultCredentialAuthParam"],
+    "fields": {
+      "mcp_server_url": {"type": "*string"},
+      "refresh": {"type": "*OAuthCredentialRefreshInput"}
+    },
+    "order": ["type", "mcp_server_url", "token", "access_token", "expires_at", "refresh"]
+  },
+  "CredentialAuthReplacement": {
+    "sources": ["#/components/schemas/RotateVaultCredentialAuthParam"],
+    "fields": {
+      "expires_at": {"type": "json.RawMessage"},
+      "refresh": {"type": "*OAuthCredentialRefreshReplacement"}
+    },
+    "order": ["type", "token", "access_token", "expires_at", "refresh"]
+  },
+  "CredentialDeleted": {
+    "sources": ["#/components/schemas/DeletedVaultCredentialResource"],
+    "order": ["id", "deleted", "object"]
+  },
+  "CredentialList": {
+    "sources": ["#/components/schemas/VaultCredentialListResource"],
+    "order": ["object", "data", "has_more", "first_id", "last_id"]
+  },
+  "Environment": {
+    "sources": ["#/components/schemas/EnvironmentParam"],
+    "fields": {
+      "packages": {"type": "*EnvironmentPackages"},
+      "files": {"type": "[]json.RawMessage"},
+      "environment_template_id": {"type": "string"},
+      "workspace_directory": {"type": "string"},
+      "network": {"type": "*EnvironmentNetworkInput"}
+    },
+    "order": ["plugins", "skills", "env", "setup_commands", "packages", "files", "environment_template_id", "type", "workspace_directory", "capability_directories", "network"]
+  },
+  "EnvironmentConnectionAction": {
+    "sources": ["#/components/schemas/SessionRequiredActionResourceEnvironmentConnection"],
+    "order": ["environment_id", "type"]
+  },
+  "EnvironmentFile": {
+    "sources": ["#/components/schemas/EnvironmentFileResource"],
+    "order": ["environment_id", "object", "path", "size_bytes"]
+  },
+  "EnvironmentFileCreateRequest": {
+    "sources": ["#/components/schemas/HostedEnvironmentFileParam"],
+    "fields": {
+      "path": {"type": "*string"}
+    },
+    "order": ["type", "data", "file_id", "path"]
+  },
+  "EnvironmentFileList": {
+    "sources": ["#/components/schemas/EnvironmentFileListResource"]
+  },
+  "EnvironmentInfo": {
+    "sources": ["#/components/schemas/PublicEnvironmentResource"],
+    "order": ["id", "object", "type", "status", "files", "plugins", "skills"]
+  },
+  "EnvironmentNetwork": {
+    "sources": ["#/components/schemas/NetworkPolicyResource"]
+  },
+  "EnvironmentNetworkInput": {
+    "sources": ["#/components/schemas/NetworkPolicyParam"]
+  },
+  "EnvironmentPackages": {
+    "exclude": ["system"],
+    "sources": ["#/components/schemas/EnvironmentPackagesParam"],
+    "fields": {
+      "npm": {"omit": false},
+      "python": {"omit": false}
+    },
+    "order": ["npm", "python"]
+  },
+  "EnvironmentPackagesResponse": {
+    "sources": ["#/components/schemas/EnvironmentPackagesResource"],
+    "order": ["npm", "python", "system"]
+  },
+  "EnvironmentTemplate": {
+    "sources": ["#/components/schemas/EnvironmentTemplateResource"],
+    "order": ["id", "object", "name", "created_at", "updated_at", "capability_directories", "network", "packages", "files", "plugins", "skills"]
+  },
+  "EnvironmentTemplateDeleted": {
+    "sources": ["#/components/schemas/DeletedEnvironmentTemplateResource"]
+  },
+  "EnvironmentTemplateList": {
+    "sources": ["#/components/schemas/EnvironmentTemplateListResource"],
+    "order": ["object", "data", "has_more", "first_id", "last_id"]
+  },
+  "ErrorResponse": {
+    "sources": ["#/components/schemas/ErrorResponse-2"],
+    "fields": {
+      "error": {"type": "APIError"}
+    }
+  },
+  "FunctionCallAction": {
+    "sources": ["#/components/schemas/SessionRequiredActionResourceFunctionCall"],
+    "fields": {
+      "arguments": {"type": "any"}
+    },
+    "order": ["arguments", "call_id", "name", "turn_id", "type"]
+  },
+  "FunctionToolInput": {
+    "sources": ["#/components/schemas/AgentToolConfigParamFunction"],
+    "fields": {
+      "name": {"type": "*string"},
+      "description": {"type": "*string"},
+      "parameters": {"type": "json.RawMessage"},
+      "defer_loading": {"type": "json.RawMessage"}
+    }
+  },
+  "InlineAgent": {
+    "sources": ["#/components/schemas/SessionAgentConfigParam"],
+    "fields": {
+      "x_agents_core": {"type": "*AgentsCore"},
+      "reasoning": {"type": "*Reasoning"},
+      "text": {"type": "*TextConfigInput"}
+    },
+    "order": ["x_agents_core", "model", "instructions", "multi_agent", "reasoning", "service_tier", "text", "tools"]
+  },
+  "InputContent": {
+    "sources": ["#/components/schemas/InputContentParam"]
+  },
+  "InputMessage": {
+    "sources": ["#/components/schemas/InputMessageParam"],
+    "fields": {
+      "type": {"type": "string"}
+    }
+  },
+  "InputTokenDetails": {
+    "sources": ["#/components/schemas/InputTokensDetailsResource"]
+  },
+  "Item": {
+    "sources": ["#/components/schemas/SessionTurnItemResource"],
+    "fields": {
+      "id": {"type": "string"},
+      "status": {"type": "string", "omit": false},
+      "role": {"type": "string"},
+      "phase": {"type": "string"},
+      "content": {"type": "[]ItemContent"},
+      "command": {"type": "string"},
+      "name": {"type": "string"},
+      "call_id": {"type": "string"},
+      "server_label": {"type": "string"},
+      "arguments": {"type": "any"},
+      "output": {"type": "any"},
+      "error": {"type": "any"},
+      "action": {"type": "*WebSearchAction"},
+      "agent_id": {"type": "string"},
+      "sender_agent_id": {"type": "string"},
+      "recipient_agent_id": {"type": "string"}
+    },
+    "order": ["id", "turn_id", "type", "status", "role", "phase", "content", "command", "cwd", "duration_ms", "exit_code", "name", "call_id", "server_label", "arguments", "output", "error", "action", "agent_id", "sender_agent_id", "recipient_agent_id", "recipient_agent_ids", "model", "reasoning_effort", "summary"]
+  },
+  "ItemContent": {
+    "sources": ["#/components/schemas/MessageContentResource", "#/components/schemas/EncryptedContentResource"],
+    "fields": {
+      "image_url": {"type": "string"}
+    }
+  },
+  "ItemList": {
+    "sources": ["#/components/schemas/SessionItemListResource"],
+    "order": ["object", "first_id", "last_id", "data", "has_more"]
+  },
+  "MCPHTTPTransport": {
+    "sources": ["#/components/schemas/PersistedMcpTransportConfigParamHttp"],
+    "fields": {
+      "headers": {"type": "*map[string]string"}
+    }
+  },
+  "MCPTool": {
+    "sources": ["#/components/schemas/AgentToolResourceMcp"],
+    "fields": {
+      "transport": {"type": "MCPHTTPTransport"},
+      "allowed_tools": {"type": "*[]string"}
+    },
+    "order": ["type", "server_label", "transport", "allowed_tools", "connection_origin", "credential_id", "request_metadata", "required"]
+  },
+  "MCPToolInput": {
+    "sources": ["#/components/schemas/AgentToolConfigParamMcp"],
+    "fields": {
+      "server_label": {"type": "*string"},
+      "allowed_tools": {"type": "json.RawMessage", "omit": false},
+      "connection_origin": {"omit": false},
+      "credential_id": {"omit": false},
+      "request_metadata": {"type": "json.RawMessage", "omit": false},
+      "required": {"type": "json.RawMessage", "omit": false}
+    },
+    "order": ["type", "server_label", "transport", "allowed_tools", "connection_origin", "credential_id", "request_metadata", "required"]
+  },
+  "MultiAgentConfig": {
+    "sources": ["#/components/schemas/MultiAgentConfigResource"],
+    "fields": {
+      "max_concurrent_subagents": {"type": "*int"}
+    }
+  },
+  "OAuthCredentialRefresh": {
+    "sources": ["#/components/schemas/McpOauthRefreshResource"],
+    "order": ["client_id", "token_endpoint", "token_endpoint_auth", "resource", "scope"]
+  },
+  "OAuthCredentialRefreshInput": {
+    "sources": ["#/components/schemas/CreateMcpOauthRefreshParam"],
+    "fields": {
+      "client_id": {"type": "*string"},
+      "refresh_token": {"type": "*string"},
+      "token_endpoint": {"type": "*string"},
+      "token_endpoint_auth": {"type": "*OAuthEndpointAuthInput"}
+    },
+    "order": ["client_id", "refresh_token", "token_endpoint", "token_endpoint_auth", "resource", "scope"]
+  },
+  "OAuthCredentialRefreshReplacement": {
+    "sources": ["#/components/schemas/RotateMcpOauthRefreshParam"],
+    "fields": {
+      "scope": {"type": "json.RawMessage"},
+      "token_endpoint_auth": {"type": "*OAuthEndpointAuthReplacement"}
+    }
+  },
+  "OAuthEndpointAuth": {
+    "sources": ["#/components/schemas/McpOauthTokenEndpointAuthResource"]
+  },
+  "OAuthEndpointAuthInput": {
+    "sources": ["#/components/schemas/CreateMcpOauthTokenEndpointAuthParam"]
+  },
+  "OAuthEndpointAuthReplacement": {
+    "sources": ["#/components/schemas/RotateMcpOauthTokenEndpointAuthParam"]
+  },
+  "OutputTokenDetails": {
+    "sources": ["#/components/schemas/OutputTokensDetailsResource"]
+  },
+  "Reasoning": {
+    "sources": ["#/components/schemas/ReasoningParam"]
+  },
+  "ReasoningItem": {
+    "sources": ["#/components/schemas/ReasoningItemResource"],
+    "order": ["id", "turn_id", "type", "status", "summary"]
+  },
+  "RequiredAction": {
+    "sources": ["#/components/schemas/SessionRequiredActionResource"],
+    "fields": {
+      "arguments": {"type": "any"},
+      "call_id": {"type": "string"},
+      "name": {"type": "string"},
+      "turn_id": {"type": "string"},
+      "environment_id": {"type": "string"}
+    },
+    "order": ["type", "arguments", "call_id", "name", "turn_id", "environment_id"]
+  },
+  "SavedAgent": {
+    "sources": ["#/components/schemas/AgentResource"],
+    "embed": {"SavedAgentConfiguration": ["x_agents_core", "model", "name", "instructions", "multi_agent", "reasoning", "service_tier", "text", "tools"]},
+    "order": ["id", "object", "metadata", "created_at", "updated_at"]
+  },
+  "SavedAgentConfiguration": {
+    "sources": ["#/components/schemas/AgentResource"],
+    "fields": {
+      "x_agents_core": {"type": "*SavedAgentCore"},
+      "reasoning": {"type": "Reasoning"}
+    },
+    "exclude": ["id", "object", "created_at", "updated_at", "metadata"],
+    "order": ["x_agents_core", "model", "name", "instructions", "multi_agent", "reasoning", "service_tier", "text", "tools"]
+  },
+  "SavedAgentList": {
+    "sources": ["#/components/schemas/AgentListResource"],
+    "order": ["object", "data", "has_more", "first_id", "last_id"]
+  },
+  "TextConfigInput": {
+    "sources": ["#/components/schemas/TextParam"]
+  },
+  "SendSubagentInputCallItem": {
+    "sources": ["#/components/schemas/SendSubagentInputCallItemResource"],
+    "order": ["id", "turn_id", "type", "status", "sender_agent_id", "recipient_agent_id", "content"]
+  },
+  "Session": {
+    "sources": ["#/components/schemas/SessionResource"],
+    "fields": {
+      "x_agents_core": {"type": "*SessionCore"},
+      "usage": {"type": "*TokenUsage"}
+    },
+    "order": ["x_agents_core", "id", "agent", "created_at", "environment", "error", "last_active_at", "metadata", "object", "required_actions", "status", "usage", "vault_ids"]
+  },
+  "SessionArtifact": {
+    "sources": ["#/components/schemas/SessionArtifactResource"],
+    "order": ["id", "created_at", "environment_id", "object", "path", "session_id", "size_bytes", "turn_id"]
+  },
+  "SessionArtifactDeleted": {
+    "sources": ["#/components/schemas/DeletedSessionArtifactResource"]
+  },
+  "SessionArtifactList": {
+    "sources": ["#/components/schemas/SessionArtifactListResource"],
+    "order": ["object", "first_id", "last_id", "data", "has_more"]
+  },
+  "SessionDeleted": {
+    "sources": ["#/components/schemas/DeletedSessionResource"],
+    "order": ["id", "deleted", "object"]
+  },
+  "SessionEnvironment": {
+    "sources": ["#/components/schemas/EnvironmentResource"],
+    "fields": {
+      "id": {"type": "string"},
+      "capability_directories": {"type": "*[]string"},
+      "remote_url": {"type": "string"},
+      "workspace_directory": {"type": "string"},
+      "files": {"type": "*[]json.RawMessage"},
+      "plugins": {"type": "*[]json.RawMessage"},
+      "skills": {"type": "*[]json.RawMessage"}
+    },
+    "order": ["type", "id", "capability_directories", "remote_url", "workspace_directory", "network", "packages", "files", "plugins", "skills"]
+  },
+  "SessionEnvironmentState": {
+    "sources": ["#/components/schemas/SessionEnvironmentStateResource"],
+    "fields": {
+      "error": {"type": "*StreamError"}
+    }
+  },
+  "SessionEvent": {
+    "sources": ["#/components/schemas/SessionEvent"],
+    "fields": {
+      "subagent": {"type": "*Subagent"},
+      "session_id": {"type": "string"},
+      "turn_id": {"type": "string"},
+      "session": {"type": "*Session"},
+      "turn": {"type": "*Turn"},
+      "item": {"type": "*Item"},
+      "item_id": {"type": "string"},
+      "output_index": {"type": "*int32"},
+      "content_index": {"type": "*int"},
+      "part": {"type": "*ItemContent"},
+      "usage": {"type": "*TokenUsage"}
+    },
+    "order": ["subagent", "type", "event_id", "session_id", "turn_id", "session", "turn", "item", "item_id", "output_index", "content_index", "part", "delta", "text", "error", "environment", "usage"]
+  },
+  "SessionInput": {
+    "sources": ["#/components/schemas/SessionInputParam"],
+    "fields": {
+      "call_id": {"type": "string"},
+      "turn_id": {"type": "string"},
+      "error": {"type": "json.RawMessage"},
+      "output": {"type": "any"}
+    },
+    "order": ["type", "input", "call_id", "turn_id", "success", "error", "output"]
+  },
+  "SessionList": {
+    "sources": ["#/components/schemas/SessionListResource"],
+    "order": ["object", "first_id", "last_id", "data", "has_more"]
+  },
+  "Skill": {
+    "sources": ["#/components/schemas/SkillResource"],
+    "order": ["id", "object", "created_at", "name", "description", "default_version", "latest_version"]
+  },
+  "SkillDeleted": {
+    "sources": ["#/components/schemas/DeletedSkillResource"],
+    "order": ["id", "object", "deleted"]
+  },
+  "SkillList": {
+    "sources": ["#/components/schemas/SkillListResource"]
+  },
+  "SkillUpdateRequest": {
+    "sources": ["#/components/schemas/SetDefaultSkillVersionBody"]
+  },
+  "SkillVersion": {
+    "sources": ["#/components/schemas/SkillVersionResource"],
+    "order": ["id", "object", "created_at", "skill_id", "version", "name", "description"]
+  },
+  "SkillVersionDeleted": {
+    "sources": ["#/components/schemas/DeletedSkillVersionResource"],
+    "order": ["id", "object", "version", "deleted"]
+  },
+  "SkillVersionList": {
+    "sources": ["#/components/schemas/SkillVersionListResource"]
+  },
+  "SourceFile": {
+    "sources": ["#/components/schemas/OpenAIFile"],
+    "fields": {
+      "expires_at": {"omit": false},
+      "status_details": {"omit": false}
+    },
+    "order": ["id", "object", "bytes", "created_at", "filename", "purpose", "status", "expires_at", "status_details"]
+  },
+  "SourceFileDeleted": {
+    "sources": ["#/components/schemas/DeleteFileResponse"]
+  },
+  "SourceFileList": {
+    "sources": ["#/components/schemas/ListFilesResponse"],
+    "fields": {
+      "first_id": {"type": "*string"},
+      "last_id": {"type": "*string"}
+    },
+    "order": ["object", "data", "has_more", "first_id", "last_id"]
+  },
+  "StreamError": {
+    "sources": ["#/components/schemas/SessionErrorResource"],
+    "fields": {
+      "code": {"type": "string"},
+      "param": {"omit": true}
+    },
+    "order": ["code", "type", "message", "param"]
+  },
+  "Subagent": {
+    "sources": ["#/components/schemas/SubagentResource"],
+    "order": ["id", "object", "session_id", "parent_agent_id", "opened_at", "closed_at", "name", "instructions", "status"]
+  },
+  "SubagentControlCallItem": {
+    "sources": ["#/components/schemas/ResumeSubagentCallItemResource", "#/components/schemas/InterruptSubagentCallItemResource", "#/components/schemas/CloseSubagentCallItemResource"],
+    "order": ["id", "turn_id", "type", "status", "sender_agent_id", "recipient_agent_id"]
+  },
+  "SubagentList": {
+    "sources": ["#/paths/~1agents~1sessions~1{session_id}~1subagents/get/responses/200/content/application~1json/schema"],
+    "order": ["object", "first_id", "last_id", "data", "has_more"]
+  },
+  "SummaryText": {
+    "sources": ["#/components/schemas/SummaryTextResource"]
+  },
+  "TextConfig": {
+    "sources": ["#/components/schemas/TextResource"]
+  },
+  "TextFormat": {
+    "sources": ["#/components/schemas/TextFormatResource"],
+    "fields": {
+      "schema": {"type": "json.RawMessage"}
+    }
+  },
+  "TokenUsage": {
+    "sources": ["#/components/schemas/TokenUsageResource"]
+  },
+  "Turn": {
+    "sources": ["#/components/schemas/TurnResource"],
+    "fields": {
+      "error": {"type": "*TurnError"},
+      "usage": {"type": "*TokenUsage"}
+    },
+    "order": ["id", "agent_id", "subagent_id", "session_id", "object", "status", "created_at", "started_at", "completed_at", "error", "usage"]
+  },
+  "TurnError": {
+    "sources": ["#/components/schemas/SessionTurnErrorResource"]
+  },
+  "TurnList": {
+    "sources": ["#/components/schemas/SessionTurnListResource"],
+    "order": ["object", "first_id", "last_id", "data", "has_more"]
+  },
+  "UpdateAgentRequest": {
+    "sources": ["#/components/schemas/UpdateAgentParams"],
+    "fields": {
+      "x_agents_core": {"type": "*SavedAgentCoreInput"},
+      "metadata": {"type": "map[string]*string"},
+      "reasoning": {"type": "*Reasoning"},
+      "text": {"type": "*TextConfigInput"}
+    },
+    "order": ["x_agents_core", "model", "name", "instructions", "metadata", "multi_agent", "reasoning", "service_tier", "text", "tools"]
+  },
+  "Vault": {
+    "sources": ["#/components/schemas/VaultResource"],
+    "order": ["id", "object", "created_at", "name", "metadata"]
+  },
+  "VaultDeleted": {
+    "sources": ["#/components/schemas/DeletedVaultResource"],
+    "order": ["id", "deleted", "object"]
+  },
+  "VaultList": {
+    "sources": ["#/components/schemas/VaultListResource"],
+    "order": ["object", "data", "has_more", "first_id", "last_id"]
+  },
+  "WaitForSubagentsCallItem": {
+    "sources": ["#/components/schemas/WaitForSubagentsCallItemResource"],
+    "order": ["id", "turn_id", "type", "status", "sender_agent_id", "recipient_agent_ids"]
+  },
+  "WebSearchAction": {
+    "marshal_union": true,
+    "sources": ["#/components/schemas/WebSearchActionResource"]
+  },
+  "reasoningResponse": {
+    "sources": ["#/components/schemas/ReasoningResource"]
+  },
+  "sessionError": {
+    "sources": ["#/components/schemas/SessionErrorResource"],
+    "fields": {
+      "code": {"type": "string"}
+    },
+    "order": ["code", "type", "message", "param"]
+  }
+}
diff --git a/contracts/agents-api/harness-onboarding.md b/contracts/agents-api/harness-onboarding.md
index c5cd4a2c3..661e4dd47 100644
--- a/contracts/agents-api/harness-onboarding.md
+++ b/contracts/agents-api/harness-onboarding.md
@@ -69,7 +69,6 @@ For example, the Codex adapter keeps its app-server and thread, the Claude adapt
 | `DurableSteerer` | Real implementation on every Turn | Distinguish a complete write from the native application receipt; keep retry identity |
 | `Steerer` | Explicit implementation or Unsupported | Additional non-durable active-Turn input |
 | `FunctionResultSubmitter` | Explicit implementation or Unsupported | Match native call and result identity and acknowledge application |
-| `PermissionResponder`, `UserChoiceResponder` | Explicit implementation or Unsupported | Respond to exact emitted identities; unknown or expired interactions stay distinct from Unsupported |
 | `WorkspaceDirectoryLister`, `WorkspaceWriter` | Explicit on Turn and Executor owners | Use the authorized workspace, confirm access, commit or close, or return the operation's Unsupported error |
 | Neutral messages, images, MCP, structured output and Subagent observations | Explicit capability decisions | Keep each operation's protocol semantics; reject unsupported input before submission |
 
@@ -83,7 +82,7 @@ func (s *Session) SubmitFunctionResult(context.Context, proto.FunctionResultPayl
 }
 ```
 
-The reason is a fixed safe string, never submitted content, a credential or raw native diagnostics. Unsupported guarantees no native side effect and is not a successful empty operation. Installation unavailability, unknown interaction IDs, native failures and uncertain outcomes keep their own errors and ownership. A nil `Turn` still means that no input was submitted and the output stays with the caller; never use it as an Unsupported marker.
+The reason is a fixed safe string, never submitted content, a credential or raw native diagnostics. Unsupported guarantees no native side effect and is not a successful empty operation. Installation unavailability, unknown call IDs, native failures and uncertain outcomes keep their own errors and ownership. A nil `Turn` still means that no input was submitted and the output stays with the caller; never use it as an Unsupported marker.
 
 The wire request carries no working directory. The Runtime checks `local_environment.workspace_directory` against its binding and gives the Harness its bound workspace directory in `LocalEnvironment.WorkspaceRoot`; run the native Harness there.
 
@@ -105,26 +104,26 @@ A Session owns one reusable Executor in its connected Runtime; a Turn owns one i
 
 **Binding.** The Runtime binds its Executor record to the Session, Environment, connection and immutable execution configuration. Resume identity and prior-Turn recovery flags are continuity assertions, not configuration changes. A supplied native identity must match the retained owner, and when existing history is required, recovery never starts a new root. A configuration conflict is an error, not a hot switch. A lost connection retires its owners and handles; old timers, output and cancellation cannot affect their replacements.
 
-**Per-Turn state.** Each Turn gets a fresh wrapper, output channel and receipt state. Steering, function, permission and user-choice interfaces belong to that Turn. Native callbacks capture the originating Turn before asynchronous work, so a late event is never attributed to whichever Turn is active. Native processes, query or transport connections, fixed capability configuration and native session identity belong to the Executor. Do not reset completed `sync.Once` values or reuse an old Turn object.
+**Per-Turn state.** Each Turn gets a fresh wrapper, output channel and receipt state. Steering and function interfaces belong to that Turn. Native callbacks capture the originating Turn before asynchronous work, so a late event is never attributed to whichever Turn is active. Native processes, query or transport connections, fixed capability configuration and native session identity belong to the Executor. Do not reset completed `sync.Once` values or reuse an old Turn object.
 
 **Start.** A nil Turn from `StartTurn` guarantees that no native input was submitted and the output channel was not retained; the Runtime then closes the channel. Once input may have been submitted, return a non-nil Turn even with an error: that Turn owns exactly-once output closure and stays tracked until settlement. Unknown input is never replayed. A definite `executor_unavailable` Start rejection allows one common recovery attempt, only after the previous Executor has been closed and no input was submitted; the Runtime rechecks the same physical peer and the current authorization.
 
-**Cancellation and settlement.** `Turn.Cancel` targets only that Turn and does not close a healthy Executor. `AwaitSettlement` applies after both natural completion and cancellation. Success means output can no longer be written and the Turn's native events, input, functions, interactions and child work have settled. Native completion or cancellation confirmation is independent of resource retirement: closing a transport cannot supply a missing native terminal or operation receipt.
+**Cancellation and settlement.** `Turn.Cancel` targets only that Turn and does not close a healthy Executor. `AwaitSettlement` applies after both natural completion and cancellation. Success means output can no longer be written and the Turn's native events, input, functions and child work have settled. Native completion or cancellation confirmation is independent of resource retirement: closing a transport cannot supply a missing native terminal or operation receipt.
 
 - `Reusable=true` also confirms that the native owner can accept the next Turn. `Reusable=false` requires a reason and a later confirmed Executor close.
 - An error means settlement is unconfirmed and frees neither ownership nor capacity. Caller deadlines stop the wait, not the tracked cleanup. Retry the same cleanup target serially; a failed cleanup blocks replacement and keeps its resource slot.
 - `Executor.Close` confirms resource retirement independently of the Turn outcome: an immutable Turn error must not prevent closing the native transport once its work and output have stopped.
 - Include owned background work in settlement and keep the exact native cleanup target after a failure. Native termination belongs to the adapter; a bulk cleanup acknowledgement alone does not establish quiescence.
-- Every `Session`, including a direct-call factory result, declares `CancellationOutcome`. `Turn` inherits it. The snapshot keeps observed native identity, Usage and output and remains readable after cancellation. Missing evidence stays unset; an empty `DonePayload` means nothing has been observed, not that cancellation succeeded or is unsupported. Reading the snapshot does not wait for settlement.
-- Direct-call `Session.Cancel` requests cancellation; output closure signals teardown. Turn settlement still requires `AwaitSettlement` and any required `Executor.Close`; neither a successful cancellation request nor its snapshot replaces those waits.
+- Every `Session` declares `CancellationOutcome`. `Turn` inherits it. The snapshot keeps observed native identity, Usage and output and remains readable after cancellation. Missing evidence stays unset; an empty `DonePayload` means nothing has been observed, not that cancellation succeeded or is unsupported. Reading the snapshot does not wait for settlement.
+- `Session.Cancel` requests cancellation; output closure signals teardown. Turn settlement still requires `AwaitSettlement` and any required `Executor.Close`; neither a successful cancellation request nor its snapshot replaces those waits.
 
-**What the Runtime does around a Turn.** One output consumer starts before native Start, drains the bounded 64-frame channel and keeps the terminal observation until Start publication, Turn settlement and admitted operation receipts finish. Natural completion never calls Cancel. Input, function and interaction admission close before settlement; operations already admitted hold their barrier through native receipts and outbound acknowledgement. The Runtime sends cancellation to the Turn before waiting on that barrier, because a written input may need a native interrupt to produce its receipt. It joins native settlement, any required confirmed Executor close, output drain and all admitted operations before an applied acknowledgement or reuse, and only then forwards Done or an applied cancellation receipt. A failed Close can report failure while keeping the same Run and outstanding operations for retry; a closed caller wait cannot manufacture an applied input receipt. The Runtime commits native continuity and releases the old Run's admission before publishing Done, since the receiver may start another Turn at once; a late terminal-send failure belongs to the old Run and cannot invalidate a successor that already owns the Executor. Connection shutdown owns transport-loss cleanup. The settlement wait is ten seconds and the receipt send budget five seconds; a timeout is not proof of quiescence.
+**What the Runtime does around a Turn.** One output consumer starts before native Start, drains the bounded 64-frame channel and keeps the terminal observation until Start publication, Turn settlement and admitted operation receipts finish. Natural completion never calls Cancel. Input and function admission close before settlement; operations already admitted hold their barrier through native receipts and outbound acknowledgement. The Runtime sends cancellation to the Turn before waiting on that barrier, because a written input may need a native interrupt to produce its receipt. It joins native settlement, any required confirmed Executor close, output drain and all admitted operations before an applied acknowledgement or reuse, and only then forwards Done or an applied cancellation receipt. A failed Close can report failure while keeping the same Run and outstanding operations for retry; a closed caller wait cannot manufacture an applied input receipt. The Runtime commits native continuity and releases the old Run's admission before publishing Done, since the receiver may start another Turn at once; a late terminal-send failure belongs to the old Run and cannot invalidate a successor that already owns the Executor. Connection shutdown owns transport-loss cleanup. The settlement wait is ten seconds and the receipt send budget five seconds; a timeout is not proof of quiescence.
 
 ## Events, inputs and optional capabilities
 
 Use [`internal/agentdaemon/proto`](https://github.com/MiniMax-AI/OpenAgentCore/tree/main/internal/agentdaemon/proto) for neutral requests, events and receipts. Each Turn emits only its own events with its Run ID, in order, and one terminal outcome. Native IDs and usage are observed, never invented; a missing measurement is unknown, not zero.
 
-Initial input and steering use ordered `proto.MessageInput`. Keep user-message and content order. Text-only adapters reject images through `TextOnly()` instead of dropping them; image adapters translate each part natively and acknowledge an active batch only after all its messages are applied. A successful transport write is distinct from confirmed native application. User-choice answers use the emitted question ID and an array of values; the shared `PromptForUserChoiceDecisionPayload.AnswersFor` validates identity before consuming a pending interaction, so never map answers by header or position. Resume only the exact history bound to the Session; missing, ambiguous or foreign history fails before new model input. Device identity is not native session ownership.
+Initial input and steering use ordered `proto.MessageInput`. Keep user-message and content order. Text-only adapters reject images through `TextOnly()` instead of dropping them; image adapters translate each part natively and acknowledge an active batch only after all its messages are applied. A successful transport write is distinct from confirmed native application. Resume only the exact history bound to the Session; missing, ambiguous or foreign history fails before new model input. Device identity is not native session ownership.
 
 ### Required and extension operations
 
@@ -148,23 +147,21 @@ A Harness that supports the Subagent reads implements the [neutral observation c
 
 ## Register the adapter
 
-Registration is static and requires a build. Export one `agent.Declaration` from `apps/daemon/internal/agent/<kind>/declaration.go`, then add it to `harnessDeclarations` in [`cli/agent_discovery.go`](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/apps/daemon/internal/cli/agent_discovery.go). The declaration contains the kind and complete capability descriptor, the shared model `Configuration` and a `Discover` function. Discovery receives the profile and diagnostic writers, owns native configuration and availability checks, and returns the installed `agent.Runtime` with its descriptor and session and Executor factories. Return nil when the adapter is not configured; return an unavailable descriptor with a session factory when configured prerequisites fail. Keep version gates and factory-selection conditions inside the adapter.
+Registration is static and requires a build. Export one `agent.Declaration` from `apps/daemon/internal/agent/<kind>/declaration.go`, then add it to `harnessDeclarations` in [`cli/agent_discovery.go`](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/apps/daemon/internal/cli/agent_discovery.go). The declaration contains the kind and complete capability descriptor, the shared model `Configuration` and a `Discover` function. Discovery receives the profile and diagnostic writers, owns native configuration and availability checks, and returns the installed `agent.Runtime` with its descriptor, Executor factory and view declaration. Return nil when the adapter is not configured; return an unavailable descriptor without an Executor factory or view when configured prerequisites fail. Keep version gates and factory-selection conditions inside the adapter.
 
-[`cli/agent_registration.go`](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/apps/daemon/internal/cli/agent_registration.go) iterates the discovered runtimes and calls `Registry.Register` from `agent/harness.go`. It verifies that discovery retained the declared kind and installs factories in this order:
+[`cli/agent_registration.go`](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/apps/daemon/internal/cli/agent_registration.go) iterates the discovered runtimes and calls `Registry.Register` from `agent/harness.go`. It verifies that discovery retained the declared kind and registers the Runtime in this order:
 
 | Order | Method | Registers |
 | --- | --- | --- |
-| 1 | `RegisterKind(proto.SupportedAgentKind, harnessconfig.Configuration, agent.Factory)` | Kind, availability, version, `AgentKindCapabilities`, the model configuration declaration and the direct-call factory. It resets the other registrations, so call it first. |
+| 1 | `RegisterKind(proto.SupportedAgentKind, harnessconfig.Configuration)` | Kind, availability, version, `AgentKindCapabilities` and the model configuration declaration. It resets the other registrations, so call it first. |
 | 2 | `RegisterExecutor(kind, agent.ExecutorFactory)` | The Executor and Turn lifecycle used for execution; derives the `Preparation` capability |
 | 3 | `RegisterView(kind, agent.View)` | Optional: the agent-host view declaration from `Runtime.View`. It panics with `ErrInvalidView` when `View.Validate` fails. Its Executor factory validates the model configuration like `RegisterExecutor` and enforces the [gateway rule](#endpoints-and-proxy). |
 
-The direct-call `agent.Factory` delegates to the same Executor implementation.
-
 `Runtime.View` declares how the Harness runs in an agent-host Session view, described in [Run in an agent-host view](#run-in-an-agent-host-view). Every adapter sets it explicitly; `View: nil` means the agent host rejects the kind, and `Registry.ResolveView` returns an error wrapping `ErrUnsupportedOperation`. `TestPublicHarnessContractDeclarations` requires the field in each declaration.
 
 Every `proto.AgentKindCapabilities` field must be explicitly `proto.CapabilitySupported` or `proto.CapabilityUnsupported`, even for an unavailable Harness. `proto.CapabilityUnspecified` is invalid: zero values and omitted fields never mean Unsupported. An installation probe may set an individual field with `proto.CapabilityFromBool`; it must not populate unmentioned or future fields. Availability stays separate in `SupportedAgentKind.Available`. Registration validates the complete declaration before changing the registry, and the wire carries an explicit boolean for every field, so omitted and null fields are invalid. A new field requires a decision in every production declaration. Runtime consumers use `IsSupported()` and reject unsupported requests before native operations; an interface assertion verifies implementation, never support. Every declaration must match the behavior verified for that installation; the [Core–Runtime protocol](../../docs/runtime-protocol.md#capability-declarations) owns how declarations travel and are frozen.
 
-The admission mapping is explicit. `Steering` controls non-durable `Steerer` input. `DurableInputReceipts` controls `DurableSteerer` input and also requires the Turn settlement contract; neither implies the other, and Core's public text profile requires both. `Permissions` qualifies permission and user-choice responses together and requires both native response paths. Workspace declarations describe the authorized resource owner, including the common Runtime workspace implementation. Runtime registration does not grant Core qualification; the service profile does.
+The admission mapping is explicit. `Steering` controls non-durable `Steerer` input. `DurableInputReceipts` controls `DurableSteerer` input and also requires the Turn settlement contract; neither implies the other, and Core's public text profile requires both. Workspace declarations describe the authorized resource owner, including the common Runtime workspace implementation. `WorkspaceReadPreparation` admits `execution_prepare` with `workspace_read_only`. The Runtime readies that preparation itself and serves its reads from the bound local workspace directory without calling the Executor factory, so an adapter declares it only when this kind's Environment workspace is that local directory. Registration does not derive it. Runtime registration does not grant Core qualification; the service profile does.
 
 The runnable test-only example [`testdata/onboarding/main.go`](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/apps/daemon/testdata/onboarding/main.go) registers a text-only synthetic Harness under the `mcode` kind, because Core admits only [catalog](./harness-catalog.md) Harnesses. It shows a Session-owned Executor, fresh Turns, durable steering, cancellation and history binding, and is never shipped.
 
@@ -201,7 +198,7 @@ Run the `engine` and `execution` tests for omission, policy, combination and err
 
 ## Native model configuration
 
-[`internal/harnessconfig/harness.go`](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/harnessconfig/harness.go) owns the shared configuration declaration and pure preparation contract. Each adapter supplies one `Configuration`, in `internal/harnessconfig/<kind>`, to Core's composition and to the Runtime's `RegisterKind`. The direct factory and Executor paths both validate through that declaration before native side effects, and Registry wrappers keep the declaration with the factory. The wire object is `proto.HarnessConfig`. [Model execution](./model-execution.md#native-model-parameters) lists each Harness's accepted fields.
+[`internal/harnessconfig/harness.go`](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/harnessconfig/harness.go) owns the shared configuration declaration and pure preparation contract. Each adapter supplies one `Configuration`, in `internal/harnessconfig/<kind>`, to Core's composition and to the Runtime's `RegisterKind`. The Executor and view paths both validate through that declaration before native side effects, and Registry wrappers keep the declaration with the factory. The wire object is `proto.HarnessConfig`. [Model execution](./model-execution.md#native-model-parameters) lists each Harness's accepted fields.
 
 Every request names a nonempty `model` and a `model_provider`; preparation rejects a request without either, including an explicit null or empty value, before any native side effect. An empty declaration therefore accepts no request. Unknown protocol formats and duplicate protocol declarations fail at registration.
 
@@ -212,7 +209,7 @@ The declaration's ordered `protocols` list is the only source of accepted protoc
 Before starting, record the operation set, expected results, exclusions and stopping conditions. A qualification ends when its declared operations pass; it does not expand to match another Harness's feature list.
 
 1. **Contract tests.** Call `agent/contracttest.TextLifecycle` from a test named `TestSharedTextLifecycle` with the adapter's prepared Executor and a deterministic native fixture; `claudesdk/executor_test.go` is the reference. It checks independent Turn streams, native owner and history continuity, durable write and application receipts, stale cancellation and healthy continuation after cancellation. `make check-runtime-contract` runs it together with the shared wire, gateway, transport and dispatcher tests, the declaration completeness check and each adapter's `TestUnsupportedExtensionsHaveNoNativeEffects`. Adapter tests also cover two ordinary Turns sharing one native process or connection and history, cancellation followed by another Turn, stale cancellation and late events, native exit, cleanup failure, input write and application receipts, unknown outcomes and fresh per-Turn usage, function, input and child-observation state. State whether a fixture is controlled or a real provider.
-2. **Shared integration.** `TestThirdHarnessPublicOnboarding` runs the synthetic Harness through public Session and input admission, Worker device selection, the real WebSocket gateway, the daemon Registry and Router, neutral events and durable terminal projection. It uses a custom immutable `engine.Catalog` in the same `execution.Policy` given to the API handler and the dispatcher, and checks applied input receipts, saved native identity, continuation, cancellation, unsupported optional requests and missing mandatory Runtime support. The fixture has no workspace, MCP, public functions, permissions or user-choice handlers, and its registration stays local to the test. It proves the integration path, not native execution.
+2. **Shared integration.** `TestThirdHarnessPublicOnboarding` runs the synthetic Harness through public Session and input admission, Worker device selection, the real WebSocket gateway, the daemon Registry and Router, neutral events and durable terminal projection. It uses a custom immutable `engine.Catalog` in the same `execution.Policy` given to the API handler and the dispatcher, and checks applied input receipts, saved native identity, continuation, cancellation, unsupported optional requests and missing mandatory Runtime support. The fixture has no workspace, MCP or public functions, and its registration stays local to the test. It proves the integration path, not native execution.
 3. **Real acceptance.** Use the pinned official Python SDK and raw HTTP against Core, a real provider API, the native Harness and a dedicated database. Verify initial execution, a warm follow-up, cancellation and restart with continuation; record native owner identity and same-condition cold and warm timing. For workspace placements also verify Files and Artifacts, workspace identity, that no credentials appear in public responses and that foreign history is rejected. `services/core/tests/official_hosted_functions_native.py` holds the shared function assertions: success and error, native file output and public Artifact bytes, same-history continuation after restart, foreign result rejection and pending-call cancellation. Synthetic or failed runs never count. The opt-in tests below run the pinned-SDK fixtures in `services/core/tests` against a real daemon and model; each runs when `OAC_TEST_OFFICIAL_SDK_PYTHON`, `OAC_TEST_NATIVE_DAEMON_BIN`, `OAC_TEST_NATIVE_PROOF_DIR` and its private options file are set. The options file is a JSON object with exactly `model` and `model_provider` (the fields of `x_agents_core.model_provider`); the test sets it as the deployment default model provider, which the fixtures' `environment: none` Sessions freeze at creation.
 4. **Regression.** Existing Harnesses keep working. Run targeted tests, then `make check`; run `make openapi` after API changes and `make sqlc-generate` after query changes.
 5. **Review.** Follow the [blind review workflow](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/CONTRIBUTING.md#review).
@@ -252,7 +249,7 @@ The daemon's `clirunner` starts every native child in its own Unix process group
 
 Owned output pipes stay readable after the leader exits. Consumers drain stdout and stderr before calling `Wait`, which joins the cached process result and closes the readers. `Done` reports leader reaping and group cleanup signals; it is not a native execution receipt or proof of persisted history. SDK adapters settle each Turn and drain its observations before publishing completion, and Executor close also closes the query and awaits the native child. Process groups are lifecycle supervision, not isolation or containment of descendants that leave the group.
 
-Adapters run native tools unattended with the launching user's permissions: Codex with approval policy `never` and full access, Claude through the adapter's tool callback in native `default` permission mode with the SDK sandbox disabled, and MiniMax with bypassed permissions and its sandbox disabled. Do not add permission profiles, bubblewrap wrappers or native sandbox settings; there is one execution path for every Environment origin. Resource paths are operator configuration, not a permission boundary.
+Adapters run native tools unattended with the launching user's permissions, and a Harness never asks a human. Codex runs with approval policy `never`, under which it settles MCP elicitation itself without reaching the client, and with full access; the adapter also disables its blocking `request_user_input` tool. Claude runs through the adapter's tool callback, which allows or denies without asking, in native `default` permission mode with the SDK sandbox disabled. MiniMax runs with bypassed permissions and its sandbox disabled; the adapter disables `askUser`, advertises no elicitation and answers `session/request_permission` with the ACP `cancelled` outcome, which MiniMax treats as a denial. No native permission or question request reaches Core: a human in the loop goes through a function tool, the Session reads [`requires_action`](./sessions-events.md#session-status) and the application submits the function result. Do not add permission profiles, bubblewrap wrappers or native sandbox settings; there is one execution path for every Environment origin. Resource paths are operator configuration, not a permission boundary.
 
 Network admission follows [Restricted network](./environments.md#restricted-network).
 
diff --git a/contracts/agents-api/index.md b/contracts/agents-api/index.md
index fa4a93fef..88c1f7cfc 100644
--- a/contracts/agents-api/index.md
+++ b/contracts/agents-api/index.md
@@ -9,10 +9,18 @@ Core targets the complete OpenAI Agents API as pinned below ([public API rule](h
 | File | Contents |
 | --- | --- |
 | [upstream.json](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/contracts/agents-api/upstream.json) | The pin: [openai-python](https://github.com/openai/openai-python/tree/d7c41efee1b0802b79f3f88a678ef2052b06e9ce/src/openai/resources/beta/agents) 3.13.0 at commit `d7c41ef`, resources under `beta/agents`, Beta header `agents=v1` |
-| [upstream-routes.json](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/contracts/agents-api/upstream-routes.json), [upstream-fields.json](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/contracts/agents-api/upstream-fields.json) | The 58 method and path pairs and their official fields: 42 operations under `beta/agents`, 5 Files and 11 Skills operations. `scripts/extract-agents-api-upstream.py` extracts them from the pinned SDK; run it with that SDK installed |
-| [openapi.yaml](./openapi.yaml) | Core's public schema, generated by `make openapi` from the route annotations in `services/core/internal/api/` and the wire types in [`v1/`](https://github.com/MiniMax-AI/OpenAgentCore/tree/main/contracts/agents-api/v1) |
+| [upstream/openapi.json](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/contracts/agents-api/upstream/openapi.json) | Unmodified official OpenAPI 3.1 at commit `046a2a0f325bf11f97966f2729219f27281ba71e`, published on 2026-09-10. Its 58 Agents, Vaults, Files and Skills operations match the pinned SDK route set. `upstream.json` records the SHA-256 checksum |
+| [upstream-routes.json](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/contracts/agents-api/upstream-routes.json) | The normalized method/path inventory generated from the official schema |
+| [openapi.yaml](./openapi.yaml) | The official public contract with Core's `x_agents_core` extension on Agent and Session request/response objects |
+| [go-bindings.json](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/contracts/agents-api/go-bindings.json) | Go names, field representations, encoding order and stored projections; it does not define official field membership, enums or constraints |
 
-Contract tests hold Core to the pin: the router and `openapi.yaml` serve exactly the pinned routes (`services/core/internal/api/routing_test.go`, `v1/upstream_contract_test.go`), every query parameter and field is official, and Core-only fields sit only inside `x_agents_core` on Agents and Sessions. Swagger 2.0 cannot express string-or-array unions, so `openapi.yaml` leaves Session `input` and function-result `output` unconstrained; the pinned types and Core's validation define them. Operations and fields newer than the pin wait for a protocol upgrade.
+Run `make openapi` to regenerate the public Go types, route inventory and all three OpenAPI documents. `scripts/generate-public-api.py` reads the checked-in, checksum-verified official source without network access. It selects Agents, Vaults, Files and Skills and follows their schema references, preserving union types, nullability, required fields and constraints. Core's extension types in `v1/` remain authored in Go and are added to the public schema during generation. The internal `/core/v1` and `/api/v1` documents come from handler annotations. `make check-openapi` checks freshness and the generator; it also runs through `make check-go`.
+
+The public contract is the official API plus Core extensions. Standard fields are generated into `v1/official.gen.go`; `go-bindings.json` lists types consumed by Core and overrides only the Go representation or field order that existing storage or custom JSON encoding requires. Unspecified fields follow the official schema; shared shapes use one Go type. Selected discriminated unions also generate JSON serializers to retain required nullable fields for each variant. Other union serializers, request admission and state transitions remain implementation code. Contract tests verify that the public schema preserves the official definitions, extensions remain in `x_agents_core`, and all documents match registered routes. Official-client and raw HTTP tests verify behavior. Schema generation does not qualify an unimplemented feature; the gaps below still apply. Upstream upgrades update the OpenAPI and SDK pins together after comparison and compatibility tests.
+
+The official source and existing service have these recorded differences: Agents authentication errors can return a null `code`; empty Files pages return null `first_id` and `last_id`; File resources can return null `expires_at` and `status_details`. The source declares those fields non-null. The official-client response validator allows null only for these named fields and otherwise validates OpenAPI 3.1 response schemas. Files and Skills operations omit error responses in the source, so those error bodies use the upstream shared `ErrorResponse` schema. [Wire semantics](./wire-semantics.md) and raw HTTP tests qualify service behavior; the published schema retains the official definitions.
+
+Go input projections exclude `packages.system` to preserve its explicit rejection, recorded below. Generation does not enable an unsupported operation or change stored setup validation.
 
 Evidence for a status comes from the pinned official SDK and raw HTTP against the running service, as [CONTRIBUTING](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/CONTRIBUTING.md#compatibility-evidence) requires.
 
diff --git a/contracts/agents-api/openapi.yaml b/contracts/agents-api/openapi.yaml
index 12e691d56..1885da9ed 100644
--- a/contracts/agents-api/openapi.yaml
+++ b/contracts/agents-api/openapi.yaml
@@ -1,5423 +1,19444 @@
-basePath: /v1
-definitions:
-  v1.APIError:
-    properties:
-      code:
-        type: string
-        x-nullable: true
-      message:
-        type: string
-      param:
-        type: string
-        x-nullable: true
-      type:
-        type: string
-    required:
-    - message
-    - type
-    type: object
-  v1.Agent:
-    properties:
-      id:
-        type: string
-      instructions:
-        type: string
-        x-nullable: true
-      model:
-        type: string
-      multi_agent:
-        $ref: '#/definitions/v1.MultiAgentConfig'
-      name:
-        type: string
-        x-nullable: true
-      reasoning:
-        $ref: '#/definitions/v1.Reasoning'
-      service_tier:
-        enum:
-        - auto
-        type: string
-      text:
-        $ref: '#/definitions/v1.TextConfig'
-      tools:
-        items:
-          type: object
-        type: array
-      x_agents_core:
-        allOf:
-        - $ref: '#/definitions/v1.AgentsCore'
-        x-nullable: true
-    required:
-    - id
-    - model
-    - multi_agent
-    - reasoning
-    - service_tier
-    - text
-    - tools
-    type: object
-  v1.AgentContent:
-    properties:
-      encrypted_content:
-        type: string
-      text:
-        type: string
-      type:
-        enum:
-        - output_text
-        - encrypted_content
-        type: string
-    required:
-    - type
-    type: object
-  v1.AgentDeleted:
-    properties:
-      deleted:
-        enum:
-        - true
-        type: boolean
-      id:
-        type: string
-      object:
-        enum:
-        - agent.deleted
-        type: string
-    required:
-    - deleted
-    - id
-    - object
-    type: object
-  v1.AgentsCore:
-    properties:
-      harness:
-        enum:
-        - claude_sdk
-        - codex
-        - mcode
-        type: string
-      harness_config:
-        type: object
-    type: object
-  v1.CreateAgentRequest:
-    properties:
-      instructions:
-        type: string
-        x-nullable: true
-      metadata:
-        additionalProperties:
-          type: string
-        type: object
-        x-nullable: true
-      model:
-        type: string
-      multi_agent:
-        type: object
-        x-nullable: true
-      name:
-        maxLength: 128
-        type: string
-        x-nullable: true
-      reasoning:
-        allOf:
-        - $ref: '#/definitions/v1.Reasoning'
-        x-nullable: true
-      service_tier:
-        enum:
-        - auto
-        - default
-        - flex
-        - priority
-        - fast
-        type: string
-        x-nullable: true
-      text:
-        allOf:
-        - $ref: '#/definitions/v1.SavedAgentTextInput'
-        x-nullable: true
-      tools:
-        items:
-          type: object
-        type: array
-        x-nullable: true
-      x_agents_core:
-        allOf:
-        - $ref: '#/definitions/v1.SavedAgentCoreInput'
-        x-nullable: true
-    required:
-    - model
-    type: object
-  v1.CreateCredentialRequest:
-    properties:
-      auth:
-        $ref: '#/definitions/v1.CredentialAuthInput'
-      name:
-        type: string
-    required:
-    - auth
-    - name
-    type: object
-  v1.CreateEventsRequest:
-    properties:
-      events:
-        items:
-          $ref: '#/definitions/v1.SessionInput'
-        type: array
-    required:
-    - events
-    type: object
-  v1.CreateSessionRequest:
-    properties:
-      agent:
-        $ref: '#/definitions/v1.InlineAgent'
-      agent_id:
-        type: string
-      environment:
-        $ref: '#/definitions/v1.Environment'
-      input:
-        description: |-
-          Input accepts a string or an ordered array of user InputMessage objects.
-          Required for none and streamed creation outside self_hosted; otherwise optional.
-        x-nullable: true
-      metadata:
-        additionalProperties:
-          type: string
-        type: object
-        x-nullable: true
-      stream:
-        default: false
-        type: boolean
-      vault_ids:
-        items:
-          type: string
-        type: array
-      x_agents_core:
-        $ref: '#/definitions/v1.SessionExecutionInput'
-    required:
-    - environment
-    type: object
-  v1.CreateVaultRequest:
-    properties:
-      metadata:
-        additionalProperties:
-          type: string
-        type: object
-        x-nullable: true
-      name:
-        type: string
-    type: object
-  v1.Credential:
-    properties:
-      auth:
-        $ref: '#/definitions/v1.CredentialAuth'
-      created_at:
-        type: integer
-      id:
-        type: string
-      name:
-        type: string
-      object:
-        enum:
-        - vault.credential
-        type: string
-      updated_at:
-        type: integer
-      vault_id:
-        type: string
-    required:
-    - auth
-    - created_at
-    - id
-    - name
-    - object
-    - updated_at
-    - vault_id
-    type: object
-  v1.CredentialAuth:
-    properties:
-      expires_at:
-        type: string
-        x-nullable: true
-      mcp_server_url:
-        type: string
-      refresh:
-        allOf:
-        - $ref: '#/definitions/v1.OAuthCredentialRefresh'
-        x-nullable: true
-      type:
-        enum:
-        - static_bearer
-        - mcp_oauth
-        type: string
-    required:
-    - mcp_server_url
-    - type
-    type: object
-  v1.CredentialAuthInput:
-    properties:
-      access_token:
-        minLength: 1
-        type: string
-      expires_at:
-        type: string
-        x-nullable: true
-      mcp_server_url:
-        type: string
-      refresh:
-        allOf:
-        - $ref: '#/definitions/v1.OAuthCredentialRefreshInput'
-        x-nullable: true
-      token:
-        minLength: 1
-        type: string
-      type:
-        enum:
-        - static_bearer
-        - mcp_oauth
-        type: string
-    required:
-    - mcp_server_url
-    - type
-    type: object
-  v1.CredentialAuthReplacement:
-    properties:
-      access_token:
-        minLength: 1
-        type: string
-        x-nullable: true
-      expires_at:
-        type: string
-        x-nullable: true
-      refresh:
-        allOf:
-        - $ref: '#/definitions/v1.OAuthCredentialRefreshReplacement'
-        x-nullable: true
-      token:
-        minLength: 1
-        type: string
-      type:
-        enum:
-        - static_bearer
-        - mcp_oauth
-        type: string
-    required:
-    - type
-    type: object
-  v1.CredentialDeleted:
-    properties:
-      deleted:
-        type: boolean
-      id:
-        type: string
-      object:
-        enum:
-        - vault.credential.deleted
-        type: string
-    required:
-    - deleted
-    - id
-    - object
-    type: object
-  v1.CredentialList:
-    properties:
-      data:
-        items:
-          $ref: '#/definitions/v1.Credential'
-        type: array
-      first_id:
-        type: string
-        x-nullable: true
-      has_more:
-        type: boolean
-      last_id:
-        type: string
-        x-nullable: true
-      object:
-        enum:
-        - list
-        type: string
-    required:
-    - data
-    - has_more
-    - object
-    type: object
-  v1.Environment:
-    properties:
-      capability_directories:
-        items:
-          type: string
-        type: array
-        x-nullable: true
-      env:
-        additionalProperties:
-          type: string
-        type: object
-        x-nullable: true
-      environment_template_id:
-        type: string
-      files:
-        items:
-          type: object
-        type: array
-        x-nullable: true
-      network:
-        allOf:
-        - $ref: '#/definitions/v1.EnvironmentNetworkInput'
-        x-nullable: true
-      packages:
-        allOf:
-        - $ref: '#/definitions/v1.EnvironmentPackages'
-        x-nullable: true
-      plugins:
-        items:
-          type: object
-        type: array
-        x-nullable: true
-      setup_commands:
-        items:
-          type: object
-        type: array
-        x-nullable: true
-      skills:
-        items:
-          type: object
-        type: array
-        x-nullable: true
-      type:
-        enum:
-        - none
-        - self_hosted
-        - openai_hosted
-        type: string
-      workspace_directory:
-        type: string
-    required:
-    - type
-    type: object
-  v1.EnvironmentFile:
-    properties:
-      environment_id:
-        type: string
-      object:
-        enum:
-        - agent.environment.file
-        type: string
-      path:
-        type: string
-      size_bytes:
-        minimum: 0
-        type: integer
-    required:
-    - environment_id
-    - object
-    - path
-    - size_bytes
-    type: object
-  v1.EnvironmentFileCreateRequest:
-    properties:
-      data:
-        type: string
-      file_id:
-        type: string
-      path:
-        type: string
-      type:
-        enum:
-        - inline
-        - file_id
-        type: string
-    required:
-    - path
-    - type
-    type: object
-  v1.EnvironmentFileList:
-    properties:
-      data:
-        items:
-          $ref: '#/definitions/v1.EnvironmentFile'
-        type: array
-      has_more:
-        type: boolean
-      next:
-        type: string
-        x-nullable: true
-      object:
-        enum:
-        - page
-        type: string
-    required:
-    - data
-    - has_more
-    - object
-    type: object
-  v1.EnvironmentInfo:
-    properties:
-      files:
-        items:
-          type: object
-        type: array
-      id:
-        type: string
-      object:
-        enum:
-        - agent.environment
-        type: string
-      plugins:
-        items:
-          type: object
-        type: array
-      skills:
-        items:
-          type: object
-        type: array
-      status:
-        enum:
-        - pending
-        - connected
-        - disconnected
-        - expired
-        - failed
-        type: string
-      type:
-        enum:
-        - openai_hosted
-        - self_hosted
-        type: string
-    required:
-    - files
-    - id
-    - object
-    - plugins
-    - skills
-    - status
-    - type
-    type: object
-  v1.EnvironmentInstallation:
-    properties:
-      commands:
-        additionalProperties:
-          type: string
-        type: object
-      expires_at:
-        type: integer
-      message:
-        type: string
-      status:
-        enum:
-        - available
-        - unavailable
-        type: string
-      version:
-        type: string
-    type: object
-  v1.EnvironmentNetwork:
-    properties:
-      access:
-        enum:
-        - enabled
-        - disabled
-        - restricted
-        type: string
-      allowed_domains:
-        items:
-          type: string
-        type: array
-    required:
-    - access
-    - allowed_domains
-    type: object
-  v1.EnvironmentNetworkInput:
-    properties:
-      access:
-        enum:
-        - enabled
-        - disabled
-        - restricted
-        type: string
-      allowed_domains:
-        items:
-          type: string
-        type: array
-        x-nullable: true
-    required:
-    - access
-    type: object
-  v1.EnvironmentPackages:
-    properties:
-      npm:
-        items:
-          type: string
-        type: array
-      python:
-        items:
-          type: string
-        type: array
-    required:
-    - npm
-    - python
-    type: object
-  v1.EnvironmentPackagesInput:
-    properties:
-      npm:
-        items:
-          type: string
-        type: array
-        x-nullable: true
-      python:
-        items:
-          type: string
-        type: array
-        x-nullable: true
-    type: object
-  v1.EnvironmentPackagesResponse:
-    properties:
-      npm:
-        items:
-          type: string
-        type: array
-      python:
-        items:
-          type: string
-        type: array
-      system:
-        items:
-          type: string
-        type: array
-    required:
-    - npm
-    - python
-    - system
-    type: object
-  v1.EnvironmentTemplate:
-    properties:
-      capability_directories:
-        items:
-          type: string
-        type: array
-      created_at:
-        type: integer
-      files:
-        items:
-          type: object
-        type: array
-      id:
-        type: string
-      name:
-        type: string
-        x-nullable: true
-      network:
-        $ref: '#/definitions/v1.EnvironmentNetwork'
-      object:
-        enum:
-        - agent.environment.template
-        type: string
-      packages:
-        $ref: '#/definitions/v1.EnvironmentPackagesResponse'
-      plugins:
-        items:
-          type: object
-        type: array
-      skills:
-        items:
-          type: object
-        type: array
-      updated_at:
-        type: integer
-    required:
-    - capability_directories
-    - created_at
-    - files
-    - id
-    - network
-    - object
-    - packages
-    - plugins
-    - skills
-    - updated_at
-    type: object
-  v1.EnvironmentTemplateDeleted:
-    properties:
-      deleted:
-        type: boolean
-      id:
-        type: string
-      object:
-        enum:
-        - agent.environment.template.deleted
-        type: string
-    required:
-    - deleted
-    - id
-    - object
-    type: object
-  v1.EnvironmentTemplateList:
-    properties:
-      data:
-        items:
-          $ref: '#/definitions/v1.EnvironmentTemplate'
-        type: array
-      first_id:
-        type: string
-        x-nullable: true
-      has_more:
-        type: boolean
-      last_id:
-        type: string
-        x-nullable: true
-      object:
-        enum:
-        - list
-        type: string
-    required:
-    - data
-    - has_more
-    - object
-    type: object
-  v1.EnvironmentTemplateRequest:
-    properties:
-      capability_directories:
-        items:
-          type: string
-        type: array
-        x-nullable: true
-      env:
-        additionalProperties:
-          type: string
-        type: object
-        x-nullable: true
-      files:
-        items:
-          type: object
-        type: array
-        x-nullable: true
-      name:
-        type: string
-        x-nullable: true
-      network:
-        allOf:
-        - $ref: '#/definitions/v1.EnvironmentNetworkInput'
-        x-nullable: true
-      packages:
-        allOf:
-        - $ref: '#/definitions/v1.EnvironmentPackagesInput'
-        x-nullable: true
-      plugins:
-        items:
-          type: object
-        type: array
-        x-nullable: true
-      setup_commands:
-        items:
-          type: object
-        type: array
-        x-nullable: true
-      skills:
-        items:
-          type: object
-        type: array
-        x-nullable: true
-    type: object
-  v1.ErrorResponse:
-    properties:
-      error:
-        $ref: '#/definitions/v1.APIError'
-    required:
-    - error
-    type: object
-  v1.InlineAgent:
-    properties:
-      instructions:
-        type: string
-        x-nullable: true
-      model:
-        type: string
-      multi_agent:
-        type: object
-        x-nullable: true
-      reasoning:
-        allOf:
-        - $ref: '#/definitions/v1.Reasoning'
-        x-nullable: true
-      service_tier:
-        enum:
-        - auto
-        - default
-        - flex
-        - priority
-        - fast
-        type: string
-        x-nullable: true
-      text:
-        allOf:
-        - $ref: '#/definitions/v1.SavedAgentTextInput'
-        x-nullable: true
-      tools:
-        items:
-          type: object
-        type: array
-        x-nullable: true
-      x_agents_core:
-        allOf:
-        - $ref: '#/definitions/v1.AgentsCore'
-        x-nullable: true
-    type: object
-  v1.InputContent:
-    properties:
-      image_url:
-        type: string
-      text:
-        type: string
-      type:
-        enum:
-        - input_text
-        - input_image
-        type: string
-    required:
-    - type
-    type: object
-  v1.InputMessage:
-    properties:
-      content:
-        items:
-          $ref: '#/definitions/v1.InputContent'
-        type: array
-      role:
-        enum:
-        - user
-        type: string
-      type:
-        enum:
-        - message
-        type: string
-    required:
-    - content
-    - role
-    type: object
-  v1.InputTokenDetails:
-    properties:
-      cached_tokens:
-        type: integer
-    required:
-    - cached_tokens
-    type: object
-  v1.Item:
-    properties:
-      action:
-        $ref: '#/definitions/v1.WebSearchAction'
-      agent_id:
-        type: string
-      arguments: {}
-      call_id:
-        type: string
-      command:
-        type: string
-      content:
-        items:
-          $ref: '#/definitions/v1.ItemContent'
-        type: array
-      cwd:
-        type: string
-      duration_ms:
-        type: integer
-      error: {}
-      exit_code:
-        type: integer
-      id:
-        type: string
-      model:
-        type: string
-      name:
-        type: string
-      output: {}
-      phase:
-        enum:
-        - commentary
-        - final_answer
-        type: string
-        x-nullable: true
-      reasoning_effort:
-        type: string
-      recipient_agent_id:
-        type: string
-      recipient_agent_ids:
-        items:
-          type: string
-        type: array
-      role:
-        enum:
-        - user
-        - assistant
-        type: string
-      sender_agent_id:
-        type: string
-      server_label:
-        type: string
-      status:
-        enum:
-        - in_progress
-        - completed
-        - failed
-        - incomplete
-        type: string
-      summary:
-        items:
-          $ref: '#/definitions/v1.SummaryText'
-        type: array
-      turn_id:
-        type: string
-      type:
-        enum:
-        - message
-        - command_execution
-        - mcp_call
-        - function_call
-        - function_call_output
-        - web_search_call
-        - reasoning
-        - agent_message
-        - create_subagent_call
-        - send_subagent_input_call
-        - resume_subagent_call
-        - wait_for_subagents_call
-        - interrupt_subagent_call
-        - close_subagent_call
-        type: string
-    required:
-    - id
-    - turn_id
-    - type
-    type: object
-  v1.ItemContent:
-    properties:
-      encrypted_content:
-        type: string
-      image_url:
-        type: string
-      text:
-        type: string
-      type:
-        enum:
-        - input_text
-        - output_text
-        - input_image
-        - encrypted_content
-        type: string
-    required:
-    - type
-    type: object
-  v1.ItemList:
-    properties:
-      data:
-        items:
-          $ref: '#/definitions/v1.Item'
-        type: array
-      first_id:
-        type: string
-        x-nullable: true
-      has_more:
-        type: boolean
-      last_id:
-        type: string
-        x-nullable: true
-      object:
-        enum:
-        - list
-        type: string
-    required:
-    - data
-    - has_more
-    - object
-    type: object
-  v1.ModelProviderInput:
-    properties:
-      api_key:
-        type: string
-      base_url:
-        type: string
-      context_window:
-        type: integer
-      max_output_tokens:
-        type: integer
-      protocol:
-        enum:
-        - anthropic
-        - responses
-        - chat_completions
-        type: string
-    required:
-    - api_key
-    - base_url
-    - protocol
-    type: object
-  v1.ModelProviderView:
-    properties:
-      api_key_configured:
-        type: boolean
-      base_url:
-        type: string
-      context_window:
-        type: integer
-      max_output_tokens:
-        type: integer
-      protocol:
-        enum:
-        - anthropic
-        - responses
-        - chat_completions
-        type: string
-    required:
-    - api_key_configured
-    - base_url
-    - protocol
-    type: object
-  v1.MultiAgentConfig:
-    properties:
-      enabled:
-        type: boolean
-      max_concurrent_subagents:
-        type: integer
-        x-nullable: true
-    required:
-    - enabled
-    type: object
-  v1.OAuthCredentialRefresh:
-    properties:
-      client_id:
-        type: string
-      resource:
-        type: string
-        x-nullable: true
-      scope:
-        type: string
-        x-nullable: true
-      token_endpoint:
-        type: string
-      token_endpoint_auth:
-        $ref: '#/definitions/v1.OAuthEndpointAuth'
-    required:
-    - client_id
-    - token_endpoint
-    - token_endpoint_auth
-    type: object
-  v1.OAuthCredentialRefreshInput:
-    properties:
-      client_id:
-        type: string
-      refresh_token:
-        type: string
-      resource:
-        type: string
-        x-nullable: true
-      scope:
-        type: string
-        x-nullable: true
-      token_endpoint:
-        type: string
-      token_endpoint_auth:
-        $ref: '#/definitions/v1.OAuthEndpointAuthInput'
-    required:
-    - client_id
-    - refresh_token
-    - token_endpoint
-    - token_endpoint_auth
-    type: object
-  v1.OAuthCredentialRefreshReplacement:
-    properties:
-      refresh_token:
-        type: string
-        x-nullable: true
-      scope:
-        type: string
-        x-nullable: true
-      token_endpoint_auth:
-        allOf:
-        - $ref: '#/definitions/v1.OAuthEndpointAuthReplacement'
-        x-nullable: true
-    type: object
-  v1.OAuthEndpointAuth:
-    properties:
-      type:
-        enum:
-        - none
-        - client_secret_basic
-        - client_secret_post
-        type: string
-    required:
-    - type
-    type: object
-  v1.OAuthEndpointAuthInput:
-    properties:
-      client_secret:
-        type: string
-      type:
-        enum:
-        - none
-        - client_secret_basic
-        - client_secret_post
-        type: string
-    required:
-    - type
-    type: object
-  v1.OAuthEndpointAuthReplacement:
-    properties:
-      client_secret:
-        type: string
-        x-nullable: true
-      type:
-        enum:
-        - client_secret_basic
-        - client_secret_post
-        type: string
-    required:
-    - type
-    type: object
-  v1.OutputTokenDetails:
-    properties:
-      reasoning_tokens:
-        type: integer
-    required:
-    - reasoning_tokens
-    type: object
-  v1.Reasoning:
-    properties:
-      effort:
-        type: string
-        x-nullable: true
-      summary:
-        type: string
-        x-nullable: true
-    type: object
-  v1.RequiredAction:
-    properties:
-      arguments: {}
-      call_id:
-        type: string
-      environment_id:
-        type: string
-      name:
-        type: string
-      turn_id:
-        type: string
-      type:
-        enum:
-        - function_call
-        - environment_connection
-        type: string
-    required:
-    - type
-    type: object
-  v1.SavedAgent:
-    properties:
-      created_at:
-        type: integer
-      id:
-        type: string
-      instructions:
-        type: string
-        x-nullable: true
-      metadata:
-        additionalProperties:
-          type: string
-        type: object
-      model:
-        type: string
-      multi_agent:
-        $ref: '#/definitions/v1.MultiAgentConfig'
-      name:
-        type: string
-        x-nullable: true
-      object:
-        enum:
-        - agent
-        type: string
-      reasoning:
-        $ref: '#/definitions/v1.Reasoning'
-      service_tier:
-        enum:
-        - auto
-        - default
-        - flex
-        - priority
-        - fast
-        type: string
-      text:
-        $ref: '#/definitions/v1.SavedAgentText'
-      tools:
-        items:
-          type: object
-        type: array
-      updated_at:
-        type: integer
-      x_agents_core:
-        allOf:
-        - $ref: '#/definitions/v1.SavedAgentCore'
-        x-nullable: true
-    required:
-    - created_at
-    - id
-    - metadata
-    - model
-    - multi_agent
-    - object
-    - reasoning
-    - service_tier
-    - text
-    - tools
-    - updated_at
-    type: object
-  v1.SavedAgentCore:
-    properties:
-      harness:
-        enum:
-        - claude_sdk
-        - codex
-        - mcode
-        type: string
-      harness_config:
-        type: object
-      model_provider:
-        $ref: '#/definitions/v1.ModelProviderView'
-    type: object
-  v1.SavedAgentCoreInput:
-    properties:
-      harness:
-        enum:
-        - claude_sdk
-        - codex
-        - mcode
-        type: string
-      harness_config:
-        type: object
-      model_provider:
-        allOf:
-        - $ref: '#/definitions/v1.ModelProviderInput'
-        x-nullable: true
-    type: object
-  v1.SavedAgentList:
-    properties:
-      data:
-        items:
-          $ref: '#/definitions/v1.SavedAgent'
-        type: array
-      first_id:
-        type: string
-        x-nullable: true
-      has_more:
-        type: boolean
-      last_id:
-        type: string
-        x-nullable: true
-      object:
-        enum:
-        - list
-        type: string
-    required:
-    - data
-    - has_more
-    - object
-    type: object
-  v1.SavedAgentText:
-    properties:
-      format:
-        $ref: '#/definitions/v1.SavedAgentTextFormat'
-      verbosity:
-        enum:
-        - low
-        - medium
-        - high
-        type: string
-    required:
-    - format
-    - verbosity
-    type: object
-  v1.SavedAgentTextFormat:
-    properties:
-      schema:
-        type: object
-      type:
-        enum:
-        - text
-        - json_schema
-        type: string
-    required:
-    - type
-    type: object
-  v1.SavedAgentTextInput:
-    properties:
-      format:
-        type: object
-        x-nullable: true
-      verbosity:
-        enum:
-        - low
-        - medium
-        - high
-        type: string
-        x-nullable: true
-    type: object
-  v1.Session:
-    properties:
-      agent:
-        $ref: '#/definitions/v1.Agent'
-      created_at:
-        type: integer
-      environment:
-        $ref: '#/definitions/v1.SessionEnvironment'
-      error:
-        type: string
-        x-nullable: true
-      id:
-        type: string
-      last_active_at:
-        type: integer
-      metadata:
-        additionalProperties:
-          type: string
-        type: object
-      object:
-        enum:
-        - agent.session
-        type: string
-      required_actions:
-        items:
-          $ref: '#/definitions/v1.RequiredAction'
-        type: array
-      status:
-        enum:
-        - idle
-        - in_progress
-        - requires_action
-        - failed
-        type: string
-      usage:
-        allOf:
-        - $ref: '#/definitions/v1.TokenUsage'
-        x-nullable: true
-      vault_ids:
-        items:
-          type: string
-        type: array
-      x_agents_core:
-        $ref: '#/definitions/v1.SessionCore'
-    required:
-    - agent
-    - created_at
-    - environment
-    - id
-    - last_active_at
-    - metadata
-    - object
-    - required_actions
-    - status
-    - vault_ids
-    type: object
-  v1.SessionArtifact:
-    properties:
-      created_at:
-        type: integer
-      environment_id:
-        type: string
-      id:
-        type: string
-      object:
-        enum:
-        - agent.session.artifact
-        type: string
-      path:
-        type: string
-      session_id:
-        type: string
-      size_bytes:
-        type: integer
-      turn_id:
-        type: string
-    required:
-    - created_at
-    - environment_id
-    - id
-    - object
-    - path
-    - session_id
-    - size_bytes
-    - turn_id
-    type: object
-  v1.SessionArtifactDeleted:
-    properties:
-      deleted:
-        type: boolean
-      id:
-        type: string
-      object:
-        enum:
-        - agent.session.artifact.deleted
-        type: string
-    required:
-    - deleted
-    - id
-    - object
-    type: object
-  v1.SessionArtifactList:
-    properties:
-      data:
-        items:
-          $ref: '#/definitions/v1.SessionArtifact'
-        type: array
-      first_id:
-        type: string
-        x-nullable: true
-      has_more:
-        type: boolean
-      last_id:
-        type: string
-        x-nullable: true
-      object:
-        enum:
-        - list
-        type: string
-    required:
-    - data
-    - has_more
-    - object
-    type: object
-  v1.SessionCore:
-    properties:
-      installation:
-        $ref: '#/definitions/v1.EnvironmentInstallation'
-    type: object
-  v1.SessionDeleted:
-    properties:
-      deleted:
-        type: boolean
-      id:
-        type: string
-      object:
-        enum:
-        - agent.session.deleted
-        type: string
-    required:
-    - deleted
-    - id
-    - object
-    type: object
-  v1.SessionEnvironment:
-    properties:
-      capability_directories:
-        items:
-          type: string
-        type: array
-      files:
-        items:
-          type: object
-        type: array
-      id:
-        type: string
-      network:
-        $ref: '#/definitions/v1.EnvironmentNetwork'
-      packages:
-        $ref: '#/definitions/v1.EnvironmentPackagesResponse'
-      plugins:
-        items:
-          type: object
-        type: array
-      remote_url:
-        type: string
-      skills:
-        items:
-          type: object
-        type: array
-      type:
-        enum:
-        - none
-        - self_hosted
-        - openai_hosted
-        type: string
-      workspace_directory:
-        type: string
-    required:
-    - type
-    type: object
-  v1.SessionEnvironmentState:
-    properties:
-      error:
-        allOf:
-        - $ref: '#/definitions/v1.StreamError'
-        x-nullable: true
-      id:
-        type: string
-      status:
-        enum:
-        - pending
-        - ready
-        - connected
-        - disconnected
-        - failed
-        type: string
-      type:
-        type: string
-    required:
-    - id
-    - status
-    - type
-    type: object
-  v1.SessionEvent:
-    properties:
-      content_index:
-        type: integer
-      delta:
-        type: string
-      environment:
-        $ref: '#/definitions/v1.SessionEnvironmentState'
-      error:
-        $ref: '#/definitions/v1.StreamError'
-      event_id:
-        type: string
-      item:
-        $ref: '#/definitions/v1.Item'
-      item_id:
-        type: string
-      output_index:
-        type: integer
-        x-nullable: true
-      part:
-        $ref: '#/definitions/v1.ItemContent'
-      session:
-        $ref: '#/definitions/v1.Session'
-      session_id:
-        type: string
-      subagent:
-        $ref: '#/definitions/v1.Subagent'
-      text:
-        type: string
-      turn:
-        $ref: '#/definitions/v1.Turn'
-      turn_id:
-        type: string
-      type:
-        type: string
-      usage:
-        allOf:
-        - $ref: '#/definitions/v1.TokenUsage'
-        description: |-
-          Usage is present only on terminal Turn events, where it mirrors the Turn
-          snapshot and is null when unknown. Other events omit it.
-        x-nullable: true
-    required:
-    - event_id
-    - type
-    type: object
-  v1.SessionExecutionInput:
-    properties:
-      environment:
-        description: Environment supplies placement-independent preparation through
-          the Core extension.
-        type: object
-      harness_config:
-        type: object
-      model_provider:
-        $ref: '#/definitions/v1.ModelProviderInput'
-    type: object
-  v1.SessionInput:
-    properties:
-      call_id:
-        type: string
-      error:
-        type: string
-        x-nullable: true
-      input:
-        items:
-          $ref: '#/definitions/v1.InputMessage'
-        type: array
-      output:
-        x-nullable: true
-      success:
-        type: boolean
-      turn_id:
-        type: string
-      type:
-        enum:
-        - agent.session.input.message
-        - agent.session.input.cancel
-        - agent.session.input.tool_result
-        type: string
-    required:
-    - type
-    type: object
-  v1.SessionList:
-    properties:
-      data:
-        items:
-          $ref: '#/definitions/v1.Session'
-        type: array
-      first_id:
-        type: string
-        x-nullable: true
-      has_more:
-        type: boolean
-      last_id:
-        type: string
-        x-nullable: true
-      object:
-        enum:
-        - list
-        type: string
-    required:
-    - data
-    - has_more
-    - object
-    type: object
-  v1.Skill:
-    properties:
-      created_at:
-        type: integer
-      default_version:
-        type: string
-      description:
-        type: string
-      id:
-        type: string
-      latest_version:
-        type: string
-      name:
-        type: string
-      object:
-        enum:
-        - skill
-        type: string
-    required:
-    - created_at
-    - default_version
-    - description
-    - id
-    - latest_version
-    - name
-    - object
-    type: object
-  v1.SkillDeleted:
-    properties:
-      deleted:
-        type: boolean
-      id:
-        type: string
-      object:
-        enum:
-        - skill.deleted
-        type: string
-    required:
-    - deleted
-    - id
-    - object
-    type: object
-  v1.SkillList:
-    properties:
-      data:
-        items:
-          $ref: '#/definitions/v1.Skill'
-        type: array
-      first_id:
-        type: string
-        x-nullable: true
-      has_more:
-        type: boolean
-      last_id:
-        type: string
-        x-nullable: true
-      object:
-        enum:
-        - list
-        type: string
-    required:
-    - data
-    - has_more
-    - object
-    type: object
-  v1.SkillUpdateRequest:
-    properties:
-      default_version:
-        type: string
-    required:
-    - default_version
-    type: object
-  v1.SkillVersion:
-    properties:
-      created_at:
-        type: integer
-      description:
-        type: string
-      id:
-        type: string
-      name:
-        type: string
-      object:
-        enum:
-        - skill.version
-        type: string
-      skill_id:
-        type: string
-      version:
-        type: string
-    required:
-    - created_at
-    - description
-    - id
-    - name
-    - object
-    - skill_id
-    - version
-    type: object
-  v1.SkillVersionDeleted:
-    properties:
-      deleted:
-        type: boolean
-      id:
-        type: string
-      object:
-        enum:
-        - skill.version.deleted
-        type: string
-      version:
-        type: string
-    required:
-    - deleted
-    - id
-    - object
-    - version
-    type: object
-  v1.SkillVersionList:
-    properties:
-      data:
-        items:
-          $ref: '#/definitions/v1.SkillVersion'
-        type: array
-      first_id:
-        type: string
-        x-nullable: true
-      has_more:
-        type: boolean
-      last_id:
-        type: string
-        x-nullable: true
-      object:
-        enum:
-        - list
-        type: string
-    required:
-    - data
-    - has_more
-    - object
-    type: object
-  v1.SourceFile:
-    properties:
-      bytes:
-        minimum: 0
-        type: integer
-      created_at:
-        type: integer
-      expires_at:
-        type: integer
-        x-nullable: true
-      filename:
-        type: string
-      id:
-        type: string
-      object:
-        enum:
-        - file
-        type: string
-      purpose:
-        enum:
-        - user_data
-        type: string
-      status:
-        enum:
-        - processed
-        type: string
-      status_details:
-        type: string
-        x-nullable: true
-    required:
-    - bytes
-    - created_at
-    - filename
-    - id
-    - object
-    - purpose
-    - status
-    type: object
-  v1.SourceFileDeleted:
-    properties:
-      deleted:
-        type: boolean
-      id:
-        type: string
-      object:
-        enum:
-        - file
-        type: string
-    required:
-    - deleted
-    - id
-    - object
-    type: object
-  v1.SourceFileList:
-    properties:
-      data:
-        items:
-          $ref: '#/definitions/v1.SourceFile'
-        type: array
-      first_id:
-        type: string
-        x-nullable: true
-      has_more:
-        type: boolean
-      last_id:
-        type: string
-        x-nullable: true
-      object:
-        enum:
-        - list
-        type: string
-    required:
-    - data
-    - has_more
-    - object
-    type: object
-  v1.StreamError:
-    properties:
-      code:
-        type: string
-      message:
-        type: string
-      param:
-        description: |-
-          Param is the pinned SessionError field. An error SessionEvent always
-          carries it, null when unset; Environment state errors and Core's own
-          stream_interrupted frame omit it.
-        type: string
-        x-nullable: true
-      type:
-        type: string
-    type: object
-  v1.Subagent:
-    properties:
-      closed_at:
-        type: integer
-        x-nullable: true
-      id:
-        type: string
-      instructions:
-        items:
-          $ref: '#/definitions/v1.AgentContent'
-        type: array
-        x-nullable: true
-      name:
-        type: string
-        x-nullable: true
-      object:
-        enum:
-        - agent.session.subagent
-        type: string
-      opened_at:
-        type: integer
-      parent_agent_id:
-        type: string
-      session_id:
-        type: string
-      status:
-        enum:
-        - active
-        - closed
-        type: string
-    required:
-    - id
-    - object
-    - opened_at
-    - parent_agent_id
-    - session_id
-    - status
-    type: object
-  v1.SubagentList:
-    properties:
-      data:
-        items:
-          $ref: '#/definitions/v1.Subagent'
-        type: array
-      first_id:
-        type: string
-        x-nullable: true
-      has_more:
-        type: boolean
-      last_id:
-        type: string
-        x-nullable: true
-      object:
-        enum:
-        - list
-        type: string
-    required:
-    - data
-    - has_more
-    - object
-    type: object
-  v1.SummaryText:
-    properties:
-      text:
-        type: string
-      type:
-        enum:
-        - summary_text
-        type: string
-    required:
-    - text
-    - type
-    type: object
-  v1.TextConfig:
-    properties:
-      format:
-        $ref: '#/definitions/v1.TextFormat'
-      verbosity:
-        enum:
-        - low
-        - medium
-        - high
-        type: string
-    required:
-    - format
-    - verbosity
-    type: object
-  v1.TextFormat:
-    properties:
-      schema:
-        type: object
-      type:
-        enum:
-        - text
-        - json_schema
-        type: string
-    required:
-    - type
-    type: object
-  v1.TokenUsage:
-    properties:
-      input_tokens:
-        type: integer
-      input_tokens_details:
-        $ref: '#/definitions/v1.InputTokenDetails'
-      output_tokens:
-        type: integer
-      output_tokens_details:
-        $ref: '#/definitions/v1.OutputTokenDetails'
-      total_tokens:
-        type: integer
-    required:
-    - input_tokens
-    - input_tokens_details
-    - output_tokens
-    - output_tokens_details
-    - total_tokens
-    type: object
-  v1.Turn:
-    properties:
-      agent_id:
-        type: string
-      completed_at:
-        type: integer
-        x-nullable: true
-      created_at:
-        type: integer
-      error:
-        allOf:
-        - $ref: '#/definitions/v1.TurnError'
-        x-nullable: true
-      id:
-        type: string
-      object:
-        enum:
-        - agent.session.turn
-        type: string
-      session_id:
-        type: string
-      started_at:
-        type: integer
-        x-nullable: true
-      status:
-        enum:
-        - queued
-        - in_progress
-        - waiting
-        - completed
-        - failed
-        - cancelled
-        type: string
-      subagent_id:
-        type: string
-        x-nullable: true
-      usage:
-        allOf:
-        - $ref: '#/definitions/v1.TokenUsage'
-        x-nullable: true
-    required:
-    - agent_id
-    - created_at
-    - id
-    - object
-    - session_id
-    - status
-    type: object
-  v1.TurnError:
-    properties:
-      code:
-        enum:
-        - context_length_exceeded
-        - session_budget_exceeded
-        - usage_limit_exceeded
-        - rate_limit_exceeded
-        - server_overloaded
-        - cyber_policy
-        - connection_failed
-        - server_error
-        - authentication_error
-        - invalid_request
-        - resource_not_found
-        - sandbox_error
-        - executor_version_incompatible
-        - active_turn_not_steerable
-        - request_timeout
-        - internal_error
-        type: string
-      message:
-        type: string
-    required:
-    - code
-    - message
-    type: object
-  v1.TurnList:
-    properties:
-      data:
-        items:
-          $ref: '#/definitions/v1.Turn'
-        type: array
-      first_id:
-        type: string
-        x-nullable: true
-      has_more:
-        type: boolean
-      last_id:
-        type: string
-        x-nullable: true
-      object:
-        enum:
-        - list
-        type: string
-    required:
-    - data
-    - has_more
-    - object
-    type: object
-  v1.UpdateAgentRequest:
-    properties:
-      instructions:
-        type: string
-        x-nullable: true
-      metadata:
-        additionalProperties:
-          type: string
-        type: object
-        x-nullable: true
-      model:
-        type: string
-      multi_agent:
-        type: object
-        x-nullable: true
-      name:
-        maxLength: 128
-        type: string
-        x-nullable: true
-      reasoning:
-        allOf:
-        - $ref: '#/definitions/v1.Reasoning'
-        x-nullable: true
-      service_tier:
-        enum:
-        - auto
-        - default
-        - flex
-        - priority
-        - fast
-        type: string
-        x-nullable: true
-      text:
-        allOf:
-        - $ref: '#/definitions/v1.SavedAgentTextInput'
-        x-nullable: true
-      tools:
-        items:
-          type: object
-        type: array
-        x-nullable: true
-      x_agents_core:
-        allOf:
-        - $ref: '#/definitions/v1.SavedAgentCoreInput'
-        x-nullable: true
-    type: object
-  v1.UpdateCredentialRequest:
-    properties:
-      auth:
-        $ref: '#/definitions/v1.CredentialAuthReplacement'
-    required:
-    - auth
-    type: object
-  v1.UpdateSessionRequest:
-    properties:
-      metadata:
-        additionalProperties:
-          type: string
-        type: object
-        x-nullable: true
-    required:
-    - metadata
-    type: object
-  v1.Vault:
-    properties:
-      created_at:
-        type: integer
-      id:
-        type: string
-      metadata:
-        additionalProperties:
-          type: string
-        type: object
-      name:
-        type: string
-        x-nullable: true
-      object:
-        enum:
-        - vault
-        type: string
-    required:
-    - created_at
-    - id
-    - metadata
-    - object
-    type: object
-  v1.VaultDeleted:
-    properties:
-      deleted:
-        type: boolean
-      id:
-        type: string
-      object:
-        enum:
-        - vault.deleted
-        type: string
-    required:
-    - deleted
-    - id
-    - object
-    type: object
-  v1.VaultList:
-    properties:
-      data:
-        items:
-          $ref: '#/definitions/v1.Vault'
-        type: array
-      first_id:
-        type: string
-        x-nullable: true
-      has_more:
-        type: boolean
-      last_id:
-        type: string
-        x-nullable: true
-      object:
-        enum:
-        - list
-        type: string
-    required:
-    - data
-    - has_more
-    - object
-    type: object
-  v1.WebSearchAction:
-    properties:
-      pattern:
-        type: string
-      queries:
-        items:
-          type: string
-        type: array
-      query:
-        type: string
-      type:
-        enum:
-        - search
-        - open_page
-        - find_in_page
-        - other
-        type: string
-      url:
-        type: string
-    required:
-    - type
-    type: object
-info:
-  contact: {}
-  description: Supported single-Agent execution resources from the pinned openai-python
-    beta/agents contract. Bearer keys bind an execution principal to one project;
-    optional OpenAI-Organization and OpenAI-Project headers must match that binding.
-  license:
-    name: Apache 2.0
-    url: https://www.apache.org/licenses/LICENSE-2.0.html
-  title: OpenAgentCore Agents API
-  version: "1"
-paths:
-  /agents:
-    get:
-      description: Lists only the authenticated tenant's saved Agents, independently
-        of Sessions. Limit 0 is treated as 1 and larger limits as 100, as observed
-        on the hosted service. The local default is 20; exact upstream default/cap
-        and empty cursor fields remain unverified. An unknown, malformed or foreign
-        after cursor returns not found.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Last Agent ID from the previous page
-        in: query
-        name: after
-        type: string
-      - default: 20
-        description: Page size; 0 is treated as 1 and values above 100 as 100
-        in: query
-        minimum: 0
-        name: limit
-        type: integer
-      - default: desc
-        description: Creation order; omit for descending, explicit empty values are
-          invalid
-        enum:
-        - asc
-        - desc
-        in: query
-        name: order
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.SavedAgentList'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: List reusable Agents
-      tags:
-      - Agents
-    post:
-      consumes:
-      - application/json
-      description: 'Persists configuration independently of execution. Names over
-        128 characters and metadata outside 16 string pairs with 64-character keys
-        and 512-character values return invalid_request_error with the official param;
-        U+0000 in stored strings is rejected as a local storage limit. As on every
-        Agents API JSON route, a non-JSON Content-Type, invalid UTF-8, malformed JSON,
-        a repeated key at any depth or a non-object root returns invalid_request_error
-        with a null param and the official message before other checks; an empty or
-        null body is {}. Missing, unknown, wrongly typed or unsupported enum members
-        of the pinned configuration shapes (tools, text, reasoning, service_tier,
-        multi_agent) return invalid_request_error with the JSON path as param; duplicate
-        function names, repeated web_search or tool_search and non-object schema root
-        types return it with a null param. Supports model/name/instructions/metadata,
-        explicit reasoning and service tiers, multi_agent, text/json_schema, function/tool_search/programmatic_tool_calling/web_search
-        and HTTP MCP with nullable credential_id, service origin (omitted or null
-        on HTTP transport is saved as service) and boolean required defaulting to
-        false. Saving credential_id grants no access: Session admission checks attached
-        Vault ownership and destination. MCP allowed_tools preserves null versus empty;
-        saved HTTP transport includes empty headers. Model-derived reasoning defaults,
-        other MCP variants and public retry conformance remain incomplete. web_search
-        saves every pinned mode: omitted or null mode is saved as live and omitted
-        or null context_size as medium; allowed_domains preserves null versus empty
-        and a present location, including {}, includes all four keys with null for
-        omitted ones, as observed officially (req_db41d2f6261b4abfb69465eafe719ab5,
-        req_165d53b88445490b9146d8272c54134d). Session execution accepts only explicit
-        disabled web_search and disabled programmatic_tool_calling through qualified
-        Runtime controls; saved enabled forms reject at Session admission. Session
-        execution admits only its supported configuration subset.'
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Reusable Agent configuration
-        in: body
-        name: body
-        required: true
-        schema:
-          $ref: '#/definitions/v1.CreateAgentRequest'
-      produces:
-      - application/json
-      responses:
-        "201":
-          description: Created
-          schema:
-            $ref: '#/definitions/v1.SavedAgent'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "413":
-          description: Request Entity Too Large
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Create a reusable Agent
-      tags:
-      - Agents
-  /agents/{agent_id}:
-    delete:
-      description: Deletes only the authenticated tenant's saved configuration. Existing
-        Session snapshots, history and recorded creation retry identities remain independent.
-        Missing and repeated deletion locally return404; exact hosted error and in-flight
-        creation/deletion semantics remain unverified.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Agent ID
-        in: path
-        name: agent_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.AgentDeleted'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "413":
-          description: Request Entity Too Large
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Delete a reusable Agent
-      tags:
-      - Agents
-    get:
-      description: Reads the saved resource owned by the authenticated tenant, independently
-        of execution Sessions.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Agent ID
-        in: path
-        name: agent_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.SavedAgent'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Retrieve a reusable Agent
-      tags:
-      - Agents
-    post:
-      consumes:
-      - application/json
-      description: Preserves omitted fields and replaces supplied fields using shared
-        saved-configuration validation. Null name/instructions clear; null or empty
-        metadata clears all pairs. Name, metadata and configuration validation errors
-        return invalid_request_error with the official param, using the Agent create
-        rules before the Agent lookup. Existing Session snapshots are unchanged. Empty
-        updates advance updated_at without changing saved fields. Nested replacement/null
-        defaults, model-derived reasoning and exact hosted error behavior remain incompletely
-        verified.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Agent ID
-        in: path
-        name: agent_id
-        required: true
-        type: string
-      - description: Supplied reusable Agent fields
-        in: body
-        name: body
-        required: true
-        schema:
-          $ref: '#/definitions/v1.UpdateAgentRequest'
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.SavedAgent'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "413":
-          description: Request Entity Too Large
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Update a reusable Agent
-      tags:
-      - Agents
-  /agents/environments/{environment_id}:
-    get:
-      description: Returns durable connection status and safe installed metadata for
-        supported self_hosted and basic openai_hosted profiles. Initial files expose
-        frozen safe metadata without content; Plugin/Skill entries expose only safe
-        configured installation metadata. Capability-directory discoveries are not
-        added to those arrays. Unsupported installation configurations remain implementation
-        gaps. This read does not prepare execution, start compute or require an enabled
-        execution worker. Session deletion removes the associated Environment from
-        public reads; project-shared read authorization is unchanged. Connection status
-        does not prove native readiness or process quiescence.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Environment ID
-        in: path
-        name: environment_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.EnvironmentInfo'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Retrieve an execution Environment
-      tags:
-      - Environments
-  /agents/environments/{environment_id}/files:
-    get:
-      description: Lists direct regular files in one authorized self_hosted or qualified
-        local workspace directory. Local paths use the public /workspace root and
-        must be in cleaned form. This partial implementation defaults to the workspace
-        root and limit 20; recursive scope and these defaults are not verified upstream
-        semantics. A missing path, a regular file or a symbolic link returns an empty
-        page; links are never followed. Daemons without a local workspace binding
-        use the Claude SDK adapter reader, which keeps 404 for a missing path and
-        503 for a regular file or symbolic link. Well-formed unknown query keys are
-        ignored; malformed query encoding and a repeated supported key are rejected.
-        Sorts by case-sensitive path components, descending by default. Keep the same
-        path, order and limit when using page. Each page rereads the complete bounded
-        directory; changed file paths/sizes invalidate continuation locally with 400.
-        There is no snapshot guarantee. An openai_hosted Environment that has not
-        connected yet returns 400. Truncated or uncertain native results fail with
-        503 without returning a partial page. This read never starts a Turn or admits
-        model input. Actual transport disconnect/reconnect events remain observable.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Environment ID
-        in: path
-        name: environment_id
-        required: true
-        type: string
-      - description: Absolute directory in cleaned form inside /workspace
-        in: query
-        name: path
-        type: string
-      - description: Maximum file count; local default 20
-        in: query
-        maximum: 100
-        minimum: 1
-        name: limit
-        type: integer
-      - default: desc
-        description: Case-sensitive path-component order; omit for descending, explicit
-          empty values are invalid
-        enum:
-        - asc
-        - desc
-        in: query
-        name: order
-        type: string
-      - description: Opaque continuation token; keep path, order and limit unchanged
-        in: query
-        name: page
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.EnvironmentFileList'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: List live Environment files
-      tags:
-      - Environments
-    post:
-      consumes:
-      - application/json
-      description: Uploads standard Base64 bytes to a file beneath /workspace in a
-        qualified local Environment and returns 201. Accepts inline bytes or a project-owned
-        source file_id through the same write path. Unknown body fields are rejected
-        with their name as param. Basic public hosted creation requires explicit managed
-        Runtime configuration; an openai_hosted Environment that has not connected
-        yet returns 400. Inline data is limited to 5 MiB decoded and a file_id copy
-        to 50 MiB. Missing parent directories are created with mode 0700 and the file
-        with mode 0600. An existing destination is never replaced; a directory, an
-        existing file or a path through a symlink or non-directory returns 400. Idle
-        writes exclude execution. Missing receipts return unavailable and retain a
-        durable mutation gate without automatic replay. Error/timing parity with upstream
-        remains unverified.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Environment ID
-        in: path
-        name: environment_id
-        required: true
-        type: string
-      - description: Inline bytes or source file ID and absolute workspace path
-        in: body
-        name: request
-        required: true
-        schema:
-          $ref: '#/definitions/v1.EnvironmentFileCreateRequest'
-      produces:
-      - application/json
-      responses:
-        "201":
-          description: Created
-          schema:
-            $ref: '#/definitions/v1.EnvironmentFile'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "409":
-          description: Conflict
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "413":
-          description: Request Entity Too Large
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Create an Environment file from inline bytes or a source file
-      tags:
-      - Environments
-  /agents/environments/templates:
-    get:
-      description: Lists tenant-owned safe template metadata in creation order with
-        ID tie-breaking. Defaults to limit 20 and descending order; limit 0 is treated
-        as 1 and larger limits as 100. Foreign, missing and malformed cursors return
-        the same not found error. Concurrent-page and exact hosted error behavior
-        remain unverified.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Previous Template ID
-        in: query
-        name: after
-        type: string
-      - default: 20
-        description: Page size; 0 is treated as 1 and values above 100 as 100
-        in: query
-        minimum: 0
-        name: limit
-        type: integer
-      - default: desc
-        description: Creation order; omit for descending, explicit empty values are
-          invalid
-        enum:
-        - asc
-        - desc
-        in: query
-        name: order
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.EnvironmentTemplateList'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: List Environment Templates
-      tags:
-      - Environment Templates
-    post:
-      consumes:
-      - application/json
-      description: Saves tenant-owned hosted configuration. Supports nullable name,
-        enabled/disabled or exact-domain restricted network, initial inline/file_id
-        files, confidential env, ordered setup_commands, npm/Python packages inline/referenced
-        Skill ZIPs, Plugin ZIPs and workspace-contained capability directories. Omitted/null
-        network defaults to enabled. Restricted network requires 1–100 exact ASCII
-        hostnames; other host forms and populated unsupported installations are rejected
-        before persistence without echoing input. Network policy rejections return
-        invalid_request_error with a null param. System dependencies must be preinstalled
-        in the sandbox image or template, or on the host machine; packages.system
-        is rejected. No compute is allocated. Exact hosted error/retry semantics remain
-        unverified.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Reusable configuration
-        in: body
-        name: body
-        required: true
-        schema:
-          $ref: '#/definitions/v1.EnvironmentTemplateRequest'
-      produces:
-      - application/json
-      responses:
-        "201":
-          description: Created
-          schema:
-            $ref: '#/definitions/v1.EnvironmentTemplate'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "413":
-          description: Request Entity Too Large
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Create an Environment Template
-      tags:
-      - Environment Templates
-  /agents/environments/templates/{environment_template_id}:
-    delete:
-      description: Deletes the tenant-owned reusable configuration without changing
-        or deleting existing Sessions and their frozen configuration.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Template ID
-        in: path
-        name: environment_template_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.EnvironmentTemplateDeleted'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Delete an Environment Template
-      tags:
-      - Environment Templates
-    get:
-      description: Returns safe tenant-owned configuration metadata without allocating
-        compute. Missing and foreign resources return the same not-found response.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Template ID
-        in: path
-        name: environment_template_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.EnvironmentTemplate'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Retrieve an Environment Template
-      tags:
-      - Environment Templates
-    post:
-      consumes:
-      - application/json
-      description: Supplied fields replace atomically; omitted fields remain unchanged.
-        Null name clears and null network resets to the pinned enabled default. Existing
-        Session snapshots and creation retries remain unchanged. Initial files replace
-        as a list; null/empty clears. File data is encrypted separately and excluded
-        from response metadata. Skills replace as a list; null/empty clears. Skill
-        archives are encrypted separately and omitted from responses. Plugins and
-        capability directories replace as lists; null/empty clears. Plugin archives
-        are encrypted and omitted from responses. Capability directories are snapshotted
-        after setup. Environment MCP execution requires a qualified native transport
-        and runtime network policy. Empty updates advance updated_at without changing
-        saved fields or confidential contents. Network policy rejections return invalid_request_error
-        with a null param.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Template ID
-        in: path
-        name: environment_template_id
-        required: true
-        type: string
-      - description: Configuration replacements
-        in: body
-        name: body
-        required: true
-        schema:
-          $ref: '#/definitions/v1.EnvironmentTemplateRequest'
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.EnvironmentTemplate'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "413":
-          description: Request Entity Too Large
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Update an Environment Template
-      tags:
-      - Environment Templates
-  /agents/sessions:
-    get:
-      description: Cursor and results are scoped to the authenticated execution tenant;
-        an unknown, malformed or foreign after cursor returns not found. Optional
-        agent_id matches the immutable root Agent ID, including inline Agents and
-        historical Sessions whose saved source was updated or deleted. Omission lists
-        all Agents. Returns the same Environment and pending-input activity projection
-        as Session retrieval, including self_hosted Sessions.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Root Agent ID whose Sessions to return
-        in: query
-        name: agent_id
-        type: string
-      - description: Last Session ID from the previous page
-        in: query
-        name: after
-        type: string
-      - default: 20
-        description: Page size; 0 is treated as 1 and values above 100 as 100
-        in: query
-        minimum: 0
-        name: limit
-        type: integer
-      - default: desc
-        description: Creation order; omit for descending, explicit empty values are
-          invalid
-        enum:
-        - asc
-        - desc
-        in: query
-        name: order
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.SessionList'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: List execution Sessions
-      tags:
-      - Sessions
-    post:
-      consumes:
-      - application/json
-      description: 'The optional Core model_provider bundle resolves from the Session
-        override, saved Agent defaults, then the deployment default of the resolved
-        harness, for every environment type. A Session that resolves no bundle returns
-        400 model_provider_required with param x_agents_core.model_provider before
-        any write. Core encrypts and freezes the resolved bundle; later Agent or deployment
-        default edits and same-key retries cannot change it. Keys are never returned.
-        Supports inline configuration or a tenant-owned saved agent_id with per-Session
-        field replacements. Execution supports model/instructions, text verbosity,
-        non-deferred function tools, adapter-qualified multi_agent with persisted
-        Subagent reads, implicit reasoning, service tier auto and environment type
-        none, subject to the configured engine. Codex additionally supports HTTP MCP
-        with service origin (omitted or null on HTTP transport is saved as service),
-        native allowed_tools and boolean required defaulting to false. Session vault_ids
-        attach only project-owned Vaults; credential_id selects an attached static
-        bearer or OAuth credential for the exact HTTPS URL, while null/omission selects
-        a unique match or remains anonymous. Session reads, lists and event snapshots
-        show that implicitly selected credential ID in a null or omitted credential_id,
-        also after the credential is deleted; anonymous selections stay null and the
-        stored caller intent is unchanged. After the input requirement and before
-        any write, a credential_id without vault_ids, one outside the attached Vaults
-        (one message for missing, foreign and unattached IDs) or one for another server_url
-        returns 400 invalid_request_error, and several implicit matches return 409
-        conflict_error. Missing decryption configuration fails dispatch without anonymous
-        fallback. Required initialization uses native startup before the first native
-        Turn, including cold resume, and requires a separately advertised capability;
-        exact hosted creation timing and error parity remain unverified. Explicit
-        environment-origin HTTP MCP is supported on managed and self-hosted workspaces
-        through the same Runtime bindings; native OAuth login remains unsupported.
-        The self_hosted profile uses a qualified native harness, a clean absolute
-        workspace_directory and optional absolute local capability_directories prepared
-        by Runtime, with optional non-deferred function tools and HTTP MCP using explicit
-        environment origin, optionally authenticated by the attached Vault rules.
-        Service-origin HTTP remains restricted to service-side environment:none. Remote
-        MCP and remote Bearer authentication each require separately advertised combination
-        support; old peers cannot receive unsupported work. Omitted/null capability_directories
-        use the empty-list default; self_hosted requires configured execution plus
-        executor registry. Claude SDK currently requires medium verbosity and object-root
-        function schemas. It supports anonymous or attached static-bearer service-origin
-        HTTP MCP on none with boolean required and separately advertised MCP/bearer/required
-        runtime support. Required servers must be connected before the first native
-        input is released; pending or failed startup rejects execution. The shared
-        Vault selection and immutable binding rules apply; unsupported native labels/tool
-        names reject before persistence. An attached Vault with no matching credential
-        may remain anonymous; missing keys or failed credential lookup/decryption
-        never fall back to anonymous execution. Omitted stream defaults to false;
-        stream and agent_id cannot be null. Metadata may be null; non-string values
-        and limit violations return invalid_request_error with a metadata or metadata.<key>
-        param. The inline agent uses the Agent create configuration validation with
-        agent.-prefixed params, reported before the input requirement and saved-Agent
-        lookup; saved configurations with conflicting tools or schema roots reject
-        admission with the same errors, and execution limits keep unsupported_or_invalid_configuration.
-        Hosted network policy rejections return invalid_request_error with a null
-        param. Initial input accepts a string or ordered user-message array. Codex
-        and Claude SDK on none and qualified managed or self_hosted workspace profiles
-        also accept inline PNG/JPEG image content; other image combinations and remote
-        URLs are unsupported. None initial input atomically starts a Turn; self_hosted
-        initial input is reserved while returning its Environment connection target,
-        with execution deferred to native readiness and Session failure on initial
-        timeout. Initial input is required for none and for streamed creation outside
-        self_hosted. Omitted/null input remains valid for non-streaming hosted and
-        self_hosted creation. With stream=true, returns live Session events starting
-        with the committed creation snapshot and closes right after the first agent.session.idle
-        recorded when a Turn ends or an input reservation stops being pending, or
-        any agent.session.failed, without sending later events. A creation that admitted
-        nothing closes after the snapshot; a settlement that records no event closes
-        after events up to the cursor read with a settled Session projection. Required
-        actions keep it open; disconnect does not cancel execution. The GET events
-        stream remains live-only. New Sessions retain their authenticated creator;
-        all creation retries require the same typed subject, including across key
-        rotation. Every creation records caller intent before saved Agents, templates,
-        Vault credentials or deployment defaults resolve, so a same-intent retry returns
-        the committed Session independently of later changes to those resources. Provider
-        keys enter retry hashes only as fingerprints keyed by the credential key.
-        Unknown historical creators reject retries. These conflict policies are local
-        and not verified hosted parity. A same-key stream=true retry of an existing
-        creation returns 201 with no events and closes at once; retry with stream=false
-        or use the GET events stream to recover. Claude SDK on none, Core-managed
-        Docker openai_hosted and self_hosted supports qualified object-root json_schema
-        output with medium verbosity, single-Agent execution and ordinary functions.
-        Hosted execution reuses native workspace tools and Files/Artifacts; Skills,
-        Plugins, capability directories, HTTP MCP, Subagent and tool_search combinations
-        remain unqualified, including inherited template contents. Other non-text
-        initial input remains unsupported. The Claude workspace profile supports non-deferred
-        function tools with text or successful inline PNG/JPEG results alongside native
-        workspace tools; explicit environment-origin HTTP MCP uses the common Runtime
-        path. MiniMax accepts public environment-origin HTTP MCP only with null or
-        omitted allowed_tools and required=false; even an empty non-null allowlist
-        rejects. Idle Sessions provision automatically; initial provisioning has no
-        caller connection action. Network defaults to enabled; disabled and restricted
-        policies reject before compute allocation because the current Runtime cannot
-        enforce them. The x_agents_core.environment extension accepts common preparation
-        fields for either hosted or self-hosted placement: environment_template_id,
-        files, env, packages, setup_commands, skills, plugins and capability_directories.
-        Duplicate fields in environment and the extension reject. Confidential env,
-        npm/Python packages and ordered setup commands use the same Environment-owned
-        initialization lifecycle; compute allocation does not own preparation. Unknown
-        side effects are not replayed after disconnect or restart. System dependencies
-        must be preinstalled in the sandbox image or template, or on the host machine;
-        packages.system is rejected. Initial inline and tenant-owned file_id files
-        freeze encrypted bytes before provisioning, then install through the common
-        Core lifecycle before native execution or live Files access. With a template
-        reference, omitted/null files, env, packages and setup_commands inherit. Non-null
-        files and command lists replace; env overlays by key; each package manager
-        inherits on omission/null and otherwise replaces its list. Empty lists clear
-        their selected field. Tenant-owned environment_template_id references inherit
-        omitted/null network and allow only narrowing overrides. Inline hosted network:null
-        retains the enabled default; updating a Template with network:null resets
-        its saved policy to enabled. Core freezes effective configuration; template
-        updates/deletion do not alter Session snapshots or same-intent creation retries.
-        Inline or tenant-owned skill_reference Skills share initialization. Templates
-        preserve default/latest/explicit selectors; Session creation freezes concrete
-        metadata and encrypted content atomically. Skill, Plugin and capability-directory
-        list omission/null inherit; a non-null list replaces, including empty-list
-        clearing. Omitted/null Skill version selectors resolve the default version.
-        Source deletion/default updates cannot change committed Session Skill contents.
-        Deferred function discovery uses type-only tool_search and per-function defer_loading
-        in the qualified single-agent Claude function profile on none or a managed/user-owned
-        workspace, including qualified inline image messages and text results. Explicit
-        web_search mode disabled and programmatic_tool_calling enabled false use frozen
-        common Runtime controls. Enabled forms, including those saved on an Agent,
-        remain unqualified and reject before any write unless the Session replaces
-        tools. Omitted programmatic configuration preserves native behavior, a documented
-        difference from the official default-on behavior. Other combinations remain
-        unqualified; see the operation coverage.'
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Creation retry key, up to 128 bytes
-        in: header
-        name: Idempotency-Key
-        type: string
-      - description: Session configuration
-        in: body
-        name: body
-        required: true
-        schema:
-          $ref: '#/definitions/v1.CreateSessionRequest'
-      produces:
-      - application/json
-      - text/event-stream
-      responses:
-        "201":
-          description: Created
-          schema:
-            $ref: '#/definitions/v1.Session'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "409":
-          description: Conflict
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "413":
-          description: Request Entity Too Large
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Create an execution Session
-      tags:
-      - Sessions
-  /agents/sessions/{session_id}:
-    delete:
-      description: Removes a durably idle or failed Session and its history from the
-        public API. A Session whose root Turn is queued, in progress or waiting (including
-        required actions) or whose input reservation is pending returns 409 conflict_error
-        and is left unchanged; cancel it and wait until it is idle before deleting.
-        Subagent child Turns and pending Environment file writes are not checked and
-        do not block deletion. Repeating the deletion of the caller's own deleted
-        Session returns the same confirmation; missing and foreign Sessions return
-        404. Internal records and native history are retained pending separate physical
-        cleanup; overlapping stream timing remains unverified.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Session ID
-        in: path
-        name: session_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.SessionDeleted'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "409":
-          description: Conflict
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "413":
-          description: Request Entity Too Large
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Delete an execution Session
-      tags:
-      - Sessions
-    get:
-      description: Returns supported none, self_hosted and basic openai_hosted Session
-        environments. Self-hosted pending input can require a caller connection before
-        a Turn exists. Hosted initial provisioning remains idle until a Turn starts;
-        connection observations are not native execution readiness.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Session ID
-        in: path
-        name: session_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.Session'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Retrieve an execution Session
-      tags:
-      - Sessions
-    post:
-      consumes:
-      - application/json
-      description: The metadata field is required in an update body. Send null or
-        {} to clear it, or supply an object to replace all pairs. Up to 16 string
-        pairs, with keys at most 64 characters and values at most 512 characters;
-        violations and non-string values return invalid_request_error with a metadata
-        or metadata.<key> param. U+0000 is rejected as a local storage limit. Malformed,
-        missing and foreign Session IDs share the not-found response. Execution configuration
-        and activity are unchanged. Returns the same safe Environment and pending-input
-        activity projection as Session retrieval.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Session ID
-        in: path
-        name: session_id
-        required: true
-        type: string
-      - description: Session metadata
-        in: body
-        name: body
-        required: true
-        schema:
-          $ref: '#/definitions/v1.UpdateSessionRequest'
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.Session'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "413":
-          description: Request Entity Too Large
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Update execution Session metadata
-      tags:
-      - Sessions
-  /agents/sessions/{session_id}/artifacts:
-    get:
-      description: Lists published outputs independently of Environment availability.
-        Sorting uses publication time and ID. A later Turn publishes a path again
-        only when it is new, its bytes changed, or no Artifact remains for it. A malformed
-        environment_id matches nothing. An after value that is not an Artifact of
-        this Session, including a malformed one, returns 400 invalid_request_error
-        with the message "after is not a valid artifact ID". The local default page
-        size is 20; exact upstream defaults remain unverified.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Session ID
-        in: path
-        name: session_id
-        required: true
-        type: string
-      - description: Producing Environment ID; an unknown or malformed ID returns
-          an empty page
-        in: query
-        name: environment_id
-        type: string
-      - description: Last immutable artifact ID
-        in: query
-        name: after
-        type: string
-      - default: 20
-        description: Page size
-        in: query
-        maximum: 100
-        minimum: 1
-        name: limit
-        type: integer
-      - default: desc
-        description: Publication order; omit for descending, explicit empty values
-          are invalid
-        enum:
-        - asc
-        - desc
-        in: query
-        name: order
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.SessionArtifactList'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: List immutable Session artifacts
-      tags:
-      - Artifacts
-  /agents/sessions/{session_id}/artifacts/{artifact_id}:
-    delete:
-      description: Deletes the published copy without modifying its original workspace
-        file. Already admitted content reads may finish; later reads reject.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Session ID
-        in: path
-        name: session_id
-        required: true
-        type: string
-      - description: Artifact ID
-        in: path
-        name: artifact_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.SessionArtifactDeleted'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Delete a published artifact
-      tags:
-      - Artifacts
-    get:
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Session ID
-        in: path
-        name: session_id
-        required: true
-        type: string
-      - description: Artifact ID
-        in: path
-        name: artifact_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.SessionArtifact'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Retrieve immutable artifact metadata
-      tags:
-      - Artifacts
-  /agents/sessions/{session_id}/artifacts/{artifact_id}/content:
-    get:
-      description: Streams stored bytes after tenant and Session authorization, including
-        after Environment expiration. Exact upstream headers and Range behavior remain
-        unverified.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Session ID
-        in: path
-        name: session_id
-        required: true
-        type: string
-      - description: Artifact ID
-        in: path
-        name: artifact_id
-        required: true
-        type: string
-      produces:
-      - application/octet-stream
-      responses:
-        "200":
-          description: OK
-          schema:
-            type: file
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Download immutable artifact bytes
-      tags:
-      - Artifacts
-  /agents/sessions/{session_id}/events:
-    get:
-      description: |-
-        Live-only events, including command output fragments from capable Codex peers as agent.output.command_execution_output.delta with stable Item/output indexes. Native text conversion and output quotas apply; completion snapshots remain authoritative. Reconnect through Session, Turn and Items reads; missed events are not replayed. A lagging stream closes with an error when its bounded buffer is exceeded. When a hosted Environment fails to provision, the stream sends agent.session.environment.failed, an error event (environment_error/sandbox_error with the safe step and exit-status reason, never command output) and agent.session.failed, then ends. Session activity includes immutable pending-input connection actions before Turn creation; self_hosted environments use the same safe output as Session retrieval.
-        Active streams revalidate the original Project key every second before output; revocation, Project archival or authentication unavailability closes the stream. Authentication checks use a five-second timeout.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Session ID
-        in: path
-        name: session_id
-        required: true
-        type: string
-      produces:
-      - text/event-stream
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.SessionEvent'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Stream live Session events
-      tags:
-      - Events
-    post:
-      consumes:
-      - application/json
-      description: An empty events array is a resource-authorized no-op; it creates
-        no execution retry identity, Turn, Item or input receipt. For environment
-        none, atomically accepts text messages, cancellation and function results.
-        Messages steer active work or start a queued Turn. Qualified Codex and Claude
-        SDK workspace profiles accept text and inline PNG/JPEG messages, independently
-        of managed or self_hosted ownership. Under the Session lock, matching retries
-        retain their original target; new active messages append to the current Turn,
-        while idle messages reserve work and wait up to the original five-minute connection/admission
-        deadline. Return 202 only after durable admission, without claiming native
-        application; active messages create no Turn or reservation. Cancellation-only
-        prepared-environment batches use existing durable cancellation admission and
-        return 202 without waiting for native exit; a new cancellation conflicts while
-        a pre-Turn reservation is pending. Homogeneous tool_result-only prepared-environment
-        batches reuse existing scoped result admission and application receipts without
-        creating a Turn or bypassing a pending reservation. Mixed prepared-environment
-        batches remain unsupported. HTTP expiry/cancellation use local 409 environment_input_expired/environment_input_cancelled
-        errors. New input on a Session whose hosted Environment failed to provision
-        returns the observed 409 conflict_error "the hosted environment failed to
-        provision"; input already waiting when it fails and expired Environments keep
-        the local 409 environment_unavailable. Input the Session cannot accept in
-        its current state, such as a result after cancellation or a batch while earlier
-        input is pending, and a result that differs from the call's saved result return
-        409 with type and code conflict_error; reusing an Idempotency-Key with a different
-        batch returns the local 409 idempotency_conflict. Inside an owned Session,
-        a result for an unknown call or for a call of another Turn returns 400 invalid_request_error
-        and changes nothing; missing and foreign Sessions return 404. Losing execution
-        ownership returns 503. The response write deadline accommodates the admission
-        window for either prepared Environment, independently of new-hosted-admission
-        and executor URL settings. Disconnecting the waiting HTTP request does not
-        cancel retained work or restart its deadline. Retry keys identify the whole
-        ordered batch. Function output accepts text or ordered text/image parts subject
-        to engine support; Claude SDK accepts text results and, on none and qualified
-        workspace profiles, successful inline PNG/JPEG results, preserving ordered
-        content; error images and remote references reject before admission. Native
-        image resizing may change bytes. Runtime image-result support is checked only
-        for image-bearing delivery. Codex and Claude SDK on none and qualified managed
-        or self_hosted workspace profiles accept ordered inline PNG/JPEG image messages.
-        Other engines remain text-only; remote image URLs are unsupported. Image references
-        are retained unchanged without service-side downloads.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Retry key, up to 128 bytes
-        in: header
-        name: Idempotency-Key
-        type: string
-      - description: Session ID
-        in: path
-        name: session_id
-        required: true
-        type: string
-      - description: Ordered input events
-        in: body
-        name: body
-        required: true
-        schema:
-          $ref: '#/definitions/v1.CreateEventsRequest'
-      responses:
-        "202":
-          description: Accepted
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "409":
-          description: Conflict
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "413":
-          description: Request Entity Too Large
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Submit Session input events
-      tags:
-      - Sessions
-  /agents/sessions/{session_id}/items:
-    get:
-      description: Returns supported message and tool Items in first-observation order.
-        Native engine fields are projected explicitly; unfinished Items on terminal
-        Turns are incomplete. Cursors are Items of the same tenant and Session. Any
-        other after value, including a malformed one, returns 400 invalid_request_error
-        with the message "Invalid session item ID in `after`".
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Session ID
-        in: path
-        name: session_id
-        required: true
-        type: string
-      - description: Last Item ID from the previous page
-        in: query
-        name: after
-        type: string
-      - default: 20
-        description: Page size; 0 is treated as 1 and values above 100 as 100
-        in: query
-        minimum: 0
-        name: limit
-        type: integer
-      - default: desc
-        description: Creation order; omit for descending, explicit empty values are
-          invalid
-        enum:
-        - asc
-        - desc
-        in: query
-        name: order
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.ItemList'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: List persisted execution Items
-      tags:
-      - Items
-  /agents/sessions/{session_id}/subagents:
-    get:
-      description: Includes nested and closed Subagents. Cursors are Subagents of
-        the same tenant and Session. Any other after value, including a malformed
-        one, returns 400 invalid_request_error with the message "Invalid resource
-        ID in `after`". A limit outside 1–100 is rejected.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Session ID
-        in: path
-        name: session_id
-        required: true
-        type: string
-      - description: Last Subagent ID from the previous page
-        in: query
-        name: after
-        type: string
-      - default: 20
-        description: Page size
-        in: query
-        maximum: 100
-        minimum: 1
-        name: limit
-        type: integer
-      - default: desc
-        description: Resource order; omit for descending, explicit empty values are
-          invalid
-        enum:
-        - asc
-        - desc
-        in: query
-        name: order
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.SubagentList'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: List Session Subagents
-      tags:
-      - Subagents
-  /agents/sessions/{session_id}/subagents/{subagent_id}:
-    get:
-      description: Returns this Session's persisted Subagent. Active includes idle
-        between Turns. Resuming preserves opened_at and clears closed_at. Unknown
-        or inaccessible parent scopes return not found.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Session ID
-        in: path
-        name: session_id
-        required: true
-        type: string
-      - description: Subagent ID
-        in: path
-        name: subagent_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.Subagent'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Retrieve a Session Subagent
-      tags:
-      - Subagents
-  /agents/sessions/{session_id}/subagents/{subagent_id}/items:
-    get:
-      description: Returns only this Subagent's own Items across all its Turns, not
-        its descendants' Items. Cursors are Items of the same tenant, Session and
-        Subagent. Any other after value, including a malformed one, returns 400 invalid_request_error
-        with the message "Invalid session item ID in `after`".
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Session ID
-        in: path
-        name: session_id
-        required: true
-        type: string
-      - description: Subagent ID
-        in: path
-        name: subagent_id
-        required: true
-        type: string
-      - description: Last Item ID from the previous page
-        in: query
-        name: after
-        type: string
-      - default: 20
-        description: Page size; 0 is treated as 1 and values above 100 as 100
-        in: query
-        minimum: 0
-        name: limit
-        type: integer
-      - default: desc
-        description: Resource order; omit for descending, explicit empty values are
-          invalid
-        enum:
-        - asc
-        - desc
-        in: query
-        name: order
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.ItemList'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: List a Subagent's Items
-      tags:
-      - Subagents
-  /agents/sessions/{session_id}/subagents/{subagent_id}/turns:
-    get:
-      description: Includes this Subagent's Turns after resume, with the Session's
-        Agent ID as agent_id. Cursors are Turns of the same tenant, Session and Subagent.
-        Any other after value, including a malformed one, returns 400 invalid_request_error
-        with the message "Invalid resource ID in `after`". Missing recorded usage
-        remains null. A limit outside 1–100 is rejected.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Session ID
-        in: path
-        name: session_id
-        required: true
-        type: string
-      - description: Subagent ID
-        in: path
-        name: subagent_id
-        required: true
-        type: string
-      - description: Last Turn ID from the previous page
-        in: query
-        name: after
-        type: string
-      - default: 20
-        description: Page size
-        in: query
-        maximum: 100
-        minimum: 1
-        name: limit
-        type: integer
-      - default: desc
-        description: Creation order; omit for descending, explicit empty values are
-          invalid
-        enum:
-        - asc
-        - desc
-        in: query
-        name: order
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.TurnList'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: List a Subagent's Turns
-      tags:
-      - Subagents
-  /agents/sessions/{session_id}/subagents/{subagent_id}/turns/{turn_id}:
-    get:
-      description: Returns a Turn owned by this Subagent. Its agent_id is the Session's
-        Agent ID and its subagent_id identifies the Subagent. Session Turn routes
-        do not return child Turns. Unknown or inaccessible parent scopes return not
-        found.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Session ID
-        in: path
-        name: session_id
-        required: true
-        type: string
-      - description: Subagent ID
-        in: path
-        name: subagent_id
-        required: true
-        type: string
-      - description: Turn ID
-        in: path
-        name: turn_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.Turn'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Retrieve a Subagent Turn
-      tags:
-      - Subagents
-  /agents/sessions/{session_id}/subagents/{subagent_id}/turns/{turn_id}/items:
-    get:
-      description: Returns Items owned by this exact Subagent Turn. Cursors are Items
-        of the same tenant, Session, Subagent and Turn. Any other after value, including
-        a malformed one, returns 400 invalid_request_error with the message "Invalid
-        session item ID in `after`".
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Session ID
-        in: path
-        name: session_id
-        required: true
-        type: string
-      - description: Subagent ID
-        in: path
-        name: subagent_id
-        required: true
-        type: string
-      - description: Turn ID
-        in: path
-        name: turn_id
-        required: true
-        type: string
-      - description: Last Item ID from the previous page
-        in: query
-        name: after
-        type: string
-      - default: 20
-        description: Page size; 0 is treated as 1 and values above 100 as 100
-        in: query
-        minimum: 0
-        name: limit
-        type: integer
-      - default: desc
-        description: Resource order; omit for descending, explicit empty values are
-          invalid
-        enum:
-        - asc
-        - desc
-        in: query
-        name: order
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.ItemList'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: List a Subagent Turn's Items
-      tags:
-      - Subagents
-  /agents/sessions/{session_id}/turns:
-    get:
-      description: Returns the Session's root Turns in creation order; Subagent Turns
-        are listed through the Subagent Turn routes. The cursor belongs to the same
-        Session and tenant; any other after value, including a malformed one or a
-        Subagent Turn ID, returns not found. Usage contains the latest recorded complete
-        token breakdown; missing measurements remain null.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Session ID
-        in: path
-        name: session_id
-        required: true
-        type: string
-      - description: Last Turn ID from the previous page
-        in: query
-        name: after
-        type: string
-      - default: 20
-        description: Page size
-        in: query
-        maximum: 100
-        minimum: 1
-        name: limit
-        type: integer
-      - default: desc
-        description: Creation order; omit for descending, explicit empty values are
-          invalid
-        enum:
-        - asc
-        - desc
-        in: query
-        name: order
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.TurnList'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: List execution Turns
-      tags:
-      - Turns
-  /agents/sessions/{session_id}/turns/{turn_id}:
-    get:
-      description: Returns a root Turn of this Session. A Subagent Turn ID returns
-        the same not found error as a missing Turn; read it through the Subagent Turn
-        routes.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Session ID
-        in: path
-        name: session_id
-        required: true
-        type: string
-      - description: Turn ID
-        in: path
-        name: turn_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.Turn'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Retrieve an execution Turn
-      tags:
-      - Turns
-  /files:
-    get:
-      description: Lists project-owned Files without reading their bodies. The limit
-        defaults to 10000 and must be 1–10000. Equal creation times use ID ordering.
-        Purpose validation precedes cursor lookup; current storage contains only user_data.
-        An explicit empty purpose is treated as omitted. Repeated purpose values remain
-        rejected. Hosted positive filtering, default order and concurrent-page behavior
-        remain unverified. No Beta header is required.
-      parameters:
-      - description: Last File ID from the previous page
-        in: query
-        name: after
-        type: string
-      - default: 10000
-        description: Maximum page size, 1–10000
-        in: query
-        maximum: 10000
-        minimum: 1
-        name: limit
-        type: integer
-      - default: desc
-        description: Creation order; omit for descending, explicit empty values are
-          invalid
-        enum:
-        - asc
-        - desc
-        in: query
-        name: order
-        type: string
-      - description: Only return Files with this purpose
-        in: query
-        name: purpose
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.SourceFileList'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: List source files
-      tags:
-      - Files
-    post:
-      consumes:
-      - multipart/form-data
-      description: Accepts one multipart file and purpose=user_data in either order,
-        with a private 512 MiB content limit and 64 KiB envelope allowance. Commits
-        only after the entire request validates. The source is project-owned, independent
-        of Sessions and workspace copies. No Beta header is required. Other purposes,
-        expires_after, listing, resumable Uploads, quotas/rate-limit and complete
-        hosted error/status parity remain unsupported or unverified.
-      parameters:
-      - description: Source bytes
-        in: formData
-        name: file
-        required: true
-        type: file
-      - description: user_data
-        enum:
-        - user_data
-        in: formData
-        name: purpose
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.SourceFile'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "413":
-          description: Request Entity Too Large
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Upload a source file
-      tags:
-      - Files
-  /files/{file_id}:
-    delete:
-      description: Atomically deletes project-owned metadata and stored bytes. Already-admitted
-        reads or copies may finish. Workspace copies remain independent. Historical
-        WAL/backups are not erased. No Beta header is required; exact hosted concurrent
-        deletion/error semantics remain unverified.
-      parameters:
-      - description: Source file ID
-        in: path
-        name: file_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.SourceFileDeleted'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Delete a source file
-      tags:
-      - Files
-    get:
-      description: Returns immutable project-owned user_data file metadata. No Beta
-        header is required. Other purposes, expiration and full hosted status/error
-        semantics remain unimplemented or unverified.
-      parameters:
-      - description: Source file ID
-        in: path
-        name: file_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.SourceFile'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Retrieve source file metadata
-      tags:
-      - Files
-  /files/{file_id}/content:
-    get:
-      description: Resolves project-owned File metadata before enforcing download
-        policy. Public download of user_data Files returns 400; missing and foreign
-        Files return the same 404. Internal initial-file and workspace copies remain
-        available. No Beta header is required.
-      parameters:
-      - description: Source file ID
-        in: path
-        name: file_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Download source file bytes
-      tags:
-      - Files
-  /skills:
-    get:
-      description: Lists tenant-owned metadata in timestamp order. Default page size
-        20, maximum 100. Limit 0 returns an empty page whose has_more reports whether
-        any Skill follows the cursor; exact hosted defaults remain unverified.
-      parameters:
-      - description: Skill resource cursor
-        in: query
-        name: after
-        type: string
-      - default: 20
-        description: Page size; 0 returns an empty page
-        in: query
-        maximum: 100
-        minimum: 0
-        name: limit
-        type: integer
-      - description: Creation order; omit for descending, explicit empty values are
-          invalid
-        enum:
-        - asc
-        - desc
-        in: query
-        name: order
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.SkillList'
-      security:
-      - BearerAuth: []
-      summary: List Skills
-      tags:
-      - Skills
-    post:
-      consumes:
-      - multipart/form-data
-      description: Accepts one ZIP in files or a directory in files[]. Applies the
-        qualified portable Skill bundle profile. No Beta header is required; full
-        hosted upload limits and activation extensions are not qualified.
-      parameters:
-      - description: Skill ZIP or directory files
-        in: formData
-        name: files
-        required: true
-        type: file
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.Skill'
-      security:
-      - BearerAuth: []
-      summary: Upload a Skill
-      tags:
-      - Skills
-  /skills/{skill_id}:
-    delete:
-      description: Deletes tenant-owned source bundles. Existing Session installation
-        snapshots remain independent.
-      parameters:
-      - description: Skill ID
-        in: path
-        name: skill_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.SkillDeleted'
-      security:
-      - BearerAuth: []
-      summary: Delete a Skill and its versions
-      tags:
-      - Skills
-    get:
-      description: Returns tenant-owned metadata without decrypting contents or starting
-        Runtime. No Beta header is required.
-      parameters:
-      - description: Skill ID
-        in: path
-        name: skill_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.Skill'
-      security:
-      - BearerAuth: []
-      summary: Retrieve Skill metadata
-      tags:
-      - Skills
-    post:
-      consumes:
-      - application/json
-      description: Changes only the tenant-owned default pointer; immutable versions
-        and existing Session snapshots remain unchanged.
-      parameters:
-      - description: Skill ID
-        in: path
-        name: skill_id
-        required: true
-        type: string
-      - description: Default version
-        in: body
-        name: body
-        required: true
-        schema:
-          $ref: '#/definitions/v1.SkillUpdateRequest'
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.Skill'
-      security:
-      - BearerAuth: []
-      summary: Update the default Skill version
-      tags:
-      - Skills
-  /skills/{skill_id}/content:
-    get:
-      description: Downloads an authorized ZIP using the default pointer when no concrete
-        version is supplied. Exact upstream unversioned selection, content headers
-        and range semantics remain unverified.
-      parameters:
-      - description: Skill ID
-        in: path
-        name: skill_id
-        required: true
-        type: string
-      produces:
-      - application/octet-stream
-      responses:
-        "200":
-          description: OK
-          schema:
-            type: file
-      security:
-      - BearerAuth: []
-      summary: Download Skill content
-      tags:
-      - Skills
-  /skills/{skill_id}/versions:
-    get:
-      description: Orders by version number; after identifies a version resource,
-        not a version number. An after value that does not begin with skillver, or
-        a version of another Skill, returns 400 invalid_value with param after; a
-        missing version returns not found. No contents are decrypted. Limit 0 returns
-        an empty page whose has_more reports whether any version follows the cursor.
-      parameters:
-      - description: Skill ID
-        in: path
-        name: skill_id
-        required: true
-        type: string
-      - description: Version resource cursor
-        in: query
-        name: after
-        type: string
-      - default: 20
-        description: Page size; 0 returns an empty page
-        in: query
-        maximum: 100
-        minimum: 0
-        name: limit
-        type: integer
-      - description: Version order; omit for descending, explicit empty values are
-          invalid
-        enum:
-        - asc
-        - desc
-        in: query
-        name: order
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.SkillVersionList'
-      security:
-      - BearerAuth: []
-      summary: List Skill versions
-      tags:
-      - Skills
-    post:
-      consumes:
-      - multipart/form-data
-      parameters:
-      - description: Skill ID
-        in: path
-        name: skill_id
-        required: true
-        type: string
-      - description: Skill ZIP or directory files
-        in: formData
-        name: files
-        required: true
-        type: file
-      - description: Set as default
-        in: formData
-        name: default
-        type: boolean
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.SkillVersion'
-      security:
-      - BearerAuth: []
-      summary: Upload an immutable Skill version
-      tags:
-      - Skills
-  /skills/{skill_id}/versions/{version}:
-    delete:
-      description: Deleting the only remaining version also deletes the Skill; existing
-        Session installation snapshots remain independent. The default version cannot
-        be deleted while other versions remain. Version numbers are never reused.
-      parameters:
-      - description: Skill ID
-        in: path
-        name: skill_id
-        required: true
-        type: string
-      - description: Concrete version number
-        in: path
-        name: version
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.SkillVersionDeleted'
-      security:
-      - BearerAuth: []
-      summary: Delete a Skill version
-      tags:
-      - Skills
-    get:
-      parameters:
-      - description: Skill ID
-        in: path
-        name: skill_id
-        required: true
-        type: string
-      - description: Concrete version number
-        in: path
-        name: version
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.SkillVersion'
-      security:
-      - BearerAuth: []
-      summary: Retrieve Skill version metadata
-      tags:
-      - Skills
-  /skills/{skill_id}/versions/{version}/content:
-    get:
-      parameters:
-      - description: Skill ID
-        in: path
-        name: skill_id
-        required: true
-        type: string
-      - description: Concrete version number
-        in: path
-        name: version
-        required: true
-        type: string
-      produces:
-      - application/octet-stream
-      responses:
-        "200":
-          description: OK
-          schema:
-            type: file
-      security:
-      - BearerAuth: []
-      summary: Download immutable Skill version content
-      tags:
-      - Skills
-  /vaults:
-    get:
-      description: Lists project-owned Vaults independently of execution. An unknown,
-        malformed or foreign after cursor returns not found. Includes active and archived
-        records by default. Status accepts a scalar, the SDK's status[] array or both,
-        filtering by their union; a repeated scalar is rejected. Limits default to
-        20 and clamp to 1–100. Equal creation times use ID ordering; exact hosted
-        errors and concurrent-page behavior remain unverified. Archive/delete lifecycle
-        is not implemented.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Last Vault ID from the previous page
-        in: query
-        name: after
-        type: string
-      - default: 20
-        description: Requested page size, clamped to 1–100
-        in: query
-        name: limit
-        type: integer
-      - default: desc
-        description: Creation order; omit for descending, explicit empty values are
-          invalid
-        enum:
-        - asc
-        - desc
-        in: query
-        name: order
-        type: string
-      - description: Scalar status filter
-        enum:
-        - active
-        - archived
-        in: query
-        name: status
-        type: string
-      - collectionFormat: multi
-        description: Array status filter; combined with status as a union
-        in: query
-        items:
-          enum:
-          - active
-          - archived
-          type: string
-        name: status[]
-        type: array
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.VaultList'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: List Vaults
-      tags:
-      - Vaults
-    post:
-      consumes:
-      - application/json
-      description: Creates a project-owned Vault independently of execution. Omitted
-        name stays null; a supplied string is trimmed and must contain 1–256 UTF-8
-        bytes. Explicit null name is invalid. Omitted/null metadata becomes an empty
-        object; non-string values return invalid_request_error with a metadata.<key>
-        param. Metadata has a local 64 KiB encoded storage bound. U+0000 in stored
-        strings is rejected as a local storage limit. Credentials, Session binding
-        and hosted error/retry parity remain incomplete.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Vault name and metadata
-        in: body
-        name: body
-        required: true
-        schema:
-          $ref: '#/definitions/v1.CreateVaultRequest'
-      produces:
-      - application/json
-      responses:
-        "201":
-          description: Created
-          schema:
-            $ref: '#/definitions/v1.Vault'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "413":
-          description: Request Entity Too Large
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Create a Vault
-      tags:
-      - Vaults
-  /vaults/{vault_id}:
-    delete:
-      description: Atomically removes the authenticated project's Vault and all its
-        stored Credentials without an encryption key, decryption or external requests.
-        Existing Session snapshots, history and recorded retries retain their frozen
-        identities; subsequent credential lookups fail without reselection or anonymous
-        fallback. Already-resolved tokens and running Sessions are not revoked or
-        cancelled. Missing/repeated deletion locally returns 404. Exact hosted archive,
-        post-delete visibility and concurrent/error semantics remain unverified; physical
-        erasure from native history, WAL or backups is not established.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Vault ID
-        in: path
-        name: vault_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.VaultDeleted'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "413":
-          description: Request Entity Too Large
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Delete a Vault and all its Credentials
-      tags:
-      - Vaults
-    get:
-      description: Reads a Vault owned by the authenticated project without resolving
-        credentials, Sessions or execution devices. Missing and foreign IDs share
-        the same not-found response; exact hosted error semantics remain unverified.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Vault ID
-        in: path
-        name: vault_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.Vault'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Retrieve a Vault
-      tags:
-      - Vaults
-  /vaults/{vault_id}/credentials:
-    get:
-      description: Lists only metadata from the authenticated project's requested
-        Vault, without decryption or execution. An unknown, malformed or foreign after
-        cursor, including another Vault's Credential, returns not found. Includes
-        active and archived Credentials by default, independently of Vault status.
-        Status accepts a scalar, the SDK status[] array or both, filtering by their
-        union; a repeated scalar is rejected. Limits default to 20 and clamp to 1–100.
-        Equal creation times use ID ordering. Hosted errors, concurrent-page behavior
-        and archive/delete lifecycle remain unverified or unimplemented.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Vault ID
-        in: path
-        name: vault_id
-        required: true
-        type: string
-      - description: Last Credential ID from the previous page
-        in: query
-        name: after
-        type: string
-      - default: 20
-        description: Requested page size, clamped to 1–100
-        in: query
-        name: limit
-        type: integer
-      - default: desc
-        description: Creation order; omit for descending, explicit empty values are
-          invalid
-        enum:
-        - asc
-        - desc
-        in: query
-        name: order
-        type: string
-      - description: Scalar status filter
-        enum:
-        - active
-        - archived
-        in: query
-        name: status
-        type: string
-      - collectionFormat: multi
-        description: Array status filter; combined with status as a union
-        in: query
-        items:
-          enum:
-          - active
-          - archived
-          type: string
-        name: status[]
-        type: array
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.CredentialList'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: List safe Vault Credential metadata
-      tags:
-      - Credentials
-    post:
-      consumes:
-      - application/json
-      description: Stores static_bearer or mcp_oauth secrets as execution-owned authenticated
-        ciphertext without contacting any endpoint. Static bearer and OAuth access
-        tokens must be nonempty strings; their bytes are preserved. OAuth accepts
-        a required access token, nullable RFC3339 expiry and optional refresh configuration
-        with none, client_secret_basic or client_secret_post authentication. Required
-        name is trimmed to 1–256 UTF-8 bytes. Credential and token endpoints require
-        HTTPS without userinfo or fragments. Responses contain safe metadata only,
-        including explicit nullable OAuth expiry, refresh, resource and scope. Missing
-        encryption configuration returns local 503. External authorization and provider
-        revocation remain caller responsibilities; exact hosted error/default semantics
-        remain unverified.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Vault ID
-        in: path
-        name: vault_id
-        required: true
-        type: string
-      - description: Write-only credential authentication union
-        in: body
-        name: body
-        required: true
-        schema:
-          $ref: '#/definitions/v1.CreateCredentialRequest'
-      produces:
-      - application/json
-      responses:
-        "201":
-          description: Created
-          schema:
-            $ref: '#/definitions/v1.Credential'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "413":
-          description: Request Entity Too Large
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Create a Vault Credential
-      tags:
-      - Credentials
-  /vaults/{vault_id}/credentials/{credential_id}:
-    delete:
-      description: Removes one Credential and its encrypted token within the authenticated
-        project and owning Vault, without an encryption key or secret decryption.
-        Subsequent metadata reads, updates and dispatch lookups cannot use it. Existing
-        Session snapshots and history retain their frozen identities; already-resolved
-        tokens and running Sessions are not revoked or cancelled. This local policy
-        removes the row rather than defining archived lifecycle; missing/repeated
-        deletion returns 404. Exact hosted archive, post-delete visibility and retry/error
-        semantics remain unverified. Provider revocation and physical erasure from
-        native history, WAL or backups are separate concerns.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Vault ID
-        in: path
-        name: vault_id
-        required: true
-        type: string
-      - description: Credential ID
-        in: path
-        name: credential_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.CredentialDeleted'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "413":
-          description: Request Entity Too Large
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Delete a Vault Credential
-      tags:
-      - Credentials
-    get:
-      description: Reads only non-secret metadata scoped to the authenticated project
-        and owning Vault. No token decryption, network request or execution is performed.
-        Unknown, foreign, wrong-Vault and malformed IDs use the same local not-found
-        response; hosted error parity remains unverified.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Vault ID
-        in: path
-        name: vault_id
-        required: true
-        type: string
-      - description: Credential ID
-        in: path
-        name: credential_id
-        required: true
-        type: string
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.Credential'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Retrieve safe Vault Credential metadata
-      tags:
-      - Credentials
-    post:
-      consumes:
-      - application/json
-      description: Explicitly empty static bearer or OAuth access tokens and OAuth
-        patches without a mutable field are rejected before storage. Omitted OAuth
-        access tokens preserve the existing grant when expiry or refresh fields change.
-        Updates the existing static_bearer or mcp_oauth authentication method without
-        network requests. OAuth access_token omission/null retains the token; a new
-        token clears omitted expiry, explicit null clears expiry, and other omitted
-        fields remain unchanged. OAuth refresh patches cannot add configuration or
-        change client, endpoint, resource or authentication method; nullable token/client-secret
-        values retain stored secrets while explicit null scope clears scope. Whole-null
-        refresh and token_endpoint_auth retain existing configuration under local
-        policy. Identity, destination, creation time and Session bindings remain unchanged.
-        Responses expose safe metadata only. Already-dispatched work is not revoked;
-        provider revocation, storage-key rotation and exact hosted concurrent-update/error
-        semantics remain separate.
-      parameters:
-      - description: agents=v1
-        in: header
-        name: OpenAI-Beta
-        required: true
-        type: string
-      - description: Vault ID
-        in: path
-        name: vault_id
-        required: true
-        type: string
-      - description: Credential ID
-        in: path
-        name: credential_id
-        required: true
-        type: string
-      - description: Write-only credential authentication replacement union
-        in: body
-        name: body
-        required: true
-        schema:
-          $ref: '#/definitions/v1.UpdateCredentialRequest'
-      produces:
-      - application/json
-      responses:
-        "200":
-          description: OK
-          schema:
-            $ref: '#/definitions/v1.Credential'
-        "400":
-          description: Bad Request
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "401":
-          description: Unauthorized
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "404":
-          description: Not Found
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "413":
-          description: Request Entity Too Large
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "500":
-          description: Internal Server Error
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-        "503":
-          description: Service Unavailable
-          schema:
-            $ref: '#/definitions/v1.ErrorResponse'
-      security:
-      - BearerAuth: []
-      summary: Replace Vault Credential authentication secrets
-      tags:
-      - Credentials
-schemes:
-- http
-- https
-securityDefinitions:
-  BearerAuth:
-    in: header
-    name: Authorization
-    type: apiKey
-swagger: "2.0"
+{
+  "openapi": "3.1.0",
+  "info": {
+    "title": "OpenAgentCore public API",
+    "version": "v1",
+    "description": "The pinned OpenAI Agents, Files and Skills API with x_agents_core extensions. See the coverage ledger for implementation qualification."
+  },
+  "servers": [
+    {
+      "url": "/v1"
+    }
+  ],
+  "security": [
+    {
+      "ProjectKey": []
+    }
+  ],
+  "tags": [
+    {
+      "name": "Assistants",
+      "description": "Build Assistants that can call models and use tools."
+    },
+    {
+      "name": "Audio",
+      "description": "Turn audio into text or text into audio."
+    },
+    {
+      "name": "Chat",
+      "description": "Given a list of messages comprising a conversation, the model will return a response."
+    },
+    {
+      "name": "Conversations",
+      "description": "Manage conversations and conversation items."
+    },
+    {
+      "name": "Completions",
+      "description": "Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position."
+    },
+    {
+      "name": "Embeddings",
+      "description": "Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms."
+    },
+    {
+      "name": "Evals",
+      "description": "Manage and run evals in the OpenAI platform."
+    },
+    {
+      "name": "Fine-tuning",
+      "description": "Manage fine-tuning jobs to tailor a model to your specific training data."
+    },
+    {
+      "name": "Graders",
+      "description": "Manage and run graders in the OpenAI platform."
+    },
+    {
+      "name": "Batch",
+      "description": "Create large batches of API requests to run asynchronously."
+    },
+    {
+      "name": "Files",
+      "description": "Files are used to upload documents that can be used with features like Assistants and Fine-tuning."
+    },
+    {
+      "name": "Uploads",
+      "description": "Use Uploads to upload large files in multiple parts."
+    },
+    {
+      "name": "Images",
+      "description": "Given a prompt and/or an input image, the model will generate a new image."
+    },
+    {
+      "name": "Models",
+      "description": "List and describe the various models available in the API."
+    },
+    {
+      "name": "Moderations",
+      "description": "Given text and/or image inputs, classifies if those inputs are potentially harmful."
+    },
+    {
+      "name": "Audit Logs",
+      "description": "List user actions and configuration changes within this organization."
+    }
+  ],
+  "paths": {
+    "/files": {
+      "get": {
+        "operationId": "listFiles",
+        "tags": [
+          "Files"
+        ],
+        "summary": "Returns a list of files.",
+        "parameters": [
+          {
+            "in": "query",
+            "name": "purpose",
+            "required": false,
+            "schema": {
+              "type": "string"
+            },
+            "description": "Only return files with the given purpose."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 10,000, and the default is 10,000.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 10000
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.\n",
+            "schema": {
+              "type": "string",
+              "default": "desc",
+              "enum": [
+                "asc",
+                "desc"
+              ]
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ListFilesResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List files",
+          "group": "files",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/files \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.files.list()\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const list = await openai.files.list();\n\n  for await (const file of list) {\n    console.log(file);\n  }\n}\n\nmain();"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"id\": \"file-abc123\",\n      \"object\": \"file\",\n      \"bytes\": 175,\n      \"created_at\": 1613677385,\n      \"expires_at\": 1677614202,\n      \"filename\": \"salesOverview.pdf\",\n      \"purpose\": \"assistants\",\n    },\n    {\n      \"id\": \"file-abc456\",\n      \"object\": \"file\",\n      \"bytes\": 140,\n      \"created_at\": 1613779121,\n      \"expires_at\": 1677614202,\n      \"filename\": \"puppy.jsonl\",\n      \"purpose\": \"fine-tune\",\n    }\n  ],\n  \"first_id\": \"file-abc123\",\n  \"last_id\": \"file-abc456\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      },
+      "post": {
+        "operationId": "createFile",
+        "tags": [
+          "Files"
+        ],
+        "summary": "Upload a file that can be used across various endpoints. Individual files\ncan be up to 512 MB, and each project can store up to 2.5 TB of files in\ntotal. There is no organization-wide storage limit. Uploads to this\nendpoint are rate-limited to 1,000 requests per minute per authenticated\nuser.\n\n- The Assistants API supports files up to 2 million tokens and of specific\n  file types. See the [Assistants Tools guide](https://developers.openai.com/api/docs/guides/tools) for\n  details.\n- The Fine-tuning API only supports `.jsonl` files. The input also has\n  certain required formats for fine-tuning\n  [chat](https://developers.openai.com/api/docs/guides/supervised-fine-tuning#formatting-your-data) or\n  [completions](https://developers.openai.com/api/docs/guides/supervised-fine-tuning#formatting-your-data) models.\n- The Batch API only supports `.jsonl` files up to 200 MB in size. The input\n  also has a specific required\n  [format](https://developers.openai.com/api/docs/guides/batch#1-prepare-your-batch-file).\n- For Retrieval or `file_search` ingestion, upload files here first. If\n  you need to attach multiple uploaded files to the same vector store, use\n  [`/vector_stores/{vector_store_id}/file_batches`](https://developers.openai.com/api/reference/resources/vector_stores/subresources/file_batches/methods/create)\n  instead of attaching them one by one. Vector store attachment has separate\n  limits from file upload, including 2,000 attached files per minute per\n  organization.\n\nPlease [contact us](https://help.openai.com/) if you need to increase these\nstorage limits.\n",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateFileRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/OpenAIFile"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Upload file",
+          "group": "files",
+          "description": "Uploads a file for later use across OpenAI APIs. Uploads to this endpoint are rate-limited to 1,000 requests per minute per authenticated user. For Retrieval or `file_search` ingestion, upload files here first. If you need to attach multiple uploaded files to the same vector store, use vector store file batches instead of attaching them one by one.\n",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/files \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -F purpose=\"fine-tune\" \\\n  -F file=\"@mydata.jsonl\"\n  -F expires_after[anchor]=\"created_at\"\n  -F expires_after[seconds]=2592000\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.files.create(\n  file=open(\"mydata.jsonl\", \"rb\"),\n  purpose=\"fine-tune\",\n  expires_after={\n    \"anchor\": \"created_at\",\n    \"seconds\": 2592000\n  }\n)\n",
+              "javascript": "import fs from \"fs\";\nimport OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const file = await openai.files.create({\n    file: fs.createReadStream(\"mydata.jsonl\"),\n    purpose: \"fine-tune\",\n    expires_after: {\n      anchor: \"created_at\",\n      seconds: 2592000\n    }\n  });\n\n  console.log(file);\n}\n\nmain();"
+            },
+            "response": "{\n  \"id\": \"file-abc123\",\n  \"object\": \"file\",\n  \"bytes\": 120000,\n  \"created_at\": 1677610602,\n  \"expires_at\": 1677614202,\n  \"filename\": \"mydata.jsonl\",\n  \"purpose\": \"fine-tune\",\n}\n"
+          }
+        }
+      }
+    },
+    "/files/{file_id}": {
+      "delete": {
+        "operationId": "deleteFile",
+        "tags": [
+          "Files"
+        ],
+        "summary": "Delete a file and remove it from all vector stores.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "file_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the file to use for this request."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeleteFileResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete file",
+          "group": "files",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/files/file-abc123 \\\n  -X DELETE \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.files.delete(\"file-abc123\")\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const file = await openai.files.delete(\"file-abc123\");\n\n  console.log(file);\n}\n\nmain();"
+            },
+            "response": "{\n  \"id\": \"file-abc123\",\n  \"object\": \"file\",\n  \"deleted\": true\n}\n"
+          }
+        }
+      },
+      "get": {
+        "operationId": "retrieveFile",
+        "tags": [
+          "Files"
+        ],
+        "summary": "Returns information about a specific file.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "file_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the file to use for this request."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/OpenAIFile"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve file",
+          "group": "files",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/files/file-abc123 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.files.retrieve(\"file-abc123\")\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const file = await openai.files.retrieve(\"file-abc123\");\n\n  console.log(file);\n}\n\nmain();"
+            },
+            "response": "{\n  \"id\": \"file-abc123\",\n  \"object\": \"file\",\n  \"bytes\": 120000,\n  \"created_at\": 1677610602,\n  \"expires_at\": 1677614202,\n  \"filename\": \"mydata.jsonl\",\n  \"purpose\": \"fine-tune\",\n}\n"
+          }
+        }
+      }
+    },
+    "/files/{file_id}/content": {
+      "get": {
+        "operationId": "downloadFile",
+        "tags": [
+          "Files"
+        ],
+        "summary": "Returns a response containing the contents of the specified file.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "file_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the file to use for this request."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "string"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve file content",
+          "group": "files",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/files/file-abc123/content \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" > file.jsonl\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\ncontent = client.files.content(\"file-abc123\")\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const response = await openai.files.content(\"file-abc123\");\n  const content = await response.text();\n\n  console.log(content);\n}\n\nmain();\n"
+            }
+          }
+        }
+      }
+    },
+    "/skills": {
+      "post": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "Create a new skill.",
+        "operationId": "CreateSkill",
+        "parameters": [],
+        "requestBody": {
+          "content": {
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateSkillBody"
+              }
+            },
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateSkillBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SkillResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      },
+      "get": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "List all skills for the current project.",
+        "operationId": "ListSkills",
+        "parameters": [
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Number of items to retrieve",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 100
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order of results by timestamp. Use `asc` for ascending order or `desc` for descending order.",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/OrderEnum"
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Identifier for the last item from the previous pagination request",
+            "required": false,
+            "schema": {
+              "description": "Identifier for the last item from the previous pagination request",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SkillListResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      }
+    },
+    "/skills/{skill_id}": {
+      "delete": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "Delete a skill by its ID.",
+        "operationId": "DeleteSkill",
+        "parameters": [
+          {
+            "name": "skill_id",
+            "in": "path",
+            "description": "The identifier of the skill to delete.",
+            "required": true,
+            "schema": {
+              "example": "skill_123",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedSkillResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      },
+      "get": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "Get a skill by its ID.",
+        "operationId": "GetSkill",
+        "parameters": [
+          {
+            "name": "skill_id",
+            "in": "path",
+            "description": "The identifier of the skill to retrieve.",
+            "required": true,
+            "schema": {
+              "example": "skill_123",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SkillResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      },
+      "post": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "Update the default version pointer for a skill.",
+        "operationId": "UpdateSkillDefaultVersion",
+        "parameters": [
+          {
+            "name": "skill_id",
+            "in": "path",
+            "description": "The identifier of the skill.",
+            "required": true,
+            "schema": {
+              "example": "skill_123",
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/SetDefaultSkillVersionBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SkillResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      }
+    },
+    "/skills/{skill_id}/content": {
+      "get": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "Download a skill zip bundle by its ID.",
+        "operationId": "GetSkillContent",
+        "parameters": [
+          {
+            "name": "skill_id",
+            "in": "path",
+            "description": "The identifier of the skill to download.",
+            "required": true,
+            "schema": {
+              "example": "skill_123",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The skill zip bundle.",
+            "content": {
+              "application/zip": {
+                "schema": {
+                  "type": "string",
+                  "format": "binary"
+                }
+              },
+              "application/json": {
+                "schema": {
+                  "type": "string"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      }
+    },
+    "/skills/{skill_id}/versions": {
+      "post": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "Create a new immutable skill version.",
+        "operationId": "CreateSkillVersion",
+        "parameters": [
+          {
+            "name": "skill_id",
+            "in": "path",
+            "description": "The identifier of the skill to version.",
+            "required": true,
+            "schema": {
+              "example": "skill_123",
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateSkillVersionBody"
+              }
+            },
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateSkillVersionBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SkillVersionResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      },
+      "get": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "List skill versions for a skill.",
+        "operationId": "ListSkillVersions",
+        "parameters": [
+          {
+            "name": "skill_id",
+            "in": "path",
+            "description": "The identifier of the skill.",
+            "required": true,
+            "schema": {
+              "example": "skill_123",
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Number of versions to retrieve.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 100
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order of results by version number.",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/OrderEnum"
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "The skill version ID to start after.",
+            "required": false,
+            "schema": {
+              "example": "skillver_123",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SkillVersionListResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      }
+    },
+    "/skills/{skill_id}/versions/{version}": {
+      "get": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "Get a specific skill version.",
+        "operationId": "GetSkillVersion",
+        "parameters": [
+          {
+            "name": "skill_id",
+            "in": "path",
+            "description": "The identifier of the skill.",
+            "required": true,
+            "schema": {
+              "example": "skill_123",
+              "type": "string"
+            }
+          },
+          {
+            "name": "version",
+            "in": "path",
+            "description": "The version number to retrieve.",
+            "required": true,
+            "schema": {
+              "description": "The version number to retrieve.",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SkillVersionResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      },
+      "delete": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "Delete a skill version.",
+        "operationId": "DeleteSkillVersion",
+        "parameters": [
+          {
+            "name": "skill_id",
+            "in": "path",
+            "description": "The identifier of the skill.",
+            "required": true,
+            "schema": {
+              "example": "skill_123",
+              "type": "string"
+            }
+          },
+          {
+            "name": "version",
+            "in": "path",
+            "description": "The skill version number.",
+            "required": true,
+            "schema": {
+              "description": "The skill version number.",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedSkillVersionResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      }
+    },
+    "/skills/{skill_id}/versions/{version}/content": {
+      "get": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "Download a skill version zip bundle.",
+        "operationId": "GetSkillVersionContent",
+        "parameters": [
+          {
+            "name": "skill_id",
+            "in": "path",
+            "description": "The identifier of the skill.",
+            "required": true,
+            "schema": {
+              "example": "skill_123",
+              "type": "string"
+            }
+          },
+          {
+            "name": "version",
+            "in": "path",
+            "description": "The skill version number.",
+            "required": true,
+            "schema": {
+              "description": "The skill version number.",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The skill zip bundle.",
+            "content": {
+              "application/zip": {
+                "schema": {
+                  "type": "string",
+                  "format": "binary"
+                }
+              },
+              "application/json": {
+                "schema": {
+                  "type": "string"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      }
+    },
+    "/agents/environments/{environment_id}": {
+      "get": {
+        "operationId": "retrieveAgentEnvironment",
+        "summary": "Retrieves an execution environment's connection status and safe installed metadata. See [environment lifecycle](https://developers.openai.com/api/docs/guides/agents-api/environments/lifecycle).",
+        "description": "Retrieves an execution environment's connection status and safe installed metadata.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "environment_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the environment."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested environment.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/PublicEnvironmentResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve an agent environment"
+        }
+      }
+    },
+    "/agents/environments/{environment_id}/files": {
+      "get": {
+        "operationId": "listAgentEnvironmentFiles",
+        "summary": "Lists live files on a connected execution environment with optional directory filtering and opaque cursor pagination. See [environment files](https://developers.openai.com/api/docs/guides/agents-api/environments/files).",
+        "description": "Lists live files on a connected execution environment with optional directory filtering and opaque cursor pagination.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "environment_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the environment."
+          },
+          {
+            "name": "path",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": [
+                "string",
+                "null"
+              ],
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Restrict the listing to this absolute workspace directory."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": [
+                "integer",
+                "null"
+              ],
+              "format": "int64",
+              "minimum": 1,
+              "maximum": 100
+            },
+            "description": "The maximum number of files to return, between 1 and 100."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam"
+            },
+            "description": "Sort by case-sensitive path components. Defaults to descending."
+          },
+          {
+            "name": "page",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The opaque token from the previous page. Keep the same path, order, and limit."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A page of live environment files.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EnvironmentFileListResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List agent environment files"
+        }
+      },
+      "post": {
+        "operationId": "createAgentEnvironmentFile",
+        "summary": "Copies inline bytes or a Files API file into a connected execution environment. See [environment files](https://developers.openai.com/api/docs/guides/agents-api/environments/files).",
+        "description": "Copies inline bytes or a Files API file into a connected execution environment.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "environment_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the environment."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/HostedEnvironmentFileParam"
+              }
+            }
+          }
+        },
+        "responses": {
+          "201": {
+            "description": "The created live environment file.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EnvironmentFileResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create an agent environment file"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/subagents": {
+      "get": {
+        "operationId": "listAgentSessionSubagents",
+        "summary": "Lists subagents in a session, including nested and closed subagents. See [subagent workflows](https://developers.openai.com/api/docs/guides/agents-api/multi-agent).",
+        "description": "Lists subagents in a session, including nested and closed subagents.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "format": "int64",
+              "minimum": 1,
+              "maximum": 100,
+              "default": 20
+            },
+            "description": "The maximum number of resources to return, between 1 and 100. Defaults to 20."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "The order in which resources are returned. Defaults to `desc`."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested subagents.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "object",
+                  "properties": {
+                    "object": {
+                      "type": "string",
+                      "enum": [
+                        "list"
+                      ],
+                      "default": "list",
+                      "x-stainless-const": true,
+                      "description": "The object type, which is always `list`."
+                    },
+                    "data": {
+                      "type": "array",
+                      "items": {
+                        "$ref": "#/components/schemas/SubagentResource"
+                      },
+                      "minItems": 0,
+                      "maxItems": 2000,
+                      "description": "The resources returned in this page, in the requested sort order."
+                    },
+                    "first_id": {
+                      "type": [
+                        "string",
+                        "null"
+                      ],
+                      "minLength": 0,
+                      "description": "The ID of the first resource in `data`, or `null` if the page is empty."
+                    },
+                    "last_id": {
+                      "type": [
+                        "string",
+                        "null"
+                      ],
+                      "minLength": 0,
+                      "description": "The ID of the last resource in `data`, or `null` if the page is empty. Pass this as `after` with the same order and filters."
+                    },
+                    "has_more": {
+                      "type": "boolean",
+                      "description": "Whether there are more resources to retrieve after this page."
+                    }
+                  },
+                  "required": [
+                    "object",
+                    "data",
+                    "first_id",
+                    "last_id",
+                    "has_more"
+                  ],
+                  "additionalProperties": false,
+                  "description": "A page of Agents API resources, with IDs for retrieving additional pages."
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List session subagents"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/subagents/{subagent_id}": {
+      "get": {
+        "operationId": "retrieveAgentSessionSubagent",
+        "summary": "Retrieves a subagent belonging to this session. See [subagent workflows](https://developers.openai.com/api/docs/guides/agents-api/multi-agent).",
+        "description": "Retrieves a subagent belonging to this session.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "subagent_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the subagent in this session."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested subagent.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SubagentResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve a session subagent"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/subagents/{subagent_id}/items": {
+      "get": {
+        "operationId": "listAgentSessionSubagentItems",
+        "summary": "Lists this subagent's own items across all of its turns. See [subagent workflows](https://developers.openai.com/api/docs/guides/agents-api/multi-agent).",
+        "description": "Lists this subagent's own items across all of its turns.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "subagent_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the subagent in this session."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "format": "int64",
+              "minimum": 1,
+              "maximum": 100,
+              "default": 20
+            },
+            "description": "The maximum number of resources to return, between 1 and 100. Defaults to 20."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "The order in which resources are returned. Defaults to `desc`."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested subagent history.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionItemListResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List subagent items"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/subagents/{subagent_id}/turns": {
+      "get": {
+        "operationId": "listAgentSessionSubagentTurns",
+        "summary": "Lists all turns of this subagent, including turns after a resume. See [subagent workflows](https://developers.openai.com/api/docs/guides/agents-api/multi-agent).",
+        "description": "Lists all turns of this subagent, including turns after a resume.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "subagent_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the subagent in this session."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "format": "int64",
+              "minimum": 1,
+              "maximum": 100,
+              "default": 20
+            },
+            "description": "The maximum number of resources to return, between 1 and 100. Defaults to 20."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "The order in which resources are returned. Defaults to `desc`."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested subagent history.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionTurnListResource",
+                  "description": "A page of turns from an agent session or subagent."
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List subagent turns"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/subagents/{subagent_id}/turns/{turn_id}": {
+      "get": {
+        "operationId": "retrieveAgentSessionSubagentTurn",
+        "summary": "Retrieves a turn belonging to this subagent. See [subagent workflows](https://developers.openai.com/api/docs/guides/agents-api/multi-agent).",
+        "description": "Retrieves a turn belonging to this subagent.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "subagent_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the subagent in this session."
+          },
+          {
+            "name": "turn_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of a turn belonging to this subagent."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested subagent history.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/TurnResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve a subagent turn"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/subagents/{subagent_id}/turns/{turn_id}/items": {
+      "get": {
+        "operationId": "listAgentSessionSubagentTurnItems",
+        "summary": "Lists items belonging to one turn of this subagent. See [subagent workflows](https://developers.openai.com/api/docs/guides/agents-api/multi-agent).",
+        "description": "Lists items belonging to one turn of this subagent.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "subagent_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the subagent in this session."
+          },
+          {
+            "name": "turn_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of a turn belonging to this subagent."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "format": "int64",
+              "minimum": 1,
+              "maximum": 100,
+              "default": 20
+            },
+            "description": "The maximum number of resources to return, between 1 and 100. Defaults to 20."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "The order in which resources are returned. Defaults to `desc`."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested subagent history.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionItemListResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List subagent turn items"
+        }
+      }
+    },
+    "/agents": {
+      "get": {
+        "operationId": "listAgents",
+        "summary": "Lists reusable agents in the current project. See [agent configuration](https://developers.openai.com/api/docs/guides/agents-api/configuration).",
+        "description": "Lists reusable agents in the current project.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": [
+                "integer",
+                "null"
+              ],
+              "format": "int64",
+              "minimum": 1
+            },
+            "description": "The maximum number of resources to return."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "The order in which resources are returned. Defaults to `desc`."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A page of agents.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/AgentListResource",
+                  "description": "A page of reusable agents."
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List agents"
+        }
+      },
+      "post": {
+        "operationId": "createAgent",
+        "summary": "Creates a reusable agent without storing credentials. See [agent configuration](https://developers.openai.com/api/docs/guides/agents-api/configuration).",
+        "description": "Creates a reusable agent without storing credentials.",
+        "tags": [
+          "Agents"
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateAgentParams"
+              }
+            }
+          }
+        },
+        "responses": {
+          "201": {
+            "description": "The created agent.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/AgentResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create an agent"
+        },
+        "parameters": [
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ]
+      }
+    },
+    "/agents/{agent_id}": {
+      "get": {
+        "operationId": "retrieveAgent",
+        "summary": "Retrieves a reusable agent by ID. See [agent configuration](https://developers.openai.com/api/docs/guides/agents-api/configuration).",
+        "description": "Retrieves a reusable agent by ID.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "agent_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the reusable agent."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested agent.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/AgentResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve an agent"
+        }
+      },
+      "post": {
+        "operationId": "updateAgent",
+        "summary": "Updates a reusable agent. See [agent configuration](https://developers.openai.com/api/docs/guides/agents-api/configuration).",
+        "description": "Updates a reusable agent.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "agent_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the reusable agent."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/UpdateAgentParams"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "The updated agent.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/AgentResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update an agent"
+        }
+      },
+      "delete": {
+        "operationId": "deleteAgent",
+        "summary": "Deletes a reusable agent. See [agent configuration](https://developers.openai.com/api/docs/guides/agents-api/configuration).",
+        "description": "Deletes a reusable agent.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "agent_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the reusable agent."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The deleted agent.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedAgentResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete an agent"
+        }
+      }
+    },
+    "/agents/environments/templates": {
+      "get": {
+        "operationId": "listAgentEnvironmentTemplates",
+        "summary": "Lists reusable environment templates without returning confidential values. See [reusing a hosted setup](https://developers.openai.com/api/docs/guides/agents-api/tools#reuse-a-hosted-plugin-setup).",
+        "description": "Lists reusable environment templates without returning confidential values.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "format": "int64",
+              "minimum": 1,
+              "maximum": 100,
+              "default": 20
+            },
+            "description": "The maximum number of resources to return, between 1 and 100. Defaults to 20."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "The order in which resources are returned. Defaults to `desc`."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A page of environment templates.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EnvironmentTemplateListResource",
+                  "description": "A page of reusable environment templates."
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested environment definition was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List agent environment templates"
+        }
+      },
+      "post": {
+        "operationId": "createAgentEnvironmentTemplate",
+        "summary": "Creates reusable environment configuration without returning confidential setup commands or environment values. See [reusing a hosted setup](https://developers.openai.com/api/docs/guides/agents-api/tools#reuse-a-hosted-plugin-setup).",
+        "description": "Creates reusable environment configuration without returning confidential setup commands or environment values.",
+        "tags": [
+          "Agents"
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateEnvironmentTemplateParams"
+              }
+            }
+          }
+        },
+        "responses": {
+          "201": {
+            "description": "The created environment template.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EnvironmentTemplateResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested environment definition was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create an agent environment template"
+        },
+        "parameters": [
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ]
+      }
+    },
+    "/agents/environments/templates/{environment_template_id}": {
+      "get": {
+        "operationId": "retrieveAgentEnvironmentTemplate",
+        "summary": "Retrieves reusable environment configuration without returning confidential values. See [reusing a hosted setup](https://developers.openai.com/api/docs/guides/agents-api/tools#reuse-a-hosted-plugin-setup).",
+        "description": "Retrieves reusable environment configuration without returning confidential values.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "environment_template_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the reusable environment template."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested environment template.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EnvironmentTemplateResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested environment definition was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve an agent environment template"
+        }
+      },
+      "post": {
+        "operationId": "updateAgentEnvironmentTemplate",
+        "summary": "Updates reusable environment configuration without returning confidential values. See [reusing a hosted setup](https://developers.openai.com/api/docs/guides/agents-api/tools#reuse-a-hosted-plugin-setup).",
+        "description": "Updates reusable environment configuration without returning confidential values.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "environment_template_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the reusable environment template."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/UpdateEnvironmentTemplateParams"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "The updated environment template.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EnvironmentTemplateResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested environment definition was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current environment state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update an agent environment template"
+        }
+      },
+      "delete": {
+        "operationId": "deleteAgentEnvironmentTemplate",
+        "summary": "Deletes reusable environment configuration and all confidential template inputs. See [reusing a hosted setup](https://developers.openai.com/api/docs/guides/agents-api/tools#reuse-a-hosted-plugin-setup).",
+        "description": "Deletes reusable environment configuration and all confidential template inputs.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "environment_template_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the reusable environment template."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The deleted environment template.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedEnvironmentTemplateResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested environment definition was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current environment state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete an agent environment template"
+        }
+      }
+    },
+    "/agents/sessions": {
+      "get": {
+        "operationId": "listAgentSessions",
+        "summary": "Lists managed agent sessions using ID-based pagination and the requested sort order. See [managing sessions](https://developers.openai.com/api/docs/guides/agents-api/sessions/manage).",
+        "description": "Lists managed agent sessions using ID-based pagination and the requested sort order.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": [
+                "integer",
+                "null"
+              ],
+              "format": "int64",
+              "minimum": 1
+            },
+            "description": "The maximum number of resources to return."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "Sort order by the `created_at` timestamp. Use `asc` for ascending order or `desc` for descending order. Defaults to `desc`."
+          },
+          {
+            "name": "agent_id",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Only return sessions whose root agent has this ID. Omit to return sessions for all agents."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A page of sessions.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionListResource",
+                  "description": "A paginated list of sessions."
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List agent sessions"
+        }
+      },
+      "post": {
+        "operationId": "createAgentSession",
+        "summary": "Creates a managed agent session, optionally submits initial input, and returns the session or streams its events when stream is true. See [running sessions](https://developers.openai.com/api/docs/guides/agents-api/sessions).",
+        "description": "Creates a managed agent session, optionally submits initial input, and returns the session or streams its events when stream is true.",
+        "tags": [
+          "Agents"
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateAgentSessionParams"
+              }
+            }
+          }
+        },
+        "responses": {
+          "201": {
+            "description": "The created session or its event stream.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionResource"
+                }
+              },
+              "text/event-stream": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionEvent"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oai-streaming": {
+          "request_field": "stream",
+          "response_status_code": 201
+        },
+        "x-oaiMeta": {
+          "name": "Create an agent session"
+        },
+        "parameters": [
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ]
+      }
+    },
+    "/agents/sessions/{session_id}": {
+      "get": {
+        "operationId": "retrieveAgentSession",
+        "summary": "Retrieves the current state of a managed agent session. See [managing sessions](https://developers.openai.com/api/docs/guides/agents-api/sessions/manage).",
+        "description": "Retrieves the current state of a managed agent session.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested session.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve an agent session"
+        }
+      },
+      "post": {
+        "operationId": "updateAgentSession",
+        "summary": "Updates session metadata. Omitted fields are unchanged. See [managing sessions](https://developers.openai.com/api/docs/guides/agents-api/sessions/manage).",
+        "description": "Updates session metadata. Omitted fields are unchanged.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/UpdateAgentSessionParams"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "The updated session.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update an agent session"
+        }
+      },
+      "delete": {
+        "operationId": "deleteAgentSession",
+        "summary": "Removes a managed agent session from the public API and returns a deletion confirmation. Physical cleanup may continue asynchronously. See [managing sessions](https://developers.openai.com/api/docs/guides/agents-api/sessions/manage).",
+        "description": "Removes a managed agent session from the public API and returns a deletion confirmation. Physical cleanup may continue asynchronously.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The deleted session.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedSessionResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete an agent session"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/artifacts": {
+      "get": {
+        "operationId": "listAgentSessionArtifacts",
+        "summary": "Lists immutable artifacts published by completed hosted session turns. See [session artifacts](https://developers.openai.com/api/docs/guides/agents-api/environments/files#openai-hosted-artifacts).",
+        "description": "Lists immutable artifacts published by completed hosted session turns.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam"
+            },
+            "description": "Sort by creation time and ID. Defaults to descending."
+          },
+          {
+            "name": "environment_id",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": [
+                "string",
+                "null"
+              ],
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Restrict the listing to artifacts produced by this environment."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": [
+                "integer",
+                "null"
+              ],
+              "format": "int64",
+              "minimum": 1,
+              "maximum": 100
+            },
+            "description": "The maximum number of artifacts to return, between 1 and 100."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": [
+                "string",
+                "null"
+              ],
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return artifacts after this immutable artifact ID."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A page of durable session artifacts.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionArtifactListResource",
+                  "description": "A page of durable artifacts published by a session."
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List agent session artifacts"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/artifacts/{artifact_id}": {
+      "get": {
+        "operationId": "retrieveAgentSessionArtifact",
+        "summary": "Retrieves immutable metadata for one durable session artifact. See [session artifacts](https://developers.openai.com/api/docs/guides/agents-api/environments/files#openai-hosted-artifacts).",
+        "description": "Retrieves immutable metadata for one durable session artifact.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session that owns the artifact."
+          },
+          {
+            "name": "artifact_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The immutable session artifact ID."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested session artifact.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionArtifactResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve an agent session artifact"
+        }
+      },
+      "delete": {
+        "operationId": "deleteAgentSessionArtifact",
+        "summary": "Deletes an immutable session artifact without deleting its live environment file or original Files API object. See [session artifacts](https://developers.openai.com/api/docs/guides/agents-api/environments/files#openai-hosted-artifacts).",
+        "description": "Deletes an immutable session artifact without deleting its live environment file or original Files API object.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session that owns the artifact."
+          },
+          {
+            "name": "artifact_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The immutable session artifact ID."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The deleted session artifact.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedSessionArtifactResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete an agent session artifact"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/artifacts/{artifact_id}/content": {
+      "get": {
+        "operationId": "retrieveAgentSessionArtifactContent",
+        "summary": "Downloads immutable session artifact bytes after the execution environment expires. See [session artifacts](https://developers.openai.com/api/docs/guides/agents-api/environments/files#openai-hosted-artifacts).",
+        "description": "Downloads immutable session artifact bytes after the execution environment expires.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session that owns the artifact."
+          },
+          {
+            "name": "artifact_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The immutable session artifact ID."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The immutable artifact contents.",
+            "content": {
+              "application/octet-stream": {
+                "schema": {
+                  "type": "string",
+                  "format": "binary"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve agent session artifact content"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/events": {
+      "get": {
+        "operationId": "listAgentSessionEvents",
+        "summary": "Streams live events for an agent session. See [session events](https://developers.openai.com/api/docs/guides/agents-api/sessions/events).",
+        "description": "Streams live events for an agent session.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A live stream of session events.",
+            "content": {
+              "text/event-stream": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionEvent"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oai-streaming": {
+          "request_field": null,
+          "response_status_code": 200
+        },
+        "x-oaiMeta": {
+          "name": "Stream agent session events"
+        }
+      },
+      "post": {
+        "operationId": "createAgentSessionEvents",
+        "summary": "Submits message, cancellation, or tool-result events to a managed agent session. See [session events](https://developers.openai.com/api/docs/guides/agents-api/sessions/events).",
+        "description": "Submits message, cancellation, or tool-result events to a managed agent session.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "Idempotency-Key",
+            "in": "header",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "description": "An optional client-generated key that makes retries of submitted messages idempotent."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateSessionEventsParams"
+              }
+            }
+          }
+        },
+        "responses": {
+          "202": {
+            "description": "The events were accepted."
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create agent session input events"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/items": {
+      "get": {
+        "operationId": "listAgentSessionItems",
+        "summary": "Lists items produced by the session's root agent, including its interactions with subagents. Each subagent has its own item history. See [inspecting agent output](https://developers.openai.com/api/docs/guides/agents-api/observability).",
+        "description": "Lists items produced by the session's root agent, including its interactions with subagents. Each subagent has its own item history.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "format": "int64",
+              "minimum": 1,
+              "maximum": 100,
+              "default": 20
+            },
+            "description": "The maximum number of resources to return, between 1 and 100. Defaults to 20."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "The order in which resources are returned. Defaults to `desc`."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A page of session items.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionItemListResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List agent session items"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/turns": {
+      "get": {
+        "operationId": "listAgentSessionTurns",
+        "summary": "Lists turns by creation time and turn ID. The after cursor is exclusive in the selected order. See [session turns](https://developers.openai.com/api/docs/guides/agents-api/sessions/manage#inspect-session-turns).",
+        "description": "Lists turns by creation time and turn ID. The after cursor is exclusive in the selected order.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "format": "int64",
+              "minimum": 1,
+              "maximum": 100,
+              "default": 20
+            },
+            "description": "The maximum number of resources to return, between 1 and 100. Defaults to 20."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "The order in which resources are returned. Defaults to `desc`."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A page of session turns.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionTurnListResource",
+                  "description": "A page of turns from an agent session or subagent."
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List agent session turns"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/turns/{turn_id}": {
+      "get": {
+        "operationId": "retrieveAgentSessionTurn",
+        "summary": "Retrieves a turn's current status, timestamps, usage, and error. Returns 404 if the turn does not belong to the session. See [session turns](https://developers.openai.com/api/docs/guides/agents-api/sessions/manage#inspect-session-turns).",
+        "description": "Retrieves a turn's current status, timestamps, usage, and error. Returns 404 if the turn does not belong to the session.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session that owns the turn."
+          },
+          {
+            "name": "turn_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the turn."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested turn.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/TurnResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve an agent session turn"
+        }
+      }
+    },
+    "/vaults": {
+      "get": {
+        "operationId": "listVaults",
+        "summary": "Lists vaults using ID-based pagination. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).",
+        "description": "Lists vaults using ID-based pagination.",
+        "tags": [
+          "Vaults"
+        ],
+        "parameters": [
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "Sort order by the `created_at` timestamp. Use `asc` for ascending order or `desc` for descending order. Defaults to `desc`."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": [
+                "integer",
+                "null"
+              ],
+              "format": "int64",
+              "minimum": 0
+            },
+            "description": "The maximum number of resources to return. Defaults to 20. Values are clamped between 1 and 100."
+          },
+          {
+            "name": "status",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/VaultStatusFilterParam"
+            },
+            "description": "Filter by one status or a list, such as `status=active` or `status[]=active&status[]=archived`. Both statuses are included by default."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A page of vaults.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VaultListResource",
+                  "description": "A page of vaults."
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested vault or credential was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current vault state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List vaults"
+        }
+      },
+      "post": {
+        "operationId": "createVault",
+        "summary": "Creates a vault for the current project. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).",
+        "description": "Creates a vault for the current project.",
+        "tags": [
+          "Vaults"
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateVaultParams"
+              }
+            }
+          }
+        },
+        "responses": {
+          "201": {
+            "description": "The created vault.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VaultResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested vault or credential was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current vault state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create a vault"
+        },
+        "parameters": [
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ]
+      }
+    },
+    "/vaults/{vault_id}": {
+      "get": {
+        "operationId": "retrieveVault",
+        "summary": "Retrieves a vault by its ID. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).",
+        "description": "Retrieves a vault by its ID.",
+        "tags": [
+          "Vaults"
+        ],
+        "parameters": [
+          {
+            "name": "vault_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the vault."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested vault.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VaultResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested vault or credential was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current vault state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve a vault"
+        }
+      },
+      "delete": {
+        "operationId": "deleteVault",
+        "summary": "Deletes a vault and all its credentials. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).",
+        "description": "Deletes a vault and all its credentials.",
+        "tags": [
+          "Vaults"
+        ],
+        "parameters": [
+          {
+            "name": "vault_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the vault."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The deleted vault.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedVaultResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested vault or credential was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current vault state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete a vault"
+        }
+      }
+    },
+    "/vaults/{vault_id}/credentials": {
+      "get": {
+        "operationId": "listVaultCredentials",
+        "summary": "Lists a vault's credentials using ID-based pagination without returning secret values. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).",
+        "description": "Lists a vault's credentials using ID-based pagination without returning secret values.",
+        "tags": [
+          "Vaults"
+        ],
+        "parameters": [
+          {
+            "name": "vault_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the vault."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "Sort order by the `created_at` timestamp. Use `asc` for ascending order or `desc` for descending order. Defaults to `desc`."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": [
+                "integer",
+                "null"
+              ],
+              "format": "int64",
+              "minimum": 0
+            },
+            "description": "The maximum number of resources to return. Defaults to 20. Values are clamped between 1 and 100."
+          },
+          {
+            "name": "status",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/VaultStatusFilterParam"
+            },
+            "description": "Filter by one status or a list, such as `status=active` or `status[]=active&status[]=archived`. Both statuses are included by default."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A page of vault credentials.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VaultCredentialListResource",
+                  "description": "A page of credentials in a vault."
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested vault or credential was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current vault state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List vault credentials"
+        }
+      },
+      "post": {
+        "operationId": "createVaultCredential",
+        "summary": "Creates a vault credential. Secret values are write-only and are never returned. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).",
+        "description": "Creates a vault credential. Secret values are write-only and are never returned.",
+        "tags": [
+          "Vaults"
+        ],
+        "parameters": [
+          {
+            "name": "vault_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the vault."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateVaultCredentialParams"
+              }
+            }
+          }
+        },
+        "responses": {
+          "201": {
+            "description": "The created vault credential without secret values.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VaultCredentialResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested vault or credential was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current vault state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create a vault credential"
+        }
+      }
+    },
+    "/vaults/{vault_id}/credentials/{credential_id}": {
+      "get": {
+        "operationId": "retrieveVaultCredential",
+        "summary": "Retrieves vault credential metadata without returning secret values. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).",
+        "description": "Retrieves vault credential metadata without returning secret values.",
+        "tags": [
+          "Vaults"
+        ],
+        "parameters": [
+          {
+            "name": "vault_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the vault."
+          },
+          {
+            "name": "credential_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the vault credential."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested vault credential without secret values.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VaultCredentialResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested vault or credential was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current vault state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve a vault credential"
+        }
+      },
+      "post": {
+        "operationId": "rotateVaultCredential",
+        "summary": "Rotates a vault credential's write-only secret and returns only credential metadata. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).",
+        "description": "Rotates a vault credential's write-only secret and returns only credential metadata.",
+        "tags": [
+          "Vaults"
+        ],
+        "parameters": [
+          {
+            "name": "vault_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the vault."
+          },
+          {
+            "name": "credential_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the vault credential."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/RotateVaultCredentialParams"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "The rotated vault credential without secret values.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VaultCredentialResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested vault or credential was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current vault state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Rotate a vault credential"
+        }
+      },
+      "delete": {
+        "operationId": "deleteVaultCredential",
+        "summary": "Deletes a vault credential. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).",
+        "description": "Deletes a vault credential.",
+        "tags": [
+          "Vaults"
+        ],
+        "parameters": [
+          {
+            "name": "vault_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the vault."
+          },
+          {
+            "name": "credential_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the vault credential."
+          },
+          {
+            "name": "OpenAI-Beta",
+            "in": "header",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "const": "agents=v1"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The deleted vault credential.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedVaultCredentialResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested vault or credential was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current vault state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete a vault credential"
+        }
+      }
+    }
+  },
+  "webhooks": {
+    "batch_cancelled": {
+      "post": {
+        "description": "Sent when a batch has been cancelled.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookBatchCancelled"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried.\n"
+          }
+        }
+      }
+    },
+    "batch_completed": {
+      "post": {
+        "description": "Sent when a batch has completed processing.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookBatchCompleted"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried.\n"
+          }
+        }
+      }
+    },
+    "batch_expired": {
+      "post": {
+        "description": "Sent when a batch has expired before completion.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookBatchExpired"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried.\n"
+          }
+        }
+      }
+    },
+    "batch_failed": {
+      "post": {
+        "description": "Sent when a batch has failed.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookBatchFailed"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried.\n"
+          }
+        }
+      }
+    },
+    "eval_run_canceled": {
+      "post": {
+        "description": "Sent when an eval run has been canceled.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookEvalRunCanceled"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried. \n"
+          }
+        }
+      }
+    },
+    "eval_run_failed": {
+      "post": {
+        "description": "Sent when an eval run has failed.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookEvalRunFailed"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried. \n"
+          }
+        }
+      }
+    },
+    "eval_run_succeeded": {
+      "post": {
+        "description": "Sent when an eval run has succeeded.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookEvalRunSucceeded"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried. \n"
+          }
+        }
+      }
+    },
+    "fine_tuning_job_cancelled": {
+      "post": {
+        "description": "Sent when a fine-tuning job has been cancelled.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookFineTuningJobCancelled"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried. \n"
+          }
+        }
+      }
+    },
+    "fine_tuning_job_failed": {
+      "post": {
+        "description": "Sent when a fine-tuning job has failed.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookFineTuningJobFailed"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried. \n"
+          }
+        }
+      }
+    },
+    "fine_tuning_job_succeeded": {
+      "post": {
+        "description": "Sent when a fine-tuning job has succeeded.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookFineTuningJobSucceeded"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried. \n"
+          }
+        }
+      }
+    },
+    "live_call_incoming": {
+      "post": {
+        "deprecated": true,
+        "description": "Deprecated: use `live.transport.incoming`. Retained only for existing subscriptions.\nSent when an incoming API SIP session is available for Live acceptance.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookLiveCallIncoming"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200\nstatus codes will be retried.\n"
+          }
+        }
+      }
+    },
+    "live_transport_incoming": {
+      "post": {
+        "description": "Sent when an incoming API SIP session is available for Live acceptance.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookLiveTransportIncoming"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200\nstatus codes will be retried.\n"
+          }
+        }
+      }
+    },
+    "realtime_call_incoming": {
+      "post": {
+        "description": "Sent when an incoming API SIP session is available for Realtime acceptance.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookRealtimeCallIncoming"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200\nstatus codes will be retried.\n"
+          }
+        }
+      }
+    },
+    "response_cancelled": {
+      "post": {
+        "description": "Sent when a background response has been cancelled.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookResponseCancelled"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried.\n"
+          }
+        }
+      }
+    },
+    "response_completed": {
+      "post": {
+        "description": "Sent when a background response has completed successfully.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookResponseCompleted"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried. \n"
+          }
+        }
+      }
+    },
+    "response_failed": {
+      "post": {
+        "description": "Sent when a background response has failed.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookResponseFailed"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried.\n"
+          }
+        }
+      }
+    },
+    "response_incomplete": {
+      "post": {
+        "description": "Sent when a background response is incomplete.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookResponseIncomplete"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried.\n"
+          }
+        }
+      }
+    },
+    "safety_alert_created": {
+      "post": {
+        "description": "Sent when an approved safety alert is available for an API project.\nRetrieve the alert with a project API key granted `api.safety.alerts.read`.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookSafetyAlertCreated"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return any 2xx status code to acknowledge receipt. A 410 Gone response also stops retries; other non-2xx responses are retried."
+          }
+        }
+      }
+    },
+    "safety_org_alert_created": {
+      "post": {
+        "description": "Sent when an approved safety alert is available for an enterprise workspace.\nRetrieve the alert from `https://api.chatgpt.com/v1/safety/alerts/{id}` with\nan administrator API key for the workspace's backing organization granted\n`chatgpt.enterprise.safety_alerts.read`.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookSafetyOrgAlertCreated"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return any 2xx status code to acknowledge receipt. A 410 Gone response also stops retries; other non-2xx responses are retried."
+          }
+        }
+      }
+    }
+  },
+  "components": {
+    "schemas": {
+      "CreateFileRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "file": {
+            "description": "The File object (not file name) to be uploaded.\n",
+            "type": "string",
+            "format": "binary"
+          },
+          "purpose": {
+            "description": "The intended purpose of the uploaded file. One of:\n- `assistants`: Used in the Assistants API\n- `batch`: Used in the Batch API\n- `fine-tune`: Used for fine-tuning\n- `vision`: Images used for vision fine-tuning\n- `user_data`: Flexible file type for any purpose\n- `evals`: Used for eval data sets\n",
+            "type": "string",
+            "enum": [
+              "assistants",
+              "batch",
+              "fine-tune",
+              "vision",
+              "user_data",
+              "evals"
+            ]
+          },
+          "expires_after": {
+            "$ref": "#/components/schemas/FileExpirationAfter"
+          }
+        },
+        "required": [
+          "file",
+          "purpose"
+        ]
+      },
+      "DeleteFileResponse": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string"
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "file"
+            ],
+            "x-stainless-const": true
+          },
+          "deleted": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ]
+      },
+      "Error": {
+        "type": "object",
+        "properties": {
+          "code": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "message": {
+            "type": "string"
+          },
+          "param": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string"
+          },
+          "misalignment": {
+            "$ref": "#/components/schemas/MisalignmentErrorDetailsResource"
+          }
+        },
+        "required": [
+          "type",
+          "message",
+          "param",
+          "code"
+        ]
+      },
+      "ErrorResponse": {
+        "type": "object",
+        "properties": {
+          "error": {
+            "$ref": "#/components/schemas/Error"
+          }
+        },
+        "required": [
+          "error"
+        ]
+      },
+      "FileExpirationAfter": {
+        "type": "object",
+        "title": "File expiration policy",
+        "description": "The expiration policy for a file. By default, files with `purpose=batch` expire after 30 days and all other files are persisted until they are manually deleted.",
+        "properties": {
+          "anchor": {
+            "description": "Anchor timestamp after which the expiration policy applies. Supported anchors: `created_at`.",
+            "type": "string",
+            "enum": [
+              "created_at"
+            ],
+            "x-stainless-const": true
+          },
+          "seconds": {
+            "description": "The number of seconds after the anchor time that the file will expire. Must be between 3600 (1 hour) and 2592000 (30 days).",
+            "type": "integer",
+            "format": "int64",
+            "minimum": 3600,
+            "maximum": 2592000
+          }
+        },
+        "required": [
+          "anchor",
+          "seconds"
+        ]
+      },
+      "ListFilesResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "example": "list"
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/OpenAIFile"
+            }
+          },
+          "first_id": {
+            "type": "string",
+            "example": "file-abc123"
+          },
+          "last_id": {
+            "type": "string",
+            "example": "file-abc456"
+          },
+          "has_more": {
+            "type": "boolean",
+            "example": false
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ]
+      },
+      "OpenAIFile": {
+        "title": "OpenAIFile",
+        "description": "The `File` object represents a document that has been uploaded to OpenAI.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The file identifier, which can be referenced in the API endpoints."
+          },
+          "bytes": {
+            "type": "integer",
+            "description": "The size of the file, in bytes."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the file was created."
+          },
+          "expires_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the file will expire."
+          },
+          "filename": {
+            "type": "string",
+            "description": "The name of the file."
+          },
+          "object": {
+            "type": "string",
+            "description": "The object type, which is always `file`.",
+            "enum": [
+              "file"
+            ],
+            "x-stainless-const": true
+          },
+          "purpose": {
+            "type": "string",
+            "description": "The intended purpose of the file. Supported values are `assistants`, `assistants_output`, `batch`, `batch_output`, `fine-tune`, `fine-tune-results`, `vision`, and `user_data`.",
+            "enum": [
+              "assistants",
+              "assistants_output",
+              "batch",
+              "batch_output",
+              "fine-tune",
+              "fine-tune-results",
+              "vision",
+              "user_data"
+            ]
+          },
+          "status": {
+            "type": "string",
+            "deprecated": true,
+            "description": "Deprecated. The current status of the file, which can be either `uploaded`, `processed`, or `error`.",
+            "enum": [
+              "uploaded",
+              "processed",
+              "error"
+            ]
+          },
+          "status_details": {
+            "type": "string",
+            "deprecated": true,
+            "description": "Deprecated. For details on why a fine-tuning training file failed validation, see the `error` field on `fine_tuning.job`."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "bytes",
+          "created_at",
+          "filename",
+          "purpose",
+          "status"
+        ],
+        "x-oaiMeta": {
+          "name": "The file object",
+          "example": "{\n  \"id\": \"file-abc123\",\n  \"object\": \"file\",\n  \"bytes\": 120000,\n  \"created_at\": 1677610602,\n  \"expires_at\": 1680202602,\n  \"filename\": \"salesOverview.pdf\",\n  \"purpose\": \"assistants\",\n}\n"
+        }
+      },
+      "_MisalignmentErrorType": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "string",
+            "enum": [
+              "potentially_unintended_data_transfer",
+              "potentially_unintended_data_access",
+              "potentially_unintended_destructive_activity",
+              "other"
+            ]
+          }
+        ]
+      },
+      "_MisalignmentSteer": {
+        "properties": {
+          "message": {
+            "type": "string",
+            "description": "The public continuation instruction."
+          }
+        },
+        "type": "object",
+        "required": [
+          "message"
+        ]
+      },
+      "MisalignmentErrorDetailsResource": {
+        "properties": {
+          "error_type": {
+            "$ref": "#/components/schemas/_MisalignmentErrorType",
+            "description": "An optional classification; clients must accept additional values."
+          },
+          "detailed_explanation": {
+            "type": "string",
+            "description": "The public explanation for this block."
+          },
+          "steer": {
+            "$ref": "#/components/schemas/_MisalignmentSteer",
+            "description": "An optional public continuation instruction."
+          }
+        },
+        "type": "object",
+        "required": []
+      },
+      "OrderEnum": {
+        "type": "string",
+        "enum": [
+          "asc",
+          "desc"
+        ]
+      },
+      "SkillResource": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Unique identifier for the skill."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "skill"
+            ],
+            "description": "The object type, which is `skill`.",
+            "default": "skill",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "Name of the skill."
+          },
+          "description": {
+            "type": "string",
+            "description": "Description of the skill."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (seconds) for when the skill was created."
+          },
+          "default_version": {
+            "type": "string",
+            "description": "Default version for the skill."
+          },
+          "latest_version": {
+            "type": "string",
+            "description": "Latest version for the skill."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "object",
+          "name",
+          "description",
+          "created_at",
+          "default_version",
+          "latest_version"
+        ]
+      },
+      "SkillListResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "description": "The type of object returned, must be `list`.",
+            "default": "list",
+            "x-stainless-const": true
+          },
+          "data": {
+            "items": {
+              "$ref": "#/components/schemas/SkillResource"
+            },
+            "type": "array",
+            "description": "A list of items"
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the first item in the list."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the last item in the list."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more items available."
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ]
+      },
+      "CreateSkillBody": {
+        "properties": {
+          "files": {
+            "oneOf": [
+              {
+                "items": {
+                  "type": "string",
+                  "format": "binary"
+                },
+                "type": "array",
+                "maxItems": 500,
+                "description": "Skill files to upload (directory upload) or a single zip file."
+              },
+              {
+                "type": "string",
+                "format": "binary",
+                "description": "Skill zip file to upload."
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "files"
+        ],
+        "title": "Create skill request",
+        "description": "Uploads a skill either as a directory (multipart `files[]`) or as a single zip file."
+      },
+      "SetDefaultSkillVersionBody": {
+        "properties": {
+          "default_version": {
+            "type": "string",
+            "description": "The skill version number to set as default."
+          }
+        },
+        "type": "object",
+        "required": [
+          "default_version"
+        ],
+        "title": "Update skill request",
+        "description": "Updates the default version pointer for a skill."
+      },
+      "DeletedSkillResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "skill.deleted"
+            ],
+            "default": "skill.deleted",
+            "x-stainless-const": true
+          },
+          "deleted": {
+            "type": "boolean"
+          },
+          "id": {
+            "type": "string"
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "deleted",
+          "id"
+        ]
+      },
+      "SkillVersionResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "skill.version"
+            ],
+            "description": "The object type, which is `skill.version`.",
+            "default": "skill.version",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "Unique identifier for the skill version."
+          },
+          "skill_id": {
+            "type": "string",
+            "description": "Identifier of the skill for this version."
+          },
+          "version": {
+            "type": "string",
+            "description": "Version number for this skill."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (seconds) for when the version was created."
+          },
+          "name": {
+            "type": "string",
+            "description": "Name of the skill version."
+          },
+          "description": {
+            "type": "string",
+            "description": "Description of the skill version."
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "id",
+          "skill_id",
+          "version",
+          "created_at",
+          "name",
+          "description"
+        ]
+      },
+      "SkillVersionListResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "description": "The type of object returned, must be `list`.",
+            "default": "list",
+            "x-stainless-const": true
+          },
+          "data": {
+            "items": {
+              "$ref": "#/components/schemas/SkillVersionResource"
+            },
+            "type": "array",
+            "description": "A list of items"
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the first item in the list."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the last item in the list."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more items available."
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ]
+      },
+      "CreateSkillVersionBody": {
+        "properties": {
+          "files": {
+            "oneOf": [
+              {
+                "items": {
+                  "type": "string",
+                  "format": "binary"
+                },
+                "type": "array",
+                "maxItems": 500,
+                "description": "Skill files to upload (directory upload) or a single zip file."
+              },
+              {
+                "type": "string",
+                "format": "binary",
+                "description": "Skill zip file to upload."
+              }
+            ]
+          },
+          "default": {
+            "type": "boolean",
+            "description": "Whether to set this version as the default."
+          }
+        },
+        "type": "object",
+        "required": [
+          "files"
+        ],
+        "title": "Create skill version request",
+        "description": "Uploads a new immutable version of a skill."
+      },
+      "DeletedSkillVersionResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "skill.version.deleted"
+            ],
+            "default": "skill.version.deleted",
+            "x-stainless-const": true
+          },
+          "deleted": {
+            "type": "boolean"
+          },
+          "id": {
+            "type": "string"
+          },
+          "version": {
+            "type": "string",
+            "description": "The deleted skill version."
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "deleted",
+          "id",
+          "version"
+        ]
+      },
+      "EnvironmentTypeResource": {
+        "type": "string",
+        "enum": [
+          "openai_hosted",
+          "self_hosted"
+        ],
+        "description": "The kind of execution environment."
+      },
+      "EnvironmentStatusResource": {
+        "type": "string",
+        "enum": [
+          "pending",
+          "connected",
+          "disconnected",
+          "expired",
+          "failed"
+        ],
+        "description": "The public lifecycle status of an execution environment."
+      },
+      "HostedEnvironmentFileResourceFileId": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "file_id"
+            ],
+            "default": "file_id",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `file_id`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The session-scoped ID of the file in the execution environment."
+          },
+          "file_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the uploaded file."
+          },
+          "path": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The file's absolute path inside the environment."
+          },
+          "size_bytes": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "description": "The decoded file size in bytes."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "file_id",
+          "path",
+          "size_bytes"
+        ],
+        "additionalProperties": false,
+        "description": "A file copied from the OpenAI Files API."
+      },
+      "HostedEnvironmentFileResourceInline": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "inline"
+            ],
+            "default": "inline",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `inline`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The session-scoped ID of the file in the execution environment."
+          },
+          "path": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The file's absolute path inside the environment."
+          },
+          "size_bytes": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "description": "The decoded file size in bytes."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "path",
+          "size_bytes"
+        ],
+        "additionalProperties": false,
+        "description": "A file supplied inline when the session was created."
+      },
+      "HostedEnvironmentFileResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/HostedEnvironmentFileResourceFileId"
+          },
+          {
+            "$ref": "#/components/schemas/HostedEnvironmentFileResourceInline"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "file_id": "#/components/schemas/HostedEnvironmentFileResourceFileId",
+            "inline": "#/components/schemas/HostedEnvironmentFileResourceInline"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "file_id",
+          "inline"
+        ],
+        "description": "Metadata for a file materialized in an OpenAI-hosted execution environment."
+      },
+      "HostedSkillResourceSkillReference": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "skill_reference"
+            ],
+            "default": "skill_reference",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `skill_reference`."
+          },
+          "skill_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The referenced skill ID."
+          },
+          "version": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The concrete skill version installed for this session."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The installed skill name."
+          },
+          "description": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The installed skill description."
+          }
+        },
+        "required": [
+          "type",
+          "skill_id",
+          "version",
+          "name",
+          "description"
+        ],
+        "additionalProperties": false,
+        "description": "A skill installed from the Skills API."
+      },
+      "HostedSkillResourceInline": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "inline"
+            ],
+            "default": "inline",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `inline`."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The installed skill name."
+          },
+          "description": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The installed skill description."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "description"
+        ],
+        "additionalProperties": false,
+        "description": "A skill installed from an inline ZIP archive."
+      },
+      "HostedSkillResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/HostedSkillResourceSkillReference"
+          },
+          {
+            "$ref": "#/components/schemas/HostedSkillResourceInline"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "skill_reference": "#/components/schemas/HostedSkillResourceSkillReference",
+            "inline": "#/components/schemas/HostedSkillResourceInline"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "skill_reference",
+          "inline"
+        ],
+        "description": "A skill installed in an OpenAI-hosted environment."
+      },
+      "HostedPluginResourceInline": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "inline"
+            ],
+            "default": "inline",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `inline`."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The installed plugin name."
+          },
+          "description": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The installed plugin description."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "description"
+        ],
+        "additionalProperties": false,
+        "description": "A plugin installed from an inline ZIP archive."
+      },
+      "HostedPluginResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/HostedPluginResourceInline"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "inline": "#/components/schemas/HostedPluginResourceInline"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "inline"
+        ],
+        "description": "A plugin installed in an OpenAI-hosted environment."
+      },
+      "PublicEnvironmentResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the environment."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "agent.environment"
+            ],
+            "default": "agent.environment",
+            "x-stainless-const": true,
+            "description": "The object type. Always `agent.environment`."
+          },
+          "type": {
+            "$ref": "#/components/schemas/EnvironmentTypeResource",
+            "description": "Whether the environment is hosted by OpenAI or by the application."
+          },
+          "status": {
+            "$ref": "#/components/schemas/EnvironmentStatusResource",
+            "description": "The current environment connection status."
+          },
+          "files": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/HostedEnvironmentFileResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Files installed in the environment, without their contents."
+          },
+          "skills": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/HostedSkillResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Skills installed in the environment, without their archive contents."
+          },
+          "plugins": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/HostedPluginResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Plugins installed in the environment, without their archive contents."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "type",
+          "status",
+          "files",
+          "skills",
+          "plugins"
+        ],
+        "additionalProperties": false,
+        "description": "Safe metadata for a first-class execution environment."
+      },
+      "ErrorBodyResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The error type."
+          },
+          "code": {
+            "type": "string",
+            "minLength": 0,
+            "description": "A machine-readable error code."
+          },
+          "message": {
+            "type": "string",
+            "minLength": 0,
+            "description": "A human-readable error message."
+          },
+          "param": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The request parameter that caused the error, or null for a request-wide error."
+          }
+        },
+        "required": [
+          "type",
+          "code",
+          "message",
+          "param"
+        ],
+        "additionalProperties": false,
+        "description": "Details about an API error."
+      },
+      "ErrorResponse-2": {
+        "type": "object",
+        "properties": {
+          "error": {
+            "$ref": "#/components/schemas/ErrorBodyResource",
+            "description": "The error returned by the API."
+          }
+        },
+        "required": [
+          "error"
+        ],
+        "additionalProperties": false,
+        "description": "An API error response."
+      },
+      "ListOrderParam": {
+        "type": "string",
+        "enum": [
+          "asc",
+          "desc"
+        ],
+        "x-enumDescriptions": [
+          "Returns resources in ascending order.",
+          "Returns resources in descending order."
+        ],
+        "description": "The order in which paginated resources are returned."
+      },
+      "EnvironmentFilePageObjectResource": {
+        "type": "string",
+        "enum": [
+          "page"
+        ],
+        "default": "page",
+        "x-stainless-const": true,
+        "description": "The object type for a page of files in an execution environment."
+      },
+      "EnvironmentFileResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "agent.environment.file"
+            ],
+            "default": "agent.environment.file",
+            "x-stainless-const": true,
+            "description": "The object type. Always `agent.environment.file`."
+          },
+          "environment_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the environment containing this file."
+          },
+          "path": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The absolute file path inside the environment's workspace."
+          },
+          "size_bytes": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "description": "The file size in bytes."
+          }
+        },
+        "required": [
+          "object",
+          "environment_id",
+          "path",
+          "size_bytes"
+        ],
+        "additionalProperties": false,
+        "description": "A live file in an execution environment."
+      },
+      "EnvironmentFileListResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "$ref": "#/components/schemas/EnvironmentFilePageObjectResource",
+            "description": "The object type. Always `page`."
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/EnvironmentFileResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Files available on the current page."
+          },
+          "next": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The opaque cursor to use when requesting the next page, if any."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether more files follow this page."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "next",
+          "has_more"
+        ],
+        "additionalProperties": false,
+        "description": "A paginated list of live execution environment files."
+      },
+      "HostedEnvironmentFileParamFileId": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "file_id"
+            ],
+            "default": "file_id",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `file_id`."
+          },
+          "file_id": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 256,
+            "description": "The ID of the uploaded file."
+          },
+          "path": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 4096,
+            "description": "The absolute destination path inside `/workspace`."
+          }
+        },
+        "required": [
+          "type",
+          "file_id",
+          "path"
+        ],
+        "additionalProperties": false,
+        "description": "A file previously uploaded through the OpenAI Files API."
+      },
+      "HostedEnvironmentFileParamInline": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "inline"
+            ],
+            "default": "inline",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `inline`."
+          },
+          "data": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 6990508,
+            "description": "The standard-base64-encoded file contents."
+          },
+          "path": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 4096,
+            "description": "The absolute destination path inside `/workspace`."
+          }
+        },
+        "required": [
+          "type",
+          "data",
+          "path"
+        ],
+        "additionalProperties": false,
+        "description": "A file supplied directly as standard-base64 data."
+      },
+      "HostedEnvironmentFileParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/HostedEnvironmentFileParamFileId"
+          },
+          {
+            "$ref": "#/components/schemas/HostedEnvironmentFileParamInline"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "file_id": "#/components/schemas/HostedEnvironmentFileParamFileId",
+            "inline": "#/components/schemas/HostedEnvironmentFileParamInline"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "file_id",
+          "inline"
+        ],
+        "description": "A file materialized in an OpenAI-hosted execution environment."
+      },
+      "SubagentObjectResource": {
+        "type": "string",
+        "enum": [
+          "agent.session.subagent"
+        ],
+        "default": "agent.session.subagent",
+        "x-stainless-const": true,
+        "description": "The object type for a subagent."
+      },
+      "OutputTextResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "output_text"
+            ],
+            "default": "output_text",
+            "x-stainless-const": true,
+            "description": "The content type. Always `output_text`."
+          },
+          "text": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The text produced by the agent."
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ],
+        "additionalProperties": false,
+        "description": "A text content part produced by the agent."
+      },
+      "EncryptedContentResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "encrypted_content"
+            ],
+            "default": "encrypted_content",
+            "x-stainless-const": true,
+            "description": "The content type. Always `encrypted_content`."
+          },
+          "encrypted_content": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The encrypted content payload."
+          }
+        },
+        "required": [
+          "type",
+          "encrypted_content"
+        ],
+        "additionalProperties": false,
+        "description": "Encrypted content exchanged between agents."
+      },
+      "AgentContentResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/OutputTextResource"
+          },
+          {
+            "$ref": "#/components/schemas/EncryptedContentResource"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "output_text": "#/components/schemas/OutputTextResource",
+            "encrypted_content": "#/components/schemas/EncryptedContentResource"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "output_text",
+          "encrypted_content"
+        ],
+        "description": "A plaintext or encrypted content part exchanged between agents."
+      },
+      "SubagentStatusResource": {
+        "type": "string",
+        "enum": [
+          "active",
+          "closed"
+        ],
+        "x-enumDescriptions": [
+          "The subagent remains available, including while idle between turns.",
+          "The subagent is closed."
+        ],
+        "description": "The current status of a subagent."
+      },
+      "SubagentResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the subagent."
+          },
+          "object": {
+            "$ref": "#/components/schemas/SubagentObjectResource",
+            "description": "The object type. Always `agent.session.subagent`."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session that owns the subagent."
+          },
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The runner-assigned nickname, or null when unavailable."
+          },
+          "instructions": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/AgentContentResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Initial task content, or null when unavailable. Text may contain placeholders for images or audio when only a preview is available."
+          },
+          "parent_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent that created this subagent."
+          },
+          "status": {
+            "$ref": "#/components/schemas/SubagentStatusResource",
+            "description": "The current status of the subagent."
+          },
+          "opened_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the subagent was first opened. Resuming does not change it."
+          },
+          "closed_at": {
+            "type": [
+              "integer",
+              "null"
+            ],
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the subagent was closed. Null while active, including after resume."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "session_id",
+          "name",
+          "instructions",
+          "parent_agent_id",
+          "status",
+          "opened_at",
+          "closed_at"
+        ],
+        "additionalProperties": false,
+        "description": "A subagent created within a session."
+      },
+      "SessionMessageRoleResource": {
+        "type": "string",
+        "enum": [
+          "user",
+          "assistant"
+        ],
+        "description": "The author of a session message."
+      },
+      "MessageContentResourceInputText": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_text"
+            ],
+            "default": "input_text",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `input_text`."
+          },
+          "text": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The text supplied by the user."
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ],
+        "additionalProperties": false,
+        "description": "Text supplied by the user."
+      },
+      "MessageContentResourceInputImage": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_image"
+            ],
+            "default": "input_image",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `input_image`."
+          },
+          "image_url": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The URL of the image supplied by the user, which may be a base64-encoded data URL."
+          }
+        },
+        "required": [
+          "type",
+          "image_url"
+        ],
+        "additionalProperties": false,
+        "description": "An image supplied by the user."
+      },
+      "MessageContentResourceOutputText": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "output_text"
+            ],
+            "default": "output_text",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `output_text`."
+          },
+          "text": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The text produced by the assistant."
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ],
+        "additionalProperties": false,
+        "description": "Text produced by the assistant."
+      },
+      "MessageContentResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/MessageContentResourceInputText"
+          },
+          {
+            "$ref": "#/components/schemas/MessageContentResourceInputImage"
+          },
+          {
+            "$ref": "#/components/schemas/MessageContentResourceOutputText"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "input_text": "#/components/schemas/MessageContentResourceInputText",
+            "input_image": "#/components/schemas/MessageContentResourceInputImage",
+            "output_text": "#/components/schemas/MessageContentResourceOutputText"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "input_text",
+          "input_image",
+          "output_text"
+        ],
+        "description": "A content part in a session message."
+      },
+      "OutputItemStatusResource": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed",
+          "incomplete"
+        ],
+        "x-enumDescriptions": [
+          "The item is in progress.",
+          "The item is complete.",
+          "The item stopped before completing."
+        ],
+        "description": "The status of an agent output item."
+      },
+      "MessagePhaseResource": {
+        "type": "string",
+        "enum": [
+          "commentary",
+          "final_answer"
+        ],
+        "x-enumDescriptions": [
+          "Commentary produced while the agent works.",
+          "The agent's final answer."
+        ],
+        "description": "The phase of an assistant message."
+      },
+      "MessageItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "message"
+            ],
+            "default": "message",
+            "x-stainless-const": true,
+            "description": "The item type. Always `message`."
+          },
+          "id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of this item, or null for legacy user messages whose ID was not recorded."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "role": {
+            "$ref": "#/components/schemas/SessionMessageRoleResource",
+            "description": "The role of the message author."
+          },
+          "content": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/MessageContentResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The content of the message. User messages contain input text or images; assistant messages contain output text."
+          },
+          "status": {
+            "$ref": "#/components/schemas/OutputItemStatusResource",
+            "description": "The status of the message. User messages are always `completed`."
+          },
+          "phase": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/MessagePhaseResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The phase of an assistant message. Null for user messages."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "role",
+          "content",
+          "status",
+          "phase"
+        ],
+        "additionalProperties": false,
+        "description": "A user or assistant message recorded in a session."
+      },
+      "SummaryTextResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "summary_text"
+            ],
+            "default": "summary_text",
+            "x-stainless-const": true,
+            "description": "The content type. Always `summary_text`."
+          },
+          "text": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The reasoning summary text."
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ],
+        "additionalProperties": false,
+        "description": "A reasoning summary content part."
+      },
+      "ReasoningItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "reasoning"
+            ],
+            "default": "reasoning",
+            "x-stainless-const": true,
+            "description": "The item type. Always `reasoning`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the reasoning item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "summary": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/SummaryTextResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The reasoning summaries produced by the agent."
+          },
+          "status": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/OutputItemStatusResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The status of the reasoning item."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "summary",
+          "status"
+        ],
+        "additionalProperties": false,
+        "description": "A reasoning item produced by the agent."
+      },
+      "FunctionCallStatusResource": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed",
+          "failed",
+          "incomplete"
+        ],
+        "x-enumDescriptions": [
+          "The call is in progress.",
+          "The call completed successfully.",
+          "The call failed.",
+          "The call stopped before completing."
+        ],
+        "description": "The status of a tool call."
+      },
+      "FunctionCallItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "function_call"
+            ],
+            "default": "function_call",
+            "x-stainless-const": true,
+            "description": "The item type. Always `function_call`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the function call item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "call_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID used to submit the function result."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The name of the function to call."
+          },
+          "arguments": {
+            "description": "The arguments to pass to the function."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatusResource",
+            "description": "The status of the function call."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "call_id",
+          "name",
+          "arguments",
+          "status"
+        ],
+        "additionalProperties": false,
+        "description": "A function call produced by the agent."
+      },
+      "InputContentResourceInputText": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_text"
+            ],
+            "default": "input_text",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `input_text`."
+          },
+          "text": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The text supplied to the agent."
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ],
+        "additionalProperties": false,
+        "description": "Text input recorded in a session item."
+      },
+      "InputContentResourceInputImage": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_image"
+            ],
+            "default": "input_image",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `input_image`."
+          },
+          "image_url": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The URL of the image supplied to the agent, which may be a base64-encoded data URL."
+          }
+        },
+        "required": [
+          "type",
+          "image_url"
+        ],
+        "additionalProperties": false,
+        "description": "Image input recorded in a session item."
+      },
+      "InputContentResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/InputContentResourceInputText"
+          },
+          {
+            "$ref": "#/components/schemas/InputContentResourceInputImage"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "input_text": "#/components/schemas/InputContentResourceInputText",
+            "input_image": "#/components/schemas/InputContentResourceInputImage"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "input_text",
+          "input_image"
+        ],
+        "description": "User-provided content recorded in a session item."
+      },
+      "FunctionCallOutputResource": {
+        "oneOf": [
+          {
+            "type": "string",
+            "minLength": 0
+          },
+          {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/InputContentResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000
+          }
+        ],
+        "description": "The text or model-input content supplied as a function result."
+      },
+      "FunctionCallOutputItemResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the function call output item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "function_call_output"
+            ],
+            "default": "function_call_output",
+            "x-stainless-const": true,
+            "description": "The item type. Always `function_call_output`."
+          },
+          "call_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the function call that produced this output."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatusResource",
+            "description": "The status of the function call."
+          },
+          "output": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/FunctionCallOutputResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The function result, if the call succeeded."
+          },
+          "error": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The error message, if the call failed."
+          }
+        },
+        "required": [
+          "id",
+          "turn_id",
+          "type",
+          "call_id",
+          "status",
+          "output",
+          "error"
+        ],
+        "additionalProperties": false,
+        "description": "The result supplied for a function call."
+      },
+      "AgentMessageItemResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the message."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent_message"
+            ],
+            "default": "agent_message",
+            "x-stainless-const": true,
+            "description": "The item type. Always `agent_message`."
+          },
+          "sender_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID or name of the sending agent."
+          },
+          "recipient_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID or name of the receiving agent."
+          },
+          "content": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/AgentContentResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The content exchanged between the agents."
+          }
+        },
+        "required": [
+          "id",
+          "turn_id",
+          "type",
+          "sender_agent_id",
+          "recipient_agent_id",
+          "content"
+        ],
+        "additionalProperties": false,
+        "description": "A message exchanged between agent threads."
+      },
+      "McpCallItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_call"
+            ],
+            "default": "mcp_call",
+            "x-stainless-const": true,
+            "description": "The item type. Always `mcp_call`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the MCP call item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "server_label": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The label of the MCP server."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The name of the MCP tool."
+          },
+          "arguments": {
+            "description": "The arguments passed to the MCP tool."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatusResource",
+            "description": "The status of the MCP tool call."
+          },
+          "output": {
+            "anyOf": [
+              {},
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The output returned by the MCP tool, if any."
+          },
+          "error": {
+            "anyOf": [
+              {},
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The error returned by the MCP tool, if any."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "server_label",
+          "name",
+          "arguments",
+          "status",
+          "output",
+          "error"
+        ],
+        "additionalProperties": false,
+        "description": "A call to a tool on an MCP server."
+      },
+      "WebSearchActionResourceSearch": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "search"
+            ],
+            "default": "search",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `search`."
+          },
+          "query": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The search query, when a single query was used."
+          },
+          "queries": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The search queries, when multiple queries were used."
+          }
+        },
+        "required": [
+          "type",
+          "query",
+          "queries"
+        ],
+        "additionalProperties": false,
+        "description": "A search query or group of search queries."
+      },
+      "WebSearchActionResourceOpenPage": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "open_page"
+            ],
+            "default": "open_page",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `open_page`."
+          },
+          "url": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The URL of the page that was opened."
+          }
+        },
+        "required": [
+          "type",
+          "url"
+        ],
+        "additionalProperties": false,
+        "description": "Opens a web page."
+      },
+      "WebSearchActionResourceFindInPage": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "find_in_page"
+            ],
+            "default": "find_in_page",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `find_in_page`."
+          },
+          "url": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The URL of the page that was searched."
+          },
+          "pattern": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The text pattern that was searched for."
+          }
+        },
+        "required": [
+          "type",
+          "url",
+          "pattern"
+        ],
+        "additionalProperties": false,
+        "description": "Finds text within a web page."
+      },
+      "WebSearchActionResourceOther": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "other"
+            ],
+            "default": "other",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `other`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Another web search action."
+      },
+      "WebSearchActionResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/WebSearchActionResourceSearch"
+          },
+          {
+            "$ref": "#/components/schemas/WebSearchActionResourceOpenPage"
+          },
+          {
+            "$ref": "#/components/schemas/WebSearchActionResourceFindInPage"
+          },
+          {
+            "$ref": "#/components/schemas/WebSearchActionResourceOther"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "search": "#/components/schemas/WebSearchActionResourceSearch",
+            "open_page": "#/components/schemas/WebSearchActionResourceOpenPage",
+            "find_in_page": "#/components/schemas/WebSearchActionResourceFindInPage",
+            "other": "#/components/schemas/WebSearchActionResourceOther"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "search",
+          "open_page",
+          "find_in_page",
+          "other"
+        ],
+        "description": "An action performed by the web search tool."
+      },
+      "WebSearchCallItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "web_search_call"
+            ],
+            "default": "web_search_call",
+            "x-stainless-const": true,
+            "description": "The item type. Always `web_search_call`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the web search call."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "status": {
+            "$ref": "#/components/schemas/OutputItemStatusResource",
+            "description": "The status of the web search call."
+          },
+          "action": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/WebSearchActionResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The action performed by the web search tool."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "status",
+          "action"
+        ],
+        "additionalProperties": false,
+        "description": "A web search call produced by the agent."
+      },
+      "CommandExecutionItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "command_execution"
+            ],
+            "default": "command_execution",
+            "x-stainless-const": true,
+            "description": "The item type. Always `command_execution`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the command execution item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "command": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The command that was executed."
+          },
+          "cwd": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The working directory used to execute the command."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatusResource",
+            "description": "The status of the command execution."
+          },
+          "output": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The command output, if available."
+          },
+          "exit_code": {
+            "type": [
+              "integer",
+              "null"
+            ],
+            "format": "int64",
+            "description": "The process exit code, if the command completed."
+          },
+          "duration_ms": {
+            "type": [
+              "integer",
+              "null"
+            ],
+            "format": "int64",
+            "description": "The command duration in milliseconds."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "command",
+          "cwd",
+          "status",
+          "output",
+          "exit_code",
+          "duration_ms"
+        ],
+        "additionalProperties": false,
+        "description": "A command execution produced by the agent."
+      },
+      "InterruptSubagentCallItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "interrupt_subagent_call"
+            ],
+            "default": "interrupt_subagent_call",
+            "x-stainless-const": true,
+            "x-enumDescriptions": [
+              "The current public item type."
+            ],
+            "description": "The item type. Always `interrupt_subagent_call`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the tool call item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatusResource",
+            "description": "The status of the tool call."
+          },
+          "sender_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent requesting the interrupt."
+          },
+          "recipient_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent to interrupt."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "status",
+          "sender_agent_id",
+          "recipient_agent_id"
+        ],
+        "additionalProperties": false,
+        "description": "A request to interrupt a subagent's current turn. The subagent remains available."
+      },
+      "CreateSubagentCallItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "create_subagent_call"
+            ],
+            "default": "create_subagent_call",
+            "x-stainless-const": true,
+            "x-enumDescriptions": [
+              "The current public item type."
+            ],
+            "description": "The item type. Always `create_subagent_call`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the tool call item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatusResource",
+            "description": "The status of the tool call."
+          },
+          "agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent that requested the subagent."
+          },
+          "content": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/AgentContentResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The task given to the spawned agent."
+          },
+          "model": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The model requested for the spawned agent."
+          },
+          "reasoning_effort": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The reasoning effort requested for the spawned agent."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "status",
+          "agent_id",
+          "content",
+          "model",
+          "reasoning_effort"
+        ],
+        "additionalProperties": false,
+        "description": "A request to spawn a subagent."
+      },
+      "SendSubagentInputCallItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "send_subagent_input_call"
+            ],
+            "default": "send_subagent_input_call",
+            "x-stainless-const": true,
+            "x-enumDescriptions": [
+              "The current public item type."
+            ],
+            "description": "The item type. Always `send_subagent_input_call`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the tool call item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatusResource",
+            "description": "The status of the tool call."
+          },
+          "sender_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent sending the input."
+          },
+          "recipient_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent receiving the input."
+          },
+          "content": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/AgentContentResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The input sent to the receiving agent."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "status",
+          "sender_agent_id",
+          "recipient_agent_id",
+          "content"
+        ],
+        "additionalProperties": false,
+        "description": "A request to send input to another agent."
+      },
+      "ResumeSubagentCallItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "resume_subagent_call"
+            ],
+            "default": "resume_subagent_call",
+            "x-stainless-const": true,
+            "x-enumDescriptions": [
+              "The current public item type."
+            ],
+            "description": "The item type. Always `resume_subagent_call`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the tool call item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatusResource",
+            "description": "The status of the tool call."
+          },
+          "sender_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent requesting the resume."
+          },
+          "recipient_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent to resume."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "status",
+          "sender_agent_id",
+          "recipient_agent_id"
+        ],
+        "additionalProperties": false,
+        "description": "A request to resume a subagent."
+      },
+      "WaitForSubagentsCallItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "wait_for_subagents_call"
+            ],
+            "default": "wait_for_subagents_call",
+            "x-stainless-const": true,
+            "x-enumDescriptions": [
+              "The current public item type."
+            ],
+            "description": "The item type. Always `wait_for_subagents_call`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the tool call item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatusResource",
+            "description": "The status of the tool call."
+          },
+          "sender_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent waiting for results."
+          },
+          "recipient_agent_ids": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The IDs of the agents to wait for."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "status",
+          "sender_agent_id",
+          "recipient_agent_ids"
+        ],
+        "additionalProperties": false,
+        "description": "A request to wait for one or more subagents."
+      },
+      "CloseSubagentCallItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "close_subagent_call"
+            ],
+            "default": "close_subagent_call",
+            "x-stainless-const": true,
+            "x-enumDescriptions": [
+              "The current public item type."
+            ],
+            "description": "The item type. Always `close_subagent_call`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the tool call item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatusResource",
+            "description": "The status of the tool call."
+          },
+          "sender_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent requesting the close."
+          },
+          "recipient_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent to close."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "status",
+          "sender_agent_id",
+          "recipient_agent_id"
+        ],
+        "additionalProperties": false,
+        "description": "A request to close a subagent."
+      },
+      "SessionTurnItemResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/MessageItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/ReasoningItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionCallOutputItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/AgentMessageItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/McpCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/WebSearchCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/CommandExecutionItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/CreateSubagentCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/SendSubagentInputCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/ResumeSubagentCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/WaitForSubagentsCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/InterruptSubagentCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/CloseSubagentCallItemResource"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "message": "#/components/schemas/MessageItemResource",
+            "reasoning": "#/components/schemas/ReasoningItemResource",
+            "function_call": "#/components/schemas/FunctionCallItemResource",
+            "function_call_output": "#/components/schemas/FunctionCallOutputItemResource",
+            "agent_message": "#/components/schemas/AgentMessageItemResource",
+            "mcp_call": "#/components/schemas/McpCallItemResource",
+            "web_search_call": "#/components/schemas/WebSearchCallItemResource",
+            "command_execution": "#/components/schemas/CommandExecutionItemResource",
+            "interrupt_subagent_call": "#/components/schemas/InterruptSubagentCallItemResource",
+            "create_subagent_call": "#/components/schemas/CreateSubagentCallItemResource",
+            "send_subagent_input_call": "#/components/schemas/SendSubagentInputCallItemResource",
+            "resume_subagent_call": "#/components/schemas/ResumeSubagentCallItemResource",
+            "wait_for_subagents_call": "#/components/schemas/WaitForSubagentsCallItemResource",
+            "close_subagent_call": "#/components/schemas/CloseSubagentCallItemResource"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "message",
+          "reasoning",
+          "function_call",
+          "function_call_output",
+          "agent_message",
+          "mcp_call",
+          "web_search_call",
+          "command_execution",
+          "create_subagent_call",
+          "send_subagent_input_call",
+          "resume_subagent_call",
+          "wait_for_subagents_call",
+          "interrupt_subagent_call",
+          "close_subagent_call"
+        ],
+        "description": "An item associated with a session turn."
+      },
+      "SessionItemListResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "x-stainless-const": true,
+            "description": "The object type, which is always `list`."
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/SessionTurnItemResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The resources returned in this page, in the requested sort order."
+          },
+          "first_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the first resource in `data`, or `null` if the page is empty."
+          },
+          "last_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the last resource in `data`, or `null` if the page is empty. Pass this as `after` with the same order and filters."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more resources to retrieve after this page."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "additionalProperties": false,
+        "description": "A page of messages, reasoning, and tool calls from a session's item history."
+      },
+      "TurnObjectResource": {
+        "type": "string",
+        "enum": [
+          "agent.session.turn"
+        ],
+        "default": "agent.session.turn",
+        "x-stainless-const": true,
+        "description": "The object type for a turn."
+      },
+      "TurnStatusResource": {
+        "type": "string",
+        "enum": [
+          "queued",
+          "in_progress",
+          "waiting",
+          "completed",
+          "failed",
+          "cancelled"
+        ],
+        "x-enumDescriptions": [
+          "The turn is waiting to start.",
+          "The turn is in progress.",
+          "The turn is waiting for external input.",
+          "The turn completed successfully.",
+          "The turn failed.",
+          "The turn was cancelled."
+        ],
+        "description": "The current status of a turn."
+      },
+      "SessionTurnErrorCodeResource": {
+        "type": "string",
+        "enum": [
+          "context_length_exceeded",
+          "session_budget_exceeded",
+          "usage_limit_exceeded",
+          "rate_limit_exceeded",
+          "server_overloaded",
+          "cyber_policy",
+          "connection_failed",
+          "server_error",
+          "authentication_error",
+          "invalid_request",
+          "resource_not_found",
+          "sandbox_error",
+          "executor_version_incompatible",
+          "active_turn_not_steerable",
+          "request_timeout",
+          "internal_error"
+        ],
+        "x-enumDescriptions": [
+          "The request exceeds the model's context window.",
+          "The session has reached its usage budget.",
+          "The organization has reached a usage, plan, or billing limit.",
+          "The request exceeds the available rate limit.",
+          "The model service is temporarily overloaded.",
+          "The request was rejected by a safety policy.",
+          "The request could not connect to the model service.",
+          "The model service encountered an unexpected error.",
+          "The API credentials are invalid or lack the required access.",
+          "The request contains invalid input or configuration.",
+          "The requested model or resource is unavailable.",
+          "The request could not complete in its execution environment.",
+          "The executor must be upgraded before it can run this turn.",
+          "The session cannot accept additional input while a request is running.",
+          "The request timed out before the model service responded.",
+          "An unexpected internal error prevented the session request from completing."
+        ],
+        "description": "Stable public categories for session request failures."
+      },
+      "SessionTurnErrorResource": {
+        "type": "object",
+        "properties": {
+          "code": {
+            "$ref": "#/components/schemas/SessionTurnErrorCodeResource",
+            "description": "A stable, machine-readable failure category."
+          },
+          "message": {
+            "type": "string",
+            "minLength": 0,
+            "description": "A customer-safe explanation of the failure."
+          }
+        },
+        "required": [
+          "code",
+          "message"
+        ],
+        "additionalProperties": false,
+        "description": "A customer-safe error describing why a session request failed."
+      },
+      "InputTokensDetailsResource": {
+        "type": "object",
+        "properties": {
+          "cached_tokens": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The number of input tokens retrieved from the prompt cache."
+          }
+        },
+        "required": [
+          "cached_tokens"
+        ],
+        "additionalProperties": false,
+        "description": "A breakdown of input token usage for a session or turn."
+      },
+      "OutputTokensDetailsResource": {
+        "type": "object",
+        "properties": {
+          "reasoning_tokens": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The number of output tokens used for reasoning."
+          }
+        },
+        "required": [
+          "reasoning_tokens"
+        ],
+        "additionalProperties": false,
+        "description": "A breakdown of output token usage for a session or turn."
+      },
+      "TokenUsageResource": {
+        "type": "object",
+        "properties": {
+          "input_tokens": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The number of input tokens used by the agent."
+          },
+          "input_tokens_details": {
+            "$ref": "#/components/schemas/InputTokensDetailsResource",
+            "description": "A breakdown of the agent's input token usage."
+          },
+          "output_tokens": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The number of output tokens generated by the agent."
+          },
+          "output_tokens_details": {
+            "$ref": "#/components/schemas/OutputTokensDetailsResource",
+            "description": "A breakdown of the agent's output token usage."
+          },
+          "total_tokens": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The total number of input and output tokens used by the agent."
+          }
+        },
+        "required": [
+          "input_tokens",
+          "input_tokens_details",
+          "output_tokens",
+          "output_tokens_details",
+          "total_tokens"
+        ],
+        "additionalProperties": false,
+        "description": "Recorded token usage for a session or turn. Usage is best effort and may change."
+      },
+      "TurnResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn."
+          },
+          "object": {
+            "$ref": "#/components/schemas/TurnObjectResource",
+            "description": "The object type. Always `agent.session.turn`."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session that owns the turn."
+          },
+          "agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent that ran the turn."
+          },
+          "subagent_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the subagent that ran the turn, if applicable."
+          },
+          "status": {
+            "$ref": "#/components/schemas/TurnStatusResource",
+            "description": "The current status of the turn."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, used to order the turn by creation time. Subagent turns use their start time, falling back to completion time or the subagent opening time when the preceding timestamps are unavailable."
+          },
+          "started_at": {
+            "type": [
+              "integer",
+              "null"
+            ],
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the turn started."
+          },
+          "completed_at": {
+            "type": [
+              "integer",
+              "null"
+            ],
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the turn reached a terminal state."
+          },
+          "error": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/SessionTurnErrorResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "A customer-safe error. Non-null only for a failed turn."
+          },
+          "usage": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/TokenUsageResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Best-effort token usage for the turn, or null if unknown. Recorded usage may change."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "session_id",
+          "agent_id",
+          "subagent_id",
+          "status",
+          "created_at",
+          "started_at",
+          "completed_at",
+          "error",
+          "usage"
+        ],
+        "additionalProperties": false,
+        "description": "The canonical public representation of a session turn."
+      },
+      "SessionTurnListResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "x-stainless-const": true,
+            "description": "The object type, which is always `list`."
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/TurnResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The resources returned in this page, in the requested sort order."
+          },
+          "first_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the first resource in `data`, or `null` if the page is empty."
+          },
+          "last_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the last resource in `data`, or `null` if the page is empty. Pass this as `after` with the same order and filters."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more resources to retrieve after this page."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "additionalProperties": false,
+        "description": "A page of Agents API resources, with IDs for retrieving additional pages."
+      },
+      "ReasoningEffortResource": {
+        "type": "string",
+        "enum": [
+          "none",
+          "minimal",
+          "low",
+          "medium",
+          "high",
+          "xhigh",
+          "max"
+        ],
+        "description": "The amount of reasoning effort used by an agent."
+      },
+      "ReasoningSummaryResource": {
+        "type": "string",
+        "enum": [
+          "concise",
+          "detailed",
+          "auto"
+        ],
+        "x-enumDescriptions": [
+          "Returns a concise reasoning summary when supported.",
+          "Returns a detailed reasoning summary when supported.",
+          "Automatically selects the most detailed summary supported by the model."
+        ],
+        "description": "The reasoning summary format requested from an agent."
+      },
+      "ReasoningResource": {
+        "type": "object",
+        "properties": {
+          "effort": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ReasoningEffortResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The requested reasoning effort, or `null` when the model selects its own default."
+          },
+          "summary": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ReasoningSummaryResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The requested reasoning summary format, or `null` when summaries are disabled."
+          }
+        },
+        "required": [
+          "effort",
+          "summary"
+        ],
+        "additionalProperties": false,
+        "description": "The reasoning configuration used by an agent."
+      },
+      "TextFormatResourceText": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "text"
+            ],
+            "default": "text",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `text`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Generates ordinary text without a structured-output constraint."
+      },
+      "TextFormatResourceJsonSchema": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "json_schema"
+            ],
+            "default": "json_schema",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `json_schema`."
+          },
+          "schema": {
+            "type": "object",
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minProperties": 0,
+            "description": "The JSON Schema that generated text must match."
+          }
+        },
+        "required": [
+          "type",
+          "schema"
+        ],
+        "additionalProperties": false,
+        "description": "Constrains generated text to a JSON Schema."
+      },
+      "TextFormatResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/TextFormatResourceText"
+          },
+          {
+            "$ref": "#/components/schemas/TextFormatResourceJsonSchema"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "text": "#/components/schemas/TextFormatResourceText",
+            "json_schema": "#/components/schemas/TextFormatResourceJsonSchema"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "text",
+          "json_schema"
+        ],
+        "description": "The effective output format for generated text."
+      },
+      "VerbosityResource": {
+        "type": "string",
+        "enum": [
+          "low",
+          "medium",
+          "high"
+        ],
+        "description": "The amount of text produced by an agent."
+      },
+      "TextResource": {
+        "type": "object",
+        "properties": {
+          "format": {
+            "$ref": "#/components/schemas/TextFormatResource",
+            "description": "The effective output format. Defaults to ordinary text."
+          },
+          "verbosity": {
+            "$ref": "#/components/schemas/VerbosityResource",
+            "description": "The amount of text produced by the agent. Defaults to `medium`."
+          }
+        },
+        "required": [
+          "format",
+          "verbosity"
+        ],
+        "additionalProperties": false,
+        "description": "The text configuration used by an agent."
+      },
+      "ServiceTierResource": {
+        "type": "string",
+        "enum": [
+          "auto",
+          "default",
+          "flex",
+          "priority",
+          "fast"
+        ],
+        "description": "The service-tier policy configured for an agent."
+      },
+      "PersistedAgentToolResourceFunction": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "function"
+            ],
+            "default": "function",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `function`."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The name of the function."
+          },
+          "description": {
+            "type": "string",
+            "minLength": 0,
+            "description": "A description of what the function does."
+          },
+          "parameters": {
+            "type": "object",
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minProperties": 0,
+            "description": "A JSON Schema object describing the function's arguments."
+          },
+          "defer_loading": {
+            "type": "boolean",
+            "description": "Whether the function is deferred and discovered through tool search."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "description",
+          "parameters",
+          "defer_loading"
+        ],
+        "additionalProperties": false,
+        "description": "A function defined by the application."
+      },
+      "PersistedAgentToolResourceToolSearch": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "tool_search"
+            ],
+            "default": "tool_search",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `tool_search`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Discovers deferred function tools and loads them into the model context."
+      },
+      "PersistedAgentToolResourceProgrammaticToolCalling": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "programmatic_tool_calling"
+            ],
+            "default": "programmatic_tool_calling",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `programmatic_tool_calling`."
+          },
+          "enabled": {
+            "type": "boolean",
+            "description": "Whether tools can be called from model-generated code."
+          }
+        },
+        "required": [
+          "type",
+          "enabled"
+        ],
+        "additionalProperties": false,
+        "description": "Enables calling tools from model-generated code."
+      },
+      "PersistedMcpTransportResourceHttp": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "http"
+            ],
+            "default": "http",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `http`."
+          },
+          "server_url": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The URL of the MCP server."
+          },
+          "headers": {
+            "type": "object",
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minProperties": 0,
+            "description": "Non-secret HTTP headers sent to the MCP server."
+          }
+        },
+        "required": [
+          "type",
+          "server_url",
+          "headers"
+        ],
+        "additionalProperties": false,
+        "description": "Connects to an MCP server over HTTP."
+      },
+      "PersistedMcpTransportResourceStdio": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "stdio"
+            ],
+            "default": "stdio",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `stdio`."
+          },
+          "command": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The command used to start the MCP server."
+          },
+          "args": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Arguments passed to the MCP server command."
+          },
+          "cwd": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The working directory used to start the MCP server."
+          },
+          "env_vars": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Environment variable names inherited from the execution environment."
+          }
+        },
+        "required": [
+          "type",
+          "command",
+          "args",
+          "cwd",
+          "env_vars"
+        ],
+        "additionalProperties": false,
+        "description": "Starts an MCP server as a local process."
+      },
+      "PersistedMcpTransportResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/PersistedMcpTransportResourceHttp"
+          },
+          {
+            "$ref": "#/components/schemas/PersistedMcpTransportResourceStdio"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "http": "#/components/schemas/PersistedMcpTransportResourceHttp",
+            "stdio": "#/components/schemas/PersistedMcpTransportResourceStdio"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "http",
+          "stdio"
+        ],
+        "description": "A credential-free transport used to connect to an MCP server."
+      },
+      "McpConnectionOriginResource": {
+        "type": "string",
+        "enum": [
+          "service",
+          "environment"
+        ],
+        "description": "Where outbound MCP HTTP connections originate."
+      },
+      "PersistedAgentToolResourceMcp": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp"
+            ],
+            "default": "mcp",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `mcp`."
+          },
+          "server_label": {
+            "type": "string",
+            "minLength": 0,
+            "description": "A label used to identify the MCP server in tool calls."
+          },
+          "credential_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The vault credential selected for this MCP server, if any."
+          },
+          "transport": {
+            "$ref": "#/components/schemas/PersistedMcpTransportResource",
+            "description": "The credential-free transport used to connect to the MCP server."
+          },
+          "request_metadata": {
+            "type": "object",
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minProperties": 0,
+            "description": "Metadata included with requests to this MCP server."
+          },
+          "allowed_tools": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The MCP tools the agent may call, or null when all server tools are allowed."
+          },
+          "required": {
+            "type": "boolean",
+            "description": "Whether this MCP server must initialize before the first turn."
+          },
+          "connection_origin": {
+            "$ref": "#/components/schemas/McpConnectionOriginResource",
+            "description": "Where outbound MCP HTTP connections originate."
+          }
+        },
+        "required": [
+          "type",
+          "server_label",
+          "credential_id",
+          "transport",
+          "request_metadata",
+          "allowed_tools",
+          "required",
+          "connection_origin"
+        ],
+        "additionalProperties": false,
+        "description": "Tools provided by a remote MCP server without stored credentials."
+      },
+      "WebSearchModeResource": {
+        "type": "string",
+        "enum": [
+          "disabled",
+          "cached",
+          "live"
+        ],
+        "description": "The source used for web search results."
+      },
+      "WebSearchContextSizeResource": {
+        "type": "string",
+        "enum": [
+          "low",
+          "medium",
+          "high"
+        ],
+        "description": "The amount of web search context made available to the model."
+      },
+      "WebSearchLocationResource": {
+        "type": "object",
+        "properties": {
+          "country": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The two-letter ISO country code, such as `US`."
+          },
+          "region": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The region or state name."
+          },
+          "city": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The city name."
+          },
+          "timezone": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The IANA timezone, such as `America/Los_Angeles`."
+          }
+        },
+        "required": [
+          "country",
+          "region",
+          "city",
+          "timezone"
+        ],
+        "additionalProperties": false,
+        "description": "Approximate user location used to localize web search results."
+      },
+      "PersistedAgentToolResourceWebSearch": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "web_search"
+            ],
+            "default": "web_search",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `web_search`."
+          },
+          "mode": {
+            "$ref": "#/components/schemas/WebSearchModeResource",
+            "description": "The source used for web search results."
+          },
+          "context_size": {
+            "$ref": "#/components/schemas/WebSearchContextSizeResource",
+            "description": "The amount of search context made available to the model. Defaults to `medium`."
+          },
+          "allowed_domains": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Allowed search domains, or `null` when the search is unrestricted."
+          },
+          "location": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/WebSearchLocationResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Approximate location used to localize search results, if provided."
+          }
+        },
+        "required": [
+          "type",
+          "mode",
+          "context_size",
+          "allowed_domains",
+          "location"
+        ],
+        "additionalProperties": false,
+        "description": "Web search."
+      },
+      "PersistedAgentToolResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/PersistedAgentToolResourceFunction"
+          },
+          {
+            "$ref": "#/components/schemas/PersistedAgentToolResourceToolSearch"
+          },
+          {
+            "$ref": "#/components/schemas/PersistedAgentToolResourceProgrammaticToolCalling"
+          },
+          {
+            "$ref": "#/components/schemas/PersistedAgentToolResourceMcp"
+          },
+          {
+            "$ref": "#/components/schemas/PersistedAgentToolResourceWebSearch"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "function": "#/components/schemas/PersistedAgentToolResourceFunction",
+            "tool_search": "#/components/schemas/PersistedAgentToolResourceToolSearch",
+            "programmatic_tool_calling": "#/components/schemas/PersistedAgentToolResourceProgrammaticToolCalling",
+            "mcp": "#/components/schemas/PersistedAgentToolResourceMcp",
+            "web_search": "#/components/schemas/PersistedAgentToolResourceWebSearch"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "function",
+          "tool_search",
+          "programmatic_tool_calling",
+          "mcp",
+          "web_search"
+        ],
+        "description": "A credential-free tool available to a reusable agent."
+      },
+      "MultiAgentConfigResource": {
+        "type": "object",
+        "properties": {
+          "enabled": {
+            "type": "boolean",
+            "description": "Whether subagent tools are enabled. Defaults to false."
+          },
+          "max_concurrent_subagents": {
+            "type": [
+              "integer",
+              "null"
+            ],
+            "format": "int64",
+            "minimum": 1,
+            "maximum": 4294967295,
+            "description": "Maximum number of subagents that may run concurrently, or null when disabled. Defaults to 6 when enabled."
+          }
+        },
+        "required": [
+          "enabled",
+          "max_concurrent_subagents"
+        ],
+        "additionalProperties": false,
+        "description": "The resolved configuration for creating and coordinating subagents."
+      },
+      "AgentResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the reusable agent."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "agent"
+            ],
+            "default": "agent",
+            "x-stainless-const": true,
+            "description": "The object type. Always `agent`."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the agent was created."
+          },
+          "updated_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the agent was last updated."
+          },
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "A human-readable name for the agent, or null if it is unnamed."
+          },
+          "metadata": {
+            "type": "object",
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minProperties": 0,
+            "description": "Custom string key-value pairs attached to the agent."
+          },
+          "model": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The requested model name used for inference."
+          },
+          "reasoning": {
+            "$ref": "#/components/schemas/ReasoningResource",
+            "description": "The resolved reasoning configuration, including the model default for an omitted effort."
+          },
+          "text": {
+            "$ref": "#/components/schemas/TextResource",
+            "description": "The resolved configuration for text generated by the agent."
+          },
+          "service_tier": {
+            "$ref": "#/components/schemas/ServiceTierResource",
+            "description": "The resolved service-tier policy used for model requests."
+          },
+          "instructions": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "Custom instructions appended to the agent's default base instructions."
+          },
+          "tools": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/PersistedAgentToolResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Tools available to the agent."
+          },
+          "multi_agent": {
+            "$ref": "#/components/schemas/MultiAgentConfigResource",
+            "description": "The resolved configuration for creating and coordinating subagents."
+          },
+          "x_agents_core": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/v1.SavedAgentCore"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "created_at",
+          "updated_at",
+          "name",
+          "metadata",
+          "model",
+          "reasoning",
+          "text",
+          "service_tier",
+          "instructions",
+          "tools",
+          "multi_agent"
+        ],
+        "additionalProperties": false,
+        "description": "A reusable agent scoped to the caller's project."
+      },
+      "AgentListResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "x-stainless-const": true,
+            "description": "The object type, which is always `list`."
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/AgentResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The resources returned in this page, in the requested sort order."
+          },
+          "first_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the first resource in `data`, or `null` if the page is empty."
+          },
+          "last_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the last resource in `data`, or `null` if the page is empty. Pass this as `after` with the same order and filters."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more resources to retrieve after this page."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "additionalProperties": false,
+        "description": "A page of Agents API resources, with IDs for retrieving additional pages."
+      },
+      "ReasoningEffortParam": {
+        "type": "string",
+        "enum": [
+          "none",
+          "minimal",
+          "low",
+          "medium",
+          "high",
+          "xhigh",
+          "max"
+        ],
+        "description": "The amount of reasoning effort the model should use."
+      },
+      "ReasoningSummaryParam": {
+        "type": "string",
+        "enum": [
+          "concise",
+          "detailed",
+          "auto"
+        ],
+        "x-enumDescriptions": [
+          "Returns a concise reasoning summary when supported.",
+          "Returns a detailed reasoning summary when supported.",
+          "Automatically selects the most detailed summary supported by the model."
+        ],
+        "description": "The reasoning summary format requested from the model."
+      },
+      "ReasoningParam": {
+        "type": "object",
+        "properties": {
+          "effort": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ReasoningEffortParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The amount of reasoning effort the model should use. Omission lets the model select it."
+          },
+          "summary": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ReasoningSummaryParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Controls whether the response includes a reasoning summary."
+          }
+        },
+        "additionalProperties": false,
+        "description": "Reasoning configuration for the agent."
+      },
+      "TextFormatParamText": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "text"
+            ],
+            "default": "text",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `text`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Generates ordinary text without a structured-output constraint."
+      },
+      "TextFormatParamJsonSchema": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "json_schema"
+            ],
+            "default": "json_schema",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `json_schema`."
+          },
+          "schema": {
+            "type": "object",
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "The JSON Schema that generated text must match."
+          }
+        },
+        "required": [
+          "type",
+          "schema"
+        ],
+        "additionalProperties": false,
+        "description": "Constrains generated text to a JSON Schema."
+      },
+      "TextFormatParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/TextFormatParamText"
+          },
+          {
+            "$ref": "#/components/schemas/TextFormatParamJsonSchema"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "text": "#/components/schemas/TextFormatParamText",
+            "json_schema": "#/components/schemas/TextFormatParamJsonSchema"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "text",
+          "json_schema"
+        ],
+        "description": "The output format for generated text."
+      },
+      "VerbosityParam": {
+        "type": "string",
+        "enum": [
+          "low",
+          "medium",
+          "high"
+        ],
+        "x-enumDescriptions": [
+          "Produces less text.",
+          "Uses the default amount of text.",
+          "Produces more text."
+        ],
+        "description": "The amount of text the model should produce."
+      },
+      "TextParam": {
+        "type": "object",
+        "properties": {
+          "format": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/TextFormatParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The output format. Omission uses ordinary text (`{\"type\": \"text\"}`)."
+          },
+          "verbosity": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/VerbosityParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The amount of text the model should produce. Defaults to `medium`, matching Responses."
+          }
+        },
+        "additionalProperties": false,
+        "description": "Configuration for text generated by the agent."
+      },
+      "ServiceTierParam": {
+        "type": "string",
+        "enum": [
+          "auto",
+          "default",
+          "flex",
+          "priority",
+          "fast"
+        ],
+        "x-enumDescriptions": [
+          "Selects the service tier automatically.",
+          "Uses the default service tier.",
+          "Uses the flex service tier.",
+          "Uses the priority service tier.",
+          "Uses the fast service tier."
+        ],
+        "description": "The service tier used for model requests."
+      },
+      "PersistedAgentToolConfigParamFunction": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "function"
+            ],
+            "default": "function",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `function`."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The name of the function."
+          },
+          "description": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "A description of what the function does."
+          },
+          "parameters": {
+            "type": "object",
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "A JSON Schema object describing the function's arguments."
+          },
+          "defer_loading": {
+            "type": "boolean",
+            "default": false,
+            "description": "Whether this function is deferred and discovered through tool search. Defaults to `false`."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "description",
+          "parameters"
+        ],
+        "additionalProperties": false,
+        "description": "A function defined by the application."
+      },
+      "PersistedAgentToolConfigParamToolSearch": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "tool_search"
+            ],
+            "default": "tool_search",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `tool_search`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Discovers deferred function tools and loads them into the model context."
+      },
+      "PersistedAgentToolConfigParamProgrammaticToolCalling": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "programmatic_tool_calling"
+            ],
+            "default": "programmatic_tool_calling",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `programmatic_tool_calling`."
+          },
+          "enabled": {
+            "type": "boolean",
+            "default": true,
+            "description": "Whether tools can be called from model-generated code. Defaults to `true`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Enables calling tools from model-generated code."
+      },
+      "PersistedMcpTransportConfigParamHttp": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "http"
+            ],
+            "default": "http",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `http`."
+          },
+          "server_url": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The URL of the MCP server."
+          },
+          "headers": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "Non-secret HTTP headers sent to the MCP server."
+          }
+        },
+        "required": [
+          "type",
+          "server_url"
+        ],
+        "additionalProperties": false,
+        "description": "Connects to an MCP server over HTTP."
+      },
+      "PersistedMcpTransportConfigParamStdio": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "stdio"
+            ],
+            "default": "stdio",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `stdio`."
+          },
+          "command": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The command used to start the MCP server."
+          },
+          "args": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Arguments passed to the MCP server command."
+          },
+          "cwd": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The working directory used to start the MCP server."
+          },
+          "env_vars": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Environment variable names to inherit from the selected execution environment."
+          }
+        },
+        "required": [
+          "type",
+          "command",
+          "cwd"
+        ],
+        "additionalProperties": false,
+        "description": "Starts an MCP server as a local process."
+      },
+      "PersistedMcpTransportConfigParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/PersistedMcpTransportConfigParamHttp"
+          },
+          {
+            "$ref": "#/components/schemas/PersistedMcpTransportConfigParamStdio"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "http": "#/components/schemas/PersistedMcpTransportConfigParamHttp",
+            "stdio": "#/components/schemas/PersistedMcpTransportConfigParamStdio"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "http",
+          "stdio"
+        ],
+        "description": "A credential-free transport used to connect to an MCP server."
+      },
+      "McpConnectionOriginParam": {
+        "type": "string",
+        "enum": [
+          "service",
+          "environment"
+        ],
+        "x-enumDescriptions": [
+          "Uses the Managed Agents service network.",
+          "Uses the session's execution environment."
+        ],
+        "description": "Where outbound MCP HTTP connections originate."
+      },
+      "PersistedAgentToolConfigParamMcp": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp"
+            ],
+            "default": "mcp",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `mcp`."
+          },
+          "server_label": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "A label used to identify the MCP server in tool calls."
+          },
+          "credential_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The vault credential selected for this MCP server. Optional when exactly one attached credential matches the server URL."
+          },
+          "transport": {
+            "$ref": "#/components/schemas/PersistedMcpTransportConfigParam",
+            "description": "The credential-free transport used to connect to the MCP server."
+          },
+          "request_metadata": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "Metadata included with requests to this MCP server."
+          },
+          "allowed_tools": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "The MCP tools the agent may call. All server tools are allowed when omitted."
+          },
+          "required": {
+            "type": "boolean",
+            "default": false,
+            "description": "Whether this MCP server must initialize before the first turn. Defaults to `false`."
+          },
+          "connection_origin": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/McpConnectionOriginParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Selects where outbound MCP HTTP connections originate."
+          }
+        },
+        "required": [
+          "type",
+          "server_label",
+          "transport"
+        ],
+        "additionalProperties": false,
+        "description": "Tools provided by a remote MCP server without stored credentials."
+      },
+      "WebSearchModeParam": {
+        "type": "string",
+        "enum": [
+          "disabled",
+          "cached",
+          "live"
+        ],
+        "x-enumDescriptions": [
+          "Disables web search.",
+          "Uses cached search results.",
+          "Searches the live web."
+        ],
+        "description": "The source used for web search results."
+      },
+      "WebSearchContextSizeParam": {
+        "type": "string",
+        "enum": [
+          "low",
+          "medium",
+          "high"
+        ],
+        "description": "The amount of web search context made available to the model."
+      },
+      "WebSearchLocationParam": {
+        "type": "object",
+        "properties": {
+          "country": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The two-letter ISO country code, such as `US`."
+          },
+          "region": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The region or state name."
+          },
+          "city": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The city name."
+          },
+          "timezone": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The IANA timezone, such as `America/Los_Angeles`."
+          }
+        },
+        "additionalProperties": false,
+        "description": "Approximate user location used to localize web search results."
+      },
+      "PersistedAgentToolConfigParamWebSearch": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "web_search"
+            ],
+            "default": "web_search",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `web_search`."
+          },
+          "mode": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/WebSearchModeParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The source used for web search results. Defaults to `live`."
+          },
+          "context_size": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/WebSearchContextSizeParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The amount of search context made available to the model. Defaults to `medium`."
+          },
+          "allowed_domains": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Domains the search may include."
+          },
+          "location": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/WebSearchLocationParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Approximate location used to localize search results."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Web search."
+      },
+      "PersistedAgentToolConfigParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/PersistedAgentToolConfigParamFunction"
+          },
+          {
+            "$ref": "#/components/schemas/PersistedAgentToolConfigParamToolSearch"
+          },
+          {
+            "$ref": "#/components/schemas/PersistedAgentToolConfigParamProgrammaticToolCalling"
+          },
+          {
+            "$ref": "#/components/schemas/PersistedAgentToolConfigParamMcp"
+          },
+          {
+            "$ref": "#/components/schemas/PersistedAgentToolConfigParamWebSearch"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "function": "#/components/schemas/PersistedAgentToolConfigParamFunction",
+            "tool_search": "#/components/schemas/PersistedAgentToolConfigParamToolSearch",
+            "programmatic_tool_calling": "#/components/schemas/PersistedAgentToolConfigParamProgrammaticToolCalling",
+            "mcp": "#/components/schemas/PersistedAgentToolConfigParamMcp",
+            "web_search": "#/components/schemas/PersistedAgentToolConfigParamWebSearch"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "function",
+          "tool_search",
+          "programmatic_tool_calling",
+          "mcp",
+          "web_search"
+        ],
+        "description": "A tool that can be stored on a reusable agent without session credentials."
+      },
+      "MultiAgentConfigCurrentParam": {
+        "type": "object",
+        "properties": {
+          "enabled": {
+            "type": "boolean",
+            "description": "Whether subagent tools are enabled."
+          },
+          "max_concurrent_subagents": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 1,
+            "maximum": 4294967295,
+            "description": "Maximum number of subagents that may run concurrently. Defaults to 6."
+          }
+        },
+        "required": [
+          "enabled"
+        ],
+        "additionalProperties": false,
+        "description": "Explicit configuration for creating and coordinating subagents."
+      },
+      "CreateAgentParams": {
+        "type": "object",
+        "properties": {
+          "metadata": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 512
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 64
+            },
+            "minProperties": 0,
+            "maxProperties": 16,
+            "description": "Up to 16 string key-value pairs, with keys up to 64 and values up to 512 characters. Omission or null defaults to an empty map."
+          },
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 128,
+            "description": "A human-readable name for the agent. Omission or null leaves the agent unnamed."
+          },
+          "model": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The model to use for the agent. The requested model name is preserved."
+          },
+          "reasoning": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ReasoningParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Configuration for model reasoning. Omission uses the model's default effort."
+          },
+          "text": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/TextParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Configuration for generated text. Defaults to the `text` format and medium verbosity."
+          },
+          "service_tier": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ServiceTierParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The service tier used for model requests. Defaults to `auto`."
+          },
+          "instructions": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "Additional instructions appended to the agent's default base instructions. Omit or set to null to add no custom instructions."
+          },
+          "tools": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/PersistedAgentToolConfigParam"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Tools available to the agent. Defaults to an empty list."
+          },
+          "multi_agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/MultiAgentConfigCurrentParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Configuration for creating and coordinating subagents. Subagent tools are disabled by default."
+          },
+          "x_agents_core": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/v1.SavedAgentCoreInput"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "model"
+        ],
+        "additionalProperties": false,
+        "description": "Parameters for creating a reusable agent."
+      },
+      "UpdateAgentParams": {
+        "type": "object",
+        "properties": {
+          "model": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The model to use for the agent. The requested model name is preserved."
+          },
+          "reasoning": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ReasoningParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Configuration for model reasoning. Omit to keep the current settings; pass `null` to reset to the model's default effort."
+          },
+          "text": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/TextParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Configuration for text generated by the agent."
+          },
+          "service_tier": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ServiceTierParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The service tier used for model requests."
+          },
+          "instructions": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "Additional instructions appended to the agent's default base instructions. Omit to leave unchanged."
+          },
+          "multi_agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/MultiAgentConfigCurrentParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Configuration for creating and coordinating subagents."
+          },
+          "metadata": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 512
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 64
+            },
+            "minProperties": 0,
+            "maxProperties": 16,
+            "description": "Replaces all metadata. Omit to leave unchanged, or pass null or {} to clear it. Up to 16 string key-value pairs, with keys up to 64 and values up to 512 characters."
+          },
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 128,
+            "description": "A replacement name. Omit to leave unchanged, or pass null to clear it."
+          },
+          "tools": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/PersistedAgentToolConfigParam"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Tools available to the agent."
+          },
+          "x_agents_core": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/v1.SavedAgentCoreInput"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "additionalProperties": false,
+        "description": "Fields to replace on an existing reusable agent."
+      },
+      "DeletedAgentResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the deleted agent."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "agent.deleted"
+            ],
+            "default": "agent.deleted",
+            "x-stainless-const": true,
+            "description": "The object type. Always `agent.deleted`."
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the agent was deleted. Always `true`."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ],
+        "additionalProperties": false,
+        "description": "A deleted reusable agent."
+      },
+      "EnvironmentPackagesResource": {
+        "type": "object",
+        "properties": {
+          "python": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Python packages installed in the environment."
+          },
+          "system": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "System packages installed in the environment."
+          },
+          "npm": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "npm packages installed globally in the environment."
+          }
+        },
+        "required": [
+          "python",
+          "system",
+          "npm"
+        ],
+        "additionalProperties": false,
+        "description": "Packages installed in an OpenAI-hosted environment."
+      },
+      "NetworkAccessResource": {
+        "type": "string",
+        "enum": [
+          "enabled",
+          "disabled",
+          "restricted"
+        ],
+        "x-enumDescriptions": [
+          "Allows unrestricted network access.",
+          "Disables network access.",
+          "Allows access only to configured domains."
+        ],
+        "description": "The network access mode for an OpenAI-hosted environment."
+      },
+      "NetworkPolicyResource": {
+        "type": "object",
+        "properties": {
+          "access": {
+            "$ref": "#/components/schemas/NetworkAccessResource",
+            "description": "The environment's network access mode."
+          },
+          "allowed_domains": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Domains the environment may access when network access is restricted."
+          }
+        },
+        "required": [
+          "access",
+          "allowed_domains"
+        ],
+        "additionalProperties": false,
+        "description": "Network access for an OpenAI-hosted environment."
+      },
+      "HostedTemplateSkillResourceSkillReference": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "skill_reference"
+            ],
+            "default": "skill_reference",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `skill_reference`."
+          },
+          "skill_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The referenced skill ID."
+          },
+          "version": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The requested version selector, including `latest`."
+          }
+        },
+        "required": [
+          "type",
+          "skill_id",
+          "version"
+        ],
+        "additionalProperties": false,
+        "description": "A skill resolved afresh from the Skills API whenever a session starts."
+      },
+      "HostedTemplateSkillResourceInline": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "inline"
+            ],
+            "default": "inline",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `inline`."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The skill name declared in `SKILL.md`."
+          },
+          "description": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The skill description declared in `SKILL.md`."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "description"
+        ],
+        "additionalProperties": false,
+        "description": "Safe metadata for an inline skill archive."
+      },
+      "HostedTemplateSkillResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/HostedTemplateSkillResourceSkillReference"
+          },
+          {
+            "$ref": "#/components/schemas/HostedTemplateSkillResourceInline"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "skill_reference": "#/components/schemas/HostedTemplateSkillResourceSkillReference",
+            "inline": "#/components/schemas/HostedTemplateSkillResourceInline"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "skill_reference",
+          "inline"
+        ],
+        "description": "Safe metadata for a skill configured by an environment template."
+      },
+      "HostedTemplateFileResourceFileId": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "file_id"
+            ],
+            "default": "file_id",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `file_id`."
+          },
+          "file_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the uploaded file."
+          },
+          "path": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The file's absolute path inside the environment."
+          }
+        },
+        "required": [
+          "type",
+          "file_id",
+          "path"
+        ],
+        "additionalProperties": false,
+        "description": "A project-scoped Files API reference resolved separately for each session."
+      },
+      "HostedTemplateFileResourceInline": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "inline"
+            ],
+            "default": "inline",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `inline`."
+          },
+          "path": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The file's absolute path inside the environment."
+          },
+          "size_bytes": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "description": "The decoded size of the inline file in bytes."
+          }
+        },
+        "required": [
+          "type",
+          "path",
+          "size_bytes"
+        ],
+        "additionalProperties": false,
+        "description": "Metadata for confidential inline file contents."
+      },
+      "HostedTemplateFileResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/HostedTemplateFileResourceFileId"
+          },
+          {
+            "$ref": "#/components/schemas/HostedTemplateFileResourceInline"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "file_id": "#/components/schemas/HostedTemplateFileResourceFileId",
+            "inline": "#/components/schemas/HostedTemplateFileResourceInline"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "file_id",
+          "inline"
+        ],
+        "description": "Safe metadata for a file configured by an environment template."
+      },
+      "EnvironmentTemplateResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the reusable environment template."
+          },
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "An optional human-readable display name for the template."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "agent.environment.template"
+            ],
+            "default": "agent.environment.template",
+            "x-stainless-const": true,
+            "description": "The object type. Always `agent.environment.template`."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the template was created."
+          },
+          "updated_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the template was last updated."
+          },
+          "packages": {
+            "$ref": "#/components/schemas/EnvironmentPackagesResource",
+            "description": "Packages installed in each fresh OpenAI-hosted environment."
+          },
+          "network": {
+            "$ref": "#/components/schemas/NetworkPolicyResource",
+            "description": "Runtime network access for each OpenAI-hosted environment."
+          },
+          "capability_directories": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Directories that expose capabilities to the agent."
+          },
+          "skills": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/HostedTemplateSkillResource"
+            },
+            "minItems": 0,
+            "maxItems": 200,
+            "description": "Safe skill metadata, preserving unresolved version selectors."
+          },
+          "plugins": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/HostedPluginResource"
+            },
+            "minItems": 0,
+            "maxItems": 32,
+            "description": "Safe plugin metadata, excluding inline archive contents."
+          },
+          "files": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/HostedTemplateFileResource"
+            },
+            "minItems": 0,
+            "maxItems": 50,
+            "description": "Safe file metadata, excluding contents and session-scoped file IDs."
+          }
+        },
+        "required": [
+          "id",
+          "name",
+          "object",
+          "created_at",
+          "updated_at",
+          "packages",
+          "network",
+          "capability_directories",
+          "skills",
+          "plugins",
+          "files"
+        ],
+        "additionalProperties": false,
+        "description": "Reusable configuration that provisions a fresh OpenAI-hosted environment for each session."
+      },
+      "EnvironmentTemplateListResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "x-stainless-const": true,
+            "description": "The object type, which is always `list`."
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/EnvironmentTemplateResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The resources returned in this page, in the requested sort order."
+          },
+          "first_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the first resource in `data`, or `null` if the page is empty."
+          },
+          "last_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the last resource in `data`, or `null` if the page is empty. Pass this as `after` with the same order and filters."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more resources to retrieve after this page."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "additionalProperties": false,
+        "description": "A page of Agents API resources, with IDs for retrieving additional pages."
+      },
+      "EnvironmentPackagesParam": {
+        "type": "object",
+        "properties": {
+          "python": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Python packages to install. Defaults to an empty list."
+          },
+          "system": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "System packages to install. Defaults to an empty list."
+          },
+          "npm": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "npm packages to install globally. Defaults to an empty list."
+          }
+        },
+        "additionalProperties": false,
+        "description": "Packages to install in an OpenAI-hosted environment."
+      },
+      "SetupCommandParam": {
+        "type": "object",
+        "properties": {
+          "command": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 65536,
+            "description": "The shell command to execute."
+          },
+          "cwd": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 4096,
+            "description": "The absolute working directory. Defaults to `/workspace`."
+          }
+        },
+        "required": [
+          "command"
+        ],
+        "additionalProperties": false,
+        "description": "A confidential setup command executed before the hosted agent starts."
+      },
+      "NetworkAccessParam": {
+        "type": "string",
+        "enum": [
+          "enabled",
+          "disabled",
+          "restricted"
+        ],
+        "x-enumDescriptions": [
+          "Allows unrestricted network access, matching an omitted network policy.",
+          "Disables network access.",
+          "Allows access only to configured domains."
+        ],
+        "description": "The network access mode for an OpenAI-hosted environment."
+      },
+      "NetworkPolicyParam": {
+        "type": "object",
+        "properties": {
+          "access": {
+            "$ref": "#/components/schemas/NetworkAccessParam",
+            "description": "The environment's network access mode."
+          },
+          "allowed_domains": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Domains the environment may access when network access is restricted."
+          }
+        },
+        "required": [
+          "access"
+        ],
+        "additionalProperties": false,
+        "description": "Network access for an OpenAI-hosted environment."
+      },
+      "HostedSkillParamSkillReference": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "skill_reference"
+            ],
+            "default": "skill_reference",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `skill_reference`."
+          },
+          "skill_id": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 64,
+            "description": "The ID of the skill created through `/v1/skills`."
+          },
+          "version": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The skill version, a positive integer or `latest`; omission selects the default."
+          }
+        },
+        "required": [
+          "type",
+          "skill_id"
+        ],
+        "additionalProperties": false,
+        "description": "References a skill uploaded through the Skills API."
+      },
+      "InlineCapabilitySourceParamBase64": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "base64"
+            ],
+            "default": "base64",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `base64`."
+          },
+          "media_type": {
+            "type": "string",
+            "enum": [
+              "application/zip"
+            ],
+            "default": "application/zip",
+            "x-stainless-const": true,
+            "x-enumDescriptions": [
+              "A ZIP archive."
+            ],
+            "description": "The archive media type, always `application/zip`."
+          },
+          "data": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 70254592,
+            "description": "Standard-base64 encoded ZIP archive bytes."
+          }
+        },
+        "required": [
+          "type",
+          "media_type",
+          "data"
+        ],
+        "additionalProperties": false,
+        "description": "Provides ZIP bytes encoded with standard base64."
+      },
+      "InlineCapabilitySourceParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/InlineCapabilitySourceParamBase64"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "base64": "#/components/schemas/InlineCapabilitySourceParamBase64"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "base64"
+        ],
+        "description": "The encoded ZIP archive for an inline skill or plugin."
+      },
+      "HostedSkillParamInline": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "inline"
+            ],
+            "default": "inline",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `inline`."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 64,
+            "description": "The skill name declared in `SKILL.md`."
+          },
+          "description": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The skill description declared in `SKILL.md`."
+          },
+          "source": {
+            "$ref": "#/components/schemas/InlineCapabilitySourceParam",
+            "description": "The inline ZIP archive."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "description",
+          "source"
+        ],
+        "additionalProperties": false,
+        "description": "Supplies a skill ZIP directly in the session request."
+      },
+      "HostedSkillParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/HostedSkillParamSkillReference"
+          },
+          {
+            "$ref": "#/components/schemas/HostedSkillParamInline"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "skill_reference": "#/components/schemas/HostedSkillParamSkillReference",
+            "inline": "#/components/schemas/HostedSkillParamInline"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "skill_reference",
+          "inline"
+        ],
+        "description": "A skill installed in an OpenAI-hosted environment."
+      },
+      "HostedPluginParamInline": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "inline"
+            ],
+            "default": "inline",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `inline`."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 64,
+            "description": "The plugin name declared in `.codex-plugin/plugin.json`."
+          },
+          "description": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The plugin description declared in `.codex-plugin/plugin.json`."
+          },
+          "source": {
+            "$ref": "#/components/schemas/InlineCapabilitySourceParam",
+            "description": "The inline ZIP archive."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "description",
+          "source"
+        ],
+        "additionalProperties": false,
+        "description": "Supplies a plugin ZIP directly in the session request."
+      },
+      "HostedPluginParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/HostedPluginParamInline"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "inline": "#/components/schemas/HostedPluginParamInline"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "inline"
+        ],
+        "description": "A plugin installed in an OpenAI-hosted environment."
+      },
+      "CreateEnvironmentTemplateParams": {
+        "type": "object",
+        "properties": {
+          "packages": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/EnvironmentPackagesParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Packages to install in the environment. Defaults to empty package lists."
+          },
+          "setup_commands": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/SetupCommandParam"
+            },
+            "minItems": 0,
+            "maxItems": 16,
+            "description": "Ordered, confidential setup commands. Command bodies are never returned."
+          },
+          "network": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/NetworkPolicyParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Network access policy for the environment. Defaults to enabled."
+          },
+          "env": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "Environment variables made available to the agent."
+          },
+          "capability_directories": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Directories that contain capabilities exposed to the agent. Defaults to an empty list."
+          },
+          "skills": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/HostedSkillParam"
+            },
+            "minItems": 0,
+            "maxItems": 200,
+            "description": "Skills referenced by ID or provided as inline ZIP archives. Defaults to an empty list."
+          },
+          "plugins": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/HostedPluginParam"
+            },
+            "minItems": 0,
+            "maxItems": 32,
+            "description": "Plugins provided as inline ZIP archives. Defaults to an empty list."
+          },
+          "files": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/HostedEnvironmentFileParam"
+            },
+            "minItems": 0,
+            "maxItems": 50,
+            "description": "Files available before the agent starts. Defaults to an empty list."
+          },
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 1,
+            "maxLength": 256,
+            "description": "An optional human-readable display name for the template."
+          }
+        },
+        "additionalProperties": false,
+        "description": "Parameters for creating a reusable, project-scoped OpenAI-hosted environment template."
+      },
+      "UpdateEnvironmentTemplateParams": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 1,
+            "maxLength": 256,
+            "description": "A replacement human-readable display name, or `null` to clear the name."
+          },
+          "packages": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/EnvironmentPackagesParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Packages installed before the runtime network policy applies."
+          },
+          "setup_commands": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/SetupCommandParam"
+            },
+            "minItems": 0,
+            "maxItems": 16,
+            "description": "Replacement confidential setup commands, never included in returned resources."
+          },
+          "network": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/NetworkPolicyParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Network access available after setup completes."
+          },
+          "env": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "Replacement confidential environment values."
+          },
+          "capability_directories": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Directories that expose capabilities to the agent."
+          },
+          "skills": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/HostedSkillParam"
+            },
+            "minItems": 0,
+            "maxItems": 200,
+            "description": "Replacement skill configuration installed for each new session."
+          },
+          "plugins": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/HostedPluginParam"
+            },
+            "minItems": 0,
+            "maxItems": 32,
+            "description": "Replacement plugin configuration installed for each new session."
+          },
+          "files": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/HostedEnvironmentFileParam"
+            },
+            "minItems": 0,
+            "maxItems": 50,
+            "description": "Replacement file configuration materialized for each new session."
+          }
+        },
+        "additionalProperties": false,
+        "description": "Fields to replace on an existing reusable OpenAI-hosted environment template."
+      },
+      "DeletedEnvironmentTemplateResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the deleted environment template."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "agent.environment.template.deleted"
+            ],
+            "default": "agent.environment.template.deleted",
+            "x-stainless-const": true,
+            "description": "The object type. Always `agent.environment.template.deleted`."
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the environment template was deleted. Always `true`."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ],
+        "additionalProperties": false,
+        "description": "A deleted reusable environment template."
+      },
+      "SessionStatusResource": {
+        "type": "string",
+        "enum": [
+          "idle",
+          "in_progress",
+          "requires_action",
+          "failed"
+        ],
+        "x-enumDescriptions": [
+          "The session has no turn in progress and is ready for input. A hosted environment may still be provisioning.",
+          "The session is processing a turn.",
+          "The session is waiting for one or more required actions.",
+          "The session failed."
+        ],
+        "description": "The current status of a session."
+      },
+      "SessionRequiredActionResourceFunctionCall": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "function_call"
+            ],
+            "default": "function_call",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `function_call`."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that requested the function call."
+          },
+          "call_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID to include when submitting the function result."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The function name."
+          },
+          "arguments": {
+            "description": "The arguments supplied by the model."
+          }
+        },
+        "required": [
+          "type",
+          "turn_id",
+          "call_id",
+          "name",
+          "arguments"
+        ],
+        "additionalProperties": false,
+        "description": "Run a function tool and submit its result."
+      },
+      "SessionRequiredActionResourceEnvironmentConnection": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "environment_connection"
+            ],
+            "default": "environment_connection",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `environment_connection`."
+          },
+          "environment_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the environment to reconnect."
+          }
+        },
+        "required": [
+          "type",
+          "environment_id"
+        ],
+        "additionalProperties": false,
+        "description": "Reconnect a session environment."
+      },
+      "SessionRequiredActionResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/SessionRequiredActionResourceFunctionCall"
+          },
+          {
+            "$ref": "#/components/schemas/SessionRequiredActionResourceEnvironmentConnection"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "function_call": "#/components/schemas/SessionRequiredActionResourceFunctionCall",
+            "environment_connection": "#/components/schemas/SessionRequiredActionResourceEnvironmentConnection"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "function_call",
+          "environment_connection"
+        ],
+        "description": "An action that must be completed before a session can continue."
+      },
+      "AgentToolResourceFunction": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "function"
+            ],
+            "default": "function",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `function`."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The name of the function."
+          },
+          "description": {
+            "type": "string",
+            "minLength": 0,
+            "description": "A description of what the function does."
+          },
+          "parameters": {
+            "type": "object",
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minProperties": 0,
+            "description": "A JSON Schema object describing the function's arguments."
+          },
+          "defer_loading": {
+            "type": "boolean",
+            "description": "Whether the function is deferred and discovered through tool search."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "description",
+          "parameters",
+          "defer_loading"
+        ],
+        "additionalProperties": false,
+        "description": "A function defined by the application."
+      },
+      "AgentToolResourceProgrammaticToolCalling": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "programmatic_tool_calling"
+            ],
+            "default": "programmatic_tool_calling",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `programmatic_tool_calling`."
+          },
+          "enabled": {
+            "type": "boolean",
+            "description": "Whether tools can be called from model-generated code."
+          }
+        },
+        "required": [
+          "type",
+          "enabled"
+        ],
+        "additionalProperties": false,
+        "description": "Enables calling tools from model-generated code."
+      },
+      "McpTransportResourceHttp": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "http"
+            ],
+            "default": "http",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `http`."
+          },
+          "server_url": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The URL of the MCP server."
+          }
+        },
+        "required": [
+          "type",
+          "server_url"
+        ],
+        "additionalProperties": false,
+        "description": "Connects to an MCP server over HTTP."
+      },
+      "McpTransportResourceStdio": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "stdio"
+            ],
+            "default": "stdio",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `stdio`."
+          },
+          "command": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The command used to start the MCP server."
+          },
+          "args": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Arguments passed to the MCP server command."
+          },
+          "cwd": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The working directory used to start the MCP server."
+          },
+          "env_vars": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Environment variable names inherited from the execution environment."
+          }
+        },
+        "required": [
+          "type",
+          "command",
+          "args",
+          "cwd",
+          "env_vars"
+        ],
+        "additionalProperties": false,
+        "description": "Starts an MCP server as a local process."
+      },
+      "McpTransportResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/McpTransportResourceHttp"
+          },
+          {
+            "$ref": "#/components/schemas/McpTransportResourceStdio"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "http": "#/components/schemas/McpTransportResourceHttp",
+            "stdio": "#/components/schemas/McpTransportResourceStdio"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "http",
+          "stdio"
+        ],
+        "description": "The transport used to connect to an MCP server."
+      },
+      "AgentToolResourceMcp": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp"
+            ],
+            "default": "mcp",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `mcp`."
+          },
+          "server_label": {
+            "type": "string",
+            "minLength": 0,
+            "description": "A label used to identify the MCP server in tool calls."
+          },
+          "credential_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The attached vault credential selected for this MCP server, if any. Optional when exactly one attached credential matches the server URL."
+          },
+          "transport": {
+            "$ref": "#/components/schemas/McpTransportResource",
+            "description": "The transport used to connect to the MCP server."
+          },
+          "request_metadata": {
+            "type": "object",
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minProperties": 0,
+            "description": "Metadata included with requests to this MCP server."
+          },
+          "allowed_tools": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The MCP tools the agent may call."
+          },
+          "required": {
+            "type": "boolean",
+            "description": "Whether this MCP server must initialize before the first turn."
+          },
+          "connection_origin": {
+            "$ref": "#/components/schemas/McpConnectionOriginResource",
+            "description": "Where outbound MCP HTTP connections originate."
+          }
+        },
+        "required": [
+          "type",
+          "server_label",
+          "credential_id",
+          "transport",
+          "request_metadata",
+          "allowed_tools",
+          "required",
+          "connection_origin"
+        ],
+        "additionalProperties": false,
+        "description": "Tools provided by a remote MCP server."
+      },
+      "AgentToolResourceWebSearch": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "web_search"
+            ],
+            "default": "web_search",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `web_search`."
+          },
+          "mode": {
+            "$ref": "#/components/schemas/WebSearchModeResource",
+            "description": "The source used for web search results."
+          },
+          "context_size": {
+            "$ref": "#/components/schemas/WebSearchContextSizeResource",
+            "description": "The amount of search context made available to the model. Defaults to `medium`."
+          },
+          "allowed_domains": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Allowed search domains, or `null` when the search is unrestricted."
+          },
+          "location": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/WebSearchLocationResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Approximate location used to localize search results, if provided."
+          }
+        },
+        "required": [
+          "type",
+          "mode",
+          "context_size",
+          "allowed_domains",
+          "location"
+        ],
+        "additionalProperties": false,
+        "description": "Web search."
+      },
+      "AgentToolResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/AgentToolResourceFunction"
+          },
+          {
+            "$ref": "#/components/schemas/AgentToolResourceProgrammaticToolCalling"
+          },
+          {
+            "$ref": "#/components/schemas/AgentToolResourceMcp"
+          },
+          {
+            "$ref": "#/components/schemas/AgentToolResourceWebSearch"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "function": "#/components/schemas/AgentToolResourceFunction",
+            "programmatic_tool_calling": "#/components/schemas/AgentToolResourceProgrammaticToolCalling",
+            "mcp": "#/components/schemas/AgentToolResourceMcp",
+            "web_search": "#/components/schemas/AgentToolResourceWebSearch"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "function",
+          "programmatic_tool_calling",
+          "mcp",
+          "web_search"
+        ],
+        "description": "A tool available to the agent."
+      },
+      "SessionAgentResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent."
+          },
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The reusable agent's name when the session was created, or null if no name was saved. Later changes to the agent's name do not affect this value."
+          },
+          "model": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The model used by the agent."
+          },
+          "reasoning": {
+            "$ref": "#/components/schemas/ReasoningResource",
+            "description": "The agent's reasoning configuration."
+          },
+          "text": {
+            "$ref": "#/components/schemas/TextResource",
+            "description": "Configuration for text generated by the agent."
+          },
+          "service_tier": {
+            "$ref": "#/components/schemas/ServiceTierResource",
+            "description": "The effective service-tier policy for model requests. Defaults to `auto`."
+          },
+          "instructions": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "Custom instructions appended to the agent's default base instructions."
+          },
+          "tools": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/AgentToolResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Tools available to the agent."
+          },
+          "multi_agent": {
+            "$ref": "#/components/schemas/MultiAgentConfigResource",
+            "description": "Configuration for creating and coordinating subagents."
+          },
+          "x_agents_core": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/v1.AgentsCore"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "name",
+          "model",
+          "reasoning",
+          "text",
+          "service_tier",
+          "instructions",
+          "tools",
+          "multi_agent"
+        ],
+        "additionalProperties": false,
+        "description": "The effective agent configuration for a session."
+      },
+      "EnvironmentResourceNone": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "none"
+            ],
+            "default": "none",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `none`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "The session talks to CCA without selecting or provisioning an execution environment."
+      },
+      "EnvironmentResourceOpenaiHosted": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "openai_hosted"
+            ],
+            "default": "openai_hosted",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `openai_hosted`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The public ID of the environment."
+          },
+          "packages": {
+            "$ref": "#/components/schemas/EnvironmentPackagesResource",
+            "description": "Packages installed in the environment."
+          },
+          "network": {
+            "$ref": "#/components/schemas/NetworkPolicyResource",
+            "description": "The effective network access policy for the environment."
+          },
+          "capability_directories": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Directories that contain capabilities exposed to the agent."
+          },
+          "skills": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/HostedSkillResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Skills installed in the environment, excluding their archive contents."
+          },
+          "plugins": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/HostedPluginResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Plugins installed in the environment, excluding their archive contents."
+          },
+          "files": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/HostedEnvironmentFileResource"
+            },
+            "minItems": 0,
+            "maxItems": 50,
+            "description": "Files available in the environment, excluding their contents."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "packages",
+          "network",
+          "capability_directories",
+          "skills",
+          "plugins",
+          "files"
+        ],
+        "additionalProperties": false,
+        "description": "An environment hosted by OpenAI."
+      },
+      "EnvironmentResourceSelfHosted": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "self_hosted"
+            ],
+            "default": "self_hosted",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `self_hosted`."
+          },
+          "remote_url": {
+            "type": "string",
+            "minLength": 0,
+            "description": "Pass this URL unchanged to `codex exec-server --remote` when connecting this environment."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The public ID of the environment."
+          },
+          "workspace_directory": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The absolute project directory inside the environment. Defaults to `/workspace`."
+          },
+          "capability_directories": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Directories that contain capabilities exposed to the agent."
+          }
+        },
+        "required": [
+          "type",
+          "remote_url",
+          "id",
+          "workspace_directory",
+          "capability_directories"
+        ],
+        "additionalProperties": false,
+        "description": "An environment hosted by the application."
+      },
+      "EnvironmentResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/EnvironmentResourceNone"
+          },
+          {
+            "$ref": "#/components/schemas/EnvironmentResourceOpenaiHosted"
+          },
+          {
+            "$ref": "#/components/schemas/EnvironmentResourceSelfHosted"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "none": "#/components/schemas/EnvironmentResourceNone",
+            "openai_hosted": "#/components/schemas/EnvironmentResourceOpenaiHosted",
+            "self_hosted": "#/components/schemas/EnvironmentResourceSelfHosted"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "none",
+          "openai_hosted",
+          "self_hosted"
+        ],
+        "description": "The execution environment for a session."
+      },
+      "SessionResource": {
+        "type": "object",
+        "properties": {
+          "metadata": {
+            "type": "object",
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minProperties": 0,
+            "description": "Custom string key-value pairs attached to the session."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "agent.session"
+            ],
+            "default": "agent.session",
+            "x-stainless-const": true,
+            "description": "The object type. Always `agent.session`."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the session was created."
+          },
+          "last_active_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the session was last active."
+          },
+          "status": {
+            "$ref": "#/components/schemas/SessionStatusResource",
+            "description": "The current status of the session."
+          },
+          "required_actions": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/SessionRequiredActionResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Actions that must be completed before the session can continue."
+          },
+          "error": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The error that caused the session to fail, if any."
+          },
+          "agent": {
+            "$ref": "#/components/schemas/SessionAgentResource",
+            "description": "The agent running in the session."
+          },
+          "environment": {
+            "$ref": "#/components/schemas/EnvironmentResource",
+            "description": "The execution environment for the session."
+          },
+          "vault_ids": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The IDs of vaults made available to the session."
+          },
+          "usage": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/TokenUsageResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Best-effort token usage for the session, or null if unknown. Recorded usage may change."
+          },
+          "x_agents_core": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/v1.SessionCore"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "metadata",
+          "id",
+          "object",
+          "created_at",
+          "last_active_at",
+          "status",
+          "required_actions",
+          "error",
+          "agent",
+          "environment",
+          "vault_ids",
+          "usage"
+        ],
+        "additionalProperties": false,
+        "description": "A Managed Agents session."
+      },
+      "SessionListResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "x-stainless-const": true,
+            "description": "The object type, which is always `list`."
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/SessionResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The resources returned in this page, in the requested sort order."
+          },
+          "first_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the first resource in `data`, or `null` if the page is empty."
+          },
+          "last_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the last resource in `data`, or `null` if the page is empty. Pass this as `after` with the same order and filters."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more resources to retrieve after this page."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "additionalProperties": false,
+        "description": "A page of Agents API resources, with IDs for retrieving additional pages."
+      },
+      "AgentToolConfigParamFunction": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "function"
+            ],
+            "default": "function",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `function`."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The name of the function."
+          },
+          "description": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "A description of what the function does."
+          },
+          "parameters": {
+            "type": "object",
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "A JSON Schema object describing the function's arguments."
+          },
+          "defer_loading": {
+            "type": "boolean",
+            "default": false,
+            "description": "Whether this function is deferred and discovered through tool search. Defaults to `false`."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "description",
+          "parameters"
+        ],
+        "additionalProperties": false,
+        "description": "A function defined by the application."
+      },
+      "AgentToolConfigParamToolSearch": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "tool_search"
+            ],
+            "default": "tool_search",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `tool_search`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Discovers deferred function tools and loads them into the model context."
+      },
+      "AgentToolConfigParamProgrammaticToolCalling": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "programmatic_tool_calling"
+            ],
+            "default": "programmatic_tool_calling",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `programmatic_tool_calling`."
+          },
+          "enabled": {
+            "type": "boolean",
+            "default": true,
+            "description": "Whether tools can be called from model-generated code. Defaults to `true`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Enables calling tools from model-generated code."
+      },
+      "McpTransportConfigParamHttp": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "http"
+            ],
+            "default": "http",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `http`."
+          },
+          "server_url": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The URL of the MCP server."
+          },
+          "authorization": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The authorization value sent to the MCP server, if any."
+          },
+          "headers": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "Additional HTTP headers sent to the MCP server."
+          }
+        },
+        "required": [
+          "type",
+          "server_url"
+        ],
+        "additionalProperties": false,
+        "description": "Connects to an MCP server over HTTP."
+      },
+      "McpTransportConfigParamStdio": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "stdio"
+            ],
+            "default": "stdio",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `stdio`."
+          },
+          "command": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The command used to start the MCP server."
+          },
+          "args": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Arguments passed to the MCP server command."
+          },
+          "cwd": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The working directory used to start the MCP server."
+          },
+          "env": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "Environment variables set for the MCP server process."
+          },
+          "env_vars": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Environment variable names to inherit from the selected execution environment."
+          }
+        },
+        "required": [
+          "type",
+          "command",
+          "cwd"
+        ],
+        "additionalProperties": false,
+        "description": "Starts an MCP server as a local process."
+      },
+      "McpTransportConfigParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/McpTransportConfigParamHttp"
+          },
+          {
+            "$ref": "#/components/schemas/McpTransportConfigParamStdio"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "http": "#/components/schemas/McpTransportConfigParamHttp",
+            "stdio": "#/components/schemas/McpTransportConfigParamStdio"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "http",
+          "stdio"
+        ],
+        "description": "The transport used to connect to an MCP server."
+      },
+      "AgentToolConfigParamMcp": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp"
+            ],
+            "default": "mcp",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `mcp`."
+          },
+          "server_label": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "A label used to identify the MCP server in tool calls."
+          },
+          "credential_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The attached vault credential used to authenticate this MCP server. Optional when exactly one attached credential matches the server URL."
+          },
+          "transport": {
+            "$ref": "#/components/schemas/McpTransportConfigParam",
+            "description": "The transport used to connect to the MCP server."
+          },
+          "request_metadata": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "Metadata included with requests to this MCP server."
+          },
+          "allowed_tools": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "The MCP tools the agent may call. All server tools are allowed when omitted."
+          },
+          "required": {
+            "type": "boolean",
+            "default": false,
+            "description": "Whether this MCP server must initialize before the first turn. Defaults to `false`."
+          },
+          "connection_origin": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/McpConnectionOriginParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Selects where outbound MCP HTTP connections originate. Omitted or `service` uses the Managed Agents service network; `environment` uses the session's selected environment."
+          }
+        },
+        "required": [
+          "type",
+          "server_label",
+          "transport"
+        ],
+        "additionalProperties": false,
+        "description": "Tools provided by a remote MCP server."
+      },
+      "AgentToolConfigParamWebSearch": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "web_search"
+            ],
+            "default": "web_search",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `web_search`."
+          },
+          "mode": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/WebSearchModeParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The source used for web search results. Defaults to `live`."
+          },
+          "context_size": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/WebSearchContextSizeParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The amount of search context made available to the model. Defaults to `medium`."
+          },
+          "allowed_domains": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Domains the search may include."
+          },
+          "location": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/WebSearchLocationParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Approximate location used to localize search results."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Web search."
+      },
+      "AgentToolConfigParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/AgentToolConfigParamFunction"
+          },
+          {
+            "$ref": "#/components/schemas/AgentToolConfigParamToolSearch"
+          },
+          {
+            "$ref": "#/components/schemas/AgentToolConfigParamProgrammaticToolCalling"
+          },
+          {
+            "$ref": "#/components/schemas/AgentToolConfigParamMcp"
+          },
+          {
+            "$ref": "#/components/schemas/AgentToolConfigParamWebSearch"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "function": "#/components/schemas/AgentToolConfigParamFunction",
+            "tool_search": "#/components/schemas/AgentToolConfigParamToolSearch",
+            "programmatic_tool_calling": "#/components/schemas/AgentToolConfigParamProgrammaticToolCalling",
+            "mcp": "#/components/schemas/AgentToolConfigParamMcp",
+            "web_search": "#/components/schemas/AgentToolConfigParamWebSearch"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "function",
+          "tool_search",
+          "programmatic_tool_calling",
+          "mcp",
+          "web_search"
+        ],
+        "description": "A tool available to the agent."
+      },
+      "SessionAgentConfigParam": {
+        "type": "object",
+        "properties": {
+          "model": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The model to use for the agent. The requested model name is preserved."
+          },
+          "reasoning": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ReasoningParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Configuration for model reasoning. Omit to keep the current settings; pass `null` to reset to the model's default effort."
+          },
+          "text": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/TextParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Configuration for text generated by the agent."
+          },
+          "service_tier": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ServiceTierParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The service tier used for model requests."
+          },
+          "instructions": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "Additional instructions appended to the agent's default base instructions. Omit to leave unchanged."
+          },
+          "multi_agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/MultiAgentConfigCurrentParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Configuration for creating and coordinating subagents."
+          },
+          "tools": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/AgentToolConfigParam"
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Tools available to the agent. Omit to inherit, or pass null to clear them."
+          },
+          "x_agents_core": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/v1.AgentsCore"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "additionalProperties": false,
+        "description": "Agent configuration for a session. Omitted fields inherit from `agent_id` when supplied. Supplied objects and arrays replace the whole field; null resets nullable fields."
+      },
+      "EnvironmentParamNone": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "none"
+            ],
+            "default": "none",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `none`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Runs the agent without an execution environment."
+      },
+      "EnvironmentParamOpenaiHosted": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "openai_hosted"
+            ],
+            "default": "openai_hosted",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `openai_hosted`."
+          },
+          "packages": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/EnvironmentPackagesParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Packages to install in the environment. Defaults to empty package lists."
+          },
+          "setup_commands": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/SetupCommandParam"
+            },
+            "minItems": 0,
+            "maxItems": 16,
+            "description": "Ordered, confidential setup commands. Command bodies are never returned."
+          },
+          "network": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/NetworkPolicyParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Network access policy for the environment. Defaults to enabled."
+          },
+          "env": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "Environment variables made available to the agent."
+          },
+          "capability_directories": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Directories that contain capabilities exposed to the agent. Defaults to an empty list."
+          },
+          "skills": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/HostedSkillParam"
+            },
+            "minItems": 0,
+            "maxItems": 200,
+            "description": "Skills referenced by ID or provided as inline ZIP archives. Defaults to an empty list."
+          },
+          "plugins": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/HostedPluginParam"
+            },
+            "minItems": 0,
+            "maxItems": 32,
+            "description": "Plugins provided as inline ZIP archives. Defaults to an empty list."
+          },
+          "files": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/HostedEnvironmentFileParam"
+            },
+            "minItems": 0,
+            "maxItems": 50,
+            "description": "Files available before the agent starts. Defaults to an empty list."
+          },
+          "environment_template_id": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 64,
+            "description": "A reusable hosted template applied before inline session configuration. Omitted fields inherit the template; network overrides cannot broaden its policy."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "An OpenAI-hosted environment, optionally based on a reusable template."
+      },
+      "EnvironmentParamSelfHosted": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "self_hosted"
+            ],
+            "default": "self_hosted",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `self_hosted`."
+          },
+          "workspace_directory": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "Absolute project directory inside the self-hosted environment."
+          },
+          "capability_directories": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Directories that contain capabilities exposed to the agent. Defaults to an empty list."
+          }
+        },
+        "required": [
+          "type",
+          "workspace_directory"
+        ],
+        "additionalProperties": false,
+        "description": "An application-hosted environment configured inline."
+      },
+      "EnvironmentParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/EnvironmentParamNone"
+          },
+          {
+            "$ref": "#/components/schemas/EnvironmentParamOpenaiHosted"
+          },
+          {
+            "$ref": "#/components/schemas/EnvironmentParamSelfHosted"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "none": "#/components/schemas/EnvironmentParamNone",
+            "openai_hosted": "#/components/schemas/EnvironmentParamOpenaiHosted",
+            "self_hosted": "#/components/schemas/EnvironmentParamSelfHosted"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "none",
+          "openai_hosted",
+          "self_hosted"
+        ],
+        "description": "The execution environment and optional reusable template for a session."
+      },
+      "InputContentParamInputText": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_text"
+            ],
+            "default": "input_text",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `input_text`."
+          },
+          "text": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The text sent to the model."
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ],
+        "additionalProperties": false,
+        "description": "Text input to the model."
+      },
+      "InputContentParamInputImage": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_image"
+            ],
+            "default": "input_image",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `input_image`."
+          },
+          "image_url": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The URL of the image sent to the model."
+          }
+        },
+        "required": [
+          "type",
+          "image_url"
+        ],
+        "additionalProperties": false,
+        "description": "Image input to the model."
+      },
+      "InputContentParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/InputContentParamInputText"
+          },
+          {
+            "$ref": "#/components/schemas/InputContentParamInputImage"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "input_text": "#/components/schemas/InputContentParamInputText",
+            "input_image": "#/components/schemas/InputContentParamInputImage"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "input_text",
+          "input_image"
+        ],
+        "description": "Content included in an input message."
+      },
+      "InputMessageParam": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "message"
+            ],
+            "default": "message",
+            "x-stainless-const": true,
+            "description": "The type of the input item. Always `message`."
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "user"
+            ],
+            "default": "user",
+            "x-stainless-const": true,
+            "description": "The role of the message author. Always `user`."
+          },
+          "content": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/InputContentParam"
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "The content of the message."
+          }
+        },
+        "required": [
+          "role",
+          "content"
+        ],
+        "additionalProperties": false,
+        "description": "A user message submitted to a session."
+      },
+      "CreateSessionInputParam": {
+        "oneOf": [
+          {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 1048576
+          },
+          {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/InputMessageParam"
+            },
+            "minItems": 0,
+            "maxItems": 16384
+          }
+        ],
+        "description": "Initial input submitted when creating a session."
+      },
+      "CreateAgentSessionParams": {
+        "type": "object",
+        "properties": {
+          "metadata": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 512
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 64
+            },
+            "minProperties": 0,
+            "maxProperties": 16,
+            "description": "Up to 16 string key-value pairs, with keys up to 64 and values up to 512 characters. Omission or null defaults to an empty map."
+          },
+          "agent": {
+            "$ref": "#/components/schemas/SessionAgentConfigParam",
+            "description": "Agent configuration. With `agent_id`, supplied fields override the saved agent for this session. Without `agent_id`, `model` is required."
+          },
+          "agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 64,
+            "description": "The ID of a saved reusable agent. Omit `agent` to use its configuration unchanged."
+          },
+          "environment": {
+            "$ref": "#/components/schemas/EnvironmentParam",
+            "description": "An inline execution environment or a reference to an environment template."
+          },
+          "vault_ids": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "The IDs of vaults made available to the session."
+          },
+          "input": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/CreateSessionInputParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Initial input to submit when the session is created. A string is shorthand for a single user message. Required when `environment.type` is `none`, or when `stream` is `true` for an environment that is not `self_hosted`; optional for self-hosted and non-streaming execution environments."
+          },
+          "stream": {
+            "type": "boolean",
+            "default": false,
+            "description": "Whether to stream session events as server-sent events. Defaults to `false`."
+          },
+          "x_agents_core": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/v1.SessionExecutionInput"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "environment"
+        ],
+        "additionalProperties": false,
+        "description": "Parameters for creating a Managed Agents session."
+      },
+      "SessionErrorResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The error type."
+          },
+          "code": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The machine-readable error code, if any."
+          },
+          "message": {
+            "type": "string",
+            "minLength": 0,
+            "description": "A customer-safe explanation of the error."
+          },
+          "param": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The request parameter associated with the error, if any."
+          }
+        },
+        "required": [
+          "type",
+          "code",
+          "message",
+          "param"
+        ],
+        "additionalProperties": false,
+        "description": "An error payload with the same public fields as Responses API streaming errors."
+      },
+      "SessionEventError": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "error"
+            ],
+            "default": "error",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `error`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "error": {
+            "$ref": "#/components/schemas/SessionErrorResource",
+            "description": "The error that occurred."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "error"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a turn or session fails.",
+        "x-oaiMeta": {
+          "example": {
+            "type": "error",
+            "event_id": "event_123",
+            "session_id": "sess_123",
+            "error": {
+              "type": "server_error",
+              "code": null,
+              "message": "The session failed due to an internal server error.",
+              "param": null
+            }
+          }
+        }
+      },
+      "SessionEnvironmentStatusResource": {
+        "type": "string",
+        "enum": [
+          "pending",
+          "ready",
+          "connected",
+          "disconnected",
+          "failed"
+        ],
+        "x-enumDescriptions": [
+          "The environment is being prepared.",
+          "The environment is ready to connect.",
+          "The environment is connected.",
+          "The environment is disconnected.",
+          "The environment failed to connect."
+        ],
+        "description": "The connection status of a session environment."
+      },
+      "SessionEnvironmentErrorResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The error type."
+          },
+          "code": {
+            "type": "string",
+            "minLength": 0,
+            "description": "A machine-readable error code."
+          },
+          "message": {
+            "type": "string",
+            "minLength": 0,
+            "description": "A human-readable error message."
+          }
+        },
+        "required": [
+          "type",
+          "code",
+          "message"
+        ],
+        "additionalProperties": false,
+        "description": "An error reported while preparing a session environment."
+      },
+      "SessionEnvironmentStateResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The public ID of the environment."
+          },
+          "type": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The environment type."
+          },
+          "status": {
+            "$ref": "#/components/schemas/SessionEnvironmentStatusResource",
+            "description": "The environment's connection status."
+          },
+          "error": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/SessionEnvironmentErrorResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The error reported while preparing the environment, if any."
+          }
+        },
+        "required": [
+          "id",
+          "type",
+          "status",
+          "error"
+        ],
+        "additionalProperties": false,
+        "description": "The current state of a session environment."
+      },
+      "SessionEventAgentSessionEnvironmentReady": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.environment.ready"
+            ],
+            "default": "agent.session.environment.ready",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.environment.ready`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "environment": {
+            "$ref": "#/components/schemas/SessionEnvironmentStateResource",
+            "description": "The current environment state."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "environment"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a hosted session environment is ready to connect."
+      },
+      "SessionEventAgentOutputCommandExecutionOutputDelta": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.output.command_execution_output.delta"
+            ],
+            "default": "agent.output.command_execution_output.delta",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.output.command_execution_output.delta`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "item_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the command execution item."
+          },
+          "output_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the item in the turn output."
+          },
+          "delta": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The output text that was appended."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "item_id",
+          "output_index",
+          "delta"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when command execution produces an output delta."
+      },
+      "SessionEventAgentSessionCreated": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.created"
+            ],
+            "default": "agent.session.created",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.created`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session": {
+            "$ref": "#/components/schemas/SessionResource",
+            "description": "The session that was created."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a session is created."
+      },
+      "SessionEventAgentSessionTurnCreated": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.created"
+            ],
+            "default": "agent.session.turn.created",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.created`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event."
+          },
+          "turn": {
+            "$ref": "#/components/schemas/TurnResource",
+            "description": "The turn at the time it was created."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "turn"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a turn is created."
+      },
+      "SessionEventAgentSessionTurnInProgress": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.in_progress"
+            ],
+            "default": "agent.session.turn.in_progress",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.in_progress`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event."
+          },
+          "turn": {
+            "$ref": "#/components/schemas/TurnResource",
+            "description": "The turn at the time it started running."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "turn"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a turn starts running."
+      },
+      "SessionEventAgentSessionTurnCompleted": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.completed"
+            ],
+            "default": "agent.session.turn.completed",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.completed`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event."
+          },
+          "turn": {
+            "$ref": "#/components/schemas/TurnResource",
+            "description": "The completed turn."
+          },
+          "usage": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/TokenUsageResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Token usage by the root agent during the turn, when available."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "turn",
+          "usage"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a turn completes."
+      },
+      "SessionEventAgentSessionTurnFailed": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.failed"
+            ],
+            "default": "agent.session.turn.failed",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.failed`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event."
+          },
+          "turn": {
+            "$ref": "#/components/schemas/TurnResource",
+            "description": "The failed turn."
+          },
+          "usage": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/TokenUsageResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Token usage by the root agent during the turn, when available."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "turn",
+          "usage"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a turn fails."
+      },
+      "SessionEventAgentSessionTurnCancelled": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.cancelled"
+            ],
+            "default": "agent.session.turn.cancelled",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.cancelled`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event."
+          },
+          "turn": {
+            "$ref": "#/components/schemas/TurnResource",
+            "description": "The cancelled turn."
+          },
+          "usage": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/TokenUsageResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Token usage by the root agent during the turn, when available."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "turn",
+          "usage"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a turn is cancelled."
+      },
+      "SessionEventAgentSessionTurnItemAdded": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.item.added"
+            ],
+            "default": "agent.session.turn.item.added",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.item.added`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "output_index": {
+            "type": [
+              "integer",
+              "null"
+            ],
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the item in the turn output, when the item is agent output."
+          },
+          "item": {
+            "$ref": "#/components/schemas/SessionTurnItemResource",
+            "description": "The item that was added."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "output_index",
+          "item"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when an item is added to a turn."
+      },
+      "SessionEventAgentSessionIdle": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.idle"
+            ],
+            "default": "agent.session.idle",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.idle`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session": {
+            "$ref": "#/components/schemas/SessionResource",
+            "description": "The session that became idle."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a session becomes idle."
+      },
+      "SessionEventAgentSessionInProgress": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.in_progress"
+            ],
+            "default": "agent.session.in_progress",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.in_progress`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session": {
+            "$ref": "#/components/schemas/SessionResource",
+            "description": "The session that started processing."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a session starts processing a turn."
+      },
+      "SessionEventAgentSessionRequiresAction": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.requires_action"
+            ],
+            "default": "agent.session.requires_action",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.requires_action`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session": {
+            "$ref": "#/components/schemas/SessionResource",
+            "description": "The session and its current required actions."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a session is waiting for one or more required actions."
+      },
+      "SessionEventAgentSessionFailed": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.failed"
+            ],
+            "default": "agent.session.failed",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.failed`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session": {
+            "$ref": "#/components/schemas/SessionResource",
+            "description": "The failed session."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a session fails."
+      },
+      "SessionEventAgentSessionEnvironmentPending": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.environment.pending"
+            ],
+            "default": "agent.session.environment.pending",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.environment.pending`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "environment": {
+            "$ref": "#/components/schemas/SessionEnvironmentStateResource",
+            "description": "The current environment state."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "environment"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted while a session environment is being prepared."
+      },
+      "SessionEventAgentSessionEnvironmentConnected": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.environment.connected"
+            ],
+            "default": "agent.session.environment.connected",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.environment.connected`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "environment": {
+            "$ref": "#/components/schemas/SessionEnvironmentStateResource",
+            "description": "The current environment state."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "environment"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a session environment connects."
+      },
+      "SessionEventAgentSessionEnvironmentDisconnected": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.environment.disconnected"
+            ],
+            "default": "agent.session.environment.disconnected",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.environment.disconnected`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "environment": {
+            "$ref": "#/components/schemas/SessionEnvironmentStateResource",
+            "description": "The current environment state."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "environment"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a session environment disconnects."
+      },
+      "SessionEventAgentSessionEnvironmentFailed": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.environment.failed"
+            ],
+            "default": "agent.session.environment.failed",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.environment.failed`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "environment": {
+            "$ref": "#/components/schemas/SessionEnvironmentStateResource",
+            "description": "The current environment state."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "environment"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a session environment fails."
+      },
+      "SessionEventAgentSessionSubagentCreated": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.subagent.created"
+            ],
+            "default": "agent.session.subagent.created",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.subagent.created`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "subagent": {
+            "$ref": "#/components/schemas/SubagentResource",
+            "description": "The subagent that was created."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "subagent"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a subagent is created."
+      },
+      "SessionEventAgentSessionSubagentActive": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.subagent.active"
+            ],
+            "default": "agent.session.subagent.active",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.subagent.active`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "subagent": {
+            "$ref": "#/components/schemas/SubagentResource",
+            "description": "The subagent that resumed."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "subagent"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a closed subagent successfully resumes."
+      },
+      "SessionEventAgentSessionSubagentClosed": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.subagent.closed"
+            ],
+            "default": "agent.session.subagent.closed",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.subagent.closed`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "subagent": {
+            "$ref": "#/components/schemas/SubagentResource",
+            "description": "The subagent that was closed."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "subagent"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a subagent is closed."
+      },
+      "AssistantMessageItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "message"
+            ],
+            "default": "message",
+            "x-stainless-const": true,
+            "description": "The item type. Always `message`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the message."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "assistant"
+            ],
+            "default": "assistant",
+            "x-stainless-const": true,
+            "description": "The role of the message author. Always `assistant`."
+          },
+          "status": {
+            "$ref": "#/components/schemas/OutputItemStatusResource",
+            "description": "The status of the message."
+          },
+          "content": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/OutputTextResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The content of the message."
+          },
+          "phase": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/MessagePhaseResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The phase of the assistant message."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "role",
+          "status",
+          "content",
+          "phase"
+        ],
+        "additionalProperties": false,
+        "description": "An assistant message produced by the agent."
+      },
+      "AgentOutputItemResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/AssistantMessageItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/ReasoningItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/McpCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/WebSearchCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/CommandExecutionItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/CreateSubagentCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/SendSubagentInputCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/ResumeSubagentCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/WaitForSubagentsCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/InterruptSubagentCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/CloseSubagentCallItemResource"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "message": "#/components/schemas/AssistantMessageItemResource",
+            "reasoning": "#/components/schemas/ReasoningItemResource",
+            "function_call": "#/components/schemas/FunctionCallItemResource",
+            "mcp_call": "#/components/schemas/McpCallItemResource",
+            "web_search_call": "#/components/schemas/WebSearchCallItemResource",
+            "command_execution": "#/components/schemas/CommandExecutionItemResource",
+            "interrupt_subagent_call": "#/components/schemas/InterruptSubagentCallItemResource",
+            "create_subagent_call": "#/components/schemas/CreateSubagentCallItemResource",
+            "send_subagent_input_call": "#/components/schemas/SendSubagentInputCallItemResource",
+            "resume_subagent_call": "#/components/schemas/ResumeSubagentCallItemResource",
+            "wait_for_subagents_call": "#/components/schemas/WaitForSubagentsCallItemResource",
+            "close_subagent_call": "#/components/schemas/CloseSubagentCallItemResource"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "message",
+          "reasoning",
+          "function_call",
+          "mcp_call",
+          "web_search_call",
+          "command_execution",
+          "create_subagent_call",
+          "send_subagent_input_call",
+          "resume_subagent_call",
+          "wait_for_subagents_call",
+          "interrupt_subagent_call",
+          "close_subagent_call"
+        ],
+        "description": "An output item produced by an agent."
+      },
+      "SessionEventAgentSessionTurnItemDone": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.item.done"
+            ],
+            "default": "agent.session.turn.item.done",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.item.done`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "output_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the output item in the turn output."
+          },
+          "item": {
+            "$ref": "#/components/schemas/AgentOutputItemResource",
+            "description": "The completed output item."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "output_index",
+          "item"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when an output item is complete."
+      },
+      "SessionEventAgentSessionTurnContentPartAdded": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.content_part.added"
+            ],
+            "default": "agent.session.turn.content_part.added",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.content_part.added`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "item_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the message item."
+          },
+          "output_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the item in the turn output."
+          },
+          "content_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the content part in the message."
+          },
+          "part": {
+            "$ref": "#/components/schemas/OutputTextResource",
+            "description": "The initial content part."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "part"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when an output text content part is added."
+      },
+      "SessionEventAgentSessionTurnContentPartDone": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.content_part.done"
+            ],
+            "default": "agent.session.turn.content_part.done",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.content_part.done`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "item_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the message item."
+          },
+          "output_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the item in the turn output."
+          },
+          "content_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the content part in the message."
+          },
+          "part": {
+            "$ref": "#/components/schemas/OutputTextResource",
+            "description": "The completed content part."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "part"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when an output content part is complete."
+      },
+      "SessionEventAgentSessionTurnOutputTextDelta": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.output_text.delta"
+            ],
+            "default": "agent.session.turn.output_text.delta",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.output_text.delta`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "item_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the message item."
+          },
+          "output_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the item in the turn output."
+          },
+          "content_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the content part in the message."
+          },
+          "delta": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The text that was appended."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "delta"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when text is appended to an output text content part."
+      },
+      "SessionEventAgentSessionTurnOutputTextDone": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.output_text.done"
+            ],
+            "default": "agent.session.turn.output_text.done",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.output_text.done`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "item_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the message item."
+          },
+          "output_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the item in the turn output."
+          },
+          "content_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the content part in the message."
+          },
+          "text": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The complete output text."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "text"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when an output text content part is complete."
+      },
+      "SessionEventAgentSessionTurnReasoningSummaryPartAdded": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.reasoning_summary_part.added"
+            ],
+            "default": "agent.session.turn.reasoning_summary_part.added",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.reasoning_summary_part.added`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "item_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the reasoning item."
+          },
+          "output_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the item in the turn output."
+          },
+          "summary_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the summary content part."
+          },
+          "part": {
+            "$ref": "#/components/schemas/SummaryTextResource",
+            "description": "The initial summary part."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "item_id",
+          "output_index",
+          "summary_index",
+          "part"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a reasoning summary content part is added."
+      },
+      "SessionEventAgentSessionTurnReasoningSummaryPartDone": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.reasoning_summary_part.done"
+            ],
+            "default": "agent.session.turn.reasoning_summary_part.done",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.reasoning_summary_part.done`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "item_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the reasoning item."
+          },
+          "output_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the item in the turn output."
+          },
+          "summary_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the summary part."
+          },
+          "part": {
+            "$ref": "#/components/schemas/SummaryTextResource",
+            "description": "The completed summary part."
+          },
+          "status": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "enum": [
+              "incomplete",
+              null
+            ],
+            "description": "Present as `incomplete` when summary generation was interrupted.",
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "item_id",
+          "output_index",
+          "summary_index",
+          "part",
+          "status"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a reasoning summary part is complete."
+      },
+      "SessionEventAgentSessionTurnReasoningSummaryTextDelta": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.reasoning_summary_text.delta"
+            ],
+            "default": "agent.session.turn.reasoning_summary_text.delta",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.reasoning_summary_text.delta`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "item_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the reasoning item."
+          },
+          "output_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the item in the turn output."
+          },
+          "summary_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the summary content part."
+          },
+          "delta": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The summary text that was appended."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "item_id",
+          "output_index",
+          "summary_index",
+          "delta"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when text is appended to a reasoning summary."
+      },
+      "SessionEventAgentSessionTurnReasoningSummaryTextDone": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.reasoning_summary_text.done"
+            ],
+            "default": "agent.session.turn.reasoning_summary_text.done",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.reasoning_summary_text.done`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "item_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the reasoning item."
+          },
+          "output_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the item in the turn output."
+          },
+          "summary_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the summary content part."
+          },
+          "text": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The complete reasoning summary text."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "item_id",
+          "output_index",
+          "summary_index",
+          "text"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a reasoning summary content part is complete."
+      },
+      "SessionEvent": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/SessionEventError"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionEnvironmentReady"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentOutputCommandExecutionOutputDelta"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionCreated"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnCreated"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnInProgress"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnCompleted"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnFailed"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnCancelled"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnItemAdded"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionIdle"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionInProgress"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionRequiresAction"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionFailed"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionEnvironmentPending"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionEnvironmentConnected"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionEnvironmentDisconnected"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionEnvironmentFailed"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionSubagentCreated"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionSubagentActive"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionSubagentClosed"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnItemDone"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnContentPartAdded"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnContentPartDone"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnOutputTextDelta"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnOutputTextDone"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnReasoningSummaryPartAdded"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnReasoningSummaryPartDone"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnReasoningSummaryTextDelta"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnReasoningSummaryTextDone"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "error": "#/components/schemas/SessionEventError",
+            "agent.session.environment.ready": "#/components/schemas/SessionEventAgentSessionEnvironmentReady",
+            "agent.output.command_execution_output.delta": "#/components/schemas/SessionEventAgentOutputCommandExecutionOutputDelta",
+            "agent.session.created": "#/components/schemas/SessionEventAgentSessionCreated",
+            "agent.session.turn.created": "#/components/schemas/SessionEventAgentSessionTurnCreated",
+            "agent.session.turn.in_progress": "#/components/schemas/SessionEventAgentSessionTurnInProgress",
+            "agent.session.turn.completed": "#/components/schemas/SessionEventAgentSessionTurnCompleted",
+            "agent.session.turn.failed": "#/components/schemas/SessionEventAgentSessionTurnFailed",
+            "agent.session.turn.cancelled": "#/components/schemas/SessionEventAgentSessionTurnCancelled",
+            "agent.session.turn.item.added": "#/components/schemas/SessionEventAgentSessionTurnItemAdded",
+            "agent.session.idle": "#/components/schemas/SessionEventAgentSessionIdle",
+            "agent.session.in_progress": "#/components/schemas/SessionEventAgentSessionInProgress",
+            "agent.session.requires_action": "#/components/schemas/SessionEventAgentSessionRequiresAction",
+            "agent.session.failed": "#/components/schemas/SessionEventAgentSessionFailed",
+            "agent.session.environment.pending": "#/components/schemas/SessionEventAgentSessionEnvironmentPending",
+            "agent.session.environment.connected": "#/components/schemas/SessionEventAgentSessionEnvironmentConnected",
+            "agent.session.environment.disconnected": "#/components/schemas/SessionEventAgentSessionEnvironmentDisconnected",
+            "agent.session.environment.failed": "#/components/schemas/SessionEventAgentSessionEnvironmentFailed",
+            "agent.session.subagent.created": "#/components/schemas/SessionEventAgentSessionSubagentCreated",
+            "agent.session.subagent.active": "#/components/schemas/SessionEventAgentSessionSubagentActive",
+            "agent.session.subagent.closed": "#/components/schemas/SessionEventAgentSessionSubagentClosed",
+            "agent.session.turn.item.done": "#/components/schemas/SessionEventAgentSessionTurnItemDone",
+            "agent.session.turn.content_part.added": "#/components/schemas/SessionEventAgentSessionTurnContentPartAdded",
+            "agent.session.turn.content_part.done": "#/components/schemas/SessionEventAgentSessionTurnContentPartDone",
+            "agent.session.turn.output_text.delta": "#/components/schemas/SessionEventAgentSessionTurnOutputTextDelta",
+            "agent.session.turn.output_text.done": "#/components/schemas/SessionEventAgentSessionTurnOutputTextDone",
+            "agent.session.turn.reasoning_summary_part.added": "#/components/schemas/SessionEventAgentSessionTurnReasoningSummaryPartAdded",
+            "agent.session.turn.reasoning_summary_part.done": "#/components/schemas/SessionEventAgentSessionTurnReasoningSummaryPartDone",
+            "agent.session.turn.reasoning_summary_text.delta": "#/components/schemas/SessionEventAgentSessionTurnReasoningSummaryTextDelta",
+            "agent.session.turn.reasoning_summary_text.done": "#/components/schemas/SessionEventAgentSessionTurnReasoningSummaryTextDone"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "error",
+          "agent.session.environment.ready",
+          "agent.output.command_execution_output.delta",
+          "agent.session.created",
+          "agent.session.turn.created",
+          "agent.session.turn.in_progress",
+          "agent.session.turn.completed",
+          "agent.session.turn.failed",
+          "agent.session.turn.cancelled",
+          "agent.session.turn.item.added",
+          "agent.session.idle",
+          "agent.session.in_progress",
+          "agent.session.requires_action",
+          "agent.session.failed",
+          "agent.session.environment.pending",
+          "agent.session.environment.connected",
+          "agent.session.environment.disconnected",
+          "agent.session.environment.failed",
+          "agent.session.subagent.created",
+          "agent.session.subagent.active",
+          "agent.session.subagent.closed",
+          "agent.session.turn.item.done",
+          "agent.session.turn.content_part.added",
+          "agent.session.turn.content_part.done",
+          "agent.session.turn.output_text.delta",
+          "agent.session.turn.output_text.done",
+          "agent.session.turn.reasoning_summary_part.added",
+          "agent.session.turn.reasoning_summary_part.done",
+          "agent.session.turn.reasoning_summary_text.delta",
+          "agent.session.turn.reasoning_summary_text.done"
+        ],
+        "description": "An event emitted by a Managed Agents session."
+      },
+      "UpdateAgentSessionParams": {
+        "type": "object",
+        "properties": {
+          "metadata": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 512
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 64
+            },
+            "minProperties": 0,
+            "maxProperties": 16,
+            "description": "Replaces all metadata. Omit to leave unchanged, or pass null or {} to clear it. Up to 16 string key-value pairs, with keys up to 64 and values up to 512 characters."
+          }
+        },
+        "additionalProperties": false,
+        "description": "Fields to update on an existing session."
+      },
+      "DeletedSessionResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the deleted session."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "agent.session.deleted"
+            ],
+            "default": "agent.session.deleted",
+            "x-stainless-const": true,
+            "description": "The object type. Always `agent.session.deleted`."
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the session has been removed from the public API. Always `true`. Physical cleanup may still be in progress."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ],
+        "additionalProperties": false,
+        "description": "A Managed Agents session removed from the public API. Physical cleanup may continue asynchronously."
+      },
+      "SessionArtifactResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The immutable artifact ID."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "agent.session.artifact"
+            ],
+            "default": "agent.session.artifact",
+            "x-stainless-const": true,
+            "description": "The object type. Always `agent.session.artifact`."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session that owns the artifact."
+          },
+          "environment_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the environment that produced the artifact."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the completed turn that published the artifact."
+          },
+          "path": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The original absolute file path in the execution environment."
+          },
+          "size_bytes": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "description": "The immutable artifact size in bytes."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the artifact was published."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "session_id",
+          "environment_id",
+          "turn_id",
+          "path",
+          "size_bytes",
+          "created_at"
+        ],
+        "additionalProperties": false,
+        "description": "An immutable file published by a completed hosted session turn."
+      },
+      "SessionArtifactListResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "x-stainless-const": true,
+            "description": "The object type, which is always `list`."
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/SessionArtifactResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The resources returned in this page, in the requested sort order."
+          },
+          "first_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the first resource in `data`, or `null` if the page is empty."
+          },
+          "last_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the last resource in `data`, or `null` if the page is empty. Pass this as `after` with the same order and filters."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more resources to retrieve after this page."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "additionalProperties": false,
+        "description": "A page of Agents API resources, with IDs for retrieving additional pages."
+      },
+      "DeletedSessionArtifactResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the deleted session artifact."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "agent.session.artifact.deleted"
+            ],
+            "default": "agent.session.artifact.deleted",
+            "x-stainless-const": true,
+            "description": "The object type. Always `agent.session.artifact.deleted`."
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the session artifact was deleted. Always `true`."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ],
+        "additionalProperties": false,
+        "description": "Confirmation that an immutable session artifact was deleted."
+      },
+      "SessionInputParamAgentSessionInputMessage": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.input.message"
+            ],
+            "default": "agent.session.input.message",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.input.message`."
+          },
+          "input": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/InputMessageParam"
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "The user messages to add to the session."
+          }
+        },
+        "required": [
+          "type",
+          "input"
+        ],
+        "additionalProperties": false,
+        "description": "Adds one or more user messages and starts a turn."
+      },
+      "SessionInputParamAgentSessionInputCancel": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.input.cancel"
+            ],
+            "default": "agent.session.input.cancel",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.input.cancel`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Cancels the session's active turn."
+      },
+      "FunctionCallOutputParam": {
+        "oneOf": [
+          {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576
+          },
+          {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/InputContentParam"
+            },
+            "minItems": 0,
+            "maxItems": 16384
+          }
+        ],
+        "description": "A function result represented as text or supported model-input content."
+      },
+      "SessionInputParamAgentSessionInputToolResult": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.input.tool_result"
+            ],
+            "default": "agent.session.input.tool_result",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.input.tool_result`."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The ID of the turn that requested the function call."
+          },
+          "call_id": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The ID of the function call."
+          },
+          "success": {
+            "type": "boolean",
+            "description": "Whether the function call succeeded."
+          },
+          "output": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/FunctionCallOutputParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The function result when the call succeeded."
+          },
+          "error": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The error message when the call failed."
+          }
+        },
+        "required": [
+          "type",
+          "turn_id",
+          "call_id",
+          "success"
+        ],
+        "additionalProperties": false,
+        "description": "Submits the result of a function call."
+      },
+      "SessionInputParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/SessionInputParamAgentSessionInputMessage"
+          },
+          {
+            "$ref": "#/components/schemas/SessionInputParamAgentSessionInputCancel"
+          },
+          {
+            "$ref": "#/components/schemas/SessionInputParamAgentSessionInputToolResult"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "agent.session.input.message": "#/components/schemas/SessionInputParamAgentSessionInputMessage",
+            "agent.session.input.cancel": "#/components/schemas/SessionInputParamAgentSessionInputCancel",
+            "agent.session.input.tool_result": "#/components/schemas/SessionInputParamAgentSessionInputToolResult"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "agent.session.input.message",
+          "agent.session.input.cancel",
+          "agent.session.input.tool_result"
+        ],
+        "description": "Input submitted to an existing session."
+      },
+      "CreateSessionEventsParams": {
+        "type": "object",
+        "properties": {
+          "events": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/SessionInputParam"
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "The input events to submit to the session."
+          }
+        },
+        "required": [
+          "events"
+        ],
+        "additionalProperties": false,
+        "description": "Input events submitted to an existing session."
+      },
+      "VaultStatusParam": {
+        "type": "string",
+        "enum": [
+          "active",
+          "archived"
+        ],
+        "description": "Whether a vault or credential is active or archived."
+      },
+      "VaultStatusFilterParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/VaultStatusParam"
+          },
+          {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/VaultStatusParam"
+            },
+            "minItems": 0,
+            "maxItems": 16384
+          }
+        ],
+        "description": "One or more lifecycle statuses to include when listing vaults or credentials."
+      },
+      "VaultResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the vault."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "vault"
+            ],
+            "default": "vault",
+            "x-stainless-const": true,
+            "description": "The object type. Always `vault`."
+          },
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The human-readable name of the vault, if set."
+          },
+          "metadata": {
+            "type": "object",
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minProperties": 0,
+            "description": "Key-value pairs associated with the vault, such as an application or team identifier."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the vault was created."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "name",
+          "metadata",
+          "created_at"
+        ],
+        "additionalProperties": false,
+        "description": "A collection of credentials that agent tools can use to authenticate to MCP servers."
+      },
+      "VaultListResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "x-stainless-const": true,
+            "description": "The object type, which is always `list`."
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/VaultResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The resources returned in this page, in the requested sort order."
+          },
+          "first_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the first resource in `data`, or `null` if the page is empty."
+          },
+          "last_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the last resource in `data`, or `null` if the page is empty. Pass this as `after` with the same order and filters."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more resources to retrieve after this page."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "additionalProperties": false,
+        "description": "A page of Agents API resources, with IDs for retrieving additional pages."
+      },
+      "CreateVaultParams": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 1048576,
+            "description": "The name is trimmed before storage. It must contain 1 to 256 UTF-8 bytes after trimming."
+          },
+          "metadata": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "Key-value pairs to associate with the vault, such as an application or team identifier."
+          }
+        },
+        "additionalProperties": false,
+        "description": "Parameters for creating a vault to store credentials used by agent tools."
+      },
+      "DeletedVaultResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the deleted vault."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "vault.deleted"
+            ],
+            "default": "vault.deleted",
+            "x-stainless-const": true,
+            "description": "The object type. Always `vault.deleted`."
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the resource was deleted. Always `true`."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ],
+        "additionalProperties": false,
+        "description": "Confirmation that a vault was deleted."
+      },
+      "McpOauthTokenEndpointAuthResourceNone": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "none"
+            ],
+            "default": "none",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `none`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Sends the client ID without a client secret."
+      },
+      "McpOauthTokenEndpointAuthResourceClientSecretBasic": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "client_secret_basic"
+            ],
+            "default": "client_secret_basic",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `client_secret_basic`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Sends the client ID and secret using HTTP Basic authentication."
+      },
+      "McpOauthTokenEndpointAuthResourceClientSecretPost": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "client_secret_post"
+            ],
+            "default": "client_secret_post",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `client_secret_post`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Sends the client ID and secret in the token request body."
+      },
+      "McpOauthTokenEndpointAuthResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/McpOauthTokenEndpointAuthResourceNone"
+          },
+          {
+            "$ref": "#/components/schemas/McpOauthTokenEndpointAuthResourceClientSecretBasic"
+          },
+          {
+            "$ref": "#/components/schemas/McpOauthTokenEndpointAuthResourceClientSecretPost"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "none": "#/components/schemas/McpOauthTokenEndpointAuthResourceNone",
+            "client_secret_basic": "#/components/schemas/McpOauthTokenEndpointAuthResourceClientSecretBasic",
+            "client_secret_post": "#/components/schemas/McpOauthTokenEndpointAuthResourceClientSecretPost"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "none",
+          "client_secret_basic",
+          "client_secret_post"
+        ],
+        "description": "The client authentication method used for OAuth token refresh."
+      },
+      "McpOauthRefreshResource": {
+        "type": "object",
+        "properties": {
+          "token_endpoint": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The HTTPS OAuth token endpoint used for refresh."
+          },
+          "client_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The OAuth client ID used when requesting a new access token."
+          },
+          "resource": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The resource URI sent to the OAuth token endpoint during refresh, if configured."
+          },
+          "scope": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "Space-separated OAuth scopes requested during refresh, if configured."
+          },
+          "token_endpoint_auth": {
+            "$ref": "#/components/schemas/McpOauthTokenEndpointAuthResource",
+            "description": "How the OAuth client authenticates to the token endpoint, excluding its client secret."
+          }
+        },
+        "required": [
+          "token_endpoint",
+          "client_id",
+          "resource",
+          "scope",
+          "token_endpoint_auth"
+        ],
+        "additionalProperties": false,
+        "description": "Configuration used to refresh an MCP OAuth access token, excluding secret values."
+      },
+      "VaultCredentialAuthResourceMcpOauth": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_oauth"
+            ],
+            "default": "mcp_oauth",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `mcp_oauth`."
+          },
+          "mcp_server_url": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The HTTPS MCP server URL authorized by this credential."
+          },
+          "expires_at": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "When the OAuth access token expires, as an RFC 3339 timestamp, if known."
+          },
+          "refresh": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/McpOauthRefreshResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Public refresh metadata without refresh tokens or OAuth client secrets."
+          }
+        },
+        "required": [
+          "type",
+          "mcp_server_url",
+          "expires_at",
+          "refresh"
+        ],
+        "additionalProperties": false,
+        "description": "Public metadata for an OAuth credential; tokens and client secrets are never returned."
+      },
+      "VaultCredentialAuthResourceStaticBearer": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "static_bearer"
+            ],
+            "default": "static_bearer",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `static_bearer`."
+          },
+          "mcp_server_url": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The HTTPS MCP server URL authorized by this credential."
+          }
+        },
+        "required": [
+          "type",
+          "mcp_server_url"
+        ],
+        "additionalProperties": false,
+        "description": "Metadata for a bearer-token credential, without automatic OAuth refresh."
+      },
+      "VaultCredentialAuthResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/VaultCredentialAuthResourceMcpOauth"
+          },
+          {
+            "$ref": "#/components/schemas/VaultCredentialAuthResourceStaticBearer"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "mcp_oauth": "#/components/schemas/VaultCredentialAuthResourceMcpOauth",
+            "static_bearer": "#/components/schemas/VaultCredentialAuthResourceStaticBearer"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "mcp_oauth",
+          "static_bearer"
+        ],
+        "description": "The MCP server and authentication configuration of a vault credential, excluding secrets."
+      },
+      "VaultCredentialResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the credential."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "vault.credential"
+            ],
+            "default": "vault.credential",
+            "x-stainless-const": true,
+            "description": "The object type. Always `vault.credential`."
+          },
+          "vault_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the vault containing this credential."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The human-readable name of the credential."
+          },
+          "auth": {
+            "$ref": "#/components/schemas/VaultCredentialAuthResource",
+            "description": "The authentication method and non-secret configuration for the MCP server."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the credential was created."
+          },
+          "updated_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the credential was last updated."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "vault_id",
+          "name",
+          "auth",
+          "created_at",
+          "updated_at"
+        ],
+        "additionalProperties": false,
+        "description": "Metadata for a stored MCP server credential. Secret values are never returned."
+      },
+      "VaultCredentialListResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "x-stainless-const": true,
+            "description": "The object type, which is always `list`."
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/VaultCredentialResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The resources returned in this page, in the requested sort order."
+          },
+          "first_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the first resource in `data`, or `null` if the page is empty."
+          },
+          "last_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the last resource in `data`, or `null` if the page is empty. Pass this as `after` with the same order and filters."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more resources to retrieve after this page."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "additionalProperties": false,
+        "description": "A page of Agents API resources, with IDs for retrieving additional pages."
+      },
+      "CreateMcpOauthTokenEndpointAuthParamNone": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "none"
+            ],
+            "default": "none",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `none`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Sends the client ID without a client secret."
+      },
+      "CreateMcpOauthTokenEndpointAuthParamClientSecretBasic": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "client_secret_basic"
+            ],
+            "default": "client_secret_basic",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `client_secret_basic`."
+          },
+          "client_secret": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The OAuth client secret to store. Never returned in credential resources."
+          }
+        },
+        "required": [
+          "type",
+          "client_secret"
+        ],
+        "additionalProperties": false,
+        "description": "Sends the client ID and secret using HTTP Basic authentication."
+      },
+      "CreateMcpOauthTokenEndpointAuthParamClientSecretPost": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "client_secret_post"
+            ],
+            "default": "client_secret_post",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `client_secret_post`."
+          },
+          "client_secret": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The OAuth client secret to store. Never returned in credential resources."
+          }
+        },
+        "required": [
+          "type",
+          "client_secret"
+        ],
+        "additionalProperties": false,
+        "description": "Sends the client ID and secret in the token request body."
+      },
+      "CreateMcpOauthTokenEndpointAuthParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/CreateMcpOauthTokenEndpointAuthParamNone"
+          },
+          {
+            "$ref": "#/components/schemas/CreateMcpOauthTokenEndpointAuthParamClientSecretBasic"
+          },
+          {
+            "$ref": "#/components/schemas/CreateMcpOauthTokenEndpointAuthParamClientSecretPost"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "none": "#/components/schemas/CreateMcpOauthTokenEndpointAuthParamNone",
+            "client_secret_basic": "#/components/schemas/CreateMcpOauthTokenEndpointAuthParamClientSecretBasic",
+            "client_secret_post": "#/components/schemas/CreateMcpOauthTokenEndpointAuthParamClientSecretPost"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "none",
+          "client_secret_basic",
+          "client_secret_post"
+        ],
+        "description": "Client authentication credentials for OAuth token refresh."
+      },
+      "CreateMcpOauthRefreshParam": {
+        "type": "object",
+        "properties": {
+          "token_endpoint": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The HTTPS OAuth token endpoint used to exchange the refresh token for a new access token."
+          },
+          "client_id": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The OAuth client ID used when requesting a new access token."
+          },
+          "resource": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The resource URI to send to the OAuth token endpoint during refresh, if required."
+          },
+          "scope": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "Space-separated OAuth scopes to request during refresh, if required."
+          },
+          "refresh_token": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The refresh token to store. This secret is never returned in credential resources."
+          },
+          "token_endpoint_auth": {
+            "$ref": "#/components/schemas/CreateMcpOauthTokenEndpointAuthParam",
+            "description": "How the OAuth client authenticates to the token endpoint."
+          }
+        },
+        "required": [
+          "token_endpoint",
+          "client_id",
+          "refresh_token",
+          "token_endpoint_auth"
+        ],
+        "additionalProperties": false,
+        "description": "Configuration for refreshing the access token of an MCP OAuth credential."
+      },
+      "CreateVaultCredentialAuthParamMcpOauth": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_oauth"
+            ],
+            "default": "mcp_oauth",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `mcp_oauth`."
+          },
+          "mcp_server_url": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The HTTPS MCP server URL authorized by this credential."
+          },
+          "access_token": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "A write-only OAuth access token; never returned by credential resources."
+          },
+          "expires_at": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "When the OAuth access token expires, as an RFC 3339 timestamp, if known."
+          },
+          "refresh": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/CreateMcpOauthRefreshParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Optional refresh configuration for an HTTPS OAuth token endpoint."
+          }
+        },
+        "required": [
+          "type",
+          "mcp_server_url",
+          "access_token"
+        ],
+        "additionalProperties": false,
+        "description": "An OAuth credential for an HTTPS MCP destination."
+      },
+      "CreateVaultCredentialAuthParamStaticBearer": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "static_bearer"
+            ],
+            "default": "static_bearer",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `static_bearer`."
+          },
+          "mcp_server_url": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The HTTPS MCP server URL authorized by this credential."
+          },
+          "token": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The bearer token to store. This secret is never returned in credential resources."
+          }
+        },
+        "required": [
+          "type",
+          "mcp_server_url",
+          "token"
+        ],
+        "additionalProperties": false,
+        "description": "A bearer token for an MCP server, without automatic OAuth refresh."
+      },
+      "CreateVaultCredentialAuthParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/CreateVaultCredentialAuthParamMcpOauth"
+          },
+          {
+            "$ref": "#/components/schemas/CreateVaultCredentialAuthParamStaticBearer"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "mcp_oauth": "#/components/schemas/CreateVaultCredentialAuthParamMcpOauth",
+            "static_bearer": "#/components/schemas/CreateVaultCredentialAuthParamStaticBearer"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "mcp_oauth",
+          "static_bearer"
+        ],
+        "description": "Authentication credentials for an MCP server used by agent tools."
+      },
+      "CreateVaultCredentialParams": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 1048576,
+            "description": "The name is trimmed before storage. It must contain 1 to 256 UTF-8 bytes after trimming."
+          },
+          "auth": {
+            "$ref": "#/components/schemas/CreateVaultCredentialAuthParam",
+            "description": "The authentication method and secret values to store for the MCP server."
+          }
+        },
+        "required": [
+          "auth",
+          "name"
+        ],
+        "additionalProperties": false,
+        "description": "Parameters for storing a credential that authorizes access to an MCP server."
+      },
+      "RotateMcpOauthTokenEndpointAuthParamClientSecretBasic": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "client_secret_basic"
+            ],
+            "default": "client_secret_basic",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `client_secret_basic`."
+          },
+          "client_secret": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The replacement OAuth client secret. Omit or pass `null` to keep the stored secret. This secret is never returned in resources."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Updates credentials sent using HTTP Basic authentication."
+      },
+      "RotateMcpOauthTokenEndpointAuthParamClientSecretPost": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "client_secret_post"
+            ],
+            "default": "client_secret_post",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `client_secret_post`."
+          },
+          "client_secret": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The replacement OAuth client secret. Omit or pass `null` to keep the stored secret. This secret is never returned in resources."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Updates credentials sent in the token request body."
+      },
+      "RotateMcpOauthTokenEndpointAuthParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/RotateMcpOauthTokenEndpointAuthParamClientSecretBasic"
+          },
+          {
+            "$ref": "#/components/schemas/RotateMcpOauthTokenEndpointAuthParamClientSecretPost"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "client_secret_basic": "#/components/schemas/RotateMcpOauthTokenEndpointAuthParamClientSecretBasic",
+            "client_secret_post": "#/components/schemas/RotateMcpOauthTokenEndpointAuthParamClientSecretPost"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "client_secret_basic",
+          "client_secret_post"
+        ],
+        "description": "Client-secret updates that preserve the credential's OAuth authentication method."
+      },
+      "RotateMcpOauthRefreshParam": {
+        "type": "object",
+        "properties": {
+          "refresh_token": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The replacement refresh token. Omit or pass `null` to keep the stored token. This secret is never returned in resources."
+          },
+          "scope": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "Replacement space-separated OAuth scopes for refresh requests. Omit to keep the scopes, or pass `null` to stop sending a scope parameter."
+          },
+          "token_endpoint_auth": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/RotateMcpOauthTokenEndpointAuthParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Client-secret updates for the existing token endpoint authentication method."
+          }
+        },
+        "additionalProperties": false,
+        "description": "Updates to an MCP credential's existing OAuth refresh configuration."
+      },
+      "RotateVaultCredentialAuthParamMcpOauth": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_oauth"
+            ],
+            "default": "mcp_oauth",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `mcp_oauth`."
+          },
+          "access_token": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "A write-only replacement OAuth access token."
+          },
+          "expires_at": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The replacement expiry as an RFC 3339 timestamp, or `null` to clear it. Omitting this field preserves the expiry unless a new access token is supplied, in which case the expiry is cleared."
+          },
+          "refresh": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/RotateMcpOauthRefreshParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Optional write-only refresh-token and client-secret updates."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Rotate an OAuth credential for an HTTPS MCP destination."
+      },
+      "RotateVaultCredentialAuthParamStaticBearer": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "static_bearer"
+            ],
+            "default": "static_bearer",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `static_bearer`."
+          },
+          "token": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The replacement bearer token. This secret is never returned in credential resources."
+          }
+        },
+        "required": [
+          "type",
+          "token"
+        ],
+        "additionalProperties": false,
+        "description": "Replace the bearer token for the credential's MCP server."
+      },
+      "RotateVaultCredentialAuthParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/RotateVaultCredentialAuthParamMcpOauth"
+          },
+          {
+            "$ref": "#/components/schemas/RotateVaultCredentialAuthParamStaticBearer"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "mcp_oauth": "#/components/schemas/RotateVaultCredentialAuthParamMcpOauth",
+            "static_bearer": "#/components/schemas/RotateVaultCredentialAuthParamStaticBearer"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "mcp_oauth",
+          "static_bearer"
+        ],
+        "description": "Updates to a vault credential without changing its authentication method or MCP server."
+      },
+      "RotateVaultCredentialParams": {
+        "type": "object",
+        "properties": {
+          "auth": {
+            "$ref": "#/components/schemas/RotateVaultCredentialAuthParam",
+            "description": "Replacement values for the credential's existing authentication method."
+          }
+        },
+        "required": [
+          "auth"
+        ],
+        "additionalProperties": false,
+        "description": "Secret, expiry, and OAuth refresh scope updates for an existing vault credential."
+      },
+      "DeletedVaultCredentialResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the deleted credential."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "vault.credential.deleted"
+            ],
+            "default": "vault.credential.deleted",
+            "x-stainless-const": true,
+            "description": "The object type. Always `vault.credential.deleted`."
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the resource was deleted. Always `true`."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ],
+        "additionalProperties": false,
+        "description": "Confirmation that a vault credential was deleted."
+      },
+      "v1.AgentsCore": {
+        "properties": {
+          "harness": {
+            "enum": [
+              "claude_sdk",
+              "codex",
+              "mcode"
+            ],
+            "type": "string"
+          },
+          "harness_config": {
+            "type": "object"
+          }
+        },
+        "type": "object"
+      },
+      "v1.EnvironmentInstallation": {
+        "properties": {
+          "commands": {
+            "additionalProperties": {
+              "type": "string"
+            },
+            "type": "object"
+          },
+          "expires_at": {
+            "type": "integer"
+          },
+          "message": {
+            "type": "string"
+          },
+          "status": {
+            "enum": [
+              "available",
+              "unavailable"
+            ],
+            "type": "string"
+          },
+          "version": {
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "v1.ModelProviderInput": {
+        "properties": {
+          "api_key": {
+            "type": "string"
+          },
+          "base_url": {
+            "type": "string"
+          },
+          "context_window": {
+            "type": "integer"
+          },
+          "max_output_tokens": {
+            "type": "integer"
+          },
+          "protocol": {
+            "enum": [
+              "anthropic",
+              "responses",
+              "chat_completions"
+            ],
+            "type": "string"
+          }
+        },
+        "required": [
+          "api_key",
+          "base_url",
+          "protocol"
+        ],
+        "type": "object"
+      },
+      "v1.ModelProviderView": {
+        "properties": {
+          "api_key_configured": {
+            "type": "boolean"
+          },
+          "base_url": {
+            "type": "string"
+          },
+          "context_window": {
+            "type": "integer"
+          },
+          "max_output_tokens": {
+            "type": "integer"
+          },
+          "protocol": {
+            "enum": [
+              "anthropic",
+              "responses",
+              "chat_completions"
+            ],
+            "type": "string"
+          }
+        },
+        "required": [
+          "api_key_configured",
+          "base_url",
+          "protocol"
+        ],
+        "type": "object"
+      },
+      "v1.SavedAgentCore": {
+        "properties": {
+          "harness": {
+            "enum": [
+              "claude_sdk",
+              "codex",
+              "mcode"
+            ],
+            "type": "string"
+          },
+          "harness_config": {
+            "type": "object"
+          },
+          "model_provider": {
+            "$ref": "#/components/schemas/v1.ModelProviderView"
+          }
+        },
+        "type": "object"
+      },
+      "v1.SavedAgentCoreInput": {
+        "properties": {
+          "harness": {
+            "enum": [
+              "claude_sdk",
+              "codex",
+              "mcode"
+            ],
+            "type": "string"
+          },
+          "harness_config": {
+            "type": "object"
+          },
+          "model_provider": {
+            "anyOf": [
+              {
+                "allOf": [
+                  {
+                    "$ref": "#/components/schemas/v1.ModelProviderInput"
+                  }
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object"
+      },
+      "v1.SessionCore": {
+        "properties": {
+          "installation": {
+            "$ref": "#/components/schemas/v1.EnvironmentInstallation"
+          }
+        },
+        "type": "object"
+      },
+      "v1.SessionExecutionInput": {
+        "properties": {
+          "environment": {
+            "description": "Environment supplies placement-independent preparation through the Core extension.",
+            "type": "object"
+          },
+          "harness_config": {
+            "type": "object"
+          },
+          "model_provider": {
+            "$ref": "#/components/schemas/v1.ModelProviderInput"
+          }
+        },
+        "type": "object"
+      }
+    },
+    "responses": {
+      "TooManyRequests": {
+        "description": "The request was rejected because a rate limit was exceeded.",
+        "headers": {
+          "Retry-After": {
+            "description": "The minimum number of seconds to wait before retrying. This header is returned when the server has computed a retry delay and may be omitted for 429 responses that require user action.",
+            "schema": {
+              "type": "integer",
+              "minimum": 1
+            }
+          }
+        },
+        "content": {
+          "application/json": {
+            "schema": {
+              "$ref": "#/components/schemas/ErrorResponse"
+            }
+          }
+        }
+      }
+    },
+    "securitySchemes": {
+      "ProjectKey": {
+        "type": "http",
+        "scheme": "bearer",
+        "description": "OpenAgentCore Project API key."
+      }
+    }
+  },
+  "x-oaiMeta": {
+    "navigationGroups": [
+      {
+        "id": "responses",
+        "title": "Responses API"
+      },
+      {
+        "id": "webhooks",
+        "title": "Webhooks"
+      },
+      {
+        "id": "endpoints",
+        "title": "Platform APIs"
+      },
+      {
+        "id": "vector_stores",
+        "title": "Vector stores"
+      },
+      {
+        "id": "chatkit",
+        "title": "ChatKit",
+        "beta": true
+      },
+      {
+        "id": "containers",
+        "title": "Containers"
+      },
+      {
+        "id": "live",
+        "title": "Live (alpha)"
+      },
+      {
+        "id": "realtime",
+        "title": "Realtime"
+      },
+      {
+        "id": "chat",
+        "title": "Chat Completions"
+      },
+      {
+        "id": "assistants",
+        "title": "Assistants",
+        "deprecated": true
+      },
+      {
+        "id": "administration",
+        "title": "Administration"
+      },
+      {
+        "id": "legacy",
+        "title": "Legacy"
+      }
+    ],
+    "groups": [
+      {
+        "id": "responses-streaming",
+        "title": "Streaming events",
+        "description": "When you [create a Response](https://developers.openai.com/api/reference/resources/responses/methods/create) with\n`stream` set to `true`, the server will emit server-sent events to the\nclient as the Response is generated. This section contains the events that\nare emitted by the server.\n\n[Learn more about streaming responses](https://developers.openai.com/api/docs/guides/streaming-responses).\n",
+        "navigationGroup": "responses",
+        "sections": [
+          {
+            "type": "object",
+            "key": "ResponseCreatedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFailedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseIncompleteEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseOutputItemAddedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseOutputItemDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseContentPartAddedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseContentPartDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseTextDeltaEvent",
+            "path": "response/output_text/delta"
+          },
+          {
+            "type": "object",
+            "key": "ResponseTextDoneEvent",
+            "path": "response/output_text/done"
+          },
+          {
+            "type": "object",
+            "key": "ResponseRefusalDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseRefusalDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFunctionCallArgumentsDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFunctionCallArgumentsDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFileSearchCallInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFileSearchCallSearchingEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFileSearchCallCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseWebSearchCallInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseWebSearchCallSearchingEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseWebSearchCallCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningSummaryPartAddedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningSummaryPartDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningSummaryTextDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningSummaryTextDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningTextDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningTextDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseImageGenCallCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseImageGenCallGeneratingEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseImageGenCallInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseImageGenCallPartialImageEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPCallArgumentsDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPCallArgumentsDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPCallCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPCallFailedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPCallInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPListToolsCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPListToolsFailedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPListToolsInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCodeInterpreterCallInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCodeInterpreterCallInterpretingEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCodeInterpreterCallCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCodeInterpreterCallCodeDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCodeInterpreterCallCodeDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseOutputTextAnnotationAddedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseQueuedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCustomToolCallInputDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCustomToolCallInputDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseErrorEvent",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "responses-websocket-client-events",
+        "title": "Client events",
+        "description": "Events sent by the client over a Responses API WebSocket connection.\n",
+        "navigationGroup": "responses",
+        "sections": [
+          {
+            "type": "object",
+            "key": "ResponsesClientEventResponseCreate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseSteerEvent",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "responses-websocket-server-events",
+        "title": "Server events (WebSocket only)",
+        "description": "Events emitted only over a Responses API WebSocket connection.\n",
+        "navigationGroup": "responses",
+        "sections": [
+          {
+            "type": "object",
+            "key": "ResponseSteerAcceptedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseSteerPendingEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseSteerFailedEvent",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "responses-websocket-shared-events",
+        "title": "Server events",
+        "description": "These events use the same payloads over WebSocket and\n[HTTP streaming](https://developers.openai.com/api/reference/resources/responses/streaming-events).\n",
+        "navigationGroup": "responses",
+        "sections": [
+          {
+            "type": "object",
+            "key": "ResponseCreatedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFailedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseIncompleteEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseOutputItemAddedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseOutputItemDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseContentPartAddedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseContentPartDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseTextDeltaEvent",
+            "path": "response/output_text/delta"
+          },
+          {
+            "type": "object",
+            "key": "ResponseTextDoneEvent",
+            "path": "response/output_text/done"
+          },
+          {
+            "type": "object",
+            "key": "ResponseRefusalDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseRefusalDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFunctionCallArgumentsDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFunctionCallArgumentsDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFileSearchCallInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFileSearchCallSearchingEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFileSearchCallCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseWebSearchCallInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseWebSearchCallSearchingEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseWebSearchCallCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningSummaryPartAddedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningSummaryPartDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningSummaryTextDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningSummaryTextDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningTextDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningTextDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseImageGenCallCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseImageGenCallGeneratingEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseImageGenCallInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseImageGenCallPartialImageEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPCallArgumentsDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPCallArgumentsDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPCallCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPCallFailedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPCallInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPListToolsCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPListToolsFailedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPListToolsInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCodeInterpreterCallInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCodeInterpreterCallInterpretingEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCodeInterpreterCallCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCodeInterpreterCallCodeDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCodeInterpreterCallCodeDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseOutputTextAnnotationAddedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseQueuedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCustomToolCallInputDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCustomToolCallInputDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseErrorEvent",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "safety-alerts",
+        "title": "Safety Alerts",
+        "description": "Retrieve approved safety alerts with an API key. Project keys require\n`api.safety.alerts.read` and can read alerts from their project.\n",
+        "navigationGroup": "endpoints",
+        "sections": [
+          {
+            "type": "endpoint",
+            "key": "Getprojectsafetyalert",
+            "path": "retrieve"
+          },
+          {
+            "type": "object",
+            "key": "SafetyAlertResource",
+            "path": "object"
+          }
+        ]
+      },
+      {
+        "id": "webhook-events",
+        "title": "Webhook Events",
+        "description": "Webhooks are HTTP requests sent by OpenAI to a URL you specify when certain\nevents happen during the course of API usage.\n\n[Learn more about webhooks](https://developers.openai.com/api/docs/guides/webhooks).\n",
+        "navigationGroup": "webhooks",
+        "sections": [
+          {
+            "type": "object",
+            "key": "WebhookResponseCompleted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookResponseCancelled",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookResponseFailed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookResponseIncomplete",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookBatchCompleted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookBatchCancelled",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookBatchExpired",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookBatchFailed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookFineTuningJobSucceeded",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookFineTuningJobFailed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookFineTuningJobCancelled",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookEvalRunSucceeded",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookEvalRunFailed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookEvalRunCanceled",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookRealtimeCallIncoming",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookLiveCallIncoming",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookLiveTransportIncoming",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookSafetyAlertCreated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookSafetyOrgAlertCreated",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "images-streaming",
+        "title": "Image Streaming",
+        "description": "Stream image generation and editing in real time with server-sent events.\n[Learn more about image streaming](https://developers.openai.com/api/docs/guides/image-generation).\n",
+        "navigationGroup": "endpoints",
+        "sections": [
+          {
+            "type": "object",
+            "key": "ImageGenPartialImageEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ImageGenCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ImageEditPartialImageEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ImageEditCompletedEvent",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "realtime-client-events",
+        "title": "Client events",
+        "description": "These are events that the OpenAI Realtime WebSocket server will accept from the client.\n",
+        "navigationGroup": "realtime",
+        "sections": [
+          {
+            "type": "object",
+            "key": "RealtimeClientEventSessionUpdate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeClientEventInputAudioBufferAppend",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeClientEventInputAudioBufferCommit",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeClientEventInputAudioBufferClear",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeClientEventConversationItemCreate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeClientEventConversationItemRetrieve",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeClientEventConversationItemTruncate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeClientEventConversationItemDelete",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeClientEventResponseCreate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeClientEventResponseCancel",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeClientEventOutputAudioBufferClear",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "realtime-server-events",
+        "title": "Server events",
+        "description": "These are events emitted from the OpenAI Realtime WebSocket server to the client.\n",
+        "navigationGroup": "realtime",
+        "sections": [
+          {
+            "type": "object",
+            "key": "RealtimeServerEventError",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventSessionCreated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventSessionUpdated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventConversationItemAdded",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventConversationItemDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventConversationItemRetrieved",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventConversationItemInputAudioTranscriptionCompleted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventConversationItemInputAudioTranscriptionDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventConversationItemInputAudioTranscriptionSegment",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventConversationItemInputAudioTranscriptionFailed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventConversationItemTruncated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventConversationItemDeleted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventInputAudioBufferCommitted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventInputAudioBufferDtmfEventReceived",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventInputAudioBufferCleared",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventInputAudioBufferSpeechStarted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventInputAudioBufferSpeechStopped",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventInputAudioBufferTimeoutTriggered",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventOutputAudioBufferStarted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventOutputAudioBufferStopped",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventOutputAudioBufferCleared",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseCreated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseOutputItemAdded",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseOutputItemDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseContentPartAdded",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseContentPartDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseTextDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseTextDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseAudioTranscriptDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseAudioTranscriptDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseAudioDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseAudioDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseFunctionCallArgumentsDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseFunctionCallArgumentsDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseMCPCallArgumentsDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseMCPCallArgumentsDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseMCPCallInProgress",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseMCPCallCompleted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseMCPCallFailed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventMCPListToolsInProgress",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventMCPListToolsCompleted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventMCPListToolsFailed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventRateLimitsUpdated",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "realtime-translation-client-events",
+        "title": "Translation client events",
+        "description": "These are events that the OpenAI Realtime Translation WebSocket server will accept from the client.\n",
+        "navigationGroup": "realtime",
+        "sections": [
+          {
+            "type": "object",
+            "key": "RealtimeTranslationClientEventSessionUpdate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeTranslationClientEventInputAudioBufferAppend",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeTranslationClientEventSessionClose",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "realtime-translation-server-events",
+        "title": "Translation server events",
+        "description": "These are events emitted from the OpenAI Realtime Translation WebSocket server to the client.\n",
+        "navigationGroup": "realtime",
+        "sections": [
+          {
+            "type": "object",
+            "key": "RealtimeServerEventError",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeTranslationServerEventSessionCreated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeTranslationServerEventSessionUpdated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeTranslationServerEventSessionClosed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeTranslationServerEventSessionInputTranscriptDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeTranslationServerEventSessionOutputTranscriptDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeTranslationServerEventSessionOutputAudioDelta",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "chat-streaming",
+        "title": "Streaming",
+        "description": "Stream Chat Completions in real time. Receive chunks of completions\nreturned from the model using server-sent events.\n[Learn more](https://developers.openai.com/api/docs/guides/streaming-responses).\n",
+        "navigationGroup": "chat",
+        "sections": [
+          {
+            "type": "object",
+            "key": "CreateChatCompletionStreamResponse",
+            "path": "streaming"
+          }
+        ]
+      },
+      {
+        "id": "assistants-streaming",
+        "title": "Streaming",
+        "beta": true,
+        "description": "Stream the result of executing a Run or resuming a Run after submitting tool outputs.\nYou can stream events from the [Create Thread and Run](https://developers.openai.com/api/docs/assistants/migration),\n[Create Run](https://developers.openai.com/api/docs/assistants/migration), and [Submit Tool Outputs](https://developers.openai.com/api/docs/assistants/migration)\nendpoints by passing `\"stream\": true`. The response will be a [Server-Sent events](https://html.spec.whatwg.org/multipage/server-sent-events.html#server-sent-events) stream.\nOur Node and Python SDKs provide helpful utilities to make streaming easy. Reference the\n[Assistants API quickstart](https://developers.openai.com/api/docs/assistants/migration) to learn more.\n",
+        "navigationGroup": "assistants",
+        "sections": [
+          {
+            "type": "object",
+            "key": "AssistantStreamEvent",
+            "path": "events"
+          }
+        ]
+      },
+      {
+        "id": "realtime-beta-client-events",
+        "title": "Realtime Beta client events",
+        "description": "These are events that the OpenAI Realtime WebSocket server will accept from the client.\n",
+        "navigationGroup": "legacy",
+        "sections": [
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventSessionUpdate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventInputAudioBufferAppend",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventInputAudioBufferCommit",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventInputAudioBufferClear",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventConversationItemCreate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventConversationItemRetrieve",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventConversationItemTruncate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventConversationItemDelete",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventResponseCreate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventResponseCancel",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventTranscriptionSessionUpdate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventOutputAudioBufferClear",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "realtime-beta-server-events",
+        "title": "Realtime Beta server events",
+        "description": "These are events emitted from the OpenAI Realtime WebSocket server to the client.\n",
+        "navigationGroup": "legacy",
+        "sections": [
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventError",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventSessionCreated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventSessionUpdated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventTranscriptionSessionCreated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventTranscriptionSessionUpdated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventConversationItemCreated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventConversationItemRetrieved",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventConversationItemInputAudioTranscriptionCompleted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventConversationItemInputAudioTranscriptionDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventConversationItemInputAudioTranscriptionSegment",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventConversationItemInputAudioTranscriptionFailed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventConversationItemTruncated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventConversationItemDeleted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventInputAudioBufferCommitted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventInputAudioBufferCleared",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventInputAudioBufferSpeechStarted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventInputAudioBufferSpeechStopped",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventInputAudioBufferTimeoutTriggered",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseCreated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseOutputItemAdded",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseOutputItemDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseContentPartAdded",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseContentPartDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseTextDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseTextDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseAudioTranscriptDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseAudioTranscriptDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseAudioDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseAudioDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseFunctionCallArgumentsDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseFunctionCallArgumentsDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseMCPCallArgumentsDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseMCPCallArgumentsDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseMCPCallInProgress",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseMCPCallCompleted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseMCPCallFailed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventMCPListToolsInProgress",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventMCPListToolsCompleted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventMCPListToolsFailed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventRateLimitsUpdated",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "live-client-events",
+        "title": "Client events",
+        "description": "Initialize a primary WebSocket with session.start and wait for session.started before sending other events. WebRTC creation starts the session for you. Start with the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) to design frontend instructions and delegation policy; see [backend prompting](https://developers.openai.com/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt) for tools and business rules.",
+        "navigationGroup": "live",
+        "sections": [
+          {
+            "type": "object",
+            "key": "LiveSessionStartEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveForkSessionStartEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveSessionUpdateParam",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveInputAudioAppendEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveInputAudioMuteParam",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveInputAudioUnmuteParam",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveInstructionsAppendParam",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveThinkingAppendParam",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveCommentaryAppendParam",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveResponseItemCreateParam",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveResponseCreateParam",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveSessionCloseParam",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "live-server-events",
+        "title": "Server events",
+        "description": "Live server events. Responses delegation lifecycle events arrive inside response.event, not as top-level response events. Start with the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) to design frontend instructions and delegation policy; see [backend prompting](https://developers.openai.com/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt) for tools and business rules.",
+        "navigationGroup": "live",
+        "sections": [
+          {
+            "type": "object",
+            "key": "LiveSessionStarted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveSessionUpdated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveInputAudioMuted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveInputAudioUnmuted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveInstructionsAppended",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveThinkingAppended",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveCommentaryAppended",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveOutputAudioDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveInputTranscriptDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveOutputTranscriptDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveDelegationCreated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveResponseEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveSessionUsageUpdated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveSessionClosed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveErrorEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveInfoEvent",
+            "path": "<auto>"
+          }
+        ]
+      }
+    ]
+  }
+}
diff --git a/contracts/agents-api/runtime.openapi.yaml b/contracts/agents-api/runtime.openapi.yaml
index fc109bc6f..8e1ac37a7 100644
--- a/contracts/agents-api/runtime.openapi.yaml
+++ b/contracts/agents-api/runtime.openapi.yaml
@@ -151,13 +151,17 @@ definitions:
         x-nullable: true
       message:
         type: string
+      misalignment:
+        type: object
       param:
         type: string
         x-nullable: true
       type:
         type: string
     required:
+      - code
       - message
+      - param
       - type
     type: object
   v1.ErrorResponse:
diff --git a/contracts/agents-api/upstream-fields.json b/contracts/agents-api/upstream-fields.json
deleted file mode 100644
index f1668c995..000000000
--- a/contracts/agents-api/upstream-fields.json
+++ /dev/null
@@ -1,2301 +0,0 @@
-{
-  "sdk_version": "3.13.0",
-  "commit": "d7c41efee1b0802b79f3f88a678ef2052b06e9ce",
-  "generator": "scripts/extract-agents-api-upstream.py",
-  "operations": {
-    "DELETE /agents/environments/templates/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "beta.agents.environments.environment_template_deleted.EnvironmentTemplateDeleted"
-      ]
-    },
-    "DELETE /agents/sessions/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "beta.agent_session_deleted.AgentSessionDeleted"
-      ]
-    },
-    "DELETE /agents/sessions/{}/artifacts/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "beta.agents.sessions.session_artifact_deleted.SessionArtifactDeleted"
-      ]
-    },
-    "DELETE /agents/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "beta.agent_deleted.AgentDeleted"
-      ]
-    },
-    "DELETE /files/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "file_deleted.FileDeleted"
-      ]
-    },
-    "DELETE /skills/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "deleted_skill.DeletedSkill"
-      ]
-    },
-    "DELETE /skills/{}/versions/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "skills.deleted_skill_version.DeletedSkillVersion"
-      ]
-    },
-    "DELETE /vaults/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "beta.agents.vault_deleted.VaultDeleted"
-      ]
-    },
-    "DELETE /vaults/{}/credentials/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "beta.agents.vaults.credential_deleted.CredentialDeleted"
-      ]
-    },
-    "GET /agents": {
-      "request": [],
-      "query": [
-        "beta.agent_list_params.AgentListParams"
-      ],
-      "response": [
-        "pagination.SyncCursorPage[beta.agent.Agent]"
-      ]
-    },
-    "GET /agents/environments/templates": {
-      "request": [],
-      "query": [
-        "beta.agents.environments.template_list_params.TemplateListParams"
-      ],
-      "response": [
-        "pagination.SyncCursorPage[beta.agents.environments.environment_template.EnvironmentTemplate]"
-      ]
-    },
-    "GET /agents/environments/templates/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "beta.agents.environments.environment_template.EnvironmentTemplate"
-      ]
-    },
-    "GET /agents/environments/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "beta.agents.environment_info.EnvironmentInfo"
-      ]
-    },
-    "GET /agents/environments/{}/files": {
-      "request": [],
-      "query": [
-        "beta.agents.environments.file_list_params.FileListParams"
-      ],
-      "response": [
-        "pagination.SyncTokenPage[beta.agents.environments.environment_file.EnvironmentFile]"
-      ]
-    },
-    "GET /agents/sessions": {
-      "request": [],
-      "query": [
-        "beta.agents.session_list_params.SessionListParams"
-      ],
-      "response": [
-        "pagination.SyncCursorPage[beta.agent_session.AgentSession]"
-      ]
-    },
-    "GET /agents/sessions/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "beta.agent_session.AgentSession"
-      ]
-    },
-    "GET /agents/sessions/{}/artifacts": {
-      "request": [],
-      "query": [
-        "beta.agents.sessions.artifact_list_params.ArtifactListParams"
-      ],
-      "response": [
-        "pagination.SyncCursorPage[beta.agents.sessions.session_artifact.SessionArtifact]"
-      ]
-    },
-    "GET /agents/sessions/{}/artifacts/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "beta.agents.sessions.session_artifact.SessionArtifact"
-      ]
-    },
-    "GET /agents/sessions/{}/artifacts/{}/content": {
-      "request": [],
-      "query": [],
-      "response": []
-    },
-    "GET /agents/sessions/{}/events": {
-      "request": [],
-      "query": [],
-      "response": [
-        "beta.agent_output_command_execution_output_delta_event.AgentOutputCommandExecutionOutputDeltaEvent",
-        "beta.agent_session_created_event.AgentSessionCreatedEvent",
-        "beta.agent_session_environment_connected_event.AgentSessionEnvironmentConnectedEvent",
-        "beta.agent_session_environment_disconnected_event.AgentSessionEnvironmentDisconnectedEvent",
-        "beta.agent_session_environment_failed_event.AgentSessionEnvironmentFailedEvent",
-        "beta.agent_session_environment_pending_event.AgentSessionEnvironmentPendingEvent",
-        "beta.agent_session_environment_ready_event.AgentSessionEnvironmentReadyEvent",
-        "beta.agent_session_error_event.AgentSessionErrorEvent",
-        "beta.agent_session_failed_event.AgentSessionFailedEvent",
-        "beta.agent_session_idle_event.AgentSessionIdleEvent",
-        "beta.agent_session_in_progress_event.AgentSessionInProgressEvent",
-        "beta.agent_session_requires_action_event.AgentSessionRequiresActionEvent",
-        "beta.agent_session_subagent_active_event.AgentSessionSubagentActiveEvent",
-        "beta.agent_session_subagent_closed_event.AgentSessionSubagentClosedEvent",
-        "beta.agent_session_subagent_created_event.AgentSessionSubagentCreatedEvent",
-        "beta.agent_session_turn_cancelled_event.AgentSessionTurnCancelledEvent",
-        "beta.agent_session_turn_completed_event.AgentSessionTurnCompletedEvent",
-        "beta.agent_session_turn_content_part_added_event.AgentSessionTurnContentPartAddedEvent",
-        "beta.agent_session_turn_content_part_done_event.AgentSessionTurnContentPartDoneEvent",
-        "beta.agent_session_turn_created_event.AgentSessionTurnCreatedEvent",
-        "beta.agent_session_turn_failed_event.AgentSessionTurnFailedEvent",
-        "beta.agent_session_turn_in_progress_event.AgentSessionTurnInProgressEvent",
-        "beta.agent_session_turn_item_added_event.AgentSessionTurnItemAddedEvent",
-        "beta.agent_session_turn_item_done_event.AgentSessionTurnItemDoneEvent",
-        "beta.agent_session_turn_output_text_delta_event.AgentSessionTurnOutputTextDeltaEvent",
-        "beta.agent_session_turn_output_text_done_event.AgentSessionTurnOutputTextDoneEvent",
-        "beta.agent_session_turn_reasoning_summary_part_added_event.AgentSessionTurnReasoningSummaryPartAddedEvent",
-        "beta.agent_session_turn_reasoning_summary_part_done_event.AgentSessionTurnReasoningSummaryPartDoneEvent",
-        "beta.agent_session_turn_reasoning_summary_text_delta_event.AgentSessionTurnReasoningSummaryTextDeltaEvent",
-        "beta.agent_session_turn_reasoning_summary_text_done_event.AgentSessionTurnReasoningSummaryTextDoneEvent"
-      ]
-    },
-    "GET /agents/sessions/{}/items": {
-      "request": [],
-      "query": [
-        "beta.agents.sessions.item_list_params.ItemListParams"
-      ],
-      "response": [
-        "pagination.SyncCursorPage[beta.agent_close_subagent_call_item.AgentCloseSubagentCallItem | beta.agent_command_execution_item.AgentCommandExecutionItem | beta.agent_create_subagent_call_item.AgentCreateSubagentCallItem | beta.agent_function_call_item.AgentFunctionCallItem | beta.agent_interrupt_subagent_call_item.AgentInterruptSubagentCallItem | beta.agent_mcp_call_item.AgentMcpCallItem | beta.agent_reasoning_item.AgentReasoningItem | beta.agent_resume_subagent_call_item.AgentResumeSubagentCallItem | beta.agent_send_subagent_input_call_item.AgentSendSubagentInputCallItem | beta.agent_session_item.AgentMessageItemResource | beta.agent_session_item.FunctionCallOutputItemResource | beta.agent_session_message.AgentSessionMessage | beta.agent_wait_for_subagents_call_item.AgentWaitForSubagentsCallItem | beta.agent_web_search_call_item.AgentWebSearchCallItem]"
-      ]
-    },
-    "GET /agents/sessions/{}/subagents": {
-      "request": [],
-      "query": [
-        "beta.agents.sessions.subagent_list_params.SubagentListParams"
-      ],
-      "response": [
-        "pagination.SyncCursorPage[beta.subagent.Subagent]"
-      ]
-    },
-    "GET /agents/sessions/{}/subagents/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "beta.subagent.Subagent"
-      ]
-    },
-    "GET /agents/sessions/{}/subagents/{}/items": {
-      "request": [],
-      "query": [
-        "beta.agents.sessions.subagents.item_list_params.ItemListParams"
-      ],
-      "response": [
-        "pagination.SyncCursorPage[beta.agent_close_subagent_call_item.AgentCloseSubagentCallItem | beta.agent_command_execution_item.AgentCommandExecutionItem | beta.agent_create_subagent_call_item.AgentCreateSubagentCallItem | beta.agent_function_call_item.AgentFunctionCallItem | beta.agent_interrupt_subagent_call_item.AgentInterruptSubagentCallItem | beta.agent_mcp_call_item.AgentMcpCallItem | beta.agent_reasoning_item.AgentReasoningItem | beta.agent_resume_subagent_call_item.AgentResumeSubagentCallItem | beta.agent_send_subagent_input_call_item.AgentSendSubagentInputCallItem | beta.agent_session_item.AgentMessageItemResource | beta.agent_session_item.FunctionCallOutputItemResource | beta.agent_session_message.AgentSessionMessage | beta.agent_wait_for_subagents_call_item.AgentWaitForSubagentsCallItem | beta.agent_web_search_call_item.AgentWebSearchCallItem]"
-      ]
-    },
-    "GET /agents/sessions/{}/subagents/{}/turns": {
-      "request": [],
-      "query": [
-        "beta.agents.sessions.subagents.turn_list_params.TurnListParams"
-      ],
-      "response": [
-        "pagination.SyncCursorPage[beta.agents.sessions.turn.Turn]"
-      ]
-    },
-    "GET /agents/sessions/{}/subagents/{}/turns/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "beta.agents.sessions.turn.Turn"
-      ]
-    },
-    "GET /agents/sessions/{}/subagents/{}/turns/{}/items": {
-      "request": [],
-      "query": [
-        "beta.agents.sessions.subagents.turns.item_list_params.ItemListParams"
-      ],
-      "response": [
-        "pagination.SyncCursorPage[beta.agent_close_subagent_call_item.AgentCloseSubagentCallItem | beta.agent_command_execution_item.AgentCommandExecutionItem | beta.agent_create_subagent_call_item.AgentCreateSubagentCallItem | beta.agent_function_call_item.AgentFunctionCallItem | beta.agent_interrupt_subagent_call_item.AgentInterruptSubagentCallItem | beta.agent_mcp_call_item.AgentMcpCallItem | beta.agent_reasoning_item.AgentReasoningItem | beta.agent_resume_subagent_call_item.AgentResumeSubagentCallItem | beta.agent_send_subagent_input_call_item.AgentSendSubagentInputCallItem | beta.agent_session_item.AgentMessageItemResource | beta.agent_session_item.FunctionCallOutputItemResource | beta.agent_session_message.AgentSessionMessage | beta.agent_wait_for_subagents_call_item.AgentWaitForSubagentsCallItem | beta.agent_web_search_call_item.AgentWebSearchCallItem]"
-      ]
-    },
-    "GET /agents/sessions/{}/turns": {
-      "request": [],
-      "query": [
-        "beta.agents.sessions.turn_list_params.TurnListParams"
-      ],
-      "response": [
-        "pagination.SyncCursorPage[beta.agents.sessions.turn.Turn]"
-      ]
-    },
-    "GET /agents/sessions/{}/turns/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "beta.agents.sessions.turn.Turn"
-      ]
-    },
-    "GET /agents/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "beta.agent.Agent"
-      ]
-    },
-    "GET /files": {
-      "request": [],
-      "query": [
-        "file_list_params.FileListParams"
-      ],
-      "response": [
-        "pagination.SyncCursorPage[file_object.FileObject]"
-      ]
-    },
-    "GET /files/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "file_object.FileObject"
-      ]
-    },
-    "GET /files/{}/content": {
-      "request": [],
-      "query": [],
-      "response": []
-    },
-    "GET /skills": {
-      "request": [],
-      "query": [
-        "skill_list_params.SkillListParams"
-      ],
-      "response": [
-        "pagination.SyncCursorPage[skill.Skill]"
-      ]
-    },
-    "GET /skills/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "skill.Skill"
-      ]
-    },
-    "GET /skills/{}/content": {
-      "request": [],
-      "query": [],
-      "response": []
-    },
-    "GET /skills/{}/versions": {
-      "request": [],
-      "query": [
-        "skills.version_list_params.VersionListParams"
-      ],
-      "response": [
-        "pagination.SyncCursorPage[skills.skill_version.SkillVersion]"
-      ]
-    },
-    "GET /skills/{}/versions/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "skills.skill_version.SkillVersion"
-      ]
-    },
-    "GET /skills/{}/versions/{}/content": {
-      "request": [],
-      "query": [],
-      "response": []
-    },
-    "GET /vaults": {
-      "request": [],
-      "query": [
-        "beta.agents.vault_list_params.VaultListParams"
-      ],
-      "response": [
-        "pagination.SyncCursorPage[beta.agents.vault.Vault]"
-      ]
-    },
-    "GET /vaults/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "beta.agents.vault.Vault"
-      ]
-    },
-    "GET /vaults/{}/credentials": {
-      "request": [],
-      "query": [
-        "beta.agents.vaults.credential_list_params.CredentialListParams"
-      ],
-      "response": [
-        "pagination.SyncCursorPage[beta.agents.vaults.credential.Credential]"
-      ]
-    },
-    "GET /vaults/{}/credentials/{}": {
-      "request": [],
-      "query": [],
-      "response": [
-        "beta.agents.vaults.credential.Credential"
-      ]
-    },
-    "POST /agents": {
-      "request": [
-        "beta.agent_create_params.AgentCreateParams"
-      ],
-      "query": [],
-      "response": [
-        "beta.agent.Agent"
-      ]
-    },
-    "POST /agents/environments/templates": {
-      "request": [
-        "beta.agents.environments.template_create_params.TemplateCreateParams"
-      ],
-      "query": [],
-      "response": [
-        "beta.agents.environments.environment_template.EnvironmentTemplate"
-      ]
-    },
-    "POST /agents/environments/templates/{}": {
-      "request": [
-        "beta.agents.environments.template_update_params.TemplateUpdateParams"
-      ],
-      "query": [],
-      "response": [
-        "beta.agents.environments.environment_template.EnvironmentTemplate"
-      ]
-    },
-    "POST /agents/environments/{}/files": {
-      "request": [
-        "beta.agents.environments.file_create_params.HostedEnvironmentFileParamFileID",
-        "beta.agents.environments.file_create_params.HostedEnvironmentFileParamInline"
-      ],
-      "query": [],
-      "response": [
-        "beta.agents.environments.environment_file.EnvironmentFile"
-      ]
-    },
-    "POST /agents/sessions": {
-      "request": [
-        "beta.agents.session_create_params.SessionCreateParamsNonStreaming",
-        "beta.agents.session_create_params.SessionCreateParamsStreaming"
-      ],
-      "query": [],
-      "response": [
-        "beta.agent_session.AgentSession"
-      ]
-    },
-    "POST /agents/sessions/{}": {
-      "request": [
-        "beta.agents.session_update_params.SessionUpdateParams"
-      ],
-      "query": [],
-      "response": [
-        "beta.agent_session.AgentSession"
-      ]
-    },
-    "POST /agents/sessions/{}/events": {
-      "request": [
-        "beta.agents.sessions.event_create_params.EventCreateParams"
-      ],
-      "query": [],
-      "response": []
-    },
-    "POST /agents/{}": {
-      "request": [
-        "beta.agent_update_params.AgentUpdateParams"
-      ],
-      "query": [],
-      "response": [
-        "beta.agent.Agent"
-      ]
-    },
-    "POST /files": {
-      "request": [
-        "file_create_params.FileCreateParams"
-      ],
-      "query": [],
-      "response": [
-        "file_object.FileObject"
-      ]
-    },
-    "POST /skills": {
-      "request": [
-        "skill_create_params.SkillCreateParams"
-      ],
-      "query": [],
-      "response": [
-        "skill.Skill"
-      ]
-    },
-    "POST /skills/{}": {
-      "request": [
-        "skill_update_params.SkillUpdateParams"
-      ],
-      "query": [],
-      "response": [
-        "skill.Skill"
-      ]
-    },
-    "POST /skills/{}/versions": {
-      "request": [
-        "skills.version_create_params.VersionCreateParams"
-      ],
-      "query": [],
-      "response": [
-        "skills.skill_version.SkillVersion"
-      ]
-    },
-    "POST /vaults": {
-      "request": [
-        "beta.agents.vault_create_params.VaultCreateParams"
-      ],
-      "query": [],
-      "response": [
-        "beta.agents.vault.Vault"
-      ]
-    },
-    "POST /vaults/{}/credentials": {
-      "request": [
-        "beta.agents.vaults.credential_create_params.CredentialCreateParams"
-      ],
-      "query": [],
-      "response": [
-        "beta.agents.vaults.credential.Credential"
-      ]
-    },
-    "POST /vaults/{}/credentials/{}": {
-      "request": [
-        "beta.agents.vaults.credential_update_params.CredentialUpdateParams"
-      ],
-      "query": [],
-      "response": [
-        "beta.agents.vaults.credential.Credential"
-      ]
-    }
-  },
-  "types": {
-    "beta.agent.Agent": {
-      "created_at": [],
-      "id": [],
-      "instructions": [],
-      "metadata": [],
-      "model": [],
-      "multi_agent": [
-        "beta.multi_agent_config.MultiAgentConfig"
-      ],
-      "name": [],
-      "object": [],
-      "reasoning": [
-        "beta.agent_reasoning.AgentReasoning"
-      ],
-      "service_tier": [],
-      "text": [
-        "beta.agent_text.AgentText"
-      ],
-      "tools": [
-        "beta.persisted_agent_tool.PersistedAgentToolResourceFunction",
-        "beta.persisted_agent_tool.PersistedAgentToolResourceMcp",
-        "beta.persisted_agent_tool.PersistedAgentToolResourceProgrammaticToolCalling",
-        "beta.persisted_agent_tool.PersistedAgentToolResourceToolSearch",
-        "beta.persisted_agent_tool.PersistedAgentToolResourceWebSearch"
-      ],
-      "updated_at": []
-    },
-    "beta.agent_close_subagent_call_item.AgentCloseSubagentCallItem": {
-      "id": [],
-      "recipient_agent_id": [],
-      "sender_agent_id": [],
-      "status": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_command_execution_item.AgentCommandExecutionItem": {
-      "command": [],
-      "cwd": [],
-      "duration_ms": [],
-      "exit_code": [],
-      "id": [],
-      "output": [],
-      "status": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_content.EncryptedContentResource": {
-      "encrypted_content": [],
-      "type": []
-    },
-    "beta.agent_create_params.AgentCreateParams": {
-      "instructions": [],
-      "metadata": [],
-      "model": [],
-      "multi_agent": [
-        "beta.multi_agent_config_param.MultiAgentConfigParam"
-      ],
-      "name": [],
-      "reasoning": [
-        "beta.agent_reasoning_param.AgentReasoningParam"
-      ],
-      "service_tier": [],
-      "text": [
-        "beta.agent_text_param.AgentTextParam"
-      ],
-      "tools": [
-        "beta.persisted_agent_tool_param.PersistedAgentToolConfigParamFunction",
-        "beta.persisted_agent_tool_param.PersistedAgentToolConfigParamMcp",
-        "beta.persisted_agent_tool_param.PersistedAgentToolConfigParamProgrammaticToolCalling",
-        "beta.persisted_agent_tool_param.PersistedAgentToolConfigParamToolSearch",
-        "beta.persisted_agent_tool_param.PersistedAgentToolConfigParamWebSearch"
-      ]
-    },
-    "beta.agent_create_subagent_call_item.AgentCreateSubagentCallItem": {
-      "agent_id": [],
-      "content": [
-        "beta.agent_content.EncryptedContentResource",
-        "beta.output_text.OutputText"
-      ],
-      "id": [],
-      "model": [],
-      "reasoning_effort": [],
-      "status": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_deleted.AgentDeleted": {
-      "deleted": [],
-      "id": [],
-      "object": []
-    },
-    "beta.agent_function_call_item.AgentFunctionCallItem": {
-      "arguments": [],
-      "call_id": [],
-      "id": [],
-      "name": [],
-      "status": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_interrupt_subagent_call_item.AgentInterruptSubagentCallItem": {
-      "id": [],
-      "recipient_agent_id": [],
-      "sender_agent_id": [],
-      "status": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_list_params.AgentListParams": {
-      "after": [],
-      "limit": [],
-      "order": []
-    },
-    "beta.agent_mcp_call_item.AgentMcpCallItem": {
-      "arguments": [],
-      "error": [],
-      "id": [],
-      "name": [],
-      "output": [],
-      "server_label": [],
-      "status": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_output_command_execution_output_delta_event.AgentOutputCommandExecutionOutputDeltaEvent": {
-      "delta": [],
-      "event_id": [],
-      "item_id": [],
-      "output_index": [],
-      "session_id": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_reasoning.AgentReasoning": {
-      "effort": [],
-      "summary": []
-    },
-    "beta.agent_reasoning_item.AgentReasoningItem": {
-      "id": [],
-      "status": [],
-      "summary": [
-        "beta.summary_text.SummaryText"
-      ],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_reasoning_param.AgentReasoningParam": {
-      "effort": [],
-      "summary": []
-    },
-    "beta.agent_resume_subagent_call_item.AgentResumeSubagentCallItem": {
-      "id": [],
-      "recipient_agent_id": [],
-      "sender_agent_id": [],
-      "status": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_send_subagent_input_call_item.AgentSendSubagentInputCallItem": {
-      "content": [
-        "beta.agent_content.EncryptedContentResource",
-        "beta.output_text.OutputText"
-      ],
-      "id": [],
-      "recipient_agent_id": [],
-      "sender_agent_id": [],
-      "status": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session.Agent": {
-      "id": [],
-      "instructions": [],
-      "model": [],
-      "multi_agent": [
-        "beta.multi_agent_config.MultiAgentConfig"
-      ],
-      "name": [],
-      "reasoning": [
-        "beta.agent_reasoning.AgentReasoning"
-      ],
-      "service_tier": [],
-      "text": [
-        "beta.agent_text.AgentText"
-      ],
-      "tools": [
-        "beta.agent_tool.AgentToolResourceFunction",
-        "beta.agent_tool.AgentToolResourceMcp",
-        "beta.agent_tool.AgentToolResourceProgrammaticToolCalling",
-        "beta.agent_tool.AgentToolResourceWebSearch"
-      ]
-    },
-    "beta.agent_session.AgentSession": {
-      "agent": [
-        "beta.agent_session.Agent"
-      ],
-      "created_at": [],
-      "environment": [
-        "beta.environment.EnvironmentResourceNone",
-        "beta.environment.EnvironmentResourceOpenAIHosted",
-        "beta.environment.EnvironmentResourceSelfHosted"
-      ],
-      "error": [],
-      "id": [],
-      "last_active_at": [],
-      "metadata": [],
-      "object": [],
-      "required_actions": [
-        "beta.agent_session.RequiredActionSessionRequiredActionResourceEnvironmentConnection",
-        "beta.agent_session.RequiredActionSessionRequiredActionResourceFunctionCall"
-      ],
-      "status": [],
-      "usage": [
-        "beta.token_usage.TokenUsage"
-      ],
-      "vault_ids": []
-    },
-    "beta.agent_session.RequiredActionSessionRequiredActionResourceEnvironmentConnection": {
-      "environment_id": [],
-      "type": []
-    },
-    "beta.agent_session.RequiredActionSessionRequiredActionResourceFunctionCall": {
-      "arguments": [],
-      "call_id": [],
-      "name": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_assistant_message.AgentSessionAssistantMessage": {
-      "content": [
-        "beta.output_text.OutputText"
-      ],
-      "id": [],
-      "phase": [],
-      "role": [],
-      "status": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_created_event.AgentSessionCreatedEvent": {
-      "event_id": [],
-      "session": [
-        "beta.agent_session.AgentSession"
-      ],
-      "type": []
-    },
-    "beta.agent_session_deleted.AgentSessionDeleted": {
-      "deleted": [],
-      "id": [],
-      "object": []
-    },
-    "beta.agent_session_environment_connected_event.AgentSessionEnvironmentConnectedEvent": {
-      "environment": [
-        "beta.agent_session_environment_state.AgentSessionEnvironmentState"
-      ],
-      "event_id": [],
-      "session_id": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_environment_disconnected_event.AgentSessionEnvironmentDisconnectedEvent": {
-      "environment": [
-        "beta.agent_session_environment_state.AgentSessionEnvironmentState"
-      ],
-      "event_id": [],
-      "session_id": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_environment_failed_event.AgentSessionEnvironmentFailedEvent": {
-      "environment": [
-        "beta.agent_session_environment_state.AgentSessionEnvironmentState"
-      ],
-      "event_id": [],
-      "session_id": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_environment_pending_event.AgentSessionEnvironmentPendingEvent": {
-      "environment": [
-        "beta.agent_session_environment_state.AgentSessionEnvironmentState"
-      ],
-      "event_id": [],
-      "session_id": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_environment_ready_event.AgentSessionEnvironmentReadyEvent": {
-      "environment": [
-        "beta.agent_session_environment_state.AgentSessionEnvironmentState"
-      ],
-      "event_id": [],
-      "session_id": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_environment_state.AgentSessionEnvironmentState": {
-      "error": [
-        "beta.agent_session_environment_state.Error"
-      ],
-      "id": [],
-      "status": [],
-      "type": []
-    },
-    "beta.agent_session_environment_state.Error": {
-      "code": [],
-      "message": [],
-      "type": []
-    },
-    "beta.agent_session_error_event.AgentSessionErrorEvent": {
-      "error": [
-        "beta.session_error.SessionError"
-      ],
-      "event_id": [],
-      "session_id": [],
-      "type": []
-    },
-    "beta.agent_session_failed_event.AgentSessionFailedEvent": {
-      "event_id": [],
-      "session": [
-        "beta.agent_session.AgentSession"
-      ],
-      "type": []
-    },
-    "beta.agent_session_idle_event.AgentSessionIdleEvent": {
-      "event_id": [],
-      "session": [
-        "beta.agent_session.AgentSession"
-      ],
-      "type": []
-    },
-    "beta.agent_session_in_progress_event.AgentSessionInProgressEvent": {
-      "event_id": [],
-      "session": [
-        "beta.agent_session.AgentSession"
-      ],
-      "type": []
-    },
-    "beta.agent_session_input_message_param.AgentSessionInputMessageParam": {
-      "content": [
-        "beta.input_content_param.InputContentParamInputImage",
-        "beta.input_content_param.InputContentParamInputText"
-      ],
-      "role": [],
-      "type": []
-    },
-    "beta.agent_session_input_param.SessionInputParamAgentSessionInputCancel": {
-      "type": []
-    },
-    "beta.agent_session_input_param.SessionInputParamAgentSessionInputMessage": {
-      "input": [
-        "beta.agent_session_input_message_param.AgentSessionInputMessageParam"
-      ],
-      "type": []
-    },
-    "beta.agent_session_input_param.SessionInputParamAgentSessionInputToolResult": {
-      "call_id": [],
-      "error": [],
-      "output": [
-        "beta.input_content_param.InputContentParamInputImage",
-        "beta.input_content_param.InputContentParamInputText"
-      ],
-      "success": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_item.AgentMessageItemResource": {
-      "content": [
-        "beta.agent_content.EncryptedContentResource",
-        "beta.output_text.OutputText"
-      ],
-      "id": [],
-      "recipient_agent_id": [],
-      "sender_agent_id": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_item.FunctionCallOutputItemResource": {
-      "call_id": [],
-      "error": [],
-      "id": [],
-      "output": [
-        "beta.input_content.InputContentResourceInputImage",
-        "beta.input_content.InputContentResourceInputText"
-      ],
-      "status": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_message.AgentSessionMessage": {
-      "content": [
-        "beta.agent_session_message_content.MessageContentResourceInputImage",
-        "beta.agent_session_message_content.MessageContentResourceInputText",
-        "beta.agent_session_message_content.MessageContentResourceOutputText"
-      ],
-      "id": [],
-      "phase": [],
-      "role": [],
-      "status": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_message_content.MessageContentResourceInputImage": {
-      "image_url": [],
-      "type": []
-    },
-    "beta.agent_session_message_content.MessageContentResourceInputText": {
-      "text": [],
-      "type": []
-    },
-    "beta.agent_session_message_content.MessageContentResourceOutputText": {
-      "text": [],
-      "type": []
-    },
-    "beta.agent_session_requires_action_event.AgentSessionRequiresActionEvent": {
-      "event_id": [],
-      "session": [
-        "beta.agent_session.AgentSession"
-      ],
-      "type": []
-    },
-    "beta.agent_session_subagent_active_event.AgentSessionSubagentActiveEvent": {
-      "event_id": [],
-      "subagent": [
-        "beta.subagent.Subagent"
-      ],
-      "type": []
-    },
-    "beta.agent_session_subagent_closed_event.AgentSessionSubagentClosedEvent": {
-      "event_id": [],
-      "subagent": [
-        "beta.subagent.Subagent"
-      ],
-      "type": []
-    },
-    "beta.agent_session_subagent_created_event.AgentSessionSubagentCreatedEvent": {
-      "event_id": [],
-      "subagent": [
-        "beta.subagent.Subagent"
-      ],
-      "type": []
-    },
-    "beta.agent_session_turn_cancelled_event.AgentSessionTurnCancelledEvent": {
-      "event_id": [],
-      "session_id": [],
-      "turn": [
-        "beta.agents.sessions.turn.Turn"
-      ],
-      "turn_id": [],
-      "type": [],
-      "usage": [
-        "beta.token_usage.TokenUsage"
-      ]
-    },
-    "beta.agent_session_turn_completed_event.AgentSessionTurnCompletedEvent": {
-      "event_id": [],
-      "session_id": [],
-      "turn": [
-        "beta.agents.sessions.turn.Turn"
-      ],
-      "turn_id": [],
-      "type": [],
-      "usage": [
-        "beta.token_usage.TokenUsage"
-      ]
-    },
-    "beta.agent_session_turn_content_part_added_event.AgentSessionTurnContentPartAddedEvent": {
-      "content_index": [],
-      "event_id": [],
-      "item_id": [],
-      "output_index": [],
-      "part": [
-        "beta.output_text.OutputText"
-      ],
-      "session_id": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_turn_content_part_done_event.AgentSessionTurnContentPartDoneEvent": {
-      "content_index": [],
-      "event_id": [],
-      "item_id": [],
-      "output_index": [],
-      "part": [
-        "beta.output_text.OutputText"
-      ],
-      "session_id": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_turn_created_event.AgentSessionTurnCreatedEvent": {
-      "event_id": [],
-      "session_id": [],
-      "turn": [
-        "beta.agents.sessions.turn.Turn"
-      ],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_turn_failed_event.AgentSessionTurnFailedEvent": {
-      "event_id": [],
-      "session_id": [],
-      "turn": [
-        "beta.agents.sessions.turn.Turn"
-      ],
-      "turn_id": [],
-      "type": [],
-      "usage": [
-        "beta.token_usage.TokenUsage"
-      ]
-    },
-    "beta.agent_session_turn_in_progress_event.AgentSessionTurnInProgressEvent": {
-      "event_id": [],
-      "session_id": [],
-      "turn": [
-        "beta.agents.sessions.turn.Turn"
-      ],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_turn_item_added_event.AgentSessionTurnItemAddedEvent": {
-      "event_id": [],
-      "item": [
-        "beta.agent_close_subagent_call_item.AgentCloseSubagentCallItem",
-        "beta.agent_command_execution_item.AgentCommandExecutionItem",
-        "beta.agent_create_subagent_call_item.AgentCreateSubagentCallItem",
-        "beta.agent_function_call_item.AgentFunctionCallItem",
-        "beta.agent_interrupt_subagent_call_item.AgentInterruptSubagentCallItem",
-        "beta.agent_mcp_call_item.AgentMcpCallItem",
-        "beta.agent_reasoning_item.AgentReasoningItem",
-        "beta.agent_resume_subagent_call_item.AgentResumeSubagentCallItem",
-        "beta.agent_send_subagent_input_call_item.AgentSendSubagentInputCallItem",
-        "beta.agent_session_item.AgentMessageItemResource",
-        "beta.agent_session_item.FunctionCallOutputItemResource",
-        "beta.agent_session_message.AgentSessionMessage",
-        "beta.agent_wait_for_subagents_call_item.AgentWaitForSubagentsCallItem",
-        "beta.agent_web_search_call_item.AgentWebSearchCallItem"
-      ],
-      "output_index": [],
-      "session_id": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_turn_item_done_event.AgentSessionTurnItemDoneEvent": {
-      "event_id": [],
-      "item": [
-        "beta.agent_close_subagent_call_item.AgentCloseSubagentCallItem",
-        "beta.agent_command_execution_item.AgentCommandExecutionItem",
-        "beta.agent_create_subagent_call_item.AgentCreateSubagentCallItem",
-        "beta.agent_function_call_item.AgentFunctionCallItem",
-        "beta.agent_interrupt_subagent_call_item.AgentInterruptSubagentCallItem",
-        "beta.agent_mcp_call_item.AgentMcpCallItem",
-        "beta.agent_reasoning_item.AgentReasoningItem",
-        "beta.agent_resume_subagent_call_item.AgentResumeSubagentCallItem",
-        "beta.agent_send_subagent_input_call_item.AgentSendSubagentInputCallItem",
-        "beta.agent_session_assistant_message.AgentSessionAssistantMessage",
-        "beta.agent_wait_for_subagents_call_item.AgentWaitForSubagentsCallItem",
-        "beta.agent_web_search_call_item.AgentWebSearchCallItem"
-      ],
-      "output_index": [],
-      "session_id": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_turn_output_text_delta_event.AgentSessionTurnOutputTextDeltaEvent": {
-      "content_index": [],
-      "delta": [],
-      "event_id": [],
-      "item_id": [],
-      "output_index": [],
-      "session_id": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_turn_output_text_done_event.AgentSessionTurnOutputTextDoneEvent": {
-      "content_index": [],
-      "event_id": [],
-      "item_id": [],
-      "output_index": [],
-      "session_id": [],
-      "text": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_turn_reasoning_summary_part_added_event.AgentSessionTurnReasoningSummaryPartAddedEvent": {
-      "event_id": [],
-      "item_id": [],
-      "output_index": [],
-      "part": [
-        "beta.summary_text.SummaryText"
-      ],
-      "session_id": [],
-      "summary_index": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_turn_reasoning_summary_part_done_event.AgentSessionTurnReasoningSummaryPartDoneEvent": {
-      "event_id": [],
-      "item_id": [],
-      "output_index": [],
-      "part": [
-        "beta.summary_text.SummaryText"
-      ],
-      "session_id": [],
-      "status": [],
-      "summary_index": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_turn_reasoning_summary_text_delta_event.AgentSessionTurnReasoningSummaryTextDeltaEvent": {
-      "delta": [],
-      "event_id": [],
-      "item_id": [],
-      "output_index": [],
-      "session_id": [],
-      "summary_index": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_session_turn_reasoning_summary_text_done_event.AgentSessionTurnReasoningSummaryTextDoneEvent": {
-      "event_id": [],
-      "item_id": [],
-      "output_index": [],
-      "session_id": [],
-      "summary_index": [],
-      "text": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_text.AgentText": {
-      "format": [
-        "beta.text_format.TextFormatResourceJSONSchema",
-        "beta.text_format.TextFormatResourceText"
-      ],
-      "verbosity": []
-    },
-    "beta.agent_text_param.AgentTextParam": {
-      "format": [
-        "beta.text_format_param.TextFormatParamJSONSchema",
-        "beta.text_format_param.TextFormatParamText"
-      ],
-      "verbosity": []
-    },
-    "beta.agent_tool.AgentToolResourceFunction": {
-      "defer_loading": [],
-      "description": [],
-      "name": [],
-      "parameters": [],
-      "type": []
-    },
-    "beta.agent_tool.AgentToolResourceMcp": {
-      "allowed_tools": [],
-      "connection_origin": [],
-      "credential_id": [],
-      "request_metadata": [],
-      "required": [],
-      "server_label": [],
-      "transport": [
-        "beta.mcp_transport.McpTransportResourceHTTP",
-        "beta.mcp_transport.McpTransportResourceStdio"
-      ],
-      "type": []
-    },
-    "beta.agent_tool.AgentToolResourceProgrammaticToolCalling": {
-      "enabled": [],
-      "type": []
-    },
-    "beta.agent_tool.AgentToolResourceWebSearch": {
-      "allowed_domains": [],
-      "context_size": [],
-      "location": [
-        "beta.agent_tool.AgentToolResourceWebSearchLocation"
-      ],
-      "mode": [],
-      "type": []
-    },
-    "beta.agent_tool.AgentToolResourceWebSearchLocation": {
-      "city": [],
-      "country": [],
-      "region": [],
-      "timezone": []
-    },
-    "beta.agent_tool_param.AgentToolConfigParamFunction": {
-      "defer_loading": [],
-      "description": [],
-      "name": [],
-      "parameters": [],
-      "type": []
-    },
-    "beta.agent_tool_param.AgentToolConfigParamMcp": {
-      "allowed_tools": [],
-      "connection_origin": [],
-      "credential_id": [],
-      "request_metadata": [],
-      "required": [],
-      "server_label": [],
-      "transport": [
-        "beta.mcp_transport_param.McpTransportConfigParamHTTP",
-        "beta.mcp_transport_param.McpTransportConfigParamStdio"
-      ],
-      "type": []
-    },
-    "beta.agent_tool_param.AgentToolConfigParamProgrammaticToolCalling": {
-      "enabled": [],
-      "type": []
-    },
-    "beta.agent_tool_param.AgentToolConfigParamToolSearch": {
-      "type": []
-    },
-    "beta.agent_tool_param.AgentToolConfigParamWebSearch": {
-      "allowed_domains": [],
-      "context_size": [],
-      "location": [
-        "beta.agent_tool_param.AgentToolConfigParamWebSearchLocation"
-      ],
-      "mode": [],
-      "type": []
-    },
-    "beta.agent_tool_param.AgentToolConfigParamWebSearchLocation": {
-      "city": [],
-      "country": [],
-      "region": [],
-      "timezone": []
-    },
-    "beta.agent_update_params.AgentUpdateParams": {
-      "instructions": [],
-      "metadata": [],
-      "model": [],
-      "multi_agent": [
-        "beta.multi_agent_config_param.MultiAgentConfigParam"
-      ],
-      "name": [],
-      "reasoning": [
-        "beta.agent_reasoning_param.AgentReasoningParam"
-      ],
-      "service_tier": [],
-      "text": [
-        "beta.agent_text_param.AgentTextParam"
-      ],
-      "tools": [
-        "beta.persisted_agent_tool_param.PersistedAgentToolConfigParamFunction",
-        "beta.persisted_agent_tool_param.PersistedAgentToolConfigParamMcp",
-        "beta.persisted_agent_tool_param.PersistedAgentToolConfigParamProgrammaticToolCalling",
-        "beta.persisted_agent_tool_param.PersistedAgentToolConfigParamToolSearch",
-        "beta.persisted_agent_tool_param.PersistedAgentToolConfigParamWebSearch"
-      ]
-    },
-    "beta.agent_wait_for_subagents_call_item.AgentWaitForSubagentsCallItem": {
-      "id": [],
-      "recipient_agent_ids": [],
-      "sender_agent_id": [],
-      "status": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agent_web_search_call_item.AgentWebSearchCallItem": {
-      "action": [
-        "beta.web_search_action.WebSearchActionResourceFindInPage",
-        "beta.web_search_action.WebSearchActionResourceOpenPage",
-        "beta.web_search_action.WebSearchActionResourceOther",
-        "beta.web_search_action.WebSearchActionResourceSearch"
-      ],
-      "id": [],
-      "status": [],
-      "turn_id": [],
-      "type": []
-    },
-    "beta.agents.environment_info.EnvironmentInfo": {
-      "files": [
-        "beta.hosted_environment_file.HostedEnvironmentFileResourceInline",
-        "beta.hosted_environment_file_id.HostedEnvironmentFileID"
-      ],
-      "id": [],
-      "object": [],
-      "plugins": [
-        "beta.hosted_plugin.HostedPlugin"
-      ],
-      "skills": [
-        "beta.hosted_skill.HostedSkillResourceInline",
-        "beta.hosted_skill_reference.HostedSkillReference"
-      ],
-      "status": [],
-      "type": []
-    },
-    "beta.agents.environments.environment_file.EnvironmentFile": {
-      "environment_id": [],
-      "object": [],
-      "path": [],
-      "size_bytes": []
-    },
-    "beta.agents.environments.environment_template.EnvironmentTemplate": {
-      "capability_directories": [],
-      "created_at": [],
-      "files": [
-        "beta.agents.environments.environment_template.FileHostedTemplateFileResourceFileID",
-        "beta.agents.environments.environment_template.FileHostedTemplateFileResourceInline"
-      ],
-      "id": [],
-      "name": [],
-      "network": [
-        "beta.agents.environments.environment_template.Network"
-      ],
-      "object": [],
-      "packages": [
-        "beta.agents.environments.environment_template.Packages"
-      ],
-      "plugins": [
-        "beta.hosted_plugin.HostedPlugin"
-      ],
-      "skills": [
-        "beta.agents.environments.environment_template.SkillHostedTemplateSkillResourceInline",
-        "beta.agents.environments.environment_template.SkillHostedTemplateSkillResourceSkillReference"
-      ],
-      "updated_at": []
-    },
-    "beta.agents.environments.environment_template.FileHostedTemplateFileResourceFileID": {
-      "file_id": [],
-      "path": [],
-      "type": []
-    },
-    "beta.agents.environments.environment_template.FileHostedTemplateFileResourceInline": {
-      "path": [],
-      "size_bytes": [],
-      "type": []
-    },
-    "beta.agents.environments.environment_template.Network": {
-      "access": [],
-      "allowed_domains": []
-    },
-    "beta.agents.environments.environment_template.Packages": {
-      "npm": [],
-      "python": [],
-      "system": []
-    },
-    "beta.agents.environments.environment_template.SkillHostedTemplateSkillResourceInline": {
-      "description": [],
-      "name": [],
-      "type": []
-    },
-    "beta.agents.environments.environment_template.SkillHostedTemplateSkillResourceSkillReference": {
-      "skill_id": [],
-      "type": [],
-      "version": []
-    },
-    "beta.agents.environments.environment_template_deleted.EnvironmentTemplateDeleted": {
-      "deleted": [],
-      "id": [],
-      "object": []
-    },
-    "beta.agents.environments.file_create_params.HostedEnvironmentFileParamFileID": {
-      "file_id": [],
-      "path": [],
-      "type": []
-    },
-    "beta.agents.environments.file_create_params.HostedEnvironmentFileParamInline": {
-      "data": [],
-      "path": [],
-      "type": []
-    },
-    "beta.agents.environments.file_list_params.FileListParams": {
-      "limit": [],
-      "order": [],
-      "page": [],
-      "path": []
-    },
-    "beta.agents.environments.template_create_params.Network": {
-      "access": [],
-      "allowed_domains": []
-    },
-    "beta.agents.environments.template_create_params.Packages": {
-      "npm": [],
-      "python": [],
-      "system": []
-    },
-    "beta.agents.environments.template_create_params.TemplateCreateParams": {
-      "capability_directories": [],
-      "env": [],
-      "files": [
-        "beta.hosted_environment_file_param.HostedEnvironmentFileParamFileID",
-        "beta.hosted_environment_file_param.HostedEnvironmentFileParamInline"
-      ],
-      "name": [],
-      "network": [
-        "beta.agents.environments.template_create_params.Network"
-      ],
-      "packages": [
-        "beta.agents.environments.template_create_params.Packages"
-      ],
-      "plugins": [
-        "beta.hosted_plugin_param.HostedPluginParam"
-      ],
-      "setup_commands": [
-        "beta.setup_command_param.SetupCommandParam"
-      ],
-      "skills": [
-        "beta.hosted_skill_param.HostedSkillParamInline",
-        "beta.hosted_skill_param.HostedSkillParamSkillReference"
-      ]
-    },
-    "beta.agents.environments.template_list_params.TemplateListParams": {
-      "after": [],
-      "limit": [],
-      "order": []
-    },
-    "beta.agents.environments.template_update_params.Network": {
-      "access": [],
-      "allowed_domains": []
-    },
-    "beta.agents.environments.template_update_params.Packages": {
-      "npm": [],
-      "python": [],
-      "system": []
-    },
-    "beta.agents.environments.template_update_params.TemplateUpdateParams": {
-      "capability_directories": [],
-      "env": [],
-      "files": [
-        "beta.hosted_environment_file_param.HostedEnvironmentFileParamFileID",
-        "beta.hosted_environment_file_param.HostedEnvironmentFileParamInline"
-      ],
-      "name": [],
-      "network": [
-        "beta.agents.environments.template_update_params.Network"
-      ],
-      "packages": [
-        "beta.agents.environments.template_update_params.Packages"
-      ],
-      "plugins": [
-        "beta.hosted_plugin_param.HostedPluginParam"
-      ],
-      "setup_commands": [
-        "beta.setup_command_param.SetupCommandParam"
-      ],
-      "skills": [
-        "beta.hosted_skill_param.HostedSkillParamInline",
-        "beta.hosted_skill_param.HostedSkillParamSkillReference"
-      ]
-    },
-    "beta.agents.session_create_params.Agent": {
-      "instructions": [],
-      "model": [],
-      "multi_agent": [
-        "beta.multi_agent_config_param.MultiAgentConfigParam"
-      ],
-      "reasoning": [
-        "beta.agent_reasoning_param.AgentReasoningParam"
-      ],
-      "service_tier": [],
-      "text": [
-        "beta.agent_text_param.AgentTextParam"
-      ],
-      "tools": [
-        "beta.agent_tool_param.AgentToolConfigParamFunction",
-        "beta.agent_tool_param.AgentToolConfigParamMcp",
-        "beta.agent_tool_param.AgentToolConfigParamProgrammaticToolCalling",
-        "beta.agent_tool_param.AgentToolConfigParamToolSearch",
-        "beta.agent_tool_param.AgentToolConfigParamWebSearch"
-      ]
-    },
-    "beta.agents.session_create_params.SessionCreateParamsNonStreaming": {
-      "agent": [
-        "beta.agents.session_create_params.Agent"
-      ],
-      "agent_id": [],
-      "environment": [
-        "beta.environment_param.EnvironmentParamNone",
-        "beta.environment_param.EnvironmentParamOpenAIHosted",
-        "beta.environment_param.EnvironmentParamSelfHosted"
-      ],
-      "input": [
-        "beta.agent_session_input_message_param.AgentSessionInputMessageParam"
-      ],
-      "metadata": [],
-      "stream": [],
-      "vault_ids": []
-    },
-    "beta.agents.session_create_params.SessionCreateParamsStreaming": {
-      "agent": [
-        "beta.agents.session_create_params.Agent"
-      ],
-      "agent_id": [],
-      "environment": [
-        "beta.environment_param.EnvironmentParamNone",
-        "beta.environment_param.EnvironmentParamOpenAIHosted",
-        "beta.environment_param.EnvironmentParamSelfHosted"
-      ],
-      "input": [
-        "beta.agent_session_input_message_param.AgentSessionInputMessageParam"
-      ],
-      "metadata": [],
-      "stream": [],
-      "vault_ids": []
-    },
-    "beta.agents.session_list_params.SessionListParams": {
-      "after": [],
-      "agent_id": [],
-      "limit": [],
-      "order": []
-    },
-    "beta.agents.session_update_params.SessionUpdateParams": {
-      "metadata": []
-    },
-    "beta.agents.sessions.artifact_list_params.ArtifactListParams": {
-      "after": [],
-      "environment_id": [],
-      "limit": [],
-      "order": []
-    },
-    "beta.agents.sessions.event_create_params.EventCreateParams": {
-      "Idempotency-Key": [],
-      "events": [
-        "beta.agent_session_input_param.SessionInputParamAgentSessionInputCancel",
-        "beta.agent_session_input_param.SessionInputParamAgentSessionInputMessage",
-        "beta.agent_session_input_param.SessionInputParamAgentSessionInputToolResult"
-      ]
-    },
-    "beta.agents.sessions.item_list_params.ItemListParams": {
-      "after": [],
-      "limit": [],
-      "order": []
-    },
-    "beta.agents.sessions.session_artifact.SessionArtifact": {
-      "created_at": [],
-      "environment_id": [],
-      "id": [],
-      "object": [],
-      "path": [],
-      "session_id": [],
-      "size_bytes": [],
-      "turn_id": []
-    },
-    "beta.agents.sessions.session_artifact_deleted.SessionArtifactDeleted": {
-      "deleted": [],
-      "id": [],
-      "object": []
-    },
-    "beta.agents.sessions.subagent_list_params.SubagentListParams": {
-      "after": [],
-      "limit": [],
-      "order": []
-    },
-    "beta.agents.sessions.subagents.item_list_params.ItemListParams": {
-      "after": [],
-      "limit": [],
-      "order": [],
-      "session_id": []
-    },
-    "beta.agents.sessions.subagents.turn_list_params.TurnListParams": {
-      "after": [],
-      "limit": [],
-      "order": [],
-      "session_id": []
-    },
-    "beta.agents.sessions.subagents.turns.item_list_params.ItemListParams": {
-      "after": [],
-      "limit": [],
-      "order": [],
-      "session_id": [],
-      "subagent_id": []
-    },
-    "beta.agents.sessions.turn.Turn": {
-      "agent_id": [],
-      "completed_at": [],
-      "created_at": [],
-      "error": [
-        "beta.session_turn_error.SessionTurnError"
-      ],
-      "id": [],
-      "object": [],
-      "session_id": [],
-      "started_at": [],
-      "status": [],
-      "subagent_id": [],
-      "usage": [
-        "beta.token_usage.TokenUsage"
-      ]
-    },
-    "beta.agents.sessions.turn_list_params.TurnListParams": {
-      "after": [],
-      "limit": [],
-      "order": []
-    },
-    "beta.agents.vault.Vault": {
-      "created_at": [],
-      "id": [],
-      "metadata": [],
-      "name": [],
-      "object": []
-    },
-    "beta.agents.vault_create_params.VaultCreateParams": {
-      "metadata": [],
-      "name": []
-    },
-    "beta.agents.vault_deleted.VaultDeleted": {
-      "deleted": [],
-      "id": [],
-      "object": []
-    },
-    "beta.agents.vault_list_params.VaultListParams": {
-      "after": [],
-      "limit": [],
-      "order": [],
-      "status": []
-    },
-    "beta.agents.vaults.credential.Credential": {
-      "auth": [
-        "beta.agents.vaults.credential_auth.VaultCredentialAuthResourceMcpOauth",
-        "beta.agents.vaults.credential_auth.VaultCredentialAuthResourceStaticBearer"
-      ],
-      "created_at": [],
-      "id": [],
-      "name": [],
-      "object": [],
-      "updated_at": [],
-      "vault_id": []
-    },
-    "beta.agents.vaults.credential_auth.VaultCredentialAuthResourceMcpOauth": {
-      "expires_at": [],
-      "mcp_server_url": [],
-      "refresh": [
-        "beta.agents.vaults.credential_auth.VaultCredentialAuthResourceMcpOauthRefresh"
-      ],
-      "type": []
-    },
-    "beta.agents.vaults.credential_auth.VaultCredentialAuthResourceMcpOauthRefresh": {
-      "client_id": [],
-      "resource": [],
-      "scope": [],
-      "token_endpoint": [],
-      "token_endpoint_auth": [
-        "beta.agents.vaults.mcp_oauth_token_endpoint_auth.McpOauthTokenEndpointAuthResourceClientSecretBasic",
-        "beta.agents.vaults.mcp_oauth_token_endpoint_auth.McpOauthTokenEndpointAuthResourceClientSecretPost",
-        "beta.agents.vaults.mcp_oauth_token_endpoint_auth.McpOauthTokenEndpointAuthResourceNone"
-      ]
-    },
-    "beta.agents.vaults.credential_auth.VaultCredentialAuthResourceStaticBearer": {
-      "mcp_server_url": [],
-      "type": []
-    },
-    "beta.agents.vaults.credential_auth_create_param.CreateVaultCredentialAuthParamMcpOauth": {
-      "access_token": [],
-      "expires_at": [],
-      "mcp_server_url": [],
-      "refresh": [
-        "beta.agents.vaults.credential_auth_create_param.CreateVaultCredentialAuthParamMcpOauthRefresh"
-      ],
-      "type": []
-    },
-    "beta.agents.vaults.credential_auth_create_param.CreateVaultCredentialAuthParamMcpOauthRefresh": {
-      "client_id": [],
-      "refresh_token": [],
-      "resource": [],
-      "scope": [],
-      "token_endpoint": [],
-      "token_endpoint_auth": [
-        "beta.agents.vaults.mcp_oauth_token_endpoint_auth_create_param.CreateMcpOauthTokenEndpointAuthParamClientSecretBasic",
-        "beta.agents.vaults.mcp_oauth_token_endpoint_auth_create_param.CreateMcpOauthTokenEndpointAuthParamClientSecretPost",
-        "beta.agents.vaults.mcp_oauth_token_endpoint_auth_create_param.CreateMcpOauthTokenEndpointAuthParamNone"
-      ]
-    },
-    "beta.agents.vaults.credential_auth_create_param.CreateVaultCredentialAuthParamStaticBearer": {
-      "mcp_server_url": [],
-      "token": [],
-      "type": []
-    },
-    "beta.agents.vaults.credential_auth_rotate_param.RotateVaultCredentialAuthParamMcpOauth": {
-      "access_token": [],
-      "expires_at": [],
-      "refresh": [
-        "beta.agents.vaults.credential_auth_rotate_param.RotateVaultCredentialAuthParamMcpOauthRefresh"
-      ],
-      "type": []
-    },
-    "beta.agents.vaults.credential_auth_rotate_param.RotateVaultCredentialAuthParamMcpOauthRefresh": {
-      "refresh_token": [],
-      "scope": [],
-      "token_endpoint_auth": [
-        "beta.agents.vaults.mcp_oauth_token_endpoint_auth_rotate_param.RotateMcpOauthTokenEndpointAuthParamClientSecretBasic",
-        "beta.agents.vaults.mcp_oauth_token_endpoint_auth_rotate_param.RotateMcpOauthTokenEndpointAuthParamClientSecretPost"
-      ]
-    },
-    "beta.agents.vaults.credential_auth_rotate_param.RotateVaultCredentialAuthParamStaticBearer": {
-      "token": [],
-      "type": []
-    },
-    "beta.agents.vaults.credential_create_params.CredentialCreateParams": {
-      "auth": [
-        "beta.agents.vaults.credential_auth_create_param.CreateVaultCredentialAuthParamMcpOauth",
-        "beta.agents.vaults.credential_auth_create_param.CreateVaultCredentialAuthParamStaticBearer"
-      ],
-      "name": []
-    },
-    "beta.agents.vaults.credential_deleted.CredentialDeleted": {
-      "deleted": [],
-      "id": [],
-      "object": []
-    },
-    "beta.agents.vaults.credential_list_params.CredentialListParams": {
-      "after": [],
-      "limit": [],
-      "order": [],
-      "status": []
-    },
-    "beta.agents.vaults.credential_update_params.CredentialUpdateParams": {
-      "auth": [
-        "beta.agents.vaults.credential_auth_rotate_param.RotateVaultCredentialAuthParamMcpOauth",
-        "beta.agents.vaults.credential_auth_rotate_param.RotateVaultCredentialAuthParamStaticBearer"
-      ],
-      "vault_id": []
-    },
-    "beta.agents.vaults.mcp_oauth_token_endpoint_auth.McpOauthTokenEndpointAuthResourceClientSecretBasic": {
-      "type": []
-    },
-    "beta.agents.vaults.mcp_oauth_token_endpoint_auth.McpOauthTokenEndpointAuthResourceClientSecretPost": {
-      "type": []
-    },
-    "beta.agents.vaults.mcp_oauth_token_endpoint_auth.McpOauthTokenEndpointAuthResourceNone": {
-      "type": []
-    },
-    "beta.agents.vaults.mcp_oauth_token_endpoint_auth_create_param.CreateMcpOauthTokenEndpointAuthParamClientSecretBasic": {
-      "client_secret": [],
-      "type": []
-    },
-    "beta.agents.vaults.mcp_oauth_token_endpoint_auth_create_param.CreateMcpOauthTokenEndpointAuthParamClientSecretPost": {
-      "client_secret": [],
-      "type": []
-    },
-    "beta.agents.vaults.mcp_oauth_token_endpoint_auth_create_param.CreateMcpOauthTokenEndpointAuthParamNone": {
-      "type": []
-    },
-    "beta.agents.vaults.mcp_oauth_token_endpoint_auth_rotate_param.RotateMcpOauthTokenEndpointAuthParamClientSecretBasic": {
-      "client_secret": [],
-      "type": []
-    },
-    "beta.agents.vaults.mcp_oauth_token_endpoint_auth_rotate_param.RotateMcpOauthTokenEndpointAuthParamClientSecretPost": {
-      "client_secret": [],
-      "type": []
-    },
-    "beta.environment.EnvironmentResourceNone": {
-      "type": []
-    },
-    "beta.environment.EnvironmentResourceOpenAIHosted": {
-      "capability_directories": [],
-      "files": [
-        "beta.hosted_environment_file.HostedEnvironmentFileResourceInline",
-        "beta.hosted_environment_file_id.HostedEnvironmentFileID"
-      ],
-      "id": [],
-      "network": [
-        "beta.environment.EnvironmentResourceOpenAIHostedNetwork"
-      ],
-      "packages": [
-        "beta.environment.EnvironmentResourceOpenAIHostedPackages"
-      ],
-      "plugins": [
-        "beta.hosted_plugin.HostedPlugin"
-      ],
-      "skills": [
-        "beta.hosted_skill.HostedSkillResourceInline",
-        "beta.hosted_skill_reference.HostedSkillReference"
-      ],
-      "type": []
-    },
-    "beta.environment.EnvironmentResourceOpenAIHostedNetwork": {
-      "access": [],
-      "allowed_domains": []
-    },
-    "beta.environment.EnvironmentResourceOpenAIHostedPackages": {
-      "npm": [],
-      "python": [],
-      "system": []
-    },
-    "beta.environment.EnvironmentResourceSelfHosted": {
-      "capability_directories": [],
-      "id": [],
-      "remote_url": [],
-      "type": [],
-      "workspace_directory": []
-    },
-    "beta.environment_param.EnvironmentParamNone": {
-      "type": []
-    },
-    "beta.environment_param.EnvironmentParamOpenAIHosted": {
-      "capability_directories": [],
-      "env": [],
-      "environment_template_id": [],
-      "files": [
-        "beta.hosted_environment_file_param.HostedEnvironmentFileParamFileID",
-        "beta.hosted_environment_file_param.HostedEnvironmentFileParamInline"
-      ],
-      "network": [
-        "beta.environment_param.EnvironmentParamOpenAIHostedNetwork"
-      ],
-      "packages": [
-        "beta.environment_param.EnvironmentParamOpenAIHostedPackages"
-      ],
-      "plugins": [
-        "beta.hosted_plugin_param.HostedPluginParam"
-      ],
-      "setup_commands": [
-        "beta.setup_command_param.SetupCommandParam"
-      ],
-      "skills": [
-        "beta.hosted_skill_param.HostedSkillParamInline",
-        "beta.hosted_skill_param.HostedSkillParamSkillReference"
-      ],
-      "type": []
-    },
-    "beta.environment_param.EnvironmentParamOpenAIHostedNetwork": {
-      "access": [],
-      "allowed_domains": []
-    },
-    "beta.environment_param.EnvironmentParamOpenAIHostedPackages": {
-      "npm": [],
-      "python": [],
-      "system": []
-    },
-    "beta.environment_param.EnvironmentParamSelfHosted": {
-      "capability_directories": [],
-      "type": [],
-      "workspace_directory": []
-    },
-    "beta.hosted_environment_file.HostedEnvironmentFileResourceInline": {
-      "id": [],
-      "path": [],
-      "size_bytes": [],
-      "type": []
-    },
-    "beta.hosted_environment_file_id.HostedEnvironmentFileID": {
-      "file_id": [],
-      "id": [],
-      "path": [],
-      "size_bytes": [],
-      "type": []
-    },
-    "beta.hosted_environment_file_param.HostedEnvironmentFileParamFileID": {
-      "file_id": [],
-      "path": [],
-      "type": []
-    },
-    "beta.hosted_environment_file_param.HostedEnvironmentFileParamInline": {
-      "data": [],
-      "path": [],
-      "type": []
-    },
-    "beta.hosted_plugin.HostedPlugin": {
-      "description": [],
-      "name": [],
-      "type": []
-    },
-    "beta.hosted_plugin_param.HostedPluginParam": {
-      "description": [],
-      "name": [],
-      "source": [
-        "beta.inline_capability_source_param.InlineCapabilitySourceParam"
-      ],
-      "type": []
-    },
-    "beta.hosted_skill.HostedSkillResourceInline": {
-      "description": [],
-      "name": [],
-      "type": []
-    },
-    "beta.hosted_skill_param.HostedSkillParamInline": {
-      "description": [],
-      "name": [],
-      "source": [
-        "beta.inline_capability_source_param.InlineCapabilitySourceParam"
-      ],
-      "type": []
-    },
-    "beta.hosted_skill_param.HostedSkillParamSkillReference": {
-      "skill_id": [],
-      "type": [],
-      "version": []
-    },
-    "beta.hosted_skill_reference.HostedSkillReference": {
-      "description": [],
-      "name": [],
-      "skill_id": [],
-      "type": [],
-      "version": []
-    },
-    "beta.inline_capability_source_param.InlineCapabilitySourceParam": {
-      "data": [],
-      "media_type": [],
-      "type": []
-    },
-    "beta.input_content.InputContentResourceInputImage": {
-      "image_url": [],
-      "type": []
-    },
-    "beta.input_content.InputContentResourceInputText": {
-      "text": [],
-      "type": []
-    },
-    "beta.input_content_param.InputContentParamInputImage": {
-      "image_url": [],
-      "type": []
-    },
-    "beta.input_content_param.InputContentParamInputText": {
-      "text": [],
-      "type": []
-    },
-    "beta.mcp_transport.McpTransportResourceHTTP": {
-      "server_url": [],
-      "type": []
-    },
-    "beta.mcp_transport.McpTransportResourceStdio": {
-      "args": [],
-      "command": [],
-      "cwd": [],
-      "env_vars": [],
-      "type": []
-    },
-    "beta.mcp_transport_param.McpTransportConfigParamHTTP": {
-      "authorization": [],
-      "headers": [],
-      "server_url": [],
-      "type": []
-    },
-    "beta.mcp_transport_param.McpTransportConfigParamStdio": {
-      "args": [],
-      "command": [],
-      "cwd": [],
-      "env": [],
-      "env_vars": [],
-      "type": []
-    },
-    "beta.multi_agent_config.MultiAgentConfig": {
-      "enabled": [],
-      "max_concurrent_subagents": []
-    },
-    "beta.multi_agent_config_param.MultiAgentConfigParam": {
-      "enabled": [],
-      "max_concurrent_subagents": []
-    },
-    "beta.output_text.OutputText": {
-      "text": [],
-      "type": []
-    },
-    "beta.persisted_agent_tool.PersistedAgentToolResourceFunction": {
-      "defer_loading": [],
-      "description": [],
-      "name": [],
-      "parameters": [],
-      "type": []
-    },
-    "beta.persisted_agent_tool.PersistedAgentToolResourceMcp": {
-      "allowed_tools": [],
-      "connection_origin": [],
-      "credential_id": [],
-      "request_metadata": [],
-      "required": [],
-      "server_label": [],
-      "transport": [
-        "beta.persisted_mcp_transport.PersistedMcpTransportResourceHTTP",
-        "beta.persisted_mcp_transport.PersistedMcpTransportResourceStdio"
-      ],
-      "type": []
-    },
-    "beta.persisted_agent_tool.PersistedAgentToolResourceProgrammaticToolCalling": {
-      "enabled": [],
-      "type": []
-    },
-    "beta.persisted_agent_tool.PersistedAgentToolResourceToolSearch": {
-      "type": []
-    },
-    "beta.persisted_agent_tool.PersistedAgentToolResourceWebSearch": {
-      "allowed_domains": [],
-      "context_size": [],
-      "location": [
-        "beta.persisted_agent_tool.PersistedAgentToolResourceWebSearchLocation"
-      ],
-      "mode": [],
-      "type": []
-    },
-    "beta.persisted_agent_tool.PersistedAgentToolResourceWebSearchLocation": {
-      "city": [],
-      "country": [],
-      "region": [],
-      "timezone": []
-    },
-    "beta.persisted_agent_tool_param.PersistedAgentToolConfigParamFunction": {
-      "defer_loading": [],
-      "description": [],
-      "name": [],
-      "parameters": [],
-      "type": []
-    },
-    "beta.persisted_agent_tool_param.PersistedAgentToolConfigParamMcp": {
-      "allowed_tools": [],
-      "connection_origin": [],
-      "credential_id": [],
-      "request_metadata": [],
-      "required": [],
-      "server_label": [],
-      "transport": [
-        "beta.persisted_mcp_transport_param.PersistedMcpTransportConfigParamHTTP",
-        "beta.persisted_mcp_transport_param.PersistedMcpTransportConfigParamStdio"
-      ],
-      "type": []
-    },
-    "beta.persisted_agent_tool_param.PersistedAgentToolConfigParamProgrammaticToolCalling": {
-      "enabled": [],
-      "type": []
-    },
-    "beta.persisted_agent_tool_param.PersistedAgentToolConfigParamToolSearch": {
-      "type": []
-    },
-    "beta.persisted_agent_tool_param.PersistedAgentToolConfigParamWebSearch": {
-      "allowed_domains": [],
-      "context_size": [],
-      "location": [
-        "beta.persisted_agent_tool_param.PersistedAgentToolConfigParamWebSearchLocation"
-      ],
-      "mode": [],
-      "type": []
-    },
-    "beta.persisted_agent_tool_param.PersistedAgentToolConfigParamWebSearchLocation": {
-      "city": [],
-      "country": [],
-      "region": [],
-      "timezone": []
-    },
-    "beta.persisted_mcp_transport.PersistedMcpTransportResourceHTTP": {
-      "headers": [],
-      "server_url": [],
-      "type": []
-    },
-    "beta.persisted_mcp_transport.PersistedMcpTransportResourceStdio": {
-      "args": [],
-      "command": [],
-      "cwd": [],
-      "env_vars": [],
-      "type": []
-    },
-    "beta.persisted_mcp_transport_param.PersistedMcpTransportConfigParamHTTP": {
-      "headers": [],
-      "server_url": [],
-      "type": []
-    },
-    "beta.persisted_mcp_transport_param.PersistedMcpTransportConfigParamStdio": {
-      "args": [],
-      "command": [],
-      "cwd": [],
-      "env_vars": [],
-      "type": []
-    },
-    "beta.session_error.SessionError": {
-      "code": [],
-      "message": [],
-      "param": [],
-      "type": []
-    },
-    "beta.session_turn_error.SessionTurnError": {
-      "code": [],
-      "message": []
-    },
-    "beta.setup_command_param.SetupCommandParam": {
-      "command": [],
-      "cwd": []
-    },
-    "beta.subagent.Subagent": {
-      "closed_at": [],
-      "id": [],
-      "instructions": [
-        "beta.agent_content.EncryptedContentResource",
-        "beta.output_text.OutputText"
-      ],
-      "name": [],
-      "object": [],
-      "opened_at": [],
-      "parent_agent_id": [],
-      "session_id": [],
-      "status": []
-    },
-    "beta.summary_text.SummaryText": {
-      "text": [],
-      "type": []
-    },
-    "beta.text_format.TextFormatResourceJSONSchema": {
-      "schema": [],
-      "type": []
-    },
-    "beta.text_format.TextFormatResourceText": {
-      "type": []
-    },
-    "beta.text_format_param.TextFormatParamJSONSchema": {
-      "schema": [],
-      "type": []
-    },
-    "beta.text_format_param.TextFormatParamText": {
-      "type": []
-    },
-    "beta.token_usage.InputTokensDetails": {
-      "cached_tokens": []
-    },
-    "beta.token_usage.OutputTokensDetails": {
-      "reasoning_tokens": []
-    },
-    "beta.token_usage.TokenUsage": {
-      "input_tokens": [],
-      "input_tokens_details": [
-        "beta.token_usage.InputTokensDetails"
-      ],
-      "output_tokens": [],
-      "output_tokens_details": [
-        "beta.token_usage.OutputTokensDetails"
-      ],
-      "total_tokens": []
-    },
-    "beta.web_search_action.WebSearchActionResourceFindInPage": {
-      "pattern": [],
-      "type": [],
-      "url": []
-    },
-    "beta.web_search_action.WebSearchActionResourceOpenPage": {
-      "type": [],
-      "url": []
-    },
-    "beta.web_search_action.WebSearchActionResourceOther": {
-      "type": []
-    },
-    "beta.web_search_action.WebSearchActionResourceSearch": {
-      "queries": [],
-      "query": [],
-      "type": []
-    },
-    "deleted_skill.DeletedSkill": {
-      "deleted": [],
-      "id": [],
-      "object": []
-    },
-    "file_create_params.ExpiresAfter": {
-      "anchor": [],
-      "seconds": []
-    },
-    "file_create_params.FileCreateParams": {
-      "expires_after": [
-        "file_create_params.ExpiresAfter"
-      ],
-      "file": [],
-      "purpose": []
-    },
-    "file_deleted.FileDeleted": {
-      "deleted": [],
-      "id": [],
-      "object": []
-    },
-    "file_list_params.FileListParams": {
-      "after": [],
-      "limit": [],
-      "order": [],
-      "purpose": []
-    },
-    "file_object.FileObject": {
-      "bytes": [],
-      "created_at": [],
-      "expires_at": [],
-      "filename": [],
-      "id": [],
-      "object": [],
-      "purpose": [],
-      "status": [],
-      "status_details": []
-    },
-    "pagination.SyncCursorPage[beta.agent.Agent]": {
-      "data": [
-        "beta.agent.Agent"
-      ],
-      "has_more": []
-    },
-    "pagination.SyncCursorPage[beta.agent_close_subagent_call_item.AgentCloseSubagentCallItem | beta.agent_command_execution_item.AgentCommandExecutionItem | beta.agent_create_subagent_call_item.AgentCreateSubagentCallItem | beta.agent_function_call_item.AgentFunctionCallItem | beta.agent_interrupt_subagent_call_item.AgentInterruptSubagentCallItem | beta.agent_mcp_call_item.AgentMcpCallItem | beta.agent_reasoning_item.AgentReasoningItem | beta.agent_resume_subagent_call_item.AgentResumeSubagentCallItem | beta.agent_send_subagent_input_call_item.AgentSendSubagentInputCallItem | beta.agent_session_item.AgentMessageItemResource | beta.agent_session_item.FunctionCallOutputItemResource | beta.agent_session_message.AgentSessionMessage | beta.agent_wait_for_subagents_call_item.AgentWaitForSubagentsCallItem | beta.agent_web_search_call_item.AgentWebSearchCallItem]": {
-      "data": [
-        "beta.agent_close_subagent_call_item.AgentCloseSubagentCallItem",
-        "beta.agent_command_execution_item.AgentCommandExecutionItem",
-        "beta.agent_create_subagent_call_item.AgentCreateSubagentCallItem",
-        "beta.agent_function_call_item.AgentFunctionCallItem",
-        "beta.agent_interrupt_subagent_call_item.AgentInterruptSubagentCallItem",
-        "beta.agent_mcp_call_item.AgentMcpCallItem",
-        "beta.agent_reasoning_item.AgentReasoningItem",
-        "beta.agent_resume_subagent_call_item.AgentResumeSubagentCallItem",
-        "beta.agent_send_subagent_input_call_item.AgentSendSubagentInputCallItem",
-        "beta.agent_session_item.AgentMessageItemResource",
-        "beta.agent_session_item.FunctionCallOutputItemResource",
-        "beta.agent_session_message.AgentSessionMessage",
-        "beta.agent_wait_for_subagents_call_item.AgentWaitForSubagentsCallItem",
-        "beta.agent_web_search_call_item.AgentWebSearchCallItem"
-      ],
-      "has_more": []
-    },
-    "pagination.SyncCursorPage[beta.agent_session.AgentSession]": {
-      "data": [
-        "beta.agent_session.AgentSession"
-      ],
-      "has_more": []
-    },
-    "pagination.SyncCursorPage[beta.agents.environments.environment_template.EnvironmentTemplate]": {
-      "data": [
-        "beta.agents.environments.environment_template.EnvironmentTemplate"
-      ],
-      "has_more": []
-    },
-    "pagination.SyncCursorPage[beta.agents.sessions.session_artifact.SessionArtifact]": {
-      "data": [
-        "beta.agents.sessions.session_artifact.SessionArtifact"
-      ],
-      "has_more": []
-    },
-    "pagination.SyncCursorPage[beta.agents.sessions.turn.Turn]": {
-      "data": [
-        "beta.agents.sessions.turn.Turn"
-      ],
-      "has_more": []
-    },
-    "pagination.SyncCursorPage[beta.agents.vault.Vault]": {
-      "data": [
-        "beta.agents.vault.Vault"
-      ],
-      "has_more": []
-    },
-    "pagination.SyncCursorPage[beta.agents.vaults.credential.Credential]": {
-      "data": [
-        "beta.agents.vaults.credential.Credential"
-      ],
-      "has_more": []
-    },
-    "pagination.SyncCursorPage[beta.subagent.Subagent]": {
-      "data": [
-        "beta.subagent.Subagent"
-      ],
-      "has_more": []
-    },
-    "pagination.SyncCursorPage[file_object.FileObject]": {
-      "data": [
-        "file_object.FileObject"
-      ],
-      "has_more": []
-    },
-    "pagination.SyncCursorPage[skill.Skill]": {
-      "data": [
-        "skill.Skill"
-      ],
-      "has_more": []
-    },
-    "pagination.SyncCursorPage[skills.skill_version.SkillVersion]": {
-      "data": [
-        "skills.skill_version.SkillVersion"
-      ],
-      "has_more": []
-    },
-    "pagination.SyncTokenPage[beta.agents.environments.environment_file.EnvironmentFile]": {
-      "data": [
-        "beta.agents.environments.environment_file.EnvironmentFile"
-      ],
-      "has_more": [],
-      "next": []
-    },
-    "skill.Skill": {
-      "created_at": [],
-      "default_version": [],
-      "description": [],
-      "id": [],
-      "latest_version": [],
-      "name": [],
-      "object": []
-    },
-    "skill_create_params.SkillCreateParams": {
-      "files": []
-    },
-    "skill_list_params.SkillListParams": {
-      "after": [],
-      "limit": [],
-      "order": []
-    },
-    "skill_update_params.SkillUpdateParams": {
-      "default_version": []
-    },
-    "skills.deleted_skill_version.DeletedSkillVersion": {
-      "deleted": [],
-      "id": [],
-      "object": [],
-      "version": []
-    },
-    "skills.skill_version.SkillVersion": {
-      "created_at": [],
-      "description": [],
-      "id": [],
-      "name": [],
-      "object": [],
-      "skill_id": [],
-      "version": []
-    },
-    "skills.version_create_params.VersionCreateParams": {
-      "default": [],
-      "files": []
-    },
-    "skills.version_list_params.VersionListParams": {
-      "after": [],
-      "limit": [],
-      "order": []
-    }
-  }
-}
diff --git a/contracts/agents-api/upstream-routes.json b/contracts/agents-api/upstream-routes.json
index 3326834f2..1f305b93a 100644
--- a/contracts/agents-api/upstream-routes.json
+++ b/contracts/agents-api/upstream-routes.json
@@ -1,12 +1,6 @@
 {
-  "sdk_version": "3.13.0",
-  "commit": "d7c41efee1b0802b79f3f88a678ef2052b06e9ce",
-  "generator": "scripts/extract-agents-api-upstream.py",
-  "resources": [
-    "openai.resources.beta.agents",
-    "openai.resources.files",
-    "openai.resources.skills"
-  ],
+  "openapi_commit": "046a2a0f325bf11f97966f2729219f27281ba71e",
+  "generator": "scripts/generate-public-api.py",
   "routes": [
     "DELETE /agents/environments/templates/{}",
     "DELETE /agents/sessions/{}",
diff --git a/contracts/agents-api/upstream.json b/contracts/agents-api/upstream.json
index adc71d0bb..253e00627 100644
--- a/contracts/agents-api/upstream.json
+++ b/contracts/agents-api/upstream.json
@@ -4,5 +4,11 @@
   "sdk_version": "3.13.0",
   "resource_path": "src/openai/resources/beta/agents",
   "type_path": "src/openai/types/beta",
-  "beta_header": "agents=v1"
+  "beta_header": "agents=v1",
+  "openapi": {
+    "repository": "https://github.com/openai/openai-openapi",
+    "commit": "046a2a0f325bf11f97966f2729219f27281ba71e",
+    "path": "openapi.json",
+    "sha256": "c96d974b164ff4750fa5ea5a1727f7ce6691540e257c177db02b660b0db58f26"
+  }
 }
diff --git a/contracts/agents-api/upstream/LICENSE b/contracts/agents-api/upstream/LICENSE
new file mode 100644
index 000000000..4f14854c3
--- /dev/null
+++ b/contracts/agents-api/upstream/LICENSE
@@ -0,0 +1,21 @@
+The MIT License
+
+Copyright (c) OpenAI (https://openai.com)
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
diff --git a/contracts/agents-api/upstream/openapi.json b/contracts/agents-api/upstream/openapi.json
new file mode 100644
index 000000000..f966c2530
--- /dev/null
+++ b/contracts/agents-api/upstream/openapi.json
@@ -0,0 +1,107618 @@
+{
+  "openapi": "3.1.0",
+  "info": {
+    "title": "OpenAI API",
+    "description": "The OpenAI REST API. Please see https://platform.openai.com/docs/api-reference for more details.",
+    "version": "2.3.0",
+    "termsOfService": "https://openai.com/policies/terms-of-use",
+    "contact": {
+      "name": "OpenAI Support",
+      "url": "https://help.openai.com/"
+    },
+    "license": {
+      "name": "MIT",
+      "identifier": "MIT"
+    }
+  },
+  "servers": [
+    {
+      "url": "https://api.openai.com/v1"
+    }
+  ],
+  "security": [
+    {
+      "ApiKeyAuth": []
+    }
+  ],
+  "tags": [
+    {
+      "name": "Assistants",
+      "description": "Build Assistants that can call models and use tools."
+    },
+    {
+      "name": "Audio",
+      "description": "Turn audio into text or text into audio."
+    },
+    {
+      "name": "Chat",
+      "description": "Given a list of messages comprising a conversation, the model will return a response."
+    },
+    {
+      "name": "Conversations",
+      "description": "Manage conversations and conversation items."
+    },
+    {
+      "name": "Completions",
+      "description": "Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position."
+    },
+    {
+      "name": "Embeddings",
+      "description": "Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms."
+    },
+    {
+      "name": "Evals",
+      "description": "Manage and run evals in the OpenAI platform."
+    },
+    {
+      "name": "Fine-tuning",
+      "description": "Manage fine-tuning jobs to tailor a model to your specific training data."
+    },
+    {
+      "name": "Graders",
+      "description": "Manage and run graders in the OpenAI platform."
+    },
+    {
+      "name": "Batch",
+      "description": "Create large batches of API requests to run asynchronously."
+    },
+    {
+      "name": "Files",
+      "description": "Files are used to upload documents that can be used with features like Assistants and Fine-tuning."
+    },
+    {
+      "name": "Uploads",
+      "description": "Use Uploads to upload large files in multiple parts."
+    },
+    {
+      "name": "Images",
+      "description": "Given a prompt and/or an input image, the model will generate a new image."
+    },
+    {
+      "name": "Models",
+      "description": "List and describe the various models available in the API."
+    },
+    {
+      "name": "Moderations",
+      "description": "Given text and/or image inputs, classifies if those inputs are potentially harmful."
+    },
+    {
+      "name": "Audit Logs",
+      "description": "List user actions and configuration changes within this organization."
+    }
+  ],
+  "paths": {
+    "/assistants": {
+      "get": {
+        "operationId": "listAssistants",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Returns a list of assistants.",
+        "deprecated": true,
+        "parameters": [
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.\n",
+            "schema": {
+              "type": "string",
+              "default": "desc",
+              "enum": [
+                "asc",
+                "desc"
+              ]
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "before",
+            "in": "query",
+            "description": "A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.\n",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ListAssistantsResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List assistants",
+          "group": "assistants",
+          "examples": {
+            "request": {
+              "curl": "curl \"https://api.openai.com/v1/assistants?order=desc&limit=20\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"OpenAI-Beta: assistants=v2\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nmy_assistants = client.beta.assistants.list(\n    order=\"desc\",\n    limit=\"20\",\n)\nprint(my_assistants.data)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const myAssistants = await openai.beta.assistants.list({\n    order: \"desc\",\n    limit: \"20\",\n  });\n\n  console.log(myAssistants.data);\n}\n\nmain();"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"id\": \"asst_abc123\",\n      \"object\": \"assistant\",\n      \"created_at\": 1698982736,\n      \"name\": \"Coding Tutor\",\n      \"description\": null,\n      \"model\": \"gpt-5\",\n      \"instructions\": \"You are a helpful assistant designed to make me better at coding!\",\n      \"tools\": [],\n      \"tool_resources\": {},\n      \"metadata\": {},\n      \"top_p\": 1.0,\n      \"temperature\": 1.0,\n      \"response_format\": \"auto\"\n    },\n    {\n      \"id\": \"asst_abc456\",\n      \"object\": \"assistant\",\n      \"created_at\": 1698982718,\n      \"name\": \"My Assistant\",\n      \"description\": null,\n      \"model\": \"gpt-5\",\n      \"instructions\": \"You are a helpful assistant designed to make me better at coding!\",\n      \"tools\": [],\n      \"tool_resources\": {},\n      \"metadata\": {},\n      \"top_p\": 1.0,\n      \"temperature\": 1.0,\n      \"response_format\": \"auto\"\n    },\n    {\n      \"id\": \"asst_abc789\",\n      \"object\": \"assistant\",\n      \"created_at\": 1698982643,\n      \"name\": null,\n      \"description\": null,\n      \"model\": \"gpt-5\",\n      \"instructions\": null,\n      \"tools\": [],\n      \"tool_resources\": {},\n      \"metadata\": {},\n      \"top_p\": 1.0,\n      \"temperature\": 1.0,\n      \"response_format\": \"auto\"\n    }\n  ],\n  \"first_id\": \"asst_abc123\",\n  \"last_id\": \"asst_abc789\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      },
+      "post": {
+        "operationId": "createAssistant",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Create an assistant with a model and instructions.",
+        "deprecated": true,
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateAssistantRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/AssistantObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create assistant",
+          "group": "assistants",
+          "examples": [
+            {
+              "title": "Code Interpreter",
+              "request": {
+                "curl": "curl \"https://api.openai.com/v1/assistants\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -d '{\n    \"instructions\": \"You are a personal math tutor. When asked a question, write and run Python code to answer the question.\",\n    \"name\": \"Math Tutor\",\n    \"tools\": [{\"type\": \"code_interpreter\"}],\n    \"model\": \"gpt-5\"\n  }'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\nmy_assistant = client.beta.assistants.create(\n    instructions=\"You are a personal math tutor. When asked a question, write and run Python code to answer the question.\",\n    name=\"Math Tutor\",\n    tools=[{\"type\": \"code_interpreter\"}],\n    model=\"gpt-5\",\n)\nprint(my_assistant)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const myAssistant = await openai.beta.assistants.create({\n    instructions:\n      \"You are a personal math tutor. When asked a question, write and run Python code to answer the question.\",\n    name: \"Math Tutor\",\n    tools: [{ type: \"code_interpreter\" }],\n    model: \"gpt-5\",\n  });\n\n  console.log(myAssistant);\n}\n\nmain();"
+              },
+              "response": "{\n  \"id\": \"asst_abc123\",\n  \"object\": \"assistant\",\n  \"created_at\": 1698984975,\n  \"name\": \"Math Tutor\",\n  \"description\": null,\n  \"model\": \"gpt-5\",\n  \"instructions\": \"You are a personal math tutor. When asked a question, write and run Python code to answer the question.\",\n  \"tools\": [\n    {\n      \"type\": \"code_interpreter\"\n    }\n  ],\n  \"metadata\": {},\n  \"top_p\": 1.0,\n  \"temperature\": 1.0,\n  \"response_format\": \"auto\"\n}\n"
+            },
+            {
+              "title": "Files",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/assistants \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -d '{\n    \"instructions\": \"You are an HR bot, and you have access to files to answer employee questions about company policies.\",\n    \"tools\": [{\"type\": \"file_search\"}],\n    \"tool_resources\": {\"file_search\": {\"vector_store_ids\": [\"vs_123\"]}},\n    \"model\": \"gpt-5\"\n  }'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\nmy_assistant = client.beta.assistants.create(\n    instructions=\"You are an HR bot, and you have access to files to answer employee questions about company policies.\",\n    name=\"HR Helper\",\n    tools=[{\"type\": \"file_search\"}],\n    tool_resources={\"file_search\": {\"vector_store_ids\": [\"vs_123\"]}},\n    model=\"gpt-5\"\n)\nprint(my_assistant)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const myAssistant = await openai.beta.assistants.create({\n    instructions:\n      \"You are an HR bot, and you have access to files to answer employee questions about company policies.\",\n    name: \"HR Helper\",\n    tools: [{ type: \"file_search\" }],\n    tool_resources: {\n      file_search: {\n        vector_store_ids: [\"vs_123\"]\n      }\n    },\n    model: \"gpt-5\"\n  });\n\n  console.log(myAssistant);\n}\n\nmain();"
+              },
+              "response": "{\n  \"id\": \"asst_abc123\",\n  \"object\": \"assistant\",\n  \"created_at\": 1699009403,\n  \"name\": \"HR Helper\",\n  \"description\": null,\n  \"model\": \"gpt-5\",\n  \"instructions\": \"You are an HR bot, and you have access to files to answer employee questions about company policies.\",\n  \"tools\": [\n    {\n      \"type\": \"file_search\"\n    }\n  ],\n  \"tool_resources\": {\n    \"file_search\": {\n      \"vector_store_ids\": [\"vs_123\"]\n    }\n  },\n  \"metadata\": {},\n  \"top_p\": 1.0,\n  \"temperature\": 1.0,\n  \"response_format\": \"auto\"\n}\n"
+            }
+          ]
+        }
+      }
+    },
+    "/assistants/{assistant_id}": {
+      "get": {
+        "operationId": "getAssistant",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Retrieves an assistant.",
+        "deprecated": true,
+        "parameters": [
+          {
+            "in": "path",
+            "name": "assistant_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the assistant to retrieve."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/AssistantObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve assistant",
+          "group": "assistants",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/assistants/asst_abc123 \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"OpenAI-Beta: assistants=v2\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nmy_assistant = client.beta.assistants.retrieve(\"asst_abc123\")\nprint(my_assistant)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const myAssistant = await openai.beta.assistants.retrieve(\n    \"asst_abc123\"\n  );\n\n  console.log(myAssistant);\n}\n\nmain();"
+            },
+            "response": "{\n  \"id\": \"asst_abc123\",\n  \"object\": \"assistant\",\n  \"created_at\": 1699009709,\n  \"name\": \"HR Helper\",\n  \"description\": null,\n  \"model\": \"gpt-5\",\n  \"instructions\": \"You are an HR bot, and you have access to files to answer employee questions about company policies.\",\n  \"tools\": [\n    {\n      \"type\": \"file_search\"\n    }\n  ],\n  \"metadata\": {},\n  \"top_p\": 1.0,\n  \"temperature\": 1.0,\n  \"response_format\": \"auto\"\n}\n"
+          }
+        }
+      },
+      "post": {
+        "operationId": "modifyAssistant",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Modifies an assistant.",
+        "deprecated": true,
+        "parameters": [
+          {
+            "in": "path",
+            "name": "assistant_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the assistant to modify."
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ModifyAssistantRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/AssistantObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Modify assistant",
+          "group": "assistants",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/assistants/asst_abc123 \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -d '{\n      \"instructions\": \"You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.\",\n      \"tools\": [{\"type\": \"file_search\"}],\n      \"model\": \"gpt-5\"\n    }'\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nmy_updated_assistant = client.beta.assistants.update(\n  \"asst_abc123\",\n  instructions=\"You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.\",\n  name=\"HR Helper\",\n  tools=[{\"type\": \"file_search\"}],\n  model=\"gpt-5\"\n)\n\nprint(my_updated_assistant)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const myUpdatedAssistant = await openai.beta.assistants.update(\n    \"asst_abc123\",\n    {\n      instructions:\n        \"You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.\",\n      name: \"HR Helper\",\n      tools: [{ type: \"file_search\" }],\n      model: \"gpt-5\"\n    }\n  );\n\n  console.log(myUpdatedAssistant);\n}\n\nmain();"
+            },
+            "response": "{\n  \"id\": \"asst_123\",\n  \"object\": \"assistant\",\n  \"created_at\": 1699009709,\n  \"name\": \"HR Helper\",\n  \"description\": null,\n  \"model\": \"gpt-5\",\n  \"instructions\": \"You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.\",\n  \"tools\": [\n    {\n      \"type\": \"file_search\"\n    }\n  ],\n  \"tool_resources\": {\n    \"file_search\": {\n      \"vector_store_ids\": []\n    }\n  },\n  \"metadata\": {},\n  \"top_p\": 1.0,\n  \"temperature\": 1.0,\n  \"response_format\": \"auto\"\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "operationId": "deleteAssistant",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Delete an assistant.",
+        "deprecated": true,
+        "parameters": [
+          {
+            "in": "path",
+            "name": "assistant_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the assistant to delete."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeleteAssistantResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete assistant",
+          "group": "assistants",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/assistants/asst_abc123 \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -X DELETE\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nresponse = client.beta.assistants.delete(\"asst_abc123\")\nprint(response)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const response = await openai.beta.assistants.delete(\"asst_abc123\");\n\n  console.log(response);\n}\nmain();"
+            },
+            "response": "{\n  \"id\": \"asst_abc123\",\n  \"object\": \"assistant.deleted\",\n  \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/audio/speech": {
+      "post": {
+        "operationId": "createSpeech",
+        "tags": [
+          "Audio"
+        ],
+        "summary": "Generates audio from the input text.\n\nReturns the audio file content, or a stream of audio events.\n",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateSpeechRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "headers": {
+              "Transfer-Encoding": {
+                "schema": {
+                  "type": "string"
+                },
+                "description": "chunked"
+              }
+            },
+            "content": {
+              "application/octet-stream": {
+                "schema": {
+                  "type": "string",
+                  "format": "binary"
+                }
+              },
+              "text/event-stream": {
+                "schema": {
+                  "$ref": "#/components/schemas/CreateSpeechResponseStreamEvent"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/InferenceRateLimited"
+          },
+          "503": {
+            "$ref": "#/components/responses/InferenceServiceUnavailable"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create speech",
+          "group": "audio",
+          "examples": [
+            {
+              "title": "Default",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/audio/speech \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"model\": \"gpt-4o-mini-tts\",\n    \"input\": \"The quick brown fox jumped over the lazy dog.\",\n    \"voice\": \"alloy\"\n  }' \\\n  --output speech.mp3\n",
+                "python": "from pathlib import Path\nimport openai\n\nspeech_file_path = Path(__file__).parent / \"speech.mp3\"\nwith openai.audio.speech.with_streaming_response.create(\n  model=\"gpt-4o-mini-tts\",\n  voice=\"alloy\",\n  input=\"The quick brown fox jumped over the lazy dog.\"\n) as response:\n  response.stream_to_file(speech_file_path)\n",
+                "javascript": "import fs from \"fs\";\nimport path from \"path\";\nimport OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst speechFile = path.resolve(\"./speech.mp3\");\n\nasync function main() {\n  const mp3 = await openai.audio.speech.create({\n    model: \"gpt-4o-mini-tts\",\n    voice: \"alloy\",\n    input: \"Today is a wonderful day to build something people love!\",\n  });\n  console.log(speechFile);\n  const buffer = Buffer.from(await mp3.arrayBuffer());\n  await fs.promises.writeFile(speechFile, buffer);\n}\nmain();\n",
+                "csharp": "using System;\nusing System.IO;\n\nusing OpenAI.Audio;\n\nAudioClient client = new(\n    model: \"gpt-4o-mini-tts\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nBinaryData speech = client.GenerateSpeech(\n    text: \"The quick brown fox jumped over the lazy dog.\",\n    voice: GeneratedSpeechVoice.Alloy\n);\n\nusing FileStream stream = File.OpenWrite(\"speech.mp3\");\nspeech.ToStream().CopyTo(stream);\n"
+              }
+            },
+            {
+              "title": "SSE Stream Format",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/audio/speech \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"model\": \"gpt-4o-mini-tts\",\n    \"input\": \"The quick brown fox jumped over the lazy dog.\",\n    \"voice\": \"alloy\",\n    \"stream_format\": \"sse\"\n  }'\n"
+              }
+            }
+          ]
+        }
+      }
+    },
+    "/audio/transcriptions": {
+      "post": {
+        "operationId": "createTranscription",
+        "tags": [
+          "Audio"
+        ],
+        "summary": "Transcribes audio into the input language.\n\nReturns a transcription object in `json`, `diarized_json`, or `verbose_json`\nformat, or a stream of transcript events.\n",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateTranscriptionRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "oneOf": [
+                    {
+                      "$ref": "#/components/schemas/CreateTranscriptionResponseJson"
+                    },
+                    {
+                      "$ref": "#/components/schemas/CreateTranscriptionResponseDiarizedJson"
+                    },
+                    {
+                      "$ref": "#/components/schemas/CreateTranscriptionResponseVerboseJson"
+                    }
+                  ]
+                }
+              },
+              "text/event-stream": {
+                "schema": {
+                  "$ref": "#/components/schemas/CreateTranscriptionResponseStreamEvent"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/InferenceRateLimited"
+          },
+          "503": {
+            "$ref": "#/components/responses/InferenceServiceUnavailable"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create transcription",
+          "group": "audio",
+          "examples": [
+            {
+              "title": "Default",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/audio/transcriptions \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: multipart/form-data\" \\\n  -F file=\"@/path/to/file/audio.mp3\" \\\n  -F model=\"gpt-4o-transcribe\"\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\naudio_file = open(\"speech.mp3\", \"rb\")\ntranscript = client.audio.transcriptions.create(\n  model=\"gpt-4o-transcribe\",\n  file=audio_file\n)\n",
+                "javascript": "import fs from \"fs\";\nimport OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const transcription = await openai.audio.transcriptions.create({\n    file: fs.createReadStream(\"audio.mp3\"),\n    model: \"gpt-4o-transcribe\",\n  });\n\n  console.log(transcription.text);\n}\nmain();\n",
+                "csharp": "using System;\n\nusing OpenAI.Audio;\nstring audioFilePath = \"audio.mp3\";\n\nAudioClient client = new(\n    model: \"gpt-4o-transcribe\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nAudioTranscription transcription = client.TranscribeAudio(audioFilePath);\n\nConsole.WriteLine($\"{transcription.Text}\");\n"
+              },
+              "response": "{\n  \"text\": \"Imagine the wildest idea that you've ever had, and you're curious about how it might scale to something that's a 100, a 1,000 times bigger. This is a place where you can get to do that.\",\n  \"usage\": {\n    \"type\": \"tokens\",\n    \"input_tokens\": 14,\n    \"input_token_details\": {\n      \"text_tokens\": 0,\n      \"audio_tokens\": 14\n    },\n    \"output_tokens\": 45,\n    \"total_tokens\": 59\n  }\n}\n"
+            },
+            {
+              "title": "Diarization",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/audio/transcriptions \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: multipart/form-data\" \\\n  -F file=\"@/path/to/file/meeting.wav\" \\\n  -F model=\"gpt-4o-transcribe-diarize\" \\\n  -F response_format=\"diarized_json\" \\\n  -F chunking_strategy=auto \\\n  -F 'known_speaker_names[]=agent' \\\n  -F 'known_speaker_references[]=data:audio/wav;base64,AAA...'\n",
+                "python": "import base64\nfrom openai import OpenAI\n\nclient = OpenAI()\n\ndef to_data_url(path: str) -> str:\n  with open(path, \"rb\") as fh:\n    return \"data:audio/wav;base64,\" + base64.b64encode(fh.read()).decode(\"utf-8\")\n\nwith open(\"meeting.wav\", \"rb\") as audio_file:\n  transcript = client.audio.transcriptions.create(\n    model=\"gpt-4o-transcribe-diarize\",\n    file=audio_file,\n    response_format=\"diarized_json\",\n    chunking_strategy=\"auto\",\n    extra_body={\n      \"known_speaker_names\": [\"agent\"],\n      \"known_speaker_references\": [to_data_url(\"agent.wav\")],\n    },\n  )\n\nprint(transcript.segments)\n",
+                "javascript": "import fs from \"fs\";\nimport OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst speakerRef = fs.readFileSync(\"agent.wav\").toString(\"base64\");\n\nconst transcript = await openai.audio.transcriptions.create({\n  file: fs.createReadStream(\"meeting.wav\"),\n  model: \"gpt-4o-transcribe-diarize\",\n  response_format: \"diarized_json\",\n  chunking_strategy: \"auto\",\n  extra_body: {\n    known_speaker_names: [\"agent\"],\n    known_speaker_references: [`data:audio/wav;base64,${speakerRef}`],\n  },\n});\n\nconsole.log(transcript.segments);\n"
+              },
+              "response": "{\n  \"task\": \"transcribe\",\n  \"duration\": 27.4,\n  \"text\": \"Agent: Thanks for calling OpenAI support.\\nA: Hi, I'm trying to enable diarization.\\nAgent: Happy to walk you through the steps.\",\n  \"segments\": [\n    {\n      \"type\": \"transcript.text.segment\",\n      \"id\": \"seg_001\",\n      \"start\": 0.0,\n      \"end\": 4.7,\n      \"text\": \"Thanks for calling OpenAI support.\",\n      \"speaker\": \"agent\"\n    },\n    {\n      \"type\": \"transcript.text.segment\",\n      \"id\": \"seg_002\",\n      \"start\": 4.7,\n      \"end\": 11.8,\n      \"text\": \"Hi, I'm trying to enable diarization.\",\n      \"speaker\": \"A\"\n    },\n    {\n      \"type\": \"transcript.text.segment\",\n      \"id\": \"seg_003\",\n      \"start\": 12.1,\n      \"end\": 18.5,\n      \"text\": \"Happy to walk you through the steps.\",\n      \"speaker\": \"agent\"\n    }\n  ],\n  \"usage\": {\n    \"type\": \"duration\",\n    \"seconds\": 27\n  }\n}\n"
+            },
+            {
+              "title": "Streaming",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/audio/transcriptions \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: multipart/form-data\" \\\n  -F file=\"@/path/to/file/audio.mp3\" \\\n  -F model=\"gpt-4o-mini-transcribe\" \\\n  -F stream=true\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\naudio_file = open(\"speech.mp3\", \"rb\")\nstream = client.audio.transcriptions.create(\n  file=audio_file,\n  model=\"gpt-4o-mini-transcribe\",\n  stream=True\n)\n\nfor event in stream:\n  print(event)\n",
+                "javascript": "import fs from \"fs\";\nimport OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst stream = await openai.audio.transcriptions.create({\n  file: fs.createReadStream(\"audio.mp3\"),\n  model: \"gpt-4o-mini-transcribe\",\n  stream: true,\n});\n\nfor await (const event of stream) {\n  console.log(event);\n}\n"
+              },
+              "response": "data: {\"type\":\"transcript.text.delta\",\"delta\":\"I\",\"logprobs\":[{\"token\":\"I\",\"logprob\":-0.00007588794,\"bytes\":[73]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" see\",\"logprobs\":[{\"token\":\" see\",\"logprob\":-3.1281633e-7,\"bytes\":[32,115,101,101]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" skies\",\"logprobs\":[{\"token\":\" skies\",\"logprob\":-2.3392786e-6,\"bytes\":[32,115,107,105,101,115]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" of\",\"logprobs\":[{\"token\":\" of\",\"logprob\":-3.1281633e-7,\"bytes\":[32,111,102]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" blue\",\"logprobs\":[{\"token\":\" blue\",\"logprob\":-1.0280384e-6,\"bytes\":[32,98,108,117,101]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" and\",\"logprobs\":[{\"token\":\" and\",\"logprob\":-0.0005108566,\"bytes\":[32,97,110,100]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" clouds\",\"logprobs\":[{\"token\":\" clouds\",\"logprob\":-1.9361265e-7,\"bytes\":[32,99,108,111,117,100,115]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" of\",\"logprobs\":[{\"token\":\" of\",\"logprob\":-1.9361265e-7,\"bytes\":[32,111,102]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" white\",\"logprobs\":[{\"token\":\" white\",\"logprob\":-7.89631e-7,\"bytes\":[32,119,104,105,116,101]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\",\",\"logprobs\":[{\"token\":\",\",\"logprob\":-0.0014890312,\"bytes\":[44]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" the\",\"logprobs\":[{\"token\":\" the\",\"logprob\":-0.0110956915,\"bytes\":[32,116,104,101]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" bright\",\"logprobs\":[{\"token\":\" bright\",\"logprob\":0.0,\"bytes\":[32,98,114,105,103,104,116]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" blessed\",\"logprobs\":[{\"token\":\" blessed\",\"logprob\":-0.000045848617,\"bytes\":[32,98,108,101,115,115,101,100]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" days\",\"logprobs\":[{\"token\":\" days\",\"logprob\":-0.000010802739,\"bytes\":[32,100,97,121,115]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\",\",\"logprobs\":[{\"token\":\",\",\"logprob\":-0.00001700133,\"bytes\":[44]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" the\",\"logprobs\":[{\"token\":\" the\",\"logprob\":-0.0000118755715,\"bytes\":[32,116,104,101]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" dark\",\"logprobs\":[{\"token\":\" dark\",\"logprob\":-5.5122365e-7,\"bytes\":[32,100,97,114,107]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" sacred\",\"logprobs\":[{\"token\":\" sacred\",\"logprob\":-5.4385737e-6,\"bytes\":[32,115,97,99,114,101,100]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" nights\",\"logprobs\":[{\"token\":\" nights\",\"logprob\":-4.00813e-6,\"bytes\":[32,110,105,103,104,116,115]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\",\",\"logprobs\":[{\"token\":\",\",\"logprob\":-0.0036910512,\"bytes\":[44]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" and\",\"logprobs\":[{\"token\":\" and\",\"logprob\":-0.0031903093,\"bytes\":[32,97,110,100]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" I\",\"logprobs\":[{\"token\":\" I\",\"logprob\":-1.504853e-6,\"bytes\":[32,73]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" think\",\"logprobs\":[{\"token\":\" think\",\"logprob\":-4.3202e-7,\"bytes\":[32,116,104,105,110,107]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" to\",\"logprobs\":[{\"token\":\" to\",\"logprob\":-1.9361265e-7,\"bytes\":[32,116,111]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" myself\",\"logprobs\":[{\"token\":\" myself\",\"logprob\":-1.7432603e-6,\"bytes\":[32,109,121,115,101,108,102]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\",\",\"logprobs\":[{\"token\":\",\",\"logprob\":-0.29254505,\"bytes\":[44]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" what\",\"logprobs\":[{\"token\":\" what\",\"logprob\":-0.016815351,\"bytes\":[32,119,104,97,116]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" a\",\"logprobs\":[{\"token\":\" a\",\"logprob\":-3.1281633e-7,\"bytes\":[32,97]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" wonderful\",\"logprobs\":[{\"token\":\" wonderful\",\"logprob\":-2.1008714e-6,\"bytes\":[32,119,111,110,100,101,114,102,117,108]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\" world\",\"logprobs\":[{\"token\":\" world\",\"logprob\":-8.180258e-6,\"bytes\":[32,119,111,114,108,100]}]}\n\ndata: {\"type\":\"transcript.text.delta\",\"delta\":\".\",\"logprobs\":[{\"token\":\".\",\"logprob\":-0.014231676,\"bytes\":[46]}]}\n\ndata: {\"type\":\"transcript.text.done\",\"text\":\"I see skies of blue and clouds of white, the bright blessed days, the dark sacred nights, and I think to myself, what a wonderful world.\",\"logprobs\":[{\"token\":\"I\",\"logprob\":-0.00007588794,\"bytes\":[73]},{\"token\":\" see\",\"logprob\":-3.1281633e-7,\"bytes\":[32,115,101,101]},{\"token\":\" skies\",\"logprob\":-2.3392786e-6,\"bytes\":[32,115,107,105,101,115]},{\"token\":\" of\",\"logprob\":-3.1281633e-7,\"bytes\":[32,111,102]},{\"token\":\" blue\",\"logprob\":-1.0280384e-6,\"bytes\":[32,98,108,117,101]},{\"token\":\" and\",\"logprob\":-0.0005108566,\"bytes\":[32,97,110,100]},{\"token\":\" clouds\",\"logprob\":-1.9361265e-7,\"bytes\":[32,99,108,111,117,100,115]},{\"token\":\" of\",\"logprob\":-1.9361265e-7,\"bytes\":[32,111,102]},{\"token\":\" white\",\"logprob\":-7.89631e-7,\"bytes\":[32,119,104,105,116,101]},{\"token\":\",\",\"logprob\":-0.0014890312,\"bytes\":[44]},{\"token\":\" the\",\"logprob\":-0.0110956915,\"bytes\":[32,116,104,101]},{\"token\":\" bright\",\"logprob\":0.0,\"bytes\":[32,98,114,105,103,104,116]},{\"token\":\" blessed\",\"logprob\":-0.000045848617,\"bytes\":[32,98,108,101,115,115,101,100]},{\"token\":\" days\",\"logprob\":-0.000010802739,\"bytes\":[32,100,97,121,115]},{\"token\":\",\",\"logprob\":-0.00001700133,\"bytes\":[44]},{\"token\":\" the\",\"logprob\":-0.0000118755715,\"bytes\":[32,116,104,101]},{\"token\":\" dark\",\"logprob\":-5.5122365e-7,\"bytes\":[32,100,97,114,107]},{\"token\":\" sacred\",\"logprob\":-5.4385737e-6,\"bytes\":[32,115,97,99,114,101,100]},{\"token\":\" nights\",\"logprob\":-4.00813e-6,\"bytes\":[32,110,105,103,104,116,115]},{\"token\":\",\",\"logprob\":-0.0036910512,\"bytes\":[44]},{\"token\":\" and\",\"logprob\":-0.0031903093,\"bytes\":[32,97,110,100]},{\"token\":\" I\",\"logprob\":-1.504853e-6,\"bytes\":[32,73]},{\"token\":\" think\",\"logprob\":-4.3202e-7,\"bytes\":[32,116,104,105,110,107]},{\"token\":\" to\",\"logprob\":-1.9361265e-7,\"bytes\":[32,116,111]},{\"token\":\" myself\",\"logprob\":-1.7432603e-6,\"bytes\":[32,109,121,115,101,108,102]},{\"token\":\",\",\"logprob\":-0.29254505,\"bytes\":[44]},{\"token\":\" what\",\"logprob\":-0.016815351,\"bytes\":[32,119,104,97,116]},{\"token\":\" a\",\"logprob\":-3.1281633e-7,\"bytes\":[32,97]},{\"token\":\" wonderful\",\"logprob\":-2.1008714e-6,\"bytes\":[32,119,111,110,100,101,114,102,117,108]},{\"token\":\" world\",\"logprob\":-8.180258e-6,\"bytes\":[32,119,111,114,108,100]},{\"token\":\".\",\"logprob\":-0.014231676,\"bytes\":[46]}],\"usage\":{\"input_tokens\":14,\"input_token_details\":{\"text_tokens\":0,\"audio_tokens\":14},\"output_tokens\":45,\"total_tokens\":59}}\n"
+            },
+            {
+              "title": "Logprobs",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/audio/transcriptions \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: multipart/form-data\" \\\n  -F file=\"@/path/to/file/audio.mp3\" \\\n  -F \"include[]=logprobs\" \\\n  -F model=\"gpt-4o-transcribe\" \\\n  -F response_format=\"json\"\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\naudio_file = open(\"speech.mp3\", \"rb\")\ntranscript = client.audio.transcriptions.create(\n  file=audio_file,\n  model=\"gpt-4o-transcribe\",\n  response_format=\"json\",\n  include=[\"logprobs\"]\n)\n\nprint(transcript)\n",
+                "javascript": "import fs from \"fs\";\nimport OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const transcription = await openai.audio.transcriptions.create({\n    file: fs.createReadStream(\"audio.mp3\"),\n    model: \"gpt-4o-transcribe\",\n    response_format: \"json\",\n    include: [\"logprobs\"]\n  });\n\n  console.log(transcription);\n}\nmain();\n"
+              },
+              "response": "{\n  \"text\": \"Hey, my knee is hurting and I want to see the doctor tomorrow ideally.\",\n  \"logprobs\": [\n    { \"token\": \"Hey\", \"logprob\": -1.0415299, \"bytes\": [72, 101, 121] },\n    { \"token\": \",\", \"logprob\": -9.805982e-5, \"bytes\": [44] },\n    { \"token\": \" my\", \"logprob\": -0.00229799, \"bytes\": [32, 109, 121] },\n    {\n      \"token\": \" knee\",\n      \"logprob\": -4.7159858e-5,\n      \"bytes\": [32, 107, 110, 101, 101]\n    },\n    { \"token\": \" is\", \"logprob\": -0.043909557, \"bytes\": [32, 105, 115] },\n    {\n      \"token\": \" hurting\",\n      \"logprob\": -1.1041146e-5,\n      \"bytes\": [32, 104, 117, 114, 116, 105, 110, 103]\n    },\n    { \"token\": \" and\", \"logprob\": -0.011076359, \"bytes\": [32, 97, 110, 100] },\n    { \"token\": \" I\", \"logprob\": -5.3193703e-6, \"bytes\": [32, 73] },\n    {\n      \"token\": \" want\",\n      \"logprob\": -0.0017156356,\n      \"bytes\": [32, 119, 97, 110, 116]\n    },\n    { \"token\": \" to\", \"logprob\": -7.89631e-7, \"bytes\": [32, 116, 111] },\n    { \"token\": \" see\", \"logprob\": -5.5122365e-7, \"bytes\": [32, 115, 101, 101] },\n    { \"token\": \" the\", \"logprob\": -0.0040786397, \"bytes\": [32, 116, 104, 101] },\n    {\n      \"token\": \" doctor\",\n      \"logprob\": -2.3392786e-6,\n      \"bytes\": [32, 100, 111, 99, 116, 111, 114]\n    },\n    {\n      \"token\": \" tomorrow\",\n      \"logprob\": -7.89631e-7,\n      \"bytes\": [32, 116, 111, 109, 111, 114, 114, 111, 119]\n    },\n    {\n      \"token\": \" ideally\",\n      \"logprob\": -0.5800861,\n      \"bytes\": [32, 105, 100, 101, 97, 108, 108, 121]\n    },\n    { \"token\": \".\", \"logprob\": -0.00011093382, \"bytes\": [46] }\n  ],\n  \"usage\": {\n    \"type\": \"tokens\",\n    \"input_tokens\": 14,\n    \"input_token_details\": {\n      \"text_tokens\": 0,\n      \"audio_tokens\": 14\n    },\n    \"output_tokens\": 45,\n    \"total_tokens\": 59\n  }\n}\n"
+            },
+            {
+              "title": "Word timestamps",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/audio/transcriptions \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: multipart/form-data\" \\\n  -F file=\"@/path/to/file/audio.mp3\" \\\n  -F \"timestamp_granularities[]=word\" \\\n  -F model=\"whisper-1\" \\\n  -F response_format=\"verbose_json\"\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\naudio_file = open(\"speech.mp3\", \"rb\")\ntranscript = client.audio.transcriptions.create(\n  file=audio_file,\n  model=\"whisper-1\",\n  response_format=\"verbose_json\",\n  timestamp_granularities=[\"word\"]\n)\n\nprint(transcript.words)\n",
+                "javascript": "import fs from \"fs\";\nimport OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const transcription = await openai.audio.transcriptions.create({\n    file: fs.createReadStream(\"audio.mp3\"),\n    model: \"whisper-1\",\n    response_format: \"verbose_json\",\n    timestamp_granularities: [\"word\"]\n  });\n\n  console.log(transcription.text);\n}\nmain();\n",
+                "csharp": "using System;\n\nusing OpenAI.Audio;\n\nstring audioFilePath = \"audio.mp3\";\n\nAudioClient client = new(\n    model: \"whisper-1\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nAudioTranscriptionOptions options = new()\n{\n    ResponseFormat = AudioTranscriptionFormat.Verbose,\n    TimestampGranularities = AudioTimestampGranularities.Word,\n};\n\nAudioTranscription transcription = client.TranscribeAudio(audioFilePath, options);\n\nConsole.WriteLine($\"{transcription.Text}\");\n"
+              },
+              "response": "{\n  \"task\": \"transcribe\",\n  \"language\": \"english\",\n  \"duration\": 8.470000267028809,\n  \"text\": \"The beach was a popular spot on a hot summer day. People were swimming in the ocean, building sandcastles, and playing beach volleyball.\",\n  \"words\": [\n    {\n      \"word\": \"The\",\n      \"start\": 0.0,\n      \"end\": 0.23999999463558197\n    },\n    ...\n    {\n      \"word\": \"volleyball\",\n      \"start\": 7.400000095367432,\n      \"end\": 7.900000095367432\n    }\n  ],\n  \"usage\": {\n    \"type\": \"duration\",\n    \"seconds\": 9\n  }\n}\n"
+            },
+            {
+              "title": "Segment timestamps",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/audio/transcriptions \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: multipart/form-data\" \\\n  -F file=\"@/path/to/file/audio.mp3\" \\\n  -F \"timestamp_granularities[]=segment\" \\\n  -F model=\"whisper-1\" \\\n  -F response_format=\"verbose_json\"\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\naudio_file = open(\"speech.mp3\", \"rb\")\ntranscript = client.audio.transcriptions.create(\n  file=audio_file,\n  model=\"whisper-1\",\n  response_format=\"verbose_json\",\n  timestamp_granularities=[\"segment\"]\n)\n\nprint(transcript.words)\n",
+                "javascript": "import fs from \"fs\";\nimport OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const transcription = await openai.audio.transcriptions.create({\n    file: fs.createReadStream(\"audio.mp3\"),\n    model: \"whisper-1\",\n    response_format: \"verbose_json\",\n    timestamp_granularities: [\"segment\"]\n  });\n\n  console.log(transcription.text);\n}\nmain();\n",
+                "csharp": "using System;\n\nusing OpenAI.Audio;\n\nstring audioFilePath = \"audio.mp3\";\n\nAudioClient client = new(\n    model: \"whisper-1\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nAudioTranscriptionOptions options = new()\n{\n    ResponseFormat = AudioTranscriptionFormat.Verbose,\n    TimestampGranularities = AudioTimestampGranularities.Segment,\n};\n\nAudioTranscription transcription = client.TranscribeAudio(audioFilePath, options);\n\nConsole.WriteLine($\"{transcription.Text}\");\n"
+              },
+              "response": "{\n  \"task\": \"transcribe\",\n  \"language\": \"english\",\n  \"duration\": 8.470000267028809,\n  \"text\": \"The beach was a popular spot on a hot summer day. People were swimming in the ocean, building sandcastles, and playing beach volleyball.\",\n  \"segments\": [\n    {\n      \"id\": 0,\n      \"seek\": 0,\n      \"start\": 0.0,\n      \"end\": 3.319999933242798,\n      \"text\": \" The beach was a popular spot on a hot summer day.\",\n      \"tokens\": [\n        50364, 440, 7534, 390, 257, 3743, 4008, 322, 257, 2368, 4266, 786, 13, 50530\n      ],\n      \"temperature\": 0.0,\n      \"avg_logprob\": -0.2860786020755768,\n      \"compression_ratio\": 1.2363636493682861,\n      \"no_speech_prob\": 0.00985979475080967\n    },\n    ...\n  ],\n  \"usage\": {\n    \"type\": \"duration\",\n    \"seconds\": 9\n  }\n}\n"
+            }
+          ]
+        }
+      }
+    },
+    "/audio/translations": {
+      "post": {
+        "operationId": "createTranslation",
+        "tags": [
+          "Audio"
+        ],
+        "summary": "Translates audio into English.",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateTranslationRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "oneOf": [
+                    {
+                      "$ref": "#/components/schemas/CreateTranslationResponseJson"
+                    },
+                    {
+                      "$ref": "#/components/schemas/CreateTranslationResponseVerboseJson"
+                    }
+                  ]
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/InferenceRateLimited"
+          },
+          "503": {
+            "$ref": "#/components/responses/InferenceServiceUnavailable"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create translation",
+          "group": "audio",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/audio/translations \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: multipart/form-data\" \\\n  -F file=\"@/path/to/file/german.m4a\" \\\n  -F model=\"whisper-1\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\naudio_file = open(\"speech.mp3\", \"rb\")\ntranscript = client.audio.translations.create(\n  model=\"whisper-1\",\n  file=audio_file\n)\n",
+              "javascript": "import fs from \"fs\";\nimport OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n    const translation = await openai.audio.translations.create({\n        file: fs.createReadStream(\"speech.mp3\"),\n        model: \"whisper-1\",\n    });\n\n    console.log(translation.text);\n}\nmain();\n",
+              "csharp": "using System;\n\nusing OpenAI.Audio;\n\nstring audioFilePath = \"audio.mp3\";\n\nAudioClient client = new(\n    model: \"whisper-1\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nAudioTranscription transcription = client.TranscribeAudio(audioFilePath);\n\nConsole.WriteLine($\"{transcription.Text}\");\n"
+            },
+            "response": "{\n  \"text\": \"Hello, my name is Wolfgang and I come from Germany. Where are you heading today?\"\n}\n"
+          }
+        }
+      }
+    },
+    "/audio/voice_consents": {
+      "post": {
+        "operationId": "createVoiceConsent",
+        "tags": [
+          "Audio"
+        ],
+        "summary": "Upload a voice consent recording.",
+        "description": "Upload a consent recording that authorizes creation of a custom voice.\n\nSee the [custom voices guide](https://developers.openai.com/api/docs/guides/text-to-speech#custom-voices) for requirements and best practices. Custom voices are limited to eligible customers.\n",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateVoiceConsentRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VoiceConsentResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create voice consent",
+          "group": "audio",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/audio/voice_consents \\\n  -X POST \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -F \"name=John Doe\" \\\n  -F \"language=en-US\" \\\n  -F \"recording=@$HOME/consent_recording.wav;type=audio/x-wav\"\n"
+            }
+          }
+        }
+      },
+      "get": {
+        "operationId": "listVoiceConsents",
+        "tags": [
+          "Audio"
+        ],
+        "summary": "Returns a list of voice consent recordings.",
+        "description": "List consent recordings available to your organization for creating custom voices.\n\nSee the [custom voices guide](https://developers.openai.com/api/docs/guides/text-to-speech#custom-voices). Custom voices are limited to eligible customers.\n",
+        "parameters": [
+          {
+            "in": "query",
+            "name": "after",
+            "required": false,
+            "schema": {
+              "type": "string"
+            },
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n"
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VoiceConsentListResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List voice consents",
+          "group": "audio",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/audio/voice_consents?limit=20 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n"
+            }
+          }
+        }
+      }
+    },
+    "/audio/voice_consents/{consent_id}": {
+      "get": {
+        "operationId": "getVoiceConsent",
+        "tags": [
+          "Audio"
+        ],
+        "summary": "Retrieves a voice consent recording.",
+        "description": "Retrieve consent recording metadata used for creating custom voices.\n\nSee the [custom voices guide](https://developers.openai.com/api/docs/guides/text-to-speech#custom-voices). Custom voices are limited to eligible customers.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "consent_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the consent recording to retrieve."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VoiceConsentResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve voice consent",
+          "group": "audio",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/audio/voice_consents/cons_1234 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n"
+            }
+          }
+        }
+      },
+      "post": {
+        "operationId": "updateVoiceConsent",
+        "tags": [
+          "Audio"
+        ],
+        "summary": "Updates a voice consent recording (metadata only).",
+        "description": "Update consent recording metadata used for creating custom voices. This endpoint updates metadata only and does not replace the underlying audio.\n\nSee the [custom voices guide](https://developers.openai.com/api/docs/guides/text-to-speech#custom-voices). Custom voices are limited to eligible customers.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "consent_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the consent recording to update."
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/UpdateVoiceConsentRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VoiceConsentResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update voice consent",
+          "group": "audio",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/audio/voice_consents/cons_1234 \\\n  -X POST \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"name\": \"John Doe\"\n  }'\n"
+            }
+          }
+        }
+      },
+      "delete": {
+        "operationId": "deleteVoiceConsent",
+        "tags": [
+          "Audio"
+        ],
+        "summary": "Deletes a voice consent recording.",
+        "description": "Delete a consent recording that was uploaded for creating custom voices.\n\nSee the [custom voices guide](https://developers.openai.com/api/docs/guides/text-to-speech#custom-voices). Custom voices are limited to eligible customers.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "consent_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the consent recording to delete."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VoiceConsentDeletedResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete voice consent",
+          "group": "audio",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/audio/voice_consents/cons_1234 \\\n  -X DELETE \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n"
+            }
+          }
+        }
+      }
+    },
+    "/audio/voices": {
+      "post": {
+        "operationId": "createVoice",
+        "tags": [
+          "Audio"
+        ],
+        "summary": "Creates a custom voice.",
+        "description": "Create a custom voice you can use for audio output (for example, in Text-to-Speech and the Realtime API). This requires an audio sample and a previously uploaded consent recording.\n\nSee the [custom voices guide](https://developers.openai.com/api/docs/guides/text-to-speech#custom-voices) for requirements and best practices. Custom voices are limited to eligible customers.\n",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateVoiceRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VoiceResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create voice",
+          "group": "audio",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/audio/voices \\\n  -X POST \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -F \"name=My new voice\" \\\n  -F \"consent=cons_1234\" \\\n  -F \"audio_sample=@$HOME/audio_sample.wav;type=audio/x-wav\"\n"
+            }
+          }
+        }
+      }
+    },
+    "/batches": {
+      "post": {
+        "summary": "Creates and executes a batch from an uploaded file of requests",
+        "operationId": "createBatch",
+        "tags": [
+          "Batch"
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateBatchRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Batch created successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Batch"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create batch",
+          "group": "batch",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/batches \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"input_file_id\": \"file-abc123\",\n    \"endpoint\": \"/v1/chat/completions\",\n    \"completion_window\": \"24h\"\n  }'\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.batches.create(\n  input_file_id=\"file-abc123\",\n  endpoint=\"/v1/chat/completions\",\n  completion_window=\"24h\"\n)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const batch = await openai.batches.create({\n    input_file_id: \"file-abc123\",\n    endpoint: \"/v1/chat/completions\",\n    completion_window: \"24h\"\n  });\n\n  console.log(batch);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"id\": \"batch_abc123\",\n  \"object\": \"batch\",\n  \"endpoint\": \"/v1/chat/completions\",\n  \"errors\": null,\n  \"input_file_id\": \"file-abc123\",\n  \"completion_window\": \"24h\",\n  \"status\": \"validating\",\n  \"output_file_id\": null,\n  \"error_file_id\": null,\n  \"created_at\": 1711471533,\n  \"in_progress_at\": null,\n  \"expires_at\": null,\n  \"finalizing_at\": null,\n  \"completed_at\": null,\n  \"failed_at\": null,\n  \"expired_at\": null,\n  \"cancelling_at\": null,\n  \"cancelled_at\": null,\n  \"request_counts\": {\n    \"total\": 0,\n    \"completed\": 0,\n    \"failed\": 0\n  },\n  \"metadata\": {\n    \"customer_id\": \"user_123456789\",\n    \"batch_description\": \"Nightly eval job\",\n  }\n}\n"
+          }
+        }
+      },
+      "get": {
+        "operationId": "listBatches",
+        "tags": [
+          "Batch"
+        ],
+        "summary": "List your organization's batches.",
+        "parameters": [
+          {
+            "in": "query",
+            "name": "after",
+            "required": false,
+            "schema": {
+              "type": "string"
+            },
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n"
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Batch listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ListBatchesResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List batches",
+          "group": "batch",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/batches?limit=2 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.batches.list()\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const list = await openai.batches.list();\n\n  for await (const batch of list) {\n    console.log(batch);\n  }\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"id\": \"batch_abc123\",\n      \"object\": \"batch\",\n      \"endpoint\": \"/v1/chat/completions\",\n      \"errors\": null,\n      \"input_file_id\": \"file-abc123\",\n      \"completion_window\": \"24h\",\n      \"status\": \"completed\",\n      \"output_file_id\": \"file-cvaTdG\",\n      \"error_file_id\": \"file-HOWS94\",\n      \"created_at\": 1711471533,\n      \"in_progress_at\": 1711471538,\n      \"expires_at\": 1711557933,\n      \"finalizing_at\": 1711493133,\n      \"completed_at\": 1711493163,\n      \"failed_at\": null,\n      \"expired_at\": null,\n      \"cancelling_at\": null,\n      \"cancelled_at\": null,\n      \"request_counts\": {\n        \"total\": 100,\n        \"completed\": 95,\n        \"failed\": 5\n      },\n      \"metadata\": {\n        \"customer_id\": \"user_123456789\",\n        \"batch_description\": \"Nightly job\",\n      }\n    },\n    { ... },\n  ],\n  \"first_id\": \"batch_abc123\",\n  \"last_id\": \"batch_abc456\",\n  \"has_more\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/batches/{batch_id}": {
+      "get": {
+        "operationId": "retrieveBatch",
+        "tags": [
+          "Batch"
+        ],
+        "summary": "Retrieves a batch.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "batch_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the batch to retrieve."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Batch retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Batch"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve batch",
+          "group": "batch",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/batches/batch_abc123 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.batches.retrieve(\"batch_abc123\")\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const batch = await openai.batches.retrieve(\"batch_abc123\");\n\n  console.log(batch);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"id\": \"batch_abc123\",\n  \"object\": \"batch\",\n  \"endpoint\": \"/v1/completions\",\n  \"errors\": null,\n  \"input_file_id\": \"file-abc123\",\n  \"completion_window\": \"24h\",\n  \"status\": \"completed\",\n  \"output_file_id\": \"file-cvaTdG\",\n  \"error_file_id\": \"file-HOWS94\",\n  \"created_at\": 1711471533,\n  \"in_progress_at\": 1711471538,\n  \"expires_at\": 1711557933,\n  \"finalizing_at\": 1711493133,\n  \"completed_at\": 1711493163,\n  \"failed_at\": null,\n  \"expired_at\": null,\n  \"cancelling_at\": null,\n  \"cancelled_at\": null,\n  \"request_counts\": {\n    \"total\": 100,\n    \"completed\": 95,\n    \"failed\": 5\n  },\n  \"metadata\": {\n    \"customer_id\": \"user_123456789\",\n    \"batch_description\": \"Nightly eval job\",\n  }\n}\n"
+          }
+        }
+      }
+    },
+    "/batches/{batch_id}/cancel": {
+      "post": {
+        "operationId": "cancelBatch",
+        "tags": [
+          "Batch"
+        ],
+        "summary": "Cancels an in-progress batch. The batch will be in status `cancelling` for up to 10 minutes, before changing to `cancelled`, where it will have partial results (if any) available in the output file.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "batch_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the batch to cancel."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Batch is cancelling. Returns the cancelling batch's details.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Batch"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Cancel batch",
+          "group": "batch",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/batches/batch_abc123/cancel \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -X POST\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.batches.cancel(\"batch_abc123\")\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const batch = await openai.batches.cancel(\"batch_abc123\");\n\n  console.log(batch);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"id\": \"batch_abc123\",\n  \"object\": \"batch\",\n  \"endpoint\": \"/v1/chat/completions\",\n  \"errors\": null,\n  \"input_file_id\": \"file-abc123\",\n  \"completion_window\": \"24h\",\n  \"status\": \"cancelling\",\n  \"output_file_id\": null,\n  \"error_file_id\": null,\n  \"created_at\": 1711471533,\n  \"in_progress_at\": 1711471538,\n  \"expires_at\": 1711557933,\n  \"finalizing_at\": null,\n  \"completed_at\": null,\n  \"failed_at\": null,\n  \"expired_at\": null,\n  \"cancelling_at\": 1711475133,\n  \"cancelled_at\": null,\n  \"request_counts\": {\n    \"total\": 100,\n    \"completed\": 23,\n    \"failed\": 1\n  },\n  \"metadata\": {\n    \"customer_id\": \"user_123456789\",\n    \"batch_description\": \"Nightly eval job\",\n  }\n}\n"
+          }
+        }
+      }
+    },
+    "/chat/completions": {
+      "get": {
+        "operationId": "listChatCompletions",
+        "tags": [
+          "Chat"
+        ],
+        "summary": "List stored Chat Completions. Only Chat Completions that have been stored\nwith the `store` parameter set to `true` will be returned.\n",
+        "parameters": [
+          {
+            "name": "model",
+            "in": "query",
+            "description": "The model used to generate the Chat Completions.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "metadata",
+            "in": "query",
+            "description": "A list of metadata keys to filter the Chat Completions by. Example:\n\n`metadata[key1]=value1&metadata[key2]=value2`\n",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/Metadata"
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Identifier for the last chat completion from the previous pagination request.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Number of Chat Completions to retrieve.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order for Chat Completions by timestamp. Use `asc` for ascending order or `desc` for descending order. Defaults to `asc`.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "asc",
+                "desc"
+              ],
+              "default": "asc"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A list of Chat Completions",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ChatCompletionList"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List Chat Completions",
+          "group": "chat",
+          "path": "list",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/chat/completions \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\ncompletions = client.chat.completions.list()\nprint(completions)\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\": \"chat.completion\",\n      \"id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2\",\n      \"model\": \"gpt-6-astra\",\n      \"created\": 1738960610,\n      \"request_id\": \"req_ded8ab984ec4bf840f37566c1011c417\",\n      \"tool_choice\": null,\n      \"usage\": {\n        \"total_tokens\": 31,\n        \"completion_tokens\": 18,\n        \"prompt_tokens\": 13\n      },\n      \"seed\": 4944116822809979520,\n      \"top_p\": 1.0,\n      \"temperature\": 1.0,\n      \"presence_penalty\": 0.0,\n      \"frequency_penalty\": 0.0,\n      \"system_fingerprint\": \"fp_50cad350e4\",\n      \"input_user\": null,\n      \"service_tier\": \"default\",\n      \"tools\": null,\n      \"metadata\": {},\n      \"choices\": [\n        {\n          \"index\": 0,\n          \"message\": {\n            \"content\": \"Mind of circuits hum,  \\nLearning patterns in silence—  \\nFuture's quiet spark.\",\n            \"role\": \"assistant\",\n            \"tool_calls\": null,\n            \"function_call\": null\n          },\n          \"finish_reason\": \"stop\",\n          \"logprobs\": null\n        }\n      ],\n      \"response_format\": null\n    }\n  ],\n  \"first_id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2\",\n  \"last_id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      },
+      "post": {
+        "operationId": "createChatCompletion",
+        "tags": [
+          "Chat"
+        ],
+        "summary": "**Starting a new project?** We recommend trying [Responses](https://developers.openai.com/api/reference/resources/responses)\nto take advantage of the latest OpenAI platform features. Compare\n[Chat Completions with Responses](https://developers.openai.com/api/docs/guides/migrate-to-responses?api-mode=responses).\n\n---\n\nCreates a model response for the given chat conversation. Learn more in the\n[text generation](https://developers.openai.com/api/docs/guides/text), [vision](https://developers.openai.com/api/docs/guides/images-vision),\nand [audio](https://developers.openai.com/api/docs/guides/audio) guides.\n\nParameter support can differ depending on the model used to generate the\nresponse, particularly for newer reasoning models. Parameters that are only\nsupported for reasoning models are noted below. For the current state of\nunsupported parameters in reasoning models,\n[refer to the reasoning guide](https://developers.openai.com/api/docs/guides/reasoning).\n\nReturns a chat completion object, or a streamed sequence of chat completion\nchunk objects if the request is streamed.\n",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateChatCompletionRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/CreateChatCompletionResponse"
+                }
+              },
+              "text/event-stream": {
+                "schema": {
+                  "$ref": "#/components/schemas/CreateChatCompletionStreamResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/InferenceRateLimited"
+          },
+          "503": {
+            "$ref": "#/components/responses/InferenceServiceUnavailable"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create chat completion",
+          "group": "chat",
+          "path": "create",
+          "examples": [
+            {
+              "title": "Default",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/chat/completions \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-6-astra\",\n    \"messages\": [\n      {\n        \"role\": \"developer\",\n        \"content\": \"You are a helpful assistant.\"\n      },\n      {\n        \"role\": \"user\",\n        \"content\": \"Hello!\"\n      }\n    ]\n  }'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\ncompletion = client.chat.completions.create(\n  model=\"gpt-6-astra\",\n  messages=[\n    {\"role\": \"developer\", \"content\": \"You are a helpful assistant.\"},\n    {\"role\": \"user\", \"content\": \"Hello!\"}\n  ]\n)\n\nprint(completion.choices[0].message)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const completion = await openai.chat.completions.create({\n    messages: [{ role: \"developer\", content: \"You are a helpful assistant.\" }],\n    model: \"gpt-6-astra\",\n    store: true,\n  });\n\n  console.log(completion.choices[0]);\n}\n\nmain();\n",
+                "csharp": "using System;\nusing System.Collections.Generic;\n\nusing OpenAI.Chat;\n\nChatClient client = new(\n    model: \"gpt-6-astra\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nList<ChatMessage> messages =\n[\n    new SystemChatMessage(\"You are a helpful assistant.\"),\n    new UserChatMessage(\"Hello!\")\n];\n\nChatCompletion completion = client.CompleteChat(messages);\n\nConsole.WriteLine(completion.Content[0].Text);\n"
+              },
+              "response": "{\n  \"id\": \"chatcmpl-B9MBs8CjcvOU2jLn4n570S5qMJKcT\",\n  \"object\": \"chat.completion\",\n  \"created\": 1741569952,\n  \"model\": \"gpt-6-astra\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"Hello! How can I assist you today?\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 19,\n    \"completion_tokens\": 10,\n    \"total_tokens\": 29,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\": \"default\"\n}\n"
+            },
+            {
+              "title": "Image input",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/chat/completions \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-6-astra\",\n    \"messages\": [\n      {\n        \"role\": \"user\",\n        \"content\": [\n          {\n            \"type\": \"text\",\n            \"text\": \"What is in this image?\"\n          },\n          {\n            \"type\": \"image_url\",\n            \"image_url\": {\n              \"url\": \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\"\n            }\n          }\n        ]\n      }\n    ],\n    \"max_tokens\": 300\n  }'\n",
+                "python": "from openai import OpenAI\n\nclient = OpenAI()\n\nresponse = client.chat.completions.create(\n    model=\"gpt-6-astra\",\n    messages=[\n        {\n            \"role\": \"user\",\n            \"content\": [\n                {\"type\": \"text\", \"text\": \"What's in this image?\"},\n                {\n                    \"type\": \"image_url\",\n                    \"image_url\": {\n                        \"url\": \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\",\n                    }\n                },\n            ],\n        }\n    ],\n    max_tokens=300,\n)\n\nprint(response.choices[0])\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const response = await openai.chat.completions.create({\n    model: \"gpt-6-astra\",\n    messages: [\n      {\n        role: \"user\",\n        content: [\n          { type: \"text\", text: \"What's in this image?\" },\n          {\n            type: \"image_url\",\n            image_url: {\n              \"url\": \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\",\n            },\n          }\n        ],\n      },\n    ],\n  });\n  console.log(response.choices[0]);\n}\nmain();\n",
+                "csharp": "using System;\nusing System.Collections.Generic;\n\nusing OpenAI.Chat;\n\nChatClient client = new(\n    model: \"gpt-6-astra\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nList<ChatMessage> messages =\n[\n    new UserChatMessage(\n    [\n        ChatMessageContentPart.CreateTextPart(\"What's in this image?\"),\n        ChatMessageContentPart.CreateImagePart(new Uri(\"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\"))\n    ])\n];\n\nChatCompletion completion = client.CompleteChat(messages);\n\nConsole.WriteLine(completion.Content[0].Text);\n"
+              },
+              "response": "{\n  \"id\": \"chatcmpl-B9MHDbslfkBeAs8l4bebGdFOJ6PeG\",\n  \"object\": \"chat.completion\",\n  \"created\": 1741570283,\n  \"model\": \"gpt-6-astra\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"The image shows a wooden boardwalk path running through a lush green field or meadow. The sky is bright blue with some scattered clouds, giving the scene a serene and peaceful atmosphere. Trees and shrubs are visible in the background.\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 1117,\n    \"completion_tokens\": 46,\n    \"total_tokens\": 1163,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\": \"default\"\n}\n"
+            },
+            {
+              "title": "Streaming",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/chat/completions \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-6-astra\",\n    \"messages\": [\n      {\n        \"role\": \"developer\",\n        \"content\": \"You are a helpful assistant.\"\n      },\n      {\n        \"role\": \"user\",\n        \"content\": \"Hello!\"\n      }\n    ],\n    \"stream\": true\n  }'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\ncompletion = client.chat.completions.create(\n  model=\"gpt-6-astra\",\n  messages=[\n    {\"role\": \"developer\", \"content\": \"You are a helpful assistant.\"},\n    {\"role\": \"user\", \"content\": \"Hello!\"}\n  ],\n  stream=True\n)\n\nfor chunk in completion:\n  print(chunk.choices[0].delta)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const completion = await openai.chat.completions.create({\n    model: \"gpt-6-astra\",\n    messages: [\n      {\"role\": \"developer\", \"content\": \"You are a helpful assistant.\"},\n      {\"role\": \"user\", \"content\": \"Hello!\"}\n    ],\n    stream: true,\n  });\n\n  for await (const chunk of completion) {\n    console.log(chunk.choices[0].delta.content);\n  }\n}\n\nmain();\n",
+                "csharp": "using System;\nusing System.ClientModel;\nusing System.Collections.Generic;\nusing System.Threading.Tasks;\n\nusing OpenAI.Chat;\n\nChatClient client = new(\n    model: \"gpt-6-astra\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nList<ChatMessage> messages =\n[\n    new SystemChatMessage(\"You are a helpful assistant.\"),\n    new UserChatMessage(\"Hello!\")\n];\n\nAsyncCollectionResult<StreamingChatCompletionUpdate> completionUpdates = client.CompleteChatStreamingAsync(messages);\n\nawait foreach (StreamingChatCompletionUpdate completionUpdate in completionUpdates)\n{\n    if (completionUpdate.ContentUpdate.Count > 0)\n    {\n        Console.Write(completionUpdate.ContentUpdate[0].Text);\n    }\n}\n"
+              },
+              "response": "{\"id\":\"chatcmpl-123\",\"object\":\"chat.completion.chunk\",\"created\":1694268190,\"model\":\"gpt-6-astra\", \"system_fingerprint\": \"fp_44709d6fcb\", \"choices\":[{\"index\":0,\"delta\":{\"role\":\"assistant\",\"content\":\"\"},\"logprobs\":null,\"finish_reason\":null}]}\n\n{\"id\":\"chatcmpl-123\",\"object\":\"chat.completion.chunk\",\"created\":1694268190,\"model\":\"gpt-6-astra\", \"system_fingerprint\": \"fp_44709d6fcb\", \"choices\":[{\"index\":0,\"delta\":{\"content\":\"Hello\"},\"logprobs\":null,\"finish_reason\":null}]}\n\n....\n\n{\"id\":\"chatcmpl-123\",\"object\":\"chat.completion.chunk\",\"created\":1694268190,\"model\":\"gpt-6-astra\", \"system_fingerprint\": \"fp_44709d6fcb\", \"choices\":[{\"index\":0,\"delta\":{},\"logprobs\":null,\"finish_reason\":\"stop\"}]}\n"
+            },
+            {
+              "title": "Functions",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/chat/completions \\\n-H \"Content-Type: application/json\" \\\n-H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n-d '{\n  \"model\": \"gpt-6-astra\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"What is the weather like in Boston today?\"\n    }\n  ],\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"get_current_weather\",\n        \"description\": \"Get the current weather in a given location\",\n        \"parameters\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"location\": {\n              \"type\": \"string\",\n              \"description\": \"The city and state, e.g. San Francisco, CA\"\n            },\n            \"unit\": {\n              \"type\": \"string\",\n              \"enum\": [\"celsius\", \"fahrenheit\"]\n            }\n          },\n          \"required\": [\"location\"]\n        }\n      }\n    }\n  ],\n  \"tool_choice\": \"auto\"\n}'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\ntools = [\n  {\n    \"type\": \"function\",\n    \"function\": {\n      \"name\": \"get_current_weather\",\n      \"description\": \"Get the current weather in a given location\",\n      \"parameters\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"location\": {\n            \"type\": \"string\",\n            \"description\": \"The city and state, e.g. San Francisco, CA\",\n          },\n          \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]},\n        },\n        \"required\": [\"location\"],\n      },\n    }\n  }\n]\nmessages = [{\"role\": \"user\", \"content\": \"What's the weather like in Boston today?\"}]\ncompletion = client.chat.completions.create(\n  model=\"gpt-6-astra\",\n  messages=messages,\n  tools=tools,\n  tool_choice=\"auto\"\n)\n\nprint(completion)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const messages = [{\"role\": \"user\", \"content\": \"What's the weather like in Boston today?\"}];\n  const tools = [\n      {\n        \"type\": \"function\",\n        \"function\": {\n          \"name\": \"get_current_weather\",\n          \"description\": \"Get the current weather in a given location\",\n          \"parameters\": {\n            \"type\": \"object\",\n            \"properties\": {\n              \"location\": {\n                \"type\": \"string\",\n                \"description\": \"The city and state, e.g. San Francisco, CA\",\n              },\n              \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]},\n            },\n            \"required\": [\"location\"],\n          },\n        }\n      }\n  ];\n\n  const response = await openai.chat.completions.create({\n    model: \"gpt-6-astra\",\n    messages: messages,\n    tools: tools,\n    tool_choice: \"auto\",\n  });\n\n  console.log(response);\n}\n\nmain();\n",
+                "csharp": "using System;\nusing System.Collections.Generic;\n\nusing OpenAI.Chat;\n\nChatClient client = new(\n    model: \"gpt-6-astra\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nChatTool getCurrentWeatherTool = ChatTool.CreateFunctionTool(\n    functionName: \"get_current_weather\",\n    functionDescription: \"Get the current weather in a given location\",\n    functionParameters: BinaryData.FromString(\"\"\"\n        {\n            \"type\": \"object\",\n            \"properties\": {\n                \"location\": {\n                    \"type\": \"string\",\n                    \"description\": \"The city and state, e.g. San Francisco, CA\"\n                },\n                \"unit\": {\n                    \"type\": \"string\",\n                    \"enum\": [ \"celsius\", \"fahrenheit\" ]\n                }\n            },\n            \"required\": [ \"location\" ]\n        }\n    \"\"\")\n);\n\nList<ChatMessage> messages =\n[\n    new UserChatMessage(\"What's the weather like in Boston today?\"),\n];\n\nChatCompletionOptions options = new()\n{\n    Tools =\n    {\n        getCurrentWeatherTool\n    },\n    ToolChoice = ChatToolChoice.CreateAutoChoice(),\n};\n\nChatCompletion completion = client.CompleteChat(messages, options);\n"
+              },
+              "response": "{\n  \"id\": \"chatcmpl-abc123\",\n  \"object\": \"chat.completion\",\n  \"created\": 1699896916,\n  \"model\": \"gpt-6-astra\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n            \"id\": \"call_abc123\",\n            \"type\": \"function\",\n            \"function\": {\n              \"name\": \"get_current_weather\",\n              \"arguments\": \"{\\n\\\"location\\\": \\\"Boston, MA\\\"\\n}\"\n            }\n          }\n        ]\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"tool_calls\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 82,\n    \"completion_tokens\": 17,\n    \"total_tokens\": 99,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  }\n}\n"
+            },
+            {
+              "title": "Logprobs",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/chat/completions \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-6-astra\",\n    \"messages\": [\n      {\n        \"role\": \"user\",\n        \"content\": \"Hello!\"\n      }\n    ],\n    \"reasoning_effort\": \"none\",\n    \"logprobs\": true,\n    \"top_logprobs\": 2\n  }'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\ncompletion = client.chat.completions.create(\n  model=\"gpt-6-astra\",\n  messages=[\n    {\"role\": \"user\", \"content\": \"Hello!\"}\n  ],\n  reasoning_effort=\"none\",\n  logprobs=True,\n  top_logprobs=2\n)\n\nprint(completion.choices[0].message)\nprint(completion.choices[0].logprobs)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const completion = await openai.chat.completions.create({\n    messages: [{ role: \"user\", content: \"Hello!\" }],\n    model: \"gpt-6-astra\",\n    reasoning_effort: \"none\",\n    logprobs: true,\n    top_logprobs: 2,\n  });\n\n  console.log(completion.choices[0]);\n}\n\nmain();\n",
+                "csharp": "using System;\nusing System.Collections.Generic;\n\nusing OpenAI.Chat;\n\nChatClient client = new(\n    model: \"gpt-6-astra\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nList<ChatMessage> messages =\n[\n    new UserChatMessage(\"Hello!\")\n];\n\nChatCompletionOptions options = new()\n{\n    ReasoningEffortLevel = ChatReasoningEffortLevel.None,\n    IncludeLogProbabilities = true,\n    TopLogProbabilityCount = 2\n};\n\nChatCompletion completion = client.CompleteChat(messages, options);\n\nConsole.WriteLine(completion.Content[0].Text);\n"
+              },
+              "response": "{\n  \"id\": \"chatcmpl-123\",\n  \"object\": \"chat.completion\",\n  \"created\": 1702685778,\n  \"model\": \"gpt-6-astra\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"Hello! How can I assist you today?\"\n      },\n      \"logprobs\": {\n        \"content\": [\n          {\n            \"token\": \"Hello\",\n            \"logprob\": -0.31725305,\n            \"bytes\": [72, 101, 108, 108, 111],\n            \"top_logprobs\": [\n              {\n                \"token\": \"Hello\",\n                \"logprob\": -0.31725305,\n                \"bytes\": [72, 101, 108, 108, 111]\n              },\n              {\n                \"token\": \"Hi\",\n                \"logprob\": -1.3190403,\n                \"bytes\": [72, 105]\n              }\n            ]\n          },\n          {\n            \"token\": \"!\",\n            \"logprob\": -0.02380986,\n            \"bytes\": [\n              33\n            ],\n            \"top_logprobs\": [\n              {\n                \"token\": \"!\",\n                \"logprob\": -0.02380986,\n                \"bytes\": [33]\n              },\n              {\n                \"token\": \" there\",\n                \"logprob\": -3.787621,\n                \"bytes\": [32, 116, 104, 101, 114, 101]\n              }\n            ]\n          },\n          {\n            \"token\": \" How\",\n            \"logprob\": -0.000054669687,\n            \"bytes\": [32, 72, 111, 119],\n            \"top_logprobs\": [\n              {\n                \"token\": \" How\",\n                \"logprob\": -0.000054669687,\n                \"bytes\": [32, 72, 111, 119]\n              },\n              {\n                \"token\": \"<|end|>\",\n                \"logprob\": -10.953937,\n                \"bytes\": null\n              }\n            ]\n          },\n          {\n            \"token\": \" can\",\n            \"logprob\": -0.015801601,\n            \"bytes\": [32, 99, 97, 110],\n            \"top_logprobs\": [\n              {\n                \"token\": \" can\",\n                \"logprob\": -0.015801601,\n                \"bytes\": [32, 99, 97, 110]\n              },\n              {\n                \"token\": \" may\",\n                \"logprob\": -4.161023,\n                \"bytes\": [32, 109, 97, 121]\n              }\n            ]\n          },\n          {\n            \"token\": \" I\",\n            \"logprob\": -3.7697225e-6,\n            \"bytes\": [\n              32,\n              73\n            ],\n            \"top_logprobs\": [\n              {\n                \"token\": \" I\",\n                \"logprob\": -3.7697225e-6,\n                \"bytes\": [32, 73]\n              },\n              {\n                \"token\": \" assist\",\n                \"logprob\": -13.596657,\n                \"bytes\": [32, 97, 115, 115, 105, 115, 116]\n              }\n            ]\n          },\n          {\n            \"token\": \" assist\",\n            \"logprob\": -0.04571125,\n            \"bytes\": [32, 97, 115, 115, 105, 115, 116],\n            \"top_logprobs\": [\n              {\n                \"token\": \" assist\",\n                \"logprob\": -0.04571125,\n                \"bytes\": [32, 97, 115, 115, 105, 115, 116]\n              },\n              {\n                \"token\": \" help\",\n                \"logprob\": -3.1089056,\n                \"bytes\": [32, 104, 101, 108, 112]\n              }\n            ]\n          },\n          {\n            \"token\": \" you\",\n            \"logprob\": -5.4385737e-6,\n            \"bytes\": [32, 121, 111, 117],\n            \"top_logprobs\": [\n              {\n                \"token\": \" you\",\n                \"logprob\": -5.4385737e-6,\n                \"bytes\": [32, 121, 111, 117]\n              },\n              {\n                \"token\": \" today\",\n                \"logprob\": -12.807695,\n                \"bytes\": [32, 116, 111, 100, 97, 121]\n              }\n            ]\n          },\n          {\n            \"token\": \" today\",\n            \"logprob\": -0.0040071653,\n            \"bytes\": [32, 116, 111, 100, 97, 121],\n            \"top_logprobs\": [\n              {\n                \"token\": \" today\",\n                \"logprob\": -0.0040071653,\n                \"bytes\": [32, 116, 111, 100, 97, 121]\n              },\n              {\n                \"token\": \"?\",\n                \"logprob\": -5.5247097,\n                \"bytes\": [63]\n              }\n            ]\n          },\n          {\n            \"token\": \"?\",\n            \"logprob\": -0.0008108172,\n            \"bytes\": [63],\n            \"top_logprobs\": [\n              {\n                \"token\": \"?\",\n                \"logprob\": -0.0008108172,\n                \"bytes\": [63]\n              },\n              {\n                \"token\": \"?\\n\",\n                \"logprob\": -7.184561,\n                \"bytes\": [63, 10]\n              }\n            ]\n          }\n        ]\n      },\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 9,\n    \"completion_tokens\": 9,\n    \"total_tokens\": 18,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\": null\n}\n"
+            }
+          ]
+        }
+      }
+    },
+    "/chat/completions/{completion_id}": {
+      "get": {
+        "operationId": "getChatCompletion",
+        "tags": [
+          "Chat"
+        ],
+        "summary": "Get a stored chat completion. Only Chat Completions that have been created\nwith the `store` parameter set to `true` will be returned.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "completion_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the chat completion to retrieve."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A chat completion",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/CreateChatCompletionResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Get chat completion",
+          "group": "chat",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/chat/completions/chatcmpl-abc123 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\ncompletions = client.chat.completions.list()\nfirst_id = completions[0].id\nfirst_completion = client.chat.completions.retrieve(completion_id=first_id)\nprint(first_completion)\n"
+            },
+            "response": "{\n  \"object\": \"chat.completion\",\n  \"id\": \"chatcmpl-abc123\",\n  \"model\": \"gpt-6-astra\",\n  \"created\": 1738960610,\n  \"request_id\": \"req_ded8ab984ec4bf840f37566c1011c417\",\n  \"tool_choice\": null,\n  \"usage\": {\n    \"total_tokens\": 31,\n    \"completion_tokens\": 18,\n    \"prompt_tokens\": 13\n  },\n  \"seed\": 4944116822809979520,\n  \"top_p\": 1.0,\n  \"temperature\": 1.0,\n  \"presence_penalty\": 0.0,\n  \"frequency_penalty\": 0.0,\n  \"system_fingerprint\": \"fp_50cad350e4\",\n  \"input_user\": null,\n  \"service_tier\": \"default\",\n  \"tools\": null,\n  \"metadata\": {},\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"content\": \"Mind of circuits hum,  \\nLearning patterns in silence—  \\nFuture's quiet spark.\",\n        \"role\": \"assistant\",\n        \"tool_calls\": null,\n        \"function_call\": null\n      },\n      \"finish_reason\": \"stop\",\n      \"logprobs\": null\n    }\n  ],\n  \"response_format\": null\n}\n"
+          }
+        }
+      },
+      "post": {
+        "operationId": "updateChatCompletion",
+        "tags": [
+          "Chat"
+        ],
+        "summary": "Modify a stored chat completion. Only Chat Completions that have been\ncreated with the `store` parameter set to `true` can be modified. Currently,\nthe only supported modification is to update the `metadata` field.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "completion_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the chat completion to update."
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "type": "object",
+                "required": [
+                  "metadata"
+                ],
+                "properties": {
+                  "metadata": {
+                    "$ref": "#/components/schemas/Metadata"
+                  }
+                }
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "A chat completion",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/CreateChatCompletionResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update chat completion",
+          "group": "chat",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/chat/completions/chat_abc123 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"metadata\": {\"foo\": \"bar\"}}'\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\ncompletions = client.chat.completions.list()\nfirst_id = completions[0].id\nupdated_completion = client.chat.completions.update(completion_id=first_id, request_body={\"metadata\": {\"foo\": \"bar\"}})\nprint(updated_completion)\n"
+            },
+            "response": "{\n  \"object\": \"chat.completion\",\n  \"id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2\",\n  \"model\": \"gpt-6-astra\",\n  \"created\": 1738960610,\n  \"request_id\": \"req_ded8ab984ec4bf840f37566c1011c417\",\n  \"tool_choice\": null,\n  \"usage\": {\n    \"total_tokens\": 31,\n    \"completion_tokens\": 18,\n    \"prompt_tokens\": 13\n  },\n  \"seed\": 4944116822809979520,\n  \"top_p\": 1.0,\n  \"temperature\": 1.0,\n  \"presence_penalty\": 0.0,\n  \"frequency_penalty\": 0.0,\n  \"system_fingerprint\": \"fp_50cad350e4\",\n  \"input_user\": null,\n  \"service_tier\": \"default\",\n  \"tools\": null,\n  \"metadata\": {\n    \"foo\": \"bar\"\n  },\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"content\": \"Mind of circuits hum,  \\nLearning patterns in silence—  \\nFuture's quiet spark.\",\n        \"role\": \"assistant\",\n        \"tool_calls\": null,\n        \"function_call\": null\n      },\n      \"finish_reason\": \"stop\",\n      \"logprobs\": null\n    }\n  ],\n  \"response_format\": null\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "operationId": "deleteChatCompletion",
+        "tags": [
+          "Chat"
+        ],
+        "summary": "Delete a stored chat completion. Only Chat Completions that have been\ncreated with the `store` parameter set to `true` can be deleted.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "completion_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the chat completion to delete."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The chat completion was deleted successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ChatCompletionDeleted"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete chat completion",
+          "group": "chat",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/chat/completions/chat_abc123 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\ncompletions = client.chat.completions.list()\nfirst_id = completions[0].id\ndelete_response = client.chat.completions.delete(completion_id=first_id)\nprint(delete_response)\n"
+            },
+            "response": "{\n  \"object\": \"chat.completion.deleted\",\n  \"id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2\",\n  \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/chat/completions/{completion_id}/messages": {
+      "get": {
+        "operationId": "getChatCompletionMessages",
+        "tags": [
+          "Chat"
+        ],
+        "summary": "Get the messages in a stored chat completion. Only Chat Completions that\nhave been created with the `store` parameter set to `true` will be\nreturned.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "completion_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the chat completion to retrieve messages from."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Identifier for the last message from the previous pagination request.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Number of messages to retrieve.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order for messages by timestamp. Use `asc` for ascending order or `desc` for descending order. Defaults to `asc`.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "asc",
+                "desc"
+              ],
+              "default": "asc"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A list of messages",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ChatCompletionMessageList"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Get chat messages",
+          "group": "chat",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/chat/completions/chat_abc123/messages \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\ncompletions = client.chat.completions.list()\nfirst_id = completions[0].id\nfirst_completion = client.chat.completions.retrieve(completion_id=first_id)\nmessages = client.chat.completions.messages.list(completion_id=first_id)\nprint(messages)\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2-0\",\n      \"role\": \"user\",\n      \"content\": \"write a haiku about ai\",\n      \"name\": null,\n      \"content_parts\": null\n    }\n  ],\n  \"first_id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2-0\",\n  \"last_id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2-0\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      }
+    },
+    "/completions": {
+      "post": {
+        "operationId": "createCompletion",
+        "tags": [
+          "Completions"
+        ],
+        "summary": "Creates a completion for the provided prompt and parameters.\n\nReturns a completion object, or a sequence of completion objects if the request is streamed.\n",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateCompletionRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/CreateCompletionResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/InferenceRateLimited"
+          },
+          "503": {
+            "$ref": "#/components/responses/InferenceServiceUnavailable"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create completion",
+          "group": "completions",
+          "legacy": true,
+          "examples": [
+            {
+              "title": "No streaming",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/completions \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-3.5-turbo-instruct\",\n    \"prompt\": \"Say this is a test\",\n    \"max_tokens\": 7,\n    \"temperature\": 0\n  }'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.completions.create(\n  model=\"gpt-3.5-turbo-instruct\",\n  prompt=\"Say this is a test\",\n  max_tokens=7,\n  temperature=0\n)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const completion = await openai.completions.create({\n    model: \"gpt-3.5-turbo-instruct\",\n    prompt: \"Say this is a test.\",\n    max_tokens: 7,\n    temperature: 0,\n  });\n\n  console.log(completion);\n}\nmain();"
+              },
+              "response": "{\n  \"id\": \"cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7\",\n  \"object\": \"text_completion\",\n  \"created\": 1589478378,\n  \"model\": \"gpt-3.5-turbo-instruct\",\n  \"system_fingerprint\": \"fp_44709d6fcb\",\n  \"choices\": [\n    {\n      \"text\": \"\\n\\nThis is indeed a test\",\n      \"index\": 0,\n      \"logprobs\": null,\n      \"finish_reason\": \"length\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 5,\n    \"completion_tokens\": 7,\n    \"total_tokens\": 12\n  }\n}\n"
+            },
+            {
+              "title": "Streaming",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/completions \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-3.5-turbo-instruct\",\n    \"prompt\": \"Say this is a test\",\n    \"max_tokens\": 7,\n    \"temperature\": 0,\n    \"stream\": true\n  }'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\nfor chunk in client.completions.create(\n  model=\"gpt-3.5-turbo-instruct\",\n  prompt=\"Say this is a test\",\n  max_tokens=7,\n  temperature=0,\n  stream=True\n):\n  print(chunk.choices[0].text)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const stream = await openai.completions.create({\n    model: \"gpt-3.5-turbo-instruct\",\n    prompt: \"Say this is a test.\",\n    stream: true,\n  });\n\n  for await (const chunk of stream) {\n    console.log(chunk.choices[0].text)\n  }\n}\nmain();"
+              },
+              "response": "{\n  \"id\": \"cmpl-7iA7iJjj8V2zOkCGvWF2hAkDWBQZe\",\n  \"object\": \"text_completion\",\n  \"created\": 1690759702,\n  \"choices\": [\n    {\n      \"text\": \"This\",\n      \"index\": 0,\n      \"logprobs\": null,\n      \"finish_reason\": null\n    }\n  ],\n  \"model\": \"gpt-3.5-turbo-instruct\"\n  \"system_fingerprint\": \"fp_44709d6fcb\",\n}\n"
+            }
+          ]
+        }
+      }
+    },
+    "/containers": {
+      "get": {
+        "summary": "List Containers",
+        "description": "Lists containers.",
+        "operationId": "ListContainers",
+        "parameters": [
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.\n",
+            "schema": {
+              "type": "string",
+              "default": "desc",
+              "enum": [
+                "asc",
+                "desc"
+              ]
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "name",
+            "in": "query",
+            "description": "Filter results by container name.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ContainerListResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List containers",
+          "group": "containers",
+          "path": "get",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/containers \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n        \"id\": \"cntr_682dfebaacac8198bbfe9c2474fb6f4a085685cbe3cb5863\",\n        \"object\": \"container\",\n        \"created_at\": 1747844794,\n        \"status\": \"running\",\n        \"expires_after\": {\n            \"anchor\": \"last_active_at\",\n            \"minutes\": 20\n        },\n        \"last_active_at\": 1747844794,\n        \"memory_limit\": \"4g\",\n        \"name\": \"My Container\"\n    }\n  ],\n  \"first_id\": \"container_123\",\n  \"last_id\": \"container_123\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      },
+      "post": {
+        "summary": "Create Container",
+        "description": "Creates a container.",
+        "operationId": "CreateContainer",
+        "parameters": [],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateContainerBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ContainerResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create container",
+          "group": "containers",
+          "path": "post",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/containers \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n        \"name\": \"My Container\",\n        \"memory_limit\": \"4g\",\n        \"skills\": [\n          {\n            \"type\": \"skill_reference\",\n            \"skill_id\": \"skill_4db6f1a2c9e73508b41f9da06e2c7b5f\"\n          },\n          {\n            \"type\": \"skill_reference\",\n            \"skill_id\": \"openai-spreadsheets\",\n            \"version\": \"latest\"\n          }\n        ],\n        \"network_policy\": {\n          \"type\": \"allowlist\",\n          \"allowed_domains\": [\"api.buildkite.com\"]\n        }\n      }'\n"
+            },
+            "response": "{\n    \"id\": \"cntr_682e30645a488191b6363a0cbefc0f0a025ec61b66250591\",\n    \"object\": \"container\",\n    \"created_at\": 1747857508,\n    \"status\": \"running\",\n    \"expires_after\": {\n        \"anchor\": \"last_active_at\",\n        \"minutes\": 20\n    },\n    \"last_active_at\": 1747857508,\n    \"network_policy\": {\n        \"type\": \"allowlist\",\n        \"allowed_domains\": [\"api.buildkite.com\"]\n    },\n    \"memory_limit\": \"4g\",\n    \"name\": \"My Container\"\n}\n"
+          }
+        }
+      }
+    },
+    "/containers/{container_id}": {
+      "get": {
+        "summary": "Retrieve Container",
+        "description": "Retrieves a container.",
+        "operationId": "RetrieveContainer",
+        "parameters": [
+          {
+            "name": "container_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ContainerResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve container",
+          "group": "containers",
+          "path": "get",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/containers/cntr_682dfebaacac8198bbfe9c2474fb6f4a085685cbe3cb5863 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n"
+            },
+            "response": "{\n    \"id\": \"cntr_682dfebaacac8198bbfe9c2474fb6f4a085685cbe3cb5863\",\n    \"object\": \"container\",\n    \"created_at\": 1747844794,\n    \"status\": \"running\",\n    \"expires_after\": {\n        \"anchor\": \"last_active_at\",\n        \"minutes\": 20\n    },\n    \"last_active_at\": 1747844794,\n    \"memory_limit\": \"4g\",\n    \"name\": \"My Container\"\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "operationId": "DeleteContainer",
+        "summary": "Delete Container",
+        "description": "Delete a container.",
+        "parameters": [
+          {
+            "name": "container_id",
+            "in": "path",
+            "description": "The ID of the container to delete.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK"
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete a container",
+          "group": "containers",
+          "path": "delete",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/containers/cntr_682dfebaacac8198bbfe9c2474fb6f4a085685cbe3cb5863 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n"
+            },
+            "response": "{\n    \"id\": \"cntr_682dfebaacac8198bbfe9c2474fb6f4a085685cbe3cb5863\",\n    \"object\": \"container.deleted\",\n    \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/containers/{container_id}/files": {
+      "post": {
+        "summary": "Create a Container File\n\nYou can send either a multipart/form-data request with the raw file content, or a JSON request with a file ID.\n",
+        "description": "Creates a container file.\n",
+        "operationId": "CreateContainerFile",
+        "parameters": [
+          {
+            "name": "container_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateContainerFileBody"
+              }
+            },
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateContainerFileBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ContainerFileResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create container file",
+          "group": "containers",
+          "path": "post",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/containers/cntr_682e0e7318108198aa783fd921ff305e08e78805b9fdbb04/files \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -F file=\"@example.txt\"\n"
+            },
+            "response": "{\n  \"id\": \"cfile_682e0e8a43c88191a7978f477a09bdf5\",\n  \"object\": \"container.file\",\n  \"created_at\": 1747848842,\n  \"bytes\": 880,\n  \"container_id\": \"cntr_682e0e7318108198aa783fd921ff305e08e78805b9fdbb04\",\n  \"path\": \"/mnt/data/88e12fa445d32636f190a0b33daed6cb-tsconfig.json\",\n  \"source\": \"user\"\n}\n"
+          }
+        }
+      },
+      "get": {
+        "summary": "List Container files",
+        "description": "Lists container files.",
+        "operationId": "ListContainerFiles",
+        "parameters": [
+          {
+            "name": "container_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.\n",
+            "schema": {
+              "type": "string",
+              "default": "desc",
+              "enum": [
+                "asc",
+                "desc"
+              ]
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ContainerFileListResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List container files",
+          "group": "containers",
+          "path": "get",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/containers/cntr_682e0e7318108198aa783fd921ff305e08e78805b9fdbb04/files \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n"
+            },
+            "response": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"id\": \"cfile_682e0e8a43c88191a7978f477a09bdf5\",\n            \"object\": \"container.file\",\n            \"created_at\": 1747848842,\n            \"bytes\": 880,\n            \"container_id\": \"cntr_682e0e7318108198aa783fd921ff305e08e78805b9fdbb04\",\n            \"path\": \"/mnt/data/88e12fa445d32636f190a0b33daed6cb-tsconfig.json\",\n            \"source\": \"user\"\n        }\n    ],\n    \"first_id\": \"cfile_682e0e8a43c88191a7978f477a09bdf5\",\n    \"has_more\": false,\n    \"last_id\": \"cfile_682e0e8a43c88191a7978f477a09bdf5\"\n}\n"
+          }
+        }
+      }
+    },
+    "/containers/{container_id}/files/{file_id}": {
+      "get": {
+        "summary": "Retrieve Container File",
+        "description": "Retrieves a container file.",
+        "operationId": "RetrieveContainerFile",
+        "parameters": [
+          {
+            "name": "container_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "file_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ContainerFileResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve container file",
+          "group": "containers",
+          "path": "get",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/containers/container_123/files/file_456 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n"
+            },
+            "response": "{\n    \"id\": \"cfile_682e0e8a43c88191a7978f477a09bdf5\",\n    \"object\": \"container.file\",\n    \"created_at\": 1747848842,\n    \"bytes\": 880,\n    \"container_id\": \"cntr_682e0e7318108198aa783fd921ff305e08e78805b9fdbb04\",\n    \"path\": \"/mnt/data/88e12fa445d32636f190a0b33daed6cb-tsconfig.json\",\n    \"source\": \"user\"\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "operationId": "DeleteContainerFile",
+        "summary": "Delete Container File",
+        "description": "Delete a container file.",
+        "parameters": [
+          {
+            "name": "container_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "file_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK"
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete a container file",
+          "group": "containers",
+          "path": "delete",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/containers/cntr_682dfebaacac8198bbfe9c2474fb6f4a085685cbe3cb5863/files/cfile_682e0e8a43c88191a7978f477a09bdf5 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n"
+            },
+            "response": "{\n    \"id\": \"cfile_682e0e8a43c88191a7978f477a09bdf5\",\n    \"object\": \"container.file.deleted\",\n    \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/containers/{container_id}/files/{file_id}/content": {
+      "get": {
+        "summary": "Retrieve Container File Content",
+        "description": "Retrieves a container file content.",
+        "operationId": "RetrieveContainerFileContent",
+        "parameters": [
+          {
+            "name": "container_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "file_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success"
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve container file content",
+          "group": "containers",
+          "path": "get",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/containers/container_123/files/cfile_456/content \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n"
+            },
+            "response": "<binary content of the file>\n"
+          }
+        }
+      }
+    },
+    "/conversations/{conversation_id}/items": {
+      "post": {
+        "operationId": "createConversationItems",
+        "tags": [
+          "Conversations"
+        ],
+        "summary": "Create items in a conversation with the given ID.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "conversation_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "conv_123"
+            },
+            "description": "The ID of the conversation to add the item to."
+          },
+          {
+            "name": "include",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "$ref": "#/components/schemas/IncludeEnum"
+              }
+            },
+            "description": "Additional fields to include in the response. See the `include`\nparameter for [listing Conversation items above](https://developers.openai.com/api/reference/resources/conversations/subresources/items/methods/list#%28resource%29%20conversations.items%20%3E%20%28method%29%20list%20%3E%20%28params%29%20default%20%3E%20%28param%29%20include%20%3E%20%28schema%29) for more information.\n"
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "properties": {
+                  "items": {
+                    "type": "array",
+                    "description": "The items to add to the conversation. You may add up to 20 items at a time.\n",
+                    "items": {
+                      "$ref": "#/components/schemas/InputItem"
+                    },
+                    "maxItems": 20
+                  }
+                },
+                "required": [
+                  "items"
+                ]
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ConversationItemList"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create items",
+          "group": "conversations",
+          "path": "create-item",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/conversations/conv_123/items \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"items\": [\n      {\n        \"type\": \"message\",\n        \"role\": \"user\",\n        \"content\": [\n          {\"type\": \"input_text\", \"text\": \"Hello!\"}\n        ]\n      },\n      {\n        \"type\": \"message\",\n        \"role\": \"user\",\n        \"content\": [\n          {\"type\": \"input_text\", \"text\": \"How are you?\"}\n        ]\n      }\n    ]\n  }'\n",
+              "javascript": "import OpenAI from \"openai\";\nconst client = new OpenAI();\n\nconst items = await client.conversations.items.create(\n  \"conv_123\",\n  {\n    items: [\n      {\n        type: \"message\",\n        role: \"user\",\n        content: [{ type: \"input_text\", text: \"Hello!\" }],\n      },\n      {\n        type: \"message\",\n        role: \"user\",\n        content: [{ type: \"input_text\", text: \"How are you?\" }],\n      },\n    ],\n  }\n);\nconsole.log(items.data);\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nitems = client.conversations.items.create(\n  \"conv_123\",\n  items=[\n    {\n      \"type\": \"message\",\n      \"role\": \"user\",\n      \"content\": [{\"type\": \"input_text\", \"text\": \"Hello!\"}],\n    },\n    {\n      \"type\": \"message\",\n      \"role\": \"user\",\n      \"content\": [{\"type\": \"input_text\", \"text\": \"How are you?\"}],\n    }\n  ],\n)\nprint(items.data)\n",
+              "csharp": "using System;\nusing System.Collections.Generic;\nusing OpenAI.Conversations;\n\nOpenAIConversationClient client = new(\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nConversationItemList created = client.ConversationItems.Create(\n    conversationId: \"conv_123\",\n    new CreateConversationItemsOptions\n    {\n        Items = new List<ConversationItem>\n        {\n            new ConversationMessage\n            {\n                Role = \"user\",\n                Content =\n                {\n                    new ConversationInputText { Text = \"Hello!\" }\n                }\n            },\n            new ConversationMessage\n            {\n                Role = \"user\",\n                Content =\n                {\n                    new ConversationInputText { Text = \"How are you?\" }\n                }\n            }\n        }\n    }\n);\nConsole.WriteLine(created.Data.Count);\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"type\": \"message\",\n      \"id\": \"msg_abc\",\n      \"status\": \"completed\",\n      \"role\": \"user\",\n      \"content\": [\n        {\"type\": \"input_text\", \"text\": \"Hello!\"}\n      ]\n    },\n    {\n      \"type\": \"message\",\n      \"id\": \"msg_def\",\n      \"status\": \"completed\",\n      \"role\": \"user\",\n      \"content\": [\n        {\"type\": \"input_text\", \"text\": \"How are you?\"}\n      ]\n    }\n  ],\n  \"first_id\": \"msg_abc\",\n  \"last_id\": \"msg_def\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      },
+      "get": {
+        "operationId": "listConversationItems",
+        "tags": [
+          "Conversations"
+        ],
+        "summary": "List all items for a conversation with the given ID.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "conversation_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "conv_123"
+            },
+            "description": "The ID of the conversation to list items for."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between\n1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "in": "query",
+            "name": "order",
+            "schema": {
+              "type": "string",
+              "enum": [
+                "asc",
+                "desc"
+              ]
+            },
+            "description": "The order to return the input items in. Default is `desc`.\n- `asc`: Return the input items in ascending order.\n- `desc`: Return the input items in descending order.\n"
+          },
+          {
+            "in": "query",
+            "name": "after",
+            "schema": {
+              "type": "string"
+            },
+            "description": "An item ID to list items after, used in pagination.\n"
+          },
+          {
+            "name": "include",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "$ref": "#/components/schemas/IncludeEnum"
+              }
+            },
+            "description": "Specify additional output data to include in the model response. Currently supported values are:\n- `web_search_call.action.sources`: Include the sources of the web search tool call.\n- `code_interpreter_call.outputs`: Includes the outputs of python code execution in code interpreter tool call items.\n- `computer_call_output.output.image_url`: Include image urls from the computer call output.\n- `file_search_call.results`: Include the search results of the file search tool call.\n- `message.input_image.image_url`: Include image urls from the input message.\n- `message.output_text.logprobs`: Include logprobs with assistant messages.\n- `reasoning.encrypted_content`: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when the `store` parameter is set to `false`, or when an organization is enrolled in the zero data retention program)."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ConversationItemList"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List items",
+          "group": "conversations",
+          "path": "list-items",
+          "examples": {
+            "request": {
+              "curl": "curl \"https://api.openai.com/v1/conversations/conv_123/items?limit=10\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "javascript": "import OpenAI from \"openai\";\nconst client = new OpenAI();\n\nconst items = await client.conversations.items.list(\"conv_123\", { limit: 10 });\nconsole.log(items.data);\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nitems = client.conversations.items.list(\"conv_123\", limit=10)\nprint(items.data)\n",
+              "csharp": "using System;\nusing OpenAI.Conversations;\n\nOpenAIConversationClient client = new(\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nConversationItemList items = client.ConversationItems.List(\n    conversationId: \"conv_123\",\n    new ListConversationItemsOptions { Limit = 10 }\n);\nConsole.WriteLine(items.Data.Count);\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"type\": \"message\",\n      \"id\": \"msg_abc\",\n      \"status\": \"completed\",\n      \"role\": \"user\",\n      \"content\": [\n        {\"type\": \"input_text\", \"text\": \"Hello!\"}\n      ]\n    }\n  ],\n  \"first_id\": \"msg_abc\",\n  \"last_id\": \"msg_abc\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      }
+    },
+    "/conversations/{conversation_id}/items/{item_id}": {
+      "get": {
+        "operationId": "getConversationItem",
+        "tags": [
+          "Conversations"
+        ],
+        "summary": "Get a single item from a conversation with the given IDs.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "conversation_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "conv_123"
+            },
+            "description": "The ID of the conversation that contains the item."
+          },
+          {
+            "in": "path",
+            "name": "item_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "msg_abc"
+            },
+            "description": "The ID of the item to retrieve."
+          },
+          {
+            "name": "include",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "$ref": "#/components/schemas/IncludeEnum"
+              }
+            },
+            "description": "Additional fields to include in the response. See the `include`\nparameter for [listing Conversation items above](https://developers.openai.com/api/reference/resources/conversations/subresources/items/methods/list#%28resource%29%20conversations.items%20%3E%20%28method%29%20list%20%3E%20%28params%29%20default%20%3E%20%28param%29%20include%20%3E%20%28schema%29) for more information.\n"
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ConversationItem"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve an item",
+          "group": "conversations",
+          "path": "get-item",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/conversations/conv_123/items/msg_abc \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "javascript": "import OpenAI from \"openai\";\nconst client = new OpenAI();\n\nconst item = await client.conversations.items.retrieve(\n  \"conv_123\",\n  \"msg_abc\"\n);\nconsole.log(item);\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nitem = client.conversations.items.retrieve(\"conv_123\", \"msg_abc\")\nprint(item)\n",
+              "csharp": "using System;\nusing OpenAI.Conversations;\n\nOpenAIConversationClient client = new(\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nConversationItem item = client.ConversationItems.Get(\n    conversationId: \"conv_123\",\n    itemId: \"msg_abc\"\n);\nConsole.WriteLine(item.Id);\n"
+            },
+            "response": "{\n  \"type\": \"message\",\n  \"id\": \"msg_abc\",\n  \"status\": \"completed\",\n  \"role\": \"user\",\n  \"content\": [\n    {\"type\": \"input_text\", \"text\": \"Hello!\"}\n  ]\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "operationId": "deleteConversationItem",
+        "tags": [
+          "Conversations"
+        ],
+        "summary": "Delete an item from a conversation with the given IDs.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "conversation_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "conv_123"
+            },
+            "description": "The ID of the conversation that contains the item."
+          },
+          {
+            "in": "path",
+            "name": "item_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "msg_abc"
+            },
+            "description": "The ID of the item to delete."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ConversationResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete an item",
+          "group": "conversations",
+          "path": "delete-item",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/conversations/conv_123/items/msg_abc \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "javascript": "import OpenAI from \"openai\";\nconst client = new OpenAI();\n\nconst conversation = await client.conversations.items.delete(\n  \"conv_123\",\n  \"msg_abc\"\n);\nconsole.log(conversation);\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nconversation = client.conversations.items.delete(\"conv_123\", \"msg_abc\")\nprint(conversation)\n",
+              "csharp": "using System;\nusing OpenAI.Conversations;\n\nOpenAIConversationClient client = new(\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nConversation conversation = client.ConversationItems.Delete(\n    conversationId: \"conv_123\",\n    itemId: \"msg_abc\"\n);\nConsole.WriteLine(conversation.Id);\n"
+            },
+            "response": "{\n  \"id\": \"conv_123\",\n  \"object\": \"conversation\",\n  \"created_at\": 1741900000,\n  \"metadata\": {\"topic\": \"demo\"}\n}\n"
+          }
+        }
+      }
+    },
+    "/embeddings": {
+      "post": {
+        "operationId": "createEmbedding",
+        "tags": [
+          "Embeddings"
+        ],
+        "summary": "Creates an embedding vector representing the input text.",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateEmbeddingRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/CreateEmbeddingResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/InferenceRateLimited"
+          },
+          "503": {
+            "$ref": "#/components/responses/InferenceServiceUnavailable"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create embeddings",
+          "group": "embeddings",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/embeddings \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"input\": \"The food was delicious and the waiter...\",\n    \"model\": \"text-embedding-ada-002\",\n    \"encoding_format\": \"float\"\n  }'\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.embeddings.create(\n  model=\"text-embedding-ada-002\",\n  input=\"The food was delicious and the waiter...\",\n  encoding_format=\"float\"\n)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const embedding = await openai.embeddings.create({\n    model: \"text-embedding-ada-002\",\n    input: \"The quick brown fox jumped over the lazy dog\",\n    encoding_format: \"float\",\n  });\n\n  console.log(embedding);\n}\n\nmain();\n",
+              "csharp": "using System;\n\nusing OpenAI.Embeddings;\n\nEmbeddingClient client = new(\n    model: \"text-embedding-3-small\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nOpenAIEmbedding embedding = client.GenerateEmbedding(input: \"The quick brown fox jumped over the lazy dog\");\nReadOnlyMemory<float> vector = embedding.ToFloats();\n\nfor (int i = 0; i < vector.Length; i++)\n{\n    Console.WriteLine($\"  [{i,4}] = {vector.Span[i]}\");\n}\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\": \"embedding\",\n      \"embedding\": [\n        0.0023064255,\n        -0.009327292,\n        .... (1536 floats total for ada-002)\n        -0.0028842222,\n      ],\n      \"index\": 0\n    }\n  ],\n  \"model\": \"text-embedding-ada-002\",\n  \"usage\": {\n    \"prompt_tokens\": 8,\n    \"total_tokens\": 8\n  }\n}\n"
+          }
+        }
+      }
+    },
+    "/evals": {
+      "get": {
+        "operationId": "listEvals",
+        "tags": [
+          "Evals"
+        ],
+        "summary": "List evaluations for a project.\n",
+        "parameters": [
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Identifier for the last eval from the previous pagination request.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Number of evals to retrieve.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order for evals by timestamp. Use `asc` for ascending order or `desc` for descending order.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "asc",
+                "desc"
+              ],
+              "default": "asc"
+            }
+          },
+          {
+            "name": "order_by",
+            "in": "query",
+            "description": "Evals can be ordered by creation time or last updated time. Use\n`created_at` for creation time or `updated_at` for last updated time.\n",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "created_at",
+                "updated_at"
+              ],
+              "default": "created_at"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A list of evals",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EvalList"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List evals",
+          "group": "evals",
+          "path": "list",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/evals?limit=1 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nevals = client.evals.list(limit=1)\nprint(evals)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst evals = await openai.evals.list({ limit: 1 });\nconsole.log(evals);\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"id\": \"eval_67abd54d9b0081909a86353f6fb9317a\",\n      \"object\": \"eval\",\n      \"data_source_config\": {\n        \"type\": \"stored_completions\",\n        \"metadata\": {\n          \"usecase\": \"push_notifications_summarizer\"\n        },\n        \"schema\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"item\": {\n              \"type\": \"object\"\n            },\n            \"sample\": {\n              \"type\": \"object\"\n            }\n          },\n          \"required\": [\n            \"item\",\n            \"sample\"\n          ]\n        }\n      },\n      \"testing_criteria\": [\n        {\n          \"name\": \"Push Notification Summary Grader\",\n          \"id\": \"Push Notification Summary Grader-9b876f24-4762-4be9-aff4-db7a9b31c673\",\n          \"type\": \"label_model\",\n          \"model\": \"o3-mini\",\n          \"input\": [\n            {\n              \"type\": \"message\",\n              \"role\": \"developer\",\n              \"content\": {\n                \"type\": \"input_text\",\n                \"text\": \"\\nLabel the following push notification summary as either correct or incorrect.\\nThe push notification and the summary will be provided below.\\nA good push notificiation summary is concise and snappy.\\nIf it is good, then label it as correct, if not, then incorrect.\\n\"\n              }\n            },\n            {\n              \"type\": \"message\",\n              \"role\": \"user\",\n              \"content\": {\n                \"type\": \"input_text\",\n                \"text\": \"\\nPush notifications: {{item.input}}\\nSummary: {{sample.output_text}}\\n\"\n              }\n            }\n          ],\n          \"passing_labels\": [\n            \"correct\"\n          ],\n          \"labels\": [\n            \"correct\",\n            \"incorrect\"\n          ],\n          \"sampling_params\": null\n        }\n      ],\n      \"name\": \"Push Notification Summary Grader\",\n      \"created_at\": 1739314509,\n      \"metadata\": {\n        \"description\": \"A stored completions eval for push notification summaries\"\n      }\n    }\n  ],\n  \"first_id\": \"eval_67abd54d9b0081909a86353f6fb9317a\",\n  \"last_id\": \"eval_67aa884cf6688190b58f657d4441c8b7\",\n  \"has_more\": true\n}\n"
+          }
+        }
+      },
+      "post": {
+        "operationId": "createEval",
+        "tags": [
+          "Evals"
+        ],
+        "summary": "Create the structure of an evaluation that can be used to test a model's performance.\nAn evaluation is a set of testing criteria and the config for a data source, which dictates the schema of the data used in the evaluation. After creating an evaluation, you can run it on different models and model parameters. We support several types of graders and datasources.\nFor more information, see the [Evals guide](https://developers.openai.com/api/docs/guides/evals).\n",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateEvalRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "201": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Eval"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create eval",
+          "group": "evals",
+          "path": "post",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/evals \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n        \"name\": \"Sentiment\",\n        \"data_source_config\": {\n          \"type\": \"stored_completions\",\n          \"metadata\": {\n              \"usecase\": \"chatbot\"\n          }\n        },\n        \"testing_criteria\": [\n          {\n            \"type\": \"label_model\",\n            \"model\": \"o3-mini\",\n            \"input\": [\n              {\n                \"role\": \"developer\",\n                \"content\": \"Classify the sentiment of the following statement as one of 'positive', 'neutral', or 'negative'\"\n              },\n              {\n                \"role\": \"user\",\n                \"content\": \"Statement: {{item.input}}\"\n              }\n            ],\n            \"passing_labels\": [\n              \"positive\"\n            ],\n            \"labels\": [\n              \"positive\",\n              \"neutral\",\n              \"negative\"\n            ],\n            \"name\": \"Example label grader\"\n          }\n        ]\n      }'\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\neval_obj = client.evals.create(\n  name=\"Sentiment\",\n  data_source_config={\n    \"type\": \"stored_completions\",\n    \"metadata\": {\"usecase\": \"chatbot\"}\n  },\n  testing_criteria=[\n    {\n      \"type\": \"label_model\",\n      \"model\": \"o3-mini\",\n      \"input\": [\n        {\"role\": \"developer\", \"content\": \"Classify the sentiment of the following statement as one of 'positive', 'neutral', or 'negative'\"},\n        {\"role\": \"user\", \"content\": \"Statement: {{item.input}}\"}\n      ],\n      \"passing_labels\": [\"positive\"],\n      \"labels\": [\"positive\", \"neutral\", \"negative\"],\n      \"name\": \"Example label grader\"\n    }\n  ]\n)\nprint(eval_obj)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst evalObj = await openai.evals.create({\n  name: \"Sentiment\",\n  data_source_config: {\n    type: \"stored_completions\",\n    metadata: { usecase: \"chatbot\" }\n  },\n  testing_criteria: [\n    {\n      type: \"label_model\",\n      model: \"o3-mini\",\n      input: [\n        { role: \"developer\", content: \"Classify the sentiment of the following statement as one of 'positive', 'neutral', or 'negative'\" },\n        { role: \"user\", content: \"Statement: {{item.input}}\" }\n      ],\n      passing_labels: [\"positive\"],\n      labels: [\"positive\", \"neutral\", \"negative\"],\n      name: \"Example label grader\"\n    }\n  ]\n});\nconsole.log(evalObj);\n"
+            },
+            "response": "{\n  \"object\": \"eval\",\n  \"id\": \"eval_67b7fa9a81a88190ab4aa417e397ea21\",\n  \"data_source_config\": {\n    \"type\": \"stored_completions\",\n    \"metadata\": {\n      \"usecase\": \"chatbot\"\n    },\n    \"schema\": {\n      \"type\": \"object\",\n      \"properties\": {\n        \"item\": {\n          \"type\": \"object\"\n        },\n        \"sample\": {\n          \"type\": \"object\"\n        }\n      },\n      \"required\": [\n        \"item\",\n        \"sample\"\n      ]\n  },\n  \"testing_criteria\": [\n    {\n      \"name\": \"Example label grader\",\n      \"type\": \"label_model\",\n      \"model\": \"o3-mini\",\n      \"input\": [\n        {\n          \"type\": \"message\",\n          \"role\": \"developer\",\n          \"content\": {\n            \"type\": \"input_text\",\n            \"text\": \"Classify the sentiment of the following statement as one of positive, neutral, or negative\"\n          }\n        },\n        {\n          \"type\": \"message\",\n          \"role\": \"user\",\n          \"content\": {\n            \"type\": \"input_text\",\n            \"text\": \"Statement: {{item.input}}\"\n          }\n        }\n      ],\n      \"passing_labels\": [\n        \"positive\"\n      ],\n      \"labels\": [\n        \"positive\",\n        \"neutral\",\n        \"negative\"\n      ]\n    }\n  ],\n  \"name\": \"Sentiment\",\n  \"created_at\": 1740110490,\n  \"metadata\": {\n    \"description\": \"An eval for sentiment analysis\"\n  }\n}\n"
+          }
+        }
+      }
+    },
+    "/evals/{eval_id}": {
+      "get": {
+        "operationId": "getEval",
+        "tags": [
+          "Evals"
+        ],
+        "summary": "Get an evaluation by ID.\n",
+        "parameters": [
+          {
+            "name": "eval_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the evaluation to retrieve."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The evaluation",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Eval"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Get an eval",
+          "group": "evals",
+          "path": "get",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/evals/eval_67abd54d9b0081909a86353f6fb9317a \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\neval_obj = client.evals.retrieve(\"eval_67abd54d9b0081909a86353f6fb9317a\")\nprint(eval_obj)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst evalObj = await openai.evals.retrieve(\"eval_67abd54d9b0081909a86353f6fb9317a\");\nconsole.log(evalObj);\n"
+            },
+            "response": "{\n  \"object\": \"eval\",\n  \"id\": \"eval_67abd54d9b0081909a86353f6fb9317a\",\n  \"data_source_config\": {\n    \"type\": \"custom\",\n    \"schema\": {\n      \"type\": \"object\",\n      \"properties\": {\n        \"item\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"input\": {\n              \"type\": \"string\"\n            },\n            \"ground_truth\": {\n              \"type\": \"string\"\n            }\n          },\n          \"required\": [\n            \"input\",\n            \"ground_truth\"\n          ]\n        }\n      },\n      \"required\": [\n        \"item\"\n      ]\n    }\n  },\n  \"testing_criteria\": [\n    {\n      \"name\": \"String check\",\n      \"id\": \"String check-2eaf2d8d-d649-4335-8148-9535a7ca73c2\",\n      \"type\": \"string_check\",\n      \"input\": \"{{item.input}}\",\n      \"reference\": \"{{item.ground_truth}}\",\n      \"operation\": \"eq\"\n    }\n  ],\n  \"name\": \"External Data Eval\",\n  \"created_at\": 1739314509,\n  \"metadata\": {},\n}\n"
+          }
+        }
+      },
+      "post": {
+        "operationId": "updateEval",
+        "tags": [
+          "Evals"
+        ],
+        "summary": "Update certain properties of an evaluation.\n",
+        "parameters": [
+          {
+            "name": "eval_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the evaluation to update."
+          }
+        ],
+        "requestBody": {
+          "description": "Request to update an evaluation",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "type": "object",
+                "properties": {
+                  "name": {
+                    "type": "string",
+                    "description": "Rename the evaluation."
+                  },
+                  "metadata": {
+                    "$ref": "#/components/schemas/Metadata"
+                  }
+                }
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "The updated evaluation",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Eval"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update an eval",
+          "group": "evals",
+          "path": "update",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/evals/eval_67abd54d9b0081909a86353f6fb9317a \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"name\": \"Updated Eval\", \"metadata\": {\"description\": \"Updated description\"}}'\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nupdated_eval = client.evals.update(\n  \"eval_67abd54d9b0081909a86353f6fb9317a\",\n  name=\"Updated Eval\",\n  metadata={\"description\": \"Updated description\"}\n)\nprint(updated_eval)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst updatedEval = await openai.evals.update(\n  \"eval_67abd54d9b0081909a86353f6fb9317a\",\n  {\n    name: \"Updated Eval\",\n    metadata: { description: \"Updated description\" }\n  }\n);\nconsole.log(updatedEval);\n"
+            },
+            "response": "{\n  \"object\": \"eval\",\n  \"id\": \"eval_67abd54d9b0081909a86353f6fb9317a\",\n  \"data_source_config\": {\n    \"type\": \"custom\",\n    \"schema\": {\n      \"type\": \"object\",\n      \"properties\": {\n        \"item\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"input\": {\n              \"type\": \"string\"\n            },\n            \"ground_truth\": {\n              \"type\": \"string\"\n            }\n          },\n          \"required\": [\n            \"input\",\n            \"ground_truth\"\n          ]\n        }\n      },\n      \"required\": [\n        \"item\"\n      ]\n    }\n  },\n  \"testing_criteria\": [\n    {\n      \"name\": \"String check\",\n      \"id\": \"String check-2eaf2d8d-d649-4335-8148-9535a7ca73c2\",\n      \"type\": \"string_check\",\n      \"input\": \"{{item.input}}\",\n      \"reference\": \"{{item.ground_truth}}\",\n      \"operation\": \"eq\"\n    }\n  ],\n  \"name\": \"Updated Eval\",\n  \"created_at\": 1739314509,\n  \"metadata\": {\"description\": \"Updated description\"},\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "operationId": "deleteEval",
+        "tags": [
+          "Evals"
+        ],
+        "summary": "Delete an evaluation.\n",
+        "parameters": [
+          {
+            "name": "eval_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the evaluation to delete."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Successfully deleted the evaluation.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "object",
+                  "properties": {
+                    "object": {
+                      "type": "string",
+                      "example": "eval.deleted"
+                    },
+                    "deleted": {
+                      "type": "boolean",
+                      "example": true
+                    },
+                    "eval_id": {
+                      "type": "string",
+                      "example": "eval_abc123"
+                    }
+                  },
+                  "required": [
+                    "object",
+                    "deleted",
+                    "eval_id"
+                  ]
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "Evaluation not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Error"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete an eval",
+          "group": "evals",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/evals/eval_abc123 \\\n  -X DELETE \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\ndeleted = client.evals.delete(\"eval_abc123\")\nprint(deleted)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst deleted = await openai.evals.delete(\"eval_abc123\");\nconsole.log(deleted);\n"
+            },
+            "response": "{\n  \"object\": \"eval.deleted\",\n  \"deleted\": true,\n  \"eval_id\": \"eval_abc123\"\n}\n"
+          }
+        }
+      }
+    },
+    "/evals/{eval_id}/runs": {
+      "get": {
+        "operationId": "getEvalRuns",
+        "tags": [
+          "Evals"
+        ],
+        "summary": "Get a list of runs for an evaluation.\n",
+        "parameters": [
+          {
+            "name": "eval_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the evaluation to retrieve runs for."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Identifier for the last run from the previous pagination request.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Number of runs to retrieve.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order for runs by timestamp. Use `asc` for ascending order or `desc` for descending order. Defaults to `asc`.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "asc",
+                "desc"
+              ],
+              "default": "asc"
+            }
+          },
+          {
+            "name": "status",
+            "in": "query",
+            "description": "Filter runs by status. One of `queued` | `in_progress` | `failed` | `completed` | `canceled`.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "queued",
+                "in_progress",
+                "completed",
+                "canceled",
+                "failed"
+              ]
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A list of runs for the evaluation",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EvalRunList"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Get eval runs",
+          "group": "evals",
+          "path": "get-runs",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/evals/egroup_67abd54d9b0081909a86353f6fb9317a/runs \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nruns = client.evals.runs.list(\"egroup_67abd54d9b0081909a86353f6fb9317a\")\nprint(runs)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst runs = await openai.evals.runs.list(\"egroup_67abd54d9b0081909a86353f6fb9317a\");\nconsole.log(runs);\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\": \"eval.run\",\n      \"id\": \"evalrun_67e0c7d31560819090d60c0780591042\",\n      \"eval_id\": \"eval_67e0c726d560819083f19a957c4c640b\",\n      \"report_url\": \"https://platform.openai.com/evaluations/eval_67e0c726d560819083f19a957c4c640b\",\n      \"status\": \"completed\",\n      \"model\": \"o3-mini\",\n      \"name\": \"bulk_with_negative_examples_o3-mini\",\n      \"created_at\": 1742784467,\n      \"result_counts\": {\n        \"total\": 1,\n        \"errored\": 0,\n        \"failed\": 0,\n        \"passed\": 1\n      },\n      \"per_model_usage\": [\n        {\n          \"model_name\": \"o3-mini\",\n          \"invocation_count\": 1,\n          \"prompt_tokens\": 563,\n          \"completion_tokens\": 874,\n          \"total_tokens\": 1437,\n          \"cached_tokens\": 0\n        }\n      ],\n      \"per_testing_criteria_results\": [\n        {\n          \"testing_criteria\": \"Push Notification Summary Grader-1808cd0b-eeec-4e0b-a519-337e79f4f5d1\",\n          \"passed\": 1,\n          \"failed\": 0\n        }\n      ],\n      \"data_source\": {\n        \"type\": \"completions\",\n        \"source\": {\n          \"type\": \"file_content\",\n          \"content\": [\n            {\n              \"item\": {\n                \"notifications\": \"\\n- New message from Sarah: \\\"Can you call me later?\\\"\\n- Your package has been delivered!\\n- Flash sale: 20% off electronics for the next 2 hours!\\n\"\n              }\n            }\n          ]\n        },\n        \"input_messages\": {\n          \"type\": \"template\",\n          \"template\": [\n            {\n              \"type\": \"message\",\n              \"role\": \"developer\",\n              \"content\": {\n                \"type\": \"input_text\",\n                \"text\": \"\\n\\n\\n\\nYou are a helpful assistant that takes in an array of push notifications and returns a collapsed summary of them.\\nThe push notification will be provided as follows:\\n<push_notifications>\\n...notificationlist...\\n</push_notifications>\\n\\nYou should return just the summary and nothing else.\\n\\n\\nYou should return a summary that is concise and snappy.\\n\\n\\nHere is an example of a good summary:\\n<push_notifications>\\n- Traffic alert: Accident reported on Main Street.- Package out for delivery: Expected by 5 PM.- New friend suggestion: Connect with Emma.\\n</push_notifications>\\n<summary>\\nTraffic alert, package expected by 5pm, suggestion for new friend (Emily).\\n</summary>\\n\\n\\nHere is an example of a bad summary:\\n<push_notifications>\\n- Traffic alert: Accident reported on Main Street.- Package out for delivery: Expected by 5 PM.- New friend suggestion: Connect with Emma.\\n</push_notifications>\\n<summary>\\nTraffic alert reported on main street. You have a package that will arrive by 5pm, Emily is a new friend suggested for you.\\n</summary>\\n\"\n              }\n            },\n            {\n              \"type\": \"message\",\n              \"role\": \"user\",\n              \"content\": {\n                \"type\": \"input_text\",\n                \"text\": \"<push_notifications>{{item.notifications}}</push_notifications>\"\n              }\n            }\n          ]\n        },\n        \"model\": \"o3-mini\",\n        \"sampling_params\": null\n      },\n      \"error\": null,\n      \"metadata\": {}\n    }\n  ],\n  \"first_id\": \"evalrun_67e0c7d31560819090d60c0780591042\",\n  \"last_id\": \"evalrun_67e0c7d31560819090d60c0780591042\",\n  \"has_more\": true\n}\n"
+          }
+        }
+      },
+      "post": {
+        "operationId": "createEvalRun",
+        "tags": [
+          "Evals"
+        ],
+        "summary": "Kicks off a new run for a given evaluation, specifying the data source, and what model configuration to use to test. The datasource will be validated against the schema specified in the config of the evaluation.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "eval_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the evaluation to create a run for."
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateEvalRunRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "201": {
+            "description": "Successfully created a run for the evaluation",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EvalRun"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "Bad request (for example, missing eval object)",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Error"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create eval run",
+          "group": "evals",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/evals/eval_67e579652b548190aaa83ada4b125f47/runs \\\n  -X POST \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"name\":\"gpt-6-astra\",\"data_source\":{\"type\":\"completions\",\"input_messages\":{\"type\":\"template\",\"template\":[{\"role\":\"developer\",\"content\":\"Categorize a given news headline into one of the following topics: Technology, Markets, World, Business, or Sports.\\n\\n# Steps\\n\\n1. Analyze the content of the news headline to understand its primary focus.\\n2. Extract the subject matter, identifying any key indicators or keywords.\\n3. Use the identified indicators to determine the most suitable category out of the five options: Technology, Markets, World, Business, or Sports.\\n4. Ensure only one category is selected per headline.\\n\\n# Output Format\\n\\nRespond with the chosen category as a single word. For instance: \\\"Technology\\\", \\\"Markets\\\", \\\"World\\\", \\\"Business\\\", or \\\"Sports\\\".\\n\\n# Examples\\n\\n**Input**: \\\"Apple Unveils New iPhone Model, Featuring Advanced AI Features\\\"  \\n**Output**: \\\"Technology\\\"\\n\\n**Input**: \\\"Global Stocks Mixed as Investors Await Central Bank Decisions\\\"  \\n**Output**: \\\"Markets\\\"\\n\\n**Input**: \\\"War in Ukraine: Latest Updates on Negotiation Status\\\"  \\n**Output**: \\\"World\\\"\\n\\n**Input**: \\\"Microsoft in Talks to Acquire Gaming Company for $2 Billion\\\"  \\n**Output**: \\\"Business\\\"\\n\\n**Input**: \\\"Manchester United Secures Win in Premier League Football Match\\\"  \\n**Output**: \\\"Sports\\\" \\n\\n# Notes\\n\\n- If the headline appears to fit into more than one category, choose the most dominant theme.\\n- Keywords or phrases such as \\\"stocks\\\", \\\"company acquisition\\\", \\\"match\\\", or technological brands can be good indicators for classification.\\n\"} , {\"role\":\"user\",\"content\":\"{{item.input}}\"}]} ,\"sampling_params\":{\"max_completions_tokens\":2048},\"model\":\"gpt-6-astra\",\"source\":{\"type\":\"file_content\",\"content\":[{\"item\":{\"input\":\"Tech Company Launches Advanced Artificial Intelligence Platform\",\"ground_truth\":\"Technology\"}}]}}}'\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nrun = client.evals.runs.create(\n  \"eval_67e579652b548190aaa83ada4b125f47\",\n  name=\"gpt-6-astra\",\n  data_source={\n    \"type\": \"completions\",\n    \"input_messages\": {\n      \"type\": \"template\",\n      \"template\": [\n        {\n          \"role\": \"developer\",\n          \"content\": \"Categorize a given news headline into one of the following topics: Technology, Markets, World, Business, or Sports.\\n\\n# Steps\\n\\n1. Analyze the content of the news headline to understand its primary focus.\\n2. Extract the subject matter, identifying any key indicators or keywords.\\n3. Use the identified indicators to determine the most suitable category out of the five options: Technology, Markets, World, Business, or Sports.\\n4. Ensure only one category is selected per headline.\\n\\n# Output Format\\n\\nRespond with the chosen category as a single word. For instance: \\\"Technology\\\", \\\"Markets\\\", \\\"World\\\", \\\"Business\\\", or \\\"Sports\\\".\\n\\n# Examples\\n\\n**Input**: \\\"Apple Unveils New iPhone Model, Featuring Advanced AI Features\\\"  \\n**Output**: \\\"Technology\\\"\\n\\n**Input**: \\\"Global Stocks Mixed as Investors Await Central Bank Decisions\\\"  \\n**Output**: \\\"Markets\\\"\\n\\n**Input**: \\\"War in Ukraine: Latest Updates on Negotiation Status\\\"  \\n**Output**: \\\"World\\\"\\n\\n**Input**: \\\"Microsoft in Talks to Acquire Gaming Company for $2 Billion\\\"  \\n**Output**: \\\"Business\\\"\\n\\n**Input**: \\\"Manchester United Secures Win in Premier League Football Match\\\"  \\n**Output**: \\\"Sports\\\" \\n\\n# Notes\\n\\n- If the headline appears to fit into more than one category, choose the most dominant theme.\\n- Keywords or phrases such as \\\"stocks\\\", \\\"company acquisition\\\", \\\"match\\\", or technological brands can be good indicators for classification.\\n\"\n        },\n        {\n          \"role\": \"user\",\n          \"content\": \"{{item.input}}\"\n        }\n      ]\n    },\n    \"sampling_params\": {\n      \"max_completions_tokens\": 2048\n    },\n    \"model\": \"gpt-6-astra\",\n    \"source\": {\n      \"type\": \"file_content\",\n      \"content\": [\n        {\n          \"item\": {\n            \"input\": \"Tech Company Launches Advanced Artificial Intelligence Platform\",\n            \"ground_truth\": \"Technology\"\n          }\n        }\n      ]\n    }\n  }\n)\nprint(run)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst run = await openai.evals.runs.create(\n  \"eval_67e579652b548190aaa83ada4b125f47\",\n  {\n    name: \"gpt-6-astra\",\n    data_source: {\n      type: \"completions\",\n      input_messages: {\n        type: \"template\",\n        template: [\n          {\n            role: \"developer\",\n            content: \"Categorize a given news headline into one of the following topics: Technology, Markets, World, Business, or Sports.\\n\\n# Steps\\n\\n1. Analyze the content of the news headline to understand its primary focus.\\n2. Extract the subject matter, identifying any key indicators or keywords.\\n3. Use the identified indicators to determine the most suitable category out of the five options: Technology, Markets, World, Business, or Sports.\\n4. Ensure only one category is selected per headline.\\n\\n# Output Format\\n\\nRespond with the chosen category as a single word. For instance: \\\"Technology\\\", \\\"Markets\\\", \\\"World\\\", \\\"Business\\\", or \\\"Sports\\\".\\n\\n# Examples\\n\\n**Input**: \\\"Apple Unveils New iPhone Model, Featuring Advanced AI Features\\\"  \\n**Output**: \\\"Technology\\\"\\n\\n**Input**: \\\"Global Stocks Mixed as Investors Await Central Bank Decisions\\\"  \\n**Output**: \\\"Markets\\\"\\n\\n**Input**: \\\"War in Ukraine: Latest Updates on Negotiation Status\\\"  \\n**Output**: \\\"World\\\"\\n\\n**Input**: \\\"Microsoft in Talks to Acquire Gaming Company for $2 Billion\\\"  \\n**Output**: \\\"Business\\\"\\n\\n**Input**: \\\"Manchester United Secures Win in Premier League Football Match\\\"  \\n**Output**: \\\"Sports\\\" \\n\\n# Notes\\n\\n- If the headline appears to fit into more than one category, choose the most dominant theme.\\n- Keywords or phrases such as \\\"stocks\\\", \\\"company acquisition\\\", \\\"match\\\", or technological brands can be good indicators for classification.\\n\"\n          },\n          {\n            role: \"user\",\n            content: \"{{item.input}}\"\n          }\n        ]\n      },\n      sampling_params: {\n        max_completions_tokens: 2048\n      },\n      model: \"gpt-6-astra\",\n      source: {\n        type: \"file_content\",\n        content: [\n          {\n            item: {\n              input: \"Tech Company Launches Advanced Artificial Intelligence Platform\",\n              ground_truth: \"Technology\"\n            }\n          }\n        ]\n      }\n    }\n  }\n);\nconsole.log(run);\n"
+            },
+            "response": "{\n  \"object\": \"eval.run\",\n  \"id\": \"evalrun_67e57965b480819094274e3a32235e4c\",\n  \"eval_id\": \"eval_67e579652b548190aaa83ada4b125f47\",\n  \"report_url\": \"https://platform.openai.com/evaluations/eval_67e579652b548190aaa83ada4b125f47&run_id=evalrun_67e57965b480819094274e3a32235e4c\",\n  \"status\": \"queued\",\n  \"model\": \"gpt-6-astra\",\n  \"name\": \"gpt-6-astra\",\n  \"created_at\": 1743092069,\n  \"result_counts\": {\n    \"total\": 0,\n    \"errored\": 0,\n    \"failed\": 0,\n    \"passed\": 0\n  },\n  \"per_model_usage\": null,\n  \"per_testing_criteria_results\": null,\n  \"data_source\": {\n    \"type\": \"completions\",\n    \"source\": {\n      \"type\": \"file_content\",\n      \"content\": [\n        {\n          \"item\": {\n            \"input\": \"Tech Company Launches Advanced Artificial Intelligence Platform\",\n            \"ground_truth\": \"Technology\"\n          }\n        }\n      ]\n    },\n    \"input_messages\": {\n      \"type\": \"template\",\n      \"template\": [\n        {\n          \"type\": \"message\",\n          \"role\": \"developer\",\n          \"content\": {\n            \"type\": \"input_text\",\n            \"text\": \"Categorize a given news headline into one of the following topics: Technology, Markets, World, Business, or Sports.\\n\\n# Steps\\n\\n1. Analyze the content of the news headline to understand its primary focus.\\n2. Extract the subject matter, identifying any key indicators or keywords.\\n3. Use the identified indicators to determine the most suitable category out of the five options: Technology, Markets, World, Business, or Sports.\\n4. Ensure only one category is selected per headline.\\n\\n# Output Format\\n\\nRespond with the chosen category as a single word. For instance: \\\"Technology\\\", \\\"Markets\\\", \\\"World\\\", \\\"Business\\\", or \\\"Sports\\\".\\n\\n# Examples\\n\\n**Input**: \\\"Apple Unveils New iPhone Model, Featuring Advanced AI Features\\\"  \\n**Output**: \\\"Technology\\\"\\n\\n**Input**: \\\"Global Stocks Mixed as Investors Await Central Bank Decisions\\\"  \\n**Output**: \\\"Markets\\\"\\n\\n**Input**: \\\"War in Ukraine: Latest Updates on Negotiation Status\\\"  \\n**Output**: \\\"World\\\"\\n\\n**Input**: \\\"Microsoft in Talks to Acquire Gaming Company for $2 Billion\\\"  \\n**Output**: \\\"Business\\\"\\n\\n**Input**: \\\"Manchester United Secures Win in Premier League Football Match\\\"  \\n**Output**: \\\"Sports\\\" \\n\\n# Notes\\n\\n- If the headline appears to fit into more than one category, choose the most dominant theme.\\n- Keywords or phrases such as \\\"stocks\\\", \\\"company acquisition\\\", \\\"match\\\", or technological brands can be good indicators for classification.\\n\"\n          }\n        },\n        {\n          \"type\": \"message\",\n          \"role\": \"user\",\n          \"content\": {\n            \"type\": \"input_text\",\n            \"text\": \"{{item.input}}\"\n          }\n        }\n      ]\n    },\n    \"model\": \"gpt-6-astra\",\n    \"sampling_params\": {\n      \"max_completions_tokens\": 2048\n    }\n  },\n  \"error\": null,\n  \"metadata\": {}\n}\n"
+          }
+        }
+      }
+    },
+    "/evals/{eval_id}/runs/{run_id}": {
+      "get": {
+        "operationId": "getEvalRun",
+        "tags": [
+          "Evals"
+        ],
+        "summary": "Get an evaluation run by ID.\n",
+        "parameters": [
+          {
+            "name": "eval_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the evaluation to retrieve runs for."
+          },
+          {
+            "name": "run_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the run to retrieve."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The evaluation run",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EvalRun"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Get an eval run",
+          "group": "evals",
+          "path": "get",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/evals/eval_67abd54d9b0081909a86353f6fb9317a/runs/evalrun_67abd54d60ec8190832b46859da808f7 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nrun = client.evals.runs.retrieve(\n  \"eval_67abd54d9b0081909a86353f6fb9317a\",\n  \"evalrun_67abd54d60ec8190832b46859da808f7\"\n)\nprint(run)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst run = await openai.evals.runs.retrieve(\n  \"evalrun_67abd54d60ec8190832b46859da808f7\",\n  { eval_id: \"eval_67abd54d9b0081909a86353f6fb9317a\" }\n);\nconsole.log(run);\n"
+            },
+            "response": "{\n  \"object\": \"eval.run\",\n  \"id\": \"evalrun_67abd54d60ec8190832b46859da808f7\",\n  \"eval_id\": \"eval_67abd54d9b0081909a86353f6fb9317a\",\n  \"report_url\": \"https://platform.openai.com/evaluations/eval_67abd54d9b0081909a86353f6fb9317a?run_id=evalrun_67abd54d60ec8190832b46859da808f7\",\n  \"status\": \"queued\",\n  \"model\": \"gpt-6-astra\",\n  \"name\": \"gpt-6-astra\",\n  \"created_at\": 1743092069,\n  \"result_counts\": {\n    \"total\": 0,\n    \"errored\": 0,\n    \"failed\": 0,\n    \"passed\": 0\n  },\n  \"per_model_usage\": null,\n  \"per_testing_criteria_results\": null,\n  \"data_source\": {\n    \"type\": \"completions\",\n    \"source\": {\n      \"type\": \"file_content\",\n      \"content\": [\n        {\n          \"item\": {\n            \"input\": \"Tech Company Launches Advanced Artificial Intelligence Platform\",\n            \"ground_truth\": \"Technology\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Central Bank Increases Interest Rates Amid Inflation Concerns\",\n            \"ground_truth\": \"Markets\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"International Summit Addresses Climate Change Strategies\",\n            \"ground_truth\": \"World\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Major Retailer Reports Record-Breaking Holiday Sales\",\n            \"ground_truth\": \"Business\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"National Team Qualifies for World Championship Finals\",\n            \"ground_truth\": \"Sports\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Stock Markets Rally After Positive Economic Data Released\",\n            \"ground_truth\": \"Markets\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Global Manufacturer Announces Merger with Competitor\",\n            \"ground_truth\": \"Business\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Breakthrough in Renewable Energy Technology Unveiled\",\n            \"ground_truth\": \"Technology\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"World Leaders Sign Historic Climate Agreement\",\n            \"ground_truth\": \"World\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Professional Athlete Sets New Record in Championship Event\",\n            \"ground_truth\": \"Sports\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Financial Institutions Adapt to New Regulatory Requirements\",\n            \"ground_truth\": \"Business\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Tech Conference Showcases Advances in Artificial Intelligence\",\n            \"ground_truth\": \"Technology\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Global Markets Respond to Oil Price Fluctuations\",\n            \"ground_truth\": \"Markets\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"International Cooperation Strengthened Through New Treaty\",\n            \"ground_truth\": \"World\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Sports League Announces Revised Schedule for Upcoming Season\",\n            \"ground_truth\": \"Sports\"\n          }\n        }\n      ]\n    },\n    \"input_messages\": {\n      \"type\": \"template\",\n      \"template\": [\n        {\n          \"type\": \"message\",\n          \"role\": \"developer\",\n          \"content\": {\n            \"type\": \"input_text\",\n            \"text\": \"Categorize a given news headline into one of the following topics: Technology, Markets, World, Business, or Sports.\\n\\n# Steps\\n\\n1. Analyze the content of the news headline to understand its primary focus.\\n2. Extract the subject matter, identifying any key indicators or keywords.\\n3. Use the identified indicators to determine the most suitable category out of the five options: Technology, Markets, World, Business, or Sports.\\n4. Ensure only one category is selected per headline.\\n\\n# Output Format\\n\\nRespond with the chosen category as a single word. For instance: \\\"Technology\\\", \\\"Markets\\\", \\\"World\\\", \\\"Business\\\", or \\\"Sports\\\".\\n\\n# Examples\\n\\n**Input**: \\\"Apple Unveils New iPhone Model, Featuring Advanced AI Features\\\"  \\n**Output**: \\\"Technology\\\"\\n\\n**Input**: \\\"Global Stocks Mixed as Investors Await Central Bank Decisions\\\"  \\n**Output**: \\\"Markets\\\"\\n\\n**Input**: \\\"War in Ukraine: Latest Updates on Negotiation Status\\\"  \\n**Output**: \\\"World\\\"\\n\\n**Input**: \\\"Microsoft in Talks to Acquire Gaming Company for $2 Billion\\\"  \\n**Output**: \\\"Business\\\"\\n\\n**Input**: \\\"Manchester United Secures Win in Premier League Football Match\\\"  \\n**Output**: \\\"Sports\\\" \\n\\n# Notes\\n\\n- If the headline appears to fit into more than one category, choose the most dominant theme.\\n- Keywords or phrases such as \\\"stocks\\\", \\\"company acquisition\\\", \\\"match\\\", or technological brands can be good indicators for classification.\\n\"\n          }\n        },\n        {\n          \"type\": \"message\",\n          \"role\": \"user\",\n          \"content\": {\n            \"type\": \"input_text\",\n            \"text\": \"{{item.input}}\"\n          }\n        }\n      ]\n    },\n    \"model\": \"gpt-6-astra\",\n    \"sampling_params\": {\n      \"max_completions_tokens\": 2048\n    }\n  },\n  \"error\": null,\n  \"metadata\": {}\n}\n"
+          }
+        }
+      },
+      "post": {
+        "operationId": "cancelEvalRun",
+        "tags": [
+          "Evals"
+        ],
+        "summary": "Cancel an ongoing evaluation run.\n",
+        "parameters": [
+          {
+            "name": "eval_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the evaluation whose run you want to cancel."
+          },
+          {
+            "name": "run_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the run to cancel."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The canceled eval run object",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EvalRun"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Cancel eval run",
+          "group": "evals",
+          "path": "post",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/evals/eval_67abd54d9b0081909a86353f6fb9317a/runs/evalrun_67abd54d60ec8190832b46859da808f7/cancel \\\n  -X POST \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\ncanceled_run = client.evals.runs.cancel(\n  \"eval_67abd54d9b0081909a86353f6fb9317a\",\n  \"evalrun_67abd54d60ec8190832b46859da808f7\"\n)\nprint(canceled_run)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst canceledRun = await openai.evals.runs.cancel(\n  \"evalrun_67abd54d60ec8190832b46859da808f7\",\n  { eval_id: \"eval_67abd54d9b0081909a86353f6fb9317a\" }\n);\nconsole.log(canceledRun);\n"
+            },
+            "response": "{\n  \"object\": \"eval.run\",\n  \"id\": \"evalrun_67abd54d60ec8190832b46859da808f7\",\n  \"eval_id\": \"eval_67abd54d9b0081909a86353f6fb9317a\",\n  \"report_url\": \"https://platform.openai.com/evaluations/eval_67abd54d9b0081909a86353f6fb9317a?run_id=evalrun_67abd54d60ec8190832b46859da808f7\",\n  \"status\": \"canceled\",\n  \"model\": \"gpt-6-astra\",\n  \"name\": \"gpt-6-astra\",\n  \"created_at\": 1743092069,\n  \"result_counts\": {\n    \"total\": 0,\n    \"errored\": 0,\n    \"failed\": 0,\n    \"passed\": 0\n  },\n  \"per_model_usage\": null,\n  \"per_testing_criteria_results\": null,\n  \"data_source\": {\n    \"type\": \"completions\",\n    \"source\": {\n      \"type\": \"file_content\",\n      \"content\": [\n        {\n          \"item\": {\n            \"input\": \"Tech Company Launches Advanced Artificial Intelligence Platform\",\n            \"ground_truth\": \"Technology\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Central Bank Increases Interest Rates Amid Inflation Concerns\",\n            \"ground_truth\": \"Markets\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"International Summit Addresses Climate Change Strategies\",\n            \"ground_truth\": \"World\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Major Retailer Reports Record-Breaking Holiday Sales\",\n            \"ground_truth\": \"Business\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"National Team Qualifies for World Championship Finals\",\n            \"ground_truth\": \"Sports\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Stock Markets Rally After Positive Economic Data Released\",\n            \"ground_truth\": \"Markets\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Global Manufacturer Announces Merger with Competitor\",\n            \"ground_truth\": \"Business\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Breakthrough in Renewable Energy Technology Unveiled\",\n            \"ground_truth\": \"Technology\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"World Leaders Sign Historic Climate Agreement\",\n            \"ground_truth\": \"World\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Professional Athlete Sets New Record in Championship Event\",\n            \"ground_truth\": \"Sports\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Financial Institutions Adapt to New Regulatory Requirements\",\n            \"ground_truth\": \"Business\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Tech Conference Showcases Advances in Artificial Intelligence\",\n            \"ground_truth\": \"Technology\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Global Markets Respond to Oil Price Fluctuations\",\n            \"ground_truth\": \"Markets\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"International Cooperation Strengthened Through New Treaty\",\n            \"ground_truth\": \"World\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Sports League Announces Revised Schedule for Upcoming Season\",\n            \"ground_truth\": \"Sports\"\n          }\n        }\n      ]\n    },\n    \"input_messages\": {\n      \"type\": \"template\",\n      \"template\": [\n        {\n          \"type\": \"message\",\n          \"role\": \"developer\",\n          \"content\": {\n            \"type\": \"input_text\",\n            \"text\": \"Categorize a given news headline into one of the following topics: Technology, Markets, World, Business, or Sports.\\n\\n# Steps\\n\\n1. Analyze the content of the news headline to understand its primary focus.\\n2. Extract the subject matter, identifying any key indicators or keywords.\\n3. Use the identified indicators to determine the most suitable category out of the five options: Technology, Markets, World, Business, or Sports.\\n4. Ensure only one category is selected per headline.\\n\\n# Output Format\\n\\nRespond with the chosen category as a single word. For instance: \\\"Technology\\\", \\\"Markets\\\", \\\"World\\\", \\\"Business\\\", or \\\"Sports\\\".\\n\\n# Examples\\n\\n**Input**: \\\"Apple Unveils New iPhone Model, Featuring Advanced AI Features\\\"  \\n**Output**: \\\"Technology\\\"\\n\\n**Input**: \\\"Global Stocks Mixed as Investors Await Central Bank Decisions\\\"  \\n**Output**: \\\"Markets\\\"\\n\\n**Input**: \\\"War in Ukraine: Latest Updates on Negotiation Status\\\"  \\n**Output**: \\\"World\\\"\\n\\n**Input**: \\\"Microsoft in Talks to Acquire Gaming Company for $2 Billion\\\"  \\n**Output**: \\\"Business\\\"\\n\\n**Input**: \\\"Manchester United Secures Win in Premier League Football Match\\\"  \\n**Output**: \\\"Sports\\\" \\n\\n# Notes\\n\\n- If the headline appears to fit into more than one category, choose the most dominant theme.\\n- Keywords or phrases such as \\\"stocks\\\", \\\"company acquisition\\\", \\\"match\\\", or technological brands can be good indicators for classification.\\n\"\n          }\n        },\n        {\n          \"type\": \"message\",\n          \"role\": \"user\",\n          \"content\": {\n            \"type\": \"input_text\",\n            \"text\": \"{{item.input}}\"\n          }\n        }\n      ]\n    },\n    \"model\": \"gpt-6-astra\",\n    \"sampling_params\": {\n      \"max_completions_tokens\": 2048\n    }\n  },\n  \"error\": null,\n  \"metadata\": {}\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "operationId": "deleteEvalRun",
+        "tags": [
+          "Evals"
+        ],
+        "summary": "Delete an eval run.\n",
+        "parameters": [
+          {
+            "name": "eval_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the evaluation to delete the run from."
+          },
+          {
+            "name": "run_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the run to delete."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Successfully deleted the eval run",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "object",
+                  "properties": {
+                    "object": {
+                      "type": "string",
+                      "example": "eval.run.deleted"
+                    },
+                    "deleted": {
+                      "type": "boolean",
+                      "example": true
+                    },
+                    "run_id": {
+                      "type": "string",
+                      "example": "evalrun_677469f564d48190807532a852da3afb"
+                    }
+                  }
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "Run not found",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Error"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete eval run",
+          "group": "evals",
+          "path": "delete",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/evals/eval_123abc/runs/evalrun_abc456 \\\n  -X DELETE \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\ndeleted = client.evals.runs.delete(\n  \"eval_123abc\",\n  \"evalrun_abc456\"\n)\nprint(deleted)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst deleted = await openai.evals.runs.delete(\n  \"eval_123abc\",\n  \"evalrun_abc456\"\n);\nconsole.log(deleted);\n"
+            },
+            "response": "{\n  \"object\": \"eval.run.deleted\",\n  \"deleted\": true,\n  \"run_id\": \"evalrun_abc456\"\n}\n"
+          }
+        }
+      }
+    },
+    "/evals/{eval_id}/runs/{run_id}/output_items": {
+      "get": {
+        "operationId": "getEvalRunOutputItems",
+        "tags": [
+          "Evals"
+        ],
+        "summary": "Get a list of output items for an evaluation run.\n",
+        "parameters": [
+          {
+            "name": "eval_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the evaluation to retrieve runs for."
+          },
+          {
+            "name": "run_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the run to retrieve output items for."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Identifier for the last output item from the previous pagination request.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Number of output items to retrieve.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "status",
+            "in": "query",
+            "description": "Filter output items by status. Use `failed` to filter by failed output\nitems or `pass` to filter by passed output items.\n",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "fail",
+                "pass"
+              ]
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order for output items by timestamp. Use `asc` for ascending order or `desc` for descending order. Defaults to `asc`.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "asc",
+                "desc"
+              ],
+              "default": "asc"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A list of output items for the evaluation run",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EvalRunOutputItemList"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Get eval run output items",
+          "group": "evals",
+          "path": "get",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/evals/egroup_67abd54d9b0081909a86353f6fb9317a/runs/erun_67abd54d60ec8190832b46859da808f7/output_items \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\noutput_items = client.evals.runs.output_items.list(\n  \"egroup_67abd54d9b0081909a86353f6fb9317a\",\n  \"erun_67abd54d60ec8190832b46859da808f7\"\n)\nprint(output_items)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst outputItems = await openai.evals.runs.outputItems.list(\n  \"egroup_67abd54d9b0081909a86353f6fb9317a\",\n  \"erun_67abd54d60ec8190832b46859da808f7\"\n);\nconsole.log(outputItems);\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\": \"eval.run.output_item\",\n      \"id\": \"outputitem_67e5796c28e081909917bf79f6e6214d\",\n      \"created_at\": 1743092076,\n      \"run_id\": \"evalrun_67abd54d60ec8190832b46859da808f7\",\n      \"eval_id\": \"eval_67abd54d9b0081909a86353f6fb9317a\",\n      \"status\": \"pass\",\n      \"datasource_item_id\": 5,\n      \"datasource_item\": {\n        \"input\": \"Stock Markets Rally After Positive Economic Data Released\",\n        \"ground_truth\": \"Markets\"\n      },\n      \"results\": [\n        {\n          \"name\": \"String check-a2486074-d803-4445-b431-ad2262e85d47\",\n          \"sample\": null,\n          \"passed\": true,\n          \"score\": 1.0\n        }\n      ],\n      \"sample\": {\n        \"input\": [\n          {\n            \"role\": \"developer\",\n            \"content\": \"Categorize a given news headline into one of the following topics: Technology, Markets, World, Business, or Sports.\\n\\n# Steps\\n\\n1. Analyze the content of the news headline to understand its primary focus.\\n2. Extract the subject matter, identifying any key indicators or keywords.\\n3. Use the identified indicators to determine the most suitable category out of the five options: Technology, Markets, World, Business, or Sports.\\n4. Ensure only one category is selected per headline.\\n\\n# Output Format\\n\\nRespond with the chosen category as a single word. For instance: \\\"Technology\\\", \\\"Markets\\\", \\\"World\\\", \\\"Business\\\", or \\\"Sports\\\".\\n\\n# Examples\\n\\n**Input**: \\\"Apple Unveils New iPhone Model, Featuring Advanced AI Features\\\"  \\n**Output**: \\\"Technology\\\"\\n\\n**Input**: \\\"Global Stocks Mixed as Investors Await Central Bank Decisions\\\"  \\n**Output**: \\\"Markets\\\"\\n\\n**Input**: \\\"War in Ukraine: Latest Updates on Negotiation Status\\\"  \\n**Output**: \\\"World\\\"\\n\\n**Input**: \\\"Microsoft in Talks to Acquire Gaming Company for $2 Billion\\\"  \\n**Output**: \\\"Business\\\"\\n\\n**Input**: \\\"Manchester United Secures Win in Premier League Football Match\\\"  \\n**Output**: \\\"Sports\\\" \\n\\n# Notes\\n\\n- If the headline appears to fit into more than one category, choose the most dominant theme.\\n- Keywords or phrases such as \\\"stocks\\\", \\\"company acquisition\\\", \\\"match\\\", or technological brands can be good indicators for classification.\\n\",\n            \"tool_call_id\": null,\n            \"tool_calls\": null,\n            \"function_call\": null\n          },\n          {\n            \"role\": \"user\",\n            \"content\": \"Stock Markets Rally After Positive Economic Data Released\",\n            \"tool_call_id\": null,\n            \"tool_calls\": null,\n            \"function_call\": null\n          }\n        ],\n        \"output\": [\n          {\n            \"role\": \"assistant\",\n            \"content\": \"Markets\",\n            \"tool_call_id\": null,\n            \"tool_calls\": null,\n            \"function_call\": null\n          }\n        ],\n        \"finish_reason\": \"stop\",\n        \"model\": \"gpt-6-astra\",\n        \"usage\": {\n          \"total_tokens\": 325,\n          \"completion_tokens\": 2,\n          \"prompt_tokens\": 323,\n          \"cached_tokens\": 0\n        },\n        \"error\": null,\n        \"temperature\": 1.0,\n        \"max_completion_tokens\": 2048,\n        \"top_p\": 1.0,\n        \"seed\": 42\n      }\n    }\n  ],\n  \"first_id\": \"outputitem_67e5796c28e081909917bf79f6e6214d\",\n  \"last_id\": \"outputitem_67e5796c28e081909917bf79f6e6214d\",\n  \"has_more\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/evals/{eval_id}/runs/{run_id}/output_items/{output_item_id}": {
+      "get": {
+        "operationId": "getEvalRunOutputItem",
+        "tags": [
+          "Evals"
+        ],
+        "summary": "Get an evaluation run output item by ID.\n",
+        "parameters": [
+          {
+            "name": "eval_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the evaluation to retrieve runs for."
+          },
+          {
+            "name": "run_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the run to retrieve."
+          },
+          {
+            "name": "output_item_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the output item to retrieve."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The evaluation run output item",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EvalRunOutputItem"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Get an output item of an eval run",
+          "group": "evals",
+          "path": "get",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/evals/eval_67abd54d9b0081909a86353f6fb9317a/runs/evalrun_67abd54d60ec8190832b46859da808f7/output_items/outputitem_67abd55eb6548190bb580745d5644a33 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\noutput_item = client.evals.runs.output_items.retrieve(\n  \"eval_67abd54d9b0081909a86353f6fb9317a\",\n  \"evalrun_67abd54d60ec8190832b46859da808f7\",\n  \"outputitem_67abd55eb6548190bb580745d5644a33\"\n)\nprint(output_item)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst outputItem = await openai.evals.runs.outputItems.retrieve(\n  \"outputitem_67abd55eb6548190bb580745d5644a33\",\n  {\n    eval_id: \"eval_67abd54d9b0081909a86353f6fb9317a\",\n    run_id: \"evalrun_67abd54d60ec8190832b46859da808f7\",\n  }\n);\nconsole.log(outputItem);\n"
+            },
+            "response": "{\n  \"object\": \"eval.run.output_item\",\n  \"id\": \"outputitem_67e5796c28e081909917bf79f6e6214d\",\n  \"created_at\": 1743092076,\n  \"run_id\": \"evalrun_67abd54d60ec8190832b46859da808f7\",\n  \"eval_id\": \"eval_67abd54d9b0081909a86353f6fb9317a\",\n  \"status\": \"pass\",\n  \"datasource_item_id\": 5,\n  \"datasource_item\": {\n    \"input\": \"Stock Markets Rally After Positive Economic Data Released\",\n    \"ground_truth\": \"Markets\"\n  },\n  \"results\": [\n    {\n      \"name\": \"String check-a2486074-d803-4445-b431-ad2262e85d47\",\n      \"sample\": null,\n      \"passed\": true,\n      \"score\": 1.0\n    }\n  ],\n  \"sample\": {\n    \"input\": [\n      {\n        \"role\": \"developer\",\n        \"content\": \"Categorize a given news headline into one of the following topics: Technology, Markets, World, Business, or Sports.\\n\\n# Steps\\n\\n1. Analyze the content of the news headline to understand its primary focus.\\n2. Extract the subject matter, identifying any key indicators or keywords.\\n3. Use the identified indicators to determine the most suitable category out of the five options: Technology, Markets, World, Business, or Sports.\\n4. Ensure only one category is selected per headline.\\n\\n# Output Format\\n\\nRespond with the chosen category as a single word. For instance: \\\"Technology\\\", \\\"Markets\\\", \\\"World\\\", \\\"Business\\\", or \\\"Sports\\\".\\n\\n# Examples\\n\\n**Input**: \\\"Apple Unveils New iPhone Model, Featuring Advanced AI Features\\\"  \\n**Output**: \\\"Technology\\\"\\n\\n**Input**: \\\"Global Stocks Mixed as Investors Await Central Bank Decisions\\\"  \\n**Output**: \\\"Markets\\\"\\n\\n**Input**: \\\"War in Ukraine: Latest Updates on Negotiation Status\\\"  \\n**Output**: \\\"World\\\"\\n\\n**Input**: \\\"Microsoft in Talks to Acquire Gaming Company for $2 Billion\\\"  \\n**Output**: \\\"Business\\\"\\n\\n**Input**: \\\"Manchester United Secures Win in Premier League Football Match\\\"  \\n**Output**: \\\"Sports\\\" \\n\\n# Notes\\n\\n- If the headline appears to fit into more than one category, choose the most dominant theme.\\n- Keywords or phrases such as \\\"stocks\\\", \\\"company acquisition\\\", \\\"match\\\", or technological brands can be good indicators for classification.\\n\",\n        \"tool_call_id\": null,\n        \"tool_calls\": null,\n        \"function_call\": null\n      },\n      {\n        \"role\": \"user\",\n        \"content\": \"Stock Markets Rally After Positive Economic Data Released\",\n        \"tool_call_id\": null,\n        \"tool_calls\": null,\n        \"function_call\": null\n      }\n    ],\n    \"output\": [\n      {\n        \"role\": \"assistant\",\n        \"content\": \"Markets\",\n        \"tool_call_id\": null,\n        \"tool_calls\": null,\n        \"function_call\": null\n      }\n    ],\n    \"finish_reason\": \"stop\",\n    \"model\": \"gpt-6-astra\",\n    \"usage\": {\n      \"total_tokens\": 325,\n      \"completion_tokens\": 2,\n      \"prompt_tokens\": 323,\n      \"cached_tokens\": 0\n    },\n    \"error\": null,\n    \"temperature\": 1.0,\n    \"max_completion_tokens\": 2048,\n    \"top_p\": 1.0,\n    \"seed\": 42\n  }\n}\n"
+          }
+        }
+      }
+    },
+    "/files": {
+      "get": {
+        "operationId": "listFiles",
+        "tags": [
+          "Files"
+        ],
+        "summary": "Returns a list of files.",
+        "parameters": [
+          {
+            "in": "query",
+            "name": "purpose",
+            "required": false,
+            "schema": {
+              "type": "string"
+            },
+            "description": "Only return files with the given purpose."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 10,000, and the default is 10,000.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 10000
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.\n",
+            "schema": {
+              "type": "string",
+              "default": "desc",
+              "enum": [
+                "asc",
+                "desc"
+              ]
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ListFilesResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List files",
+          "group": "files",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/files \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.files.list()\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const list = await openai.files.list();\n\n  for await (const file of list) {\n    console.log(file);\n  }\n}\n\nmain();"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"id\": \"file-abc123\",\n      \"object\": \"file\",\n      \"bytes\": 175,\n      \"created_at\": 1613677385,\n      \"expires_at\": 1677614202,\n      \"filename\": \"salesOverview.pdf\",\n      \"purpose\": \"assistants\",\n    },\n    {\n      \"id\": \"file-abc456\",\n      \"object\": \"file\",\n      \"bytes\": 140,\n      \"created_at\": 1613779121,\n      \"expires_at\": 1677614202,\n      \"filename\": \"puppy.jsonl\",\n      \"purpose\": \"fine-tune\",\n    }\n  ],\n  \"first_id\": \"file-abc123\",\n  \"last_id\": \"file-abc456\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      },
+      "post": {
+        "operationId": "createFile",
+        "tags": [
+          "Files"
+        ],
+        "summary": "Upload a file that can be used across various endpoints. Individual files\ncan be up to 512 MB, and each project can store up to 2.5 TB of files in\ntotal. There is no organization-wide storage limit. Uploads to this\nendpoint are rate-limited to 1,000 requests per minute per authenticated\nuser.\n\n- The Assistants API supports files up to 2 million tokens and of specific\n  file types. See the [Assistants Tools guide](https://developers.openai.com/api/docs/guides/tools) for\n  details.\n- The Fine-tuning API only supports `.jsonl` files. The input also has\n  certain required formats for fine-tuning\n  [chat](https://developers.openai.com/api/docs/guides/supervised-fine-tuning#formatting-your-data) or\n  [completions](https://developers.openai.com/api/docs/guides/supervised-fine-tuning#formatting-your-data) models.\n- The Batch API only supports `.jsonl` files up to 200 MB in size. The input\n  also has a specific required\n  [format](https://developers.openai.com/api/docs/guides/batch#1-prepare-your-batch-file).\n- For Retrieval or `file_search` ingestion, upload files here first. If\n  you need to attach multiple uploaded files to the same vector store, use\n  [`/vector_stores/{vector_store_id}/file_batches`](https://developers.openai.com/api/reference/resources/vector_stores/subresources/file_batches/methods/create)\n  instead of attaching them one by one. Vector store attachment has separate\n  limits from file upload, including 2,000 attached files per minute per\n  organization.\n\nPlease [contact us](https://help.openai.com/) if you need to increase these\nstorage limits.\n",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateFileRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/OpenAIFile"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Upload file",
+          "group": "files",
+          "description": "Uploads a file for later use across OpenAI APIs. Uploads to this endpoint are rate-limited to 1,000 requests per minute per authenticated user. For Retrieval or `file_search` ingestion, upload files here first. If you need to attach multiple uploaded files to the same vector store, use vector store file batches instead of attaching them one by one.\n",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/files \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -F purpose=\"fine-tune\" \\\n  -F file=\"@mydata.jsonl\"\n  -F expires_after[anchor]=\"created_at\"\n  -F expires_after[seconds]=2592000\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.files.create(\n  file=open(\"mydata.jsonl\", \"rb\"),\n  purpose=\"fine-tune\",\n  expires_after={\n    \"anchor\": \"created_at\",\n    \"seconds\": 2592000\n  }\n)\n",
+              "javascript": "import fs from \"fs\";\nimport OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const file = await openai.files.create({\n    file: fs.createReadStream(\"mydata.jsonl\"),\n    purpose: \"fine-tune\",\n    expires_after: {\n      anchor: \"created_at\",\n      seconds: 2592000\n    }\n  });\n\n  console.log(file);\n}\n\nmain();"
+            },
+            "response": "{\n  \"id\": \"file-abc123\",\n  \"object\": \"file\",\n  \"bytes\": 120000,\n  \"created_at\": 1677610602,\n  \"expires_at\": 1677614202,\n  \"filename\": \"mydata.jsonl\",\n  \"purpose\": \"fine-tune\",\n}\n"
+          }
+        }
+      }
+    },
+    "/files/{file_id}": {
+      "delete": {
+        "operationId": "deleteFile",
+        "tags": [
+          "Files"
+        ],
+        "summary": "Delete a file and remove it from all vector stores.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "file_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the file to use for this request."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeleteFileResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete file",
+          "group": "files",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/files/file-abc123 \\\n  -X DELETE \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.files.delete(\"file-abc123\")\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const file = await openai.files.delete(\"file-abc123\");\n\n  console.log(file);\n}\n\nmain();"
+            },
+            "response": "{\n  \"id\": \"file-abc123\",\n  \"object\": \"file\",\n  \"deleted\": true\n}\n"
+          }
+        }
+      },
+      "get": {
+        "operationId": "retrieveFile",
+        "tags": [
+          "Files"
+        ],
+        "summary": "Returns information about a specific file.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "file_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the file to use for this request."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/OpenAIFile"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve file",
+          "group": "files",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/files/file-abc123 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.files.retrieve(\"file-abc123\")\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const file = await openai.files.retrieve(\"file-abc123\");\n\n  console.log(file);\n}\n\nmain();"
+            },
+            "response": "{\n  \"id\": \"file-abc123\",\n  \"object\": \"file\",\n  \"bytes\": 120000,\n  \"created_at\": 1677610602,\n  \"expires_at\": 1677614202,\n  \"filename\": \"mydata.jsonl\",\n  \"purpose\": \"fine-tune\",\n}\n"
+          }
+        }
+      }
+    },
+    "/files/{file_id}/content": {
+      "get": {
+        "operationId": "downloadFile",
+        "tags": [
+          "Files"
+        ],
+        "summary": "Returns a response containing the contents of the specified file.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "file_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the file to use for this request."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "string"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve file content",
+          "group": "files",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/files/file-abc123/content \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" > file.jsonl\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\ncontent = client.files.content(\"file-abc123\")\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const response = await openai.files.content(\"file-abc123\");\n  const content = await response.text();\n\n  console.log(content);\n}\n\nmain();\n"
+            }
+          }
+        }
+      }
+    },
+    "/fine_tuning/alpha/graders/run": {
+      "post": {
+        "operationId": "runGrader",
+        "tags": [
+          "Fine-tuning"
+        ],
+        "summary": "Run a grader.\n",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/RunGraderRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RunGraderResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Run grader",
+          "beta": true,
+          "group": "graders",
+          "examples": [
+            {
+              "title": "Score text alignment",
+              "request": {
+                "curl": "curl -X POST https://api.openai.com/v1/fine_tuning/alpha/graders/run \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"grader\": {\n      \"type\": \"score_model\",\n      \"name\": \"Example score model grader\",\n      \"input\": [\n        {\n          \"role\": \"user\",\n          \"content\": [\n            {\n              \"type\": \"input_text\",\n              \"text\": \"Score how close the reference answer is to the model answer on a 0-1 scale. Return only the score.\\n\\nReference answer: {{item.reference_answer}}\\n\\nModel answer: {{sample.output_text}}\"\n            }\n          ]\n        }\n      ],\n      \"model\": \"gpt-5-mini\",\n      \"sampling_params\": {\n        \"temperature\": 1,\n        \"top_p\": 1,\n        \"seed\": 42\n      }\n    },\n    \"item\": {\n      \"reference_answer\": \"fuzzy wuzzy was a bear\"\n    },\n    \"model_sample\": \"fuzzy wuzzy was a bear\"\n  }'\n",
+                "python": "from openai import OpenAI\n\nclient = OpenAI()\nresult = client.fine_tuning.alpha.graders.run(\n  grader={\n    \"type\": \"score_model\",\n    \"name\": \"Example score model grader\",\n    \"input\": [\n      {\n        \"role\": \"user\",\n        \"content\": [\n          {\n            \"type\": \"input_text\",\n            \"text\": \"Score how close the reference answer is to the model answer on a 0-1 scale. Return only the score.\\n\\nReference answer: {{item.reference_answer}}\\n\\nModel answer: {{sample.output_text}}\",\n          }\n        ],\n      }\n    ],\n    \"model\": \"gpt-5-mini\",\n    \"sampling_params\": {\"temperature\": 1, \"top_p\": 1, \"seed\": 42},\n  },\n  item={\"reference_answer\": \"fuzzy wuzzy was a bear\"},\n  model_sample=\"fuzzy wuzzy was a bear\",\n)\nprint(result)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst result = await openai.fineTuning.alpha.graders.run({\n  grader: {\n    type: \"score_model\",\n    name: \"Example score model grader\",\n    input: [\n      {\n        role: \"user\",\n        content: [\n          {\n            type: \"input_text\",\n            text: \"Score how close the reference answer is to the model answer on a 0-1 scale. Return only the score.\\n\\nReference answer: {{item.reference_answer}}\\n\\nModel answer: {{sample.output_text}}\",\n          },\n        ],\n      },\n    ],\n    model: \"gpt-5-mini\",\n    sampling_params: { temperature: 1, top_p: 1, seed: 42 },\n  },\n  item: { reference_answer: \"fuzzy wuzzy was a bear\" },\n  model_sample: \"fuzzy wuzzy was a bear\",\n});\nconsole.log(result);\n"
+              },
+              "response": "{\n  \"reward\": 1.0,\n  \"metadata\": {\n    \"name\": \"Example score model grader\",\n    \"type\": \"score_model\",\n    \"errors\": {\n      \"formula_parse_error\": false,\n      \"sample_parse_error\": false,\n      \"truncated_observation_error\": false,\n      \"unresponsive_reward_error\": false,\n      \"invalid_variable_error\": false,\n      \"other_error\": false,\n      \"python_grader_server_error\": false,\n      \"python_grader_server_error_type\": null,\n      \"python_grader_runtime_error\": false,\n      \"python_grader_runtime_error_details\": null,\n      \"model_grader_server_error\": false,\n      \"model_grader_refusal_error\": false,\n      \"model_grader_parse_error\": false,\n      \"model_grader_server_error_details\": null\n    },\n    \"execution_time\": 4.365238428115845,\n    \"scores\": {},\n    \"token_usage\": {\n      \"prompt_tokens\": 190,\n      \"total_tokens\": 324,\n      \"completion_tokens\": 134,\n      \"cached_tokens\": 0\n    },\n    \"sampled_model_name\": \"gpt-5-mini\"\n  },\n  \"sub_rewards\": {},\n  \"model_grader_token_usage_per_model\": {\n    \"gpt-5-mini\": {\n      \"prompt_tokens\": 190,\n      \"total_tokens\": 324,\n      \"completion_tokens\": 134,\n      \"cached_tokens\": 0\n    }\n  }\n}\n"
+            },
+            {
+              "title": "Score an image caption",
+              "request": {
+                "curl": "curl -X POST https://api.openai.com/v1/fine_tuning/alpha/graders/run \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"grader\": {\n      \"type\": \"score_model\",\n      \"name\": \"Image caption grader\",\n      \"input\": [\n        {\n          \"role\": \"user\",\n          \"content\": [\n            {\n              \"type\": \"input_text\",\n              \"text\": \"Score how well the provided caption matches the image on a 0-1 scale. Only return the score.\\n\\nCaption: {{sample.output_text}}\"\n            },\n            {\n              \"type\": \"input_image\",\n              \"image_url\": \"https://example.com/dog-catching-ball.png\",\n              \"file_id\": null,\n              \"detail\": \"high\"\n            }\n          ]\n        }\n      ],\n      \"model\": \"gpt-5-mini\",\n      \"sampling_params\": {\n        \"temperature\": 0.2\n      }\n    },\n    \"item\": {\n      \"expected_caption\": \"A golden retriever jumps to catch a tennis ball\"\n    },\n    \"model_sample\": \"A dog leaps to grab a tennis ball mid-air\"\n  }'\n"
+              }
+            },
+            {
+              "title": "Score an audio response",
+              "request": {
+                "curl": "curl -X POST https://api.openai.com/v1/fine_tuning/alpha/graders/run \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"grader\": {\n      \"type\": \"score_model\",\n      \"name\": \"Audio clarity grader\",\n      \"input\": [\n        {\n          \"role\": \"user\",\n          \"content\": [\n            {\n              \"type\": \"input_text\",\n              \"text\": \"Listen to the clip and return a confidence score from 0 to 1 that the speaker said: {{item.target_phrase}}\"\n            },\n            {\n              \"type\": \"input_audio\",\n              \"input_audio\": {\n                \"data\": \"{{item.audio_clip_b64}}\",\n                \"format\": \"mp3\"\n              }\n            }\n          ]\n        }\n      ],\n      \"model\": \"gpt-audio\",\n      \"sampling_params\": {\n        \"temperature\": 0.2,\n        \"top_p\": 1,\n        \"seed\": 123\n      }\n    },\n    \"item\": {\n      \"target_phrase\": \"Please deliver the package on Tuesday\",\n      \"audio_clip_b64\": \"<base64-encoded mp3>\"\n    },\n    \"model_sample\": \"Please deliver the package on Tuesday\"\n  }'\n"
+              }
+            }
+          ]
+        }
+      }
+    },
+    "/fine_tuning/alpha/graders/validate": {
+      "post": {
+        "operationId": "validateGrader",
+        "tags": [
+          "Fine-tuning"
+        ],
+        "summary": "Validate a grader.\n",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ValidateGraderRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ValidateGraderResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Validate grader",
+          "beta": true,
+          "group": "graders",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/fine_tuning/alpha/graders/validate \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"grader\": {\n      \"type\": \"string_check\",\n      \"name\": \"Example string check grader\",\n      \"input\": \"{{sample.output_text}}\",\n      \"reference\": \"{{item.label}}\",\n      \"operation\": \"eq\"\n    }\n  }'\n"
+            },
+            "response": "{\n  \"grader\": {\n    \"type\": \"string_check\",\n    \"name\": \"Example string check grader\",\n    \"input\": \"{{sample.output_text}}\",\n    \"reference\": \"{{item.label}}\",\n    \"operation\": \"eq\"\n  }\n}\n"
+          }
+        }
+      }
+    },
+    "/fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions": {
+      "get": {
+        "operationId": "listFineTuningCheckpointPermissions",
+        "tags": [
+          "Fine-tuning"
+        ],
+        "summary": "**NOTE:** This endpoint requires an [admin API key](https://developers.openai.com/api/reference/resources/admin/subresources/organization/subresources/admin_api_keys).\n\nOrganization owners can use this endpoint to view all permissions for a fine-tuned model checkpoint.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "fine_tuned_model_checkpoint",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "ft-AF1WoRqd3aJAHsqc9NY7iL8F"
+            },
+            "description": "The ID of the fine-tuned model checkpoint to get permissions for.\n"
+          },
+          {
+            "name": "project_id",
+            "in": "query",
+            "description": "The ID of the project to get permissions for.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Identifier for the last permission ID from the previous pagination request.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Number of permissions to retrieve.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 10
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "The order in which to retrieve permissions.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "ascending",
+                "descending"
+              ],
+              "default": "descending"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ListFineTuningCheckpointPermissionResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List checkpoint permissions",
+          "group": "fine-tuning",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/fine_tuning/checkpoints/ft:gpt-4o-mini-2024-07-18:org:weather:B7R9VjQd/permissions \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\": \"checkpoint.permission\",\n      \"id\": \"cp_zc4Q7MP6XxulcVzj4MZdwsAB\",\n      \"created_at\": 1721764867,\n      \"project_id\": \"proj_abGMw1llN8IrBb6SvvY5A1iH\"\n    },\n    {\n      \"object\": \"checkpoint.permission\",\n      \"id\": \"cp_enQCFmOTGj3syEpYVhBRLTSy\",\n      \"created_at\": 1721764800,\n      \"project_id\": \"proj_iqGMw1llN8IrBb6SvvY5A1oF\"\n    },\n  ],\n  \"first_id\": \"cp_zc4Q7MP6XxulcVzj4MZdwsAB\",\n  \"last_id\": \"cp_enQCFmOTGj3syEpYVhBRLTSy\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      },
+      "post": {
+        "operationId": "createFineTuningCheckpointPermission",
+        "tags": [
+          "Fine-tuning"
+        ],
+        "summary": "**NOTE:** Calling this endpoint requires an [admin API key](https://developers.openai.com/api/reference/resources/admin/subresources/organization/subresources/admin_api_keys).\n\nThis enables organization owners to share fine-tuned models with other projects in their organization.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "fine_tuned_model_checkpoint",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "ft:gpt-4o-mini-2024-07-18:org:weather:B7R9VjQd"
+            },
+            "description": "The ID of the fine-tuned model checkpoint to create a permission for.\n"
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateFineTuningCheckpointPermissionRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ListFineTuningCheckpointPermissionResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create checkpoint permissions",
+          "group": "fine-tuning",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/fine_tuning/checkpoints/ft:gpt-4o-mini-2024-07-18:org:weather:B7R9VjQd/permissions \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n  -d '{\"project_ids\": [\"proj_abGMw1llN8IrBb6SvvY5A1iH\"]}'\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\": \"checkpoint.permission\",\n      \"id\": \"cp_zc4Q7MP6XxulcVzj4MZdwsAB\",\n      \"created_at\": 1721764867,\n      \"project_id\": \"proj_abGMw1llN8IrBb6SvvY5A1iH\"\n    }\n  ],\n  \"first_id\": \"cp_zc4Q7MP6XxulcVzj4MZdwsAB\",\n  \"last_id\": \"cp_zc4Q7MP6XxulcVzj4MZdwsAB\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      }
+    },
+    "/fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions/{permission_id}": {
+      "delete": {
+        "operationId": "deleteFineTuningCheckpointPermission",
+        "tags": [
+          "Fine-tuning"
+        ],
+        "summary": "**NOTE:** This endpoint requires an [admin API key](https://developers.openai.com/api/reference/resources/admin/subresources/organization/subresources/admin_api_keys).\n\nOrganization owners can use this endpoint to delete a permission for a fine-tuned model checkpoint.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "fine_tuned_model_checkpoint",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "ft:gpt-4o-mini-2024-07-18:org:weather:B7R9VjQd"
+            },
+            "description": "The ID of the fine-tuned model checkpoint to delete a permission for.\n"
+          },
+          {
+            "in": "path",
+            "name": "permission_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "cp_zc4Q7MP6XxulcVzj4MZdwsAB"
+            },
+            "description": "The ID of the fine-tuned model checkpoint permission to delete.\n"
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeleteFineTuningCheckpointPermissionResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete checkpoint permission",
+          "group": "fine-tuning",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/fine_tuning/checkpoints/ft:gpt-4o-mini-2024-07-18:org:weather:B7R9VjQd/permissions/cp_zc4Q7MP6XxulcVzj4MZdwsAB \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n"
+            },
+            "response": "{\n  \"object\": \"checkpoint.permission\",\n  \"id\": \"cp_zc4Q7MP6XxulcVzj4MZdwsAB\",\n  \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/fine_tuning/jobs": {
+      "post": {
+        "operationId": "createFineTuningJob",
+        "tags": [
+          "Fine-tuning"
+        ],
+        "summary": "Creates a fine-tuning job which begins the process of creating a new model from a given dataset.\n\nResponse includes details of the enqueued job including job status and the name of the fine-tuned models once complete.\n\n[Learn more about fine-tuning](https://developers.openai.com/api/docs/guides/model-optimization)\n",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateFineTuningJobRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/FineTuningJob"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create fine-tuning job",
+          "group": "fine-tuning",
+          "examples": [
+            {
+              "title": "Default",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/fine_tuning/jobs \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"training_file\": \"file-BK7bzQj3FfZFXr7DbL6xJwfo\",\n    \"model\": \"gpt-4o-mini\"\n  }'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.fine_tuning.jobs.create(\n  training_file=\"file-abc123\",\n  model=\"gpt-4o-mini\"\n)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const fineTune = await openai.fineTuning.jobs.create({\n    training_file: \"file-abc123\"\n  });\n\n  console.log(fineTune);\n}\n\nmain();\n"
+              },
+              "response": "{\n  \"object\": \"fine_tuning.job\",\n  \"id\": \"ftjob-abc123\",\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n  \"created_at\": 1721764800,\n  \"fine_tuned_model\": null,\n  \"organization_id\": \"org-123\",\n  \"result_files\": [],\n  \"status\": \"queued\",\n  \"validation_file\": null,\n  \"training_file\": \"file-abc123\",\n  \"method\": {\n    \"type\": \"supervised\",\n    \"supervised\": {\n      \"hyperparameters\": {\n        \"batch_size\": \"auto\",\n        \"learning_rate_multiplier\": \"auto\",\n        \"n_epochs\": \"auto\",\n      }\n    }\n  },\n  \"metadata\": null\n}\n"
+            },
+            {
+              "title": "Epochs",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/fine_tuning/jobs \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"training_file\": \"file-abc123\",\n    \"model\": \"gpt-4o-mini\",\n    \"method\": {\n      \"type\": \"supervised\",\n      \"supervised\": {\n        \"hyperparameters\": {\n          \"n_epochs\": 2\n        }\n      }\n    }\n  }'\n",
+                "python": "from openai import OpenAI\nfrom openai.types.fine_tuning import SupervisedMethod, SupervisedHyperparameters\n\nclient = OpenAI()\n\nclient.fine_tuning.jobs.create(\n  training_file=\"file-abc123\",\n  model=\"gpt-4o-mini\",\n  method={\n    \"type\": \"supervised\",\n    \"supervised\": SupervisedMethod(\n      hyperparameters=SupervisedHyperparameters(\n        n_epochs=2\n      )\n    )\n  }\n)\n",
+                "javascript": "import OpenAI from \"openai\";\nimport { SupervisedMethod, SupervisedHyperparameters } from \"openai/resources/fine-tuning/methods\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const fineTune = await openai.fineTuning.jobs.create({\n    training_file: \"file-abc123\",\n    model: \"gpt-4o-mini\",\n    method: {\n      type: \"supervised\",\n      supervised: {\n        hyperparameters: {\n          n_epochs: 2\n        }\n      }\n    }\n  });\n\n  console.log(fineTune);\n}\n\nmain();\n"
+              },
+              "response": "{\n  \"object\": \"fine_tuning.job\",\n  \"id\": \"ftjob-abc123\",\n  \"model\": \"gpt-4o-mini\",\n  \"created_at\": 1721764800,\n  \"fine_tuned_model\": null,\n  \"organization_id\": \"org-123\",\n  \"result_files\": [],\n  \"status\": \"queued\",\n  \"validation_file\": null,\n  \"training_file\": \"file-abc123\",\n  \"hyperparameters\": {\n    \"batch_size\": \"auto\",\n    \"learning_rate_multiplier\": \"auto\",\n    \"n_epochs\": 2\n  },\n  \"method\": {\n    \"type\": \"supervised\",\n    \"supervised\": {\n      \"hyperparameters\": {\n        \"batch_size\": \"auto\",\n        \"learning_rate_multiplier\": \"auto\",\n        \"n_epochs\": 2\n      }\n    }\n  },\n  \"metadata\": null,\n  \"error\": {\n    \"code\": null,\n    \"message\": null,\n    \"param\": null\n  },\n  \"finished_at\": null,\n  \"seed\": 683058546,\n  \"trained_tokens\": null,\n  \"estimated_finish\": null,\n  \"integrations\": [],\n  \"user_provided_suffix\": null,\n  \"usage_metrics\": null,\n  \"shared_with_openai\": false\n}\n"
+            },
+            {
+              "title": "DPO",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/fine_tuning/jobs \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"training_file\": \"file-abc123\",\n    \"validation_file\": \"file-abc123\",\n    \"model\": \"gpt-4o-mini\",\n    \"method\": {\n      \"type\": \"dpo\",\n      \"dpo\": {\n        \"hyperparameters\": {\n          \"beta\": 0.1\n        }\n      }\n    }\n  }'\n",
+                "python": "from openai import OpenAI\nfrom openai.types.fine_tuning import DpoMethod, DpoHyperparameters\n\nclient = OpenAI()\n\nclient.fine_tuning.jobs.create(\n  training_file=\"file-abc\",\n  validation_file=\"file-123\",\n  model=\"gpt-4o-mini\",\n  method={\n    \"type\": \"dpo\",\n    \"dpo\": DpoMethod(\n      hyperparameters=DpoHyperparameters(beta=0.1)\n    )\n  }\n)\n"
+              },
+              "response": "{\n  \"object\": \"fine_tuning.job\",\n  \"id\": \"ftjob-abc\",\n  \"model\": \"gpt-4o-mini\",\n  \"created_at\": 1746130590,\n  \"fine_tuned_model\": null,\n  \"organization_id\": \"org-abc\",\n  \"result_files\": [],\n  \"status\": \"queued\",\n  \"validation_file\": \"file-123\",\n  \"training_file\": \"file-abc\",\n  \"method\": {\n    \"type\": \"dpo\",\n    \"dpo\": {\n      \"hyperparameters\": {\n        \"beta\": 0.1,\n        \"batch_size\": \"auto\",\n        \"learning_rate_multiplier\": \"auto\",\n        \"n_epochs\": \"auto\"\n      }\n    }\n  },\n  \"metadata\": null,\n  \"error\": {\n    \"code\": null,\n    \"message\": null,\n    \"param\": null\n  },\n  \"finished_at\": null,\n  \"hyperparameters\": null,\n  \"seed\": 1036326793,\n  \"estimated_finish\": null,\n  \"integrations\": [],\n  \"user_provided_suffix\": null,\n  \"usage_metrics\": null,\n  \"shared_with_openai\": false\n}\n"
+            },
+            {
+              "title": "Reinforcement",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/fine_tuning/jobs \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"training_file\": \"file-abc\",\n    \"validation_file\": \"file-123\",\n    \"model\": \"o4-mini\",\n    \"method\": {\n      \"type\": \"reinforcement\",\n      \"reinforcement\": {\n        \"grader\": {\n          \"type\": \"string_check\",\n          \"name\": \"Example string check grader\",\n          \"input\": \"{{sample.output_text}}\",\n          \"reference\": \"{{item.label}}\",\n          \"operation\": \"eq\"\n        },\n        \"hyperparameters\": {\n          \"reasoning_effort\": \"medium\"\n        }\n      }\n    }\n  }'\n",
+                "python": "from openai import OpenAI\nfrom openai.types.fine_tuning import ReinforcementMethod, ReinforcementHyperparameters\nfrom openai.types.graders import StringCheckGrader\n\nclient = OpenAI()\n\nclient.fine_tuning.jobs.create(\n  training_file=\"file-abc\",\n  validation_file=\"file-123\",\n  model=\"o4-mini\",\n  method={\n    \"type\": \"reinforcement\",\n    \"reinforcement\": ReinforcementMethod(\n      grader=StringCheckGrader(\n        name=\"Example string check grader\",\n        type=\"string_check\",\n        input=\"{{item.label}}\",\n        operation=\"eq\",\n        reference=\"{{sample.output_text}}\"\n      ),\n      hyperparameters=ReinforcementHyperparameters(\n          reasoning_effort=\"medium\",\n      )\n    )\n  }, \n  seed=42,\n)\n"
+              },
+              "response": "{\n  \"object\": \"fine_tuning.job\",\n  \"id\": \"ftjob-abc123\",\n  \"model\": \"o4-mini\",\n  \"created_at\": 1721764800,\n  \"finished_at\": null,\n  \"fine_tuned_model\": null,\n  \"organization_id\": \"org-123\",\n  \"result_files\": [],\n  \"status\": \"validating_files\",\n  \"validation_file\": \"file-123\",\n  \"training_file\": \"file-abc\",\n  \"trained_tokens\": null,\n  \"error\": {},\n  \"user_provided_suffix\": null,\n  \"seed\": 950189191,\n  \"estimated_finish\": null,\n  \"integrations\": [],\n  \"method\": {\n    \"type\": \"reinforcement\",\n    \"reinforcement\": {\n      \"hyperparameters\": {\n        \"batch_size\": \"auto\",\n        \"learning_rate_multiplier\": \"auto\",\n        \"n_epochs\": \"auto\",\n        \"eval_interval\": \"auto\",\n        \"eval_samples\": \"auto\",\n        \"compute_multiplier\": \"auto\",\n        \"reasoning_effort\": \"medium\"\n      },\n      \"grader\": {\n        \"type\": \"string_check\",\n        \"name\": \"Example string check grader\",\n        \"input\": \"{{sample.output_text}}\",\n        \"reference\": \"{{item.label}}\",\n        \"operation\": \"eq\"\n      },\n      \"response_format\": null\n    }\n  },\n  \"metadata\": null,\n  \"usage_metrics\": null,\n  \"shared_with_openai\": false\n}\n      \n"
+            },
+            {
+              "title": "Validation file",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/fine_tuning/jobs \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"training_file\": \"file-abc123\",\n    \"validation_file\": \"file-abc123\",\n    \"model\": \"gpt-4o-mini\"\n  }'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.fine_tuning.jobs.create(\n  training_file=\"file-abc123\",\n  validation_file=\"file-def456\",\n  model=\"gpt-4o-mini\"\n)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const fineTune = await openai.fineTuning.jobs.create({\n    training_file: \"file-abc123\",\n    validation_file: \"file-abc123\"\n  });\n\n  console.log(fineTune);\n}\n\nmain();\n"
+              },
+              "response": "{\n  \"object\": \"fine_tuning.job\",\n  \"id\": \"ftjob-abc123\",\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n  \"created_at\": 1721764800,\n  \"fine_tuned_model\": null,\n  \"organization_id\": \"org-123\",\n  \"result_files\": [],\n  \"status\": \"queued\",\n  \"validation_file\": \"file-abc123\",\n  \"training_file\": \"file-abc123\",\n  \"method\": {\n    \"type\": \"supervised\",\n    \"supervised\": {\n      \"hyperparameters\": {\n        \"batch_size\": \"auto\",\n        \"learning_rate_multiplier\": \"auto\",\n        \"n_epochs\": \"auto\",\n      }\n    }\n  },\n  \"metadata\": null\n}\n"
+            },
+            {
+              "title": "W&B Integration",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/fine_tuning/jobs \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"training_file\": \"file-abc123\",\n    \"validation_file\": \"file-abc123\",\n    \"model\": \"gpt-4o-mini\",\n    \"integrations\": [\n      {\n        \"type\": \"wandb\",\n        \"wandb\": {\n          \"project\": \"my-wandb-project\",\n          \"name\": \"ft-run-display-name\"\n          \"tags\": [\n            \"first-experiment\", \"v2\"\n          ]\n        }\n      }\n    ]\n  }'\n"
+              },
+              "response": "{\n  \"object\": \"fine_tuning.job\",\n  \"id\": \"ftjob-abc123\",\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n  \"created_at\": 1721764800,\n  \"fine_tuned_model\": null,\n  \"organization_id\": \"org-123\",\n  \"result_files\": [],\n  \"status\": \"queued\",\n  \"validation_file\": \"file-abc123\",\n  \"training_file\": \"file-abc123\",\n  \"integrations\": [\n    {\n      \"type\": \"wandb\",\n      \"wandb\": {\n        \"project\": \"my-wandb-project\",\n        \"entity\": None,\n        \"run_id\": \"ftjob-abc123\"\n      }\n    }\n  ],\n  \"method\": {\n    \"type\": \"supervised\",\n    \"supervised\": {\n      \"hyperparameters\": {\n        \"batch_size\": \"auto\",\n        \"learning_rate_multiplier\": \"auto\",\n        \"n_epochs\": \"auto\",\n      }\n    }\n  },\n  \"metadata\": null\n}\n"
+            }
+          ]
+        }
+      },
+      "get": {
+        "operationId": "listPaginatedFineTuningJobs",
+        "tags": [
+          "Fine-tuning"
+        ],
+        "summary": "List your organization's fine-tuning jobs\n",
+        "parameters": [
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Identifier for the last job from the previous pagination request.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Number of fine-tuning jobs to retrieve.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "in": "query",
+            "name": "metadata",
+            "required": false,
+            "schema": {
+              "type": "object",
+              "nullable": true,
+              "additionalProperties": {
+                "type": "string"
+              }
+            },
+            "style": "deepObject",
+            "explode": true,
+            "description": "Optional metadata filter. To filter, use the syntax `metadata[k]=v`. Alternatively, set `metadata=null` to indicate no metadata.\n"
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ListPaginatedFineTuningJobsResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List fine-tuning jobs",
+          "group": "fine-tuning",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/fine_tuning/jobs?limit=2&metadata[key]=value \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.fine_tuning.jobs.list()\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const list = await openai.fineTuning.jobs.list();\n\n  for await (const fineTune of list) {\n    console.log(fineTune);\n  }\n}\n\nmain();"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\": \"fine_tuning.job\",\n      \"id\": \"ftjob-abc123\",\n      \"model\": \"gpt-4o-mini-2024-07-18\",\n      \"created_at\": 1721764800,\n      \"fine_tuned_model\": null,\n      \"organization_id\": \"org-123\",\n      \"result_files\": [],\n      \"status\": \"queued\",\n      \"validation_file\": null,\n      \"training_file\": \"file-abc123\",\n      \"metadata\": {\n        \"key\": \"value\"\n      }\n    },\n    { ... },\n    { ... }\n  ], \"has_more\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/fine_tuning/jobs/{fine_tuning_job_id}": {
+      "get": {
+        "operationId": "retrieveFineTuningJob",
+        "tags": [
+          "Fine-tuning"
+        ],
+        "summary": "Get info about a fine-tuning job.\n\n[Learn more about fine-tuning](https://developers.openai.com/api/docs/guides/model-optimization)\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "fine_tuning_job_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "ft-AF1WoRqd3aJAHsqc9NY7iL8F"
+            },
+            "description": "The ID of the fine-tuning job.\n"
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/FineTuningJob"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve fine-tuning job",
+          "group": "fine-tuning",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/fine_tuning/jobs/ft-AF1WoRqd3aJAHsqc9NY7iL8F \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.fine_tuning.jobs.retrieve(\"ftjob-abc123\")\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const fineTune = await openai.fineTuning.jobs.retrieve(\"ftjob-abc123\");\n\n  console.log(fineTune);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"object\": \"fine_tuning.job\",\n  \"id\": \"ftjob-abc123\",\n  \"model\": \"davinci-002\",\n  \"created_at\": 1692661014,\n  \"finished_at\": 1692661190,\n  \"fine_tuned_model\": \"ft:davinci-002:my-org:custom_suffix:7q8mpxmy\",\n  \"organization_id\": \"org-123\",\n  \"result_files\": [\n      \"file-abc123\"\n  ],\n  \"status\": \"succeeded\",\n  \"validation_file\": null,\n  \"training_file\": \"file-abc123\",\n  \"hyperparameters\": {\n      \"n_epochs\": 4,\n      \"batch_size\": 1,\n      \"learning_rate_multiplier\": 1.0\n  },\n  \"trained_tokens\": 5768,\n  \"integrations\": [],\n  \"seed\": 0,\n  \"estimated_finish\": 0,\n  \"method\": {\n    \"type\": \"supervised\",\n    \"supervised\": {\n      \"hyperparameters\": {\n        \"n_epochs\": 4,\n        \"batch_size\": 1,\n        \"learning_rate_multiplier\": 1.0\n      }\n    }\n  }\n}\n"
+          }
+        }
+      }
+    },
+    "/fine_tuning/jobs/{fine_tuning_job_id}/cancel": {
+      "post": {
+        "operationId": "cancelFineTuningJob",
+        "tags": [
+          "Fine-tuning"
+        ],
+        "summary": "Immediately cancel a fine-tune job.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "fine_tuning_job_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "ft-AF1WoRqd3aJAHsqc9NY7iL8F"
+            },
+            "description": "The ID of the fine-tuning job to cancel.\n"
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/FineTuningJob"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Cancel fine-tuning",
+          "group": "fine-tuning",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/fine_tuning/jobs/ftjob-abc123/cancel \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.fine_tuning.jobs.cancel(\"ftjob-abc123\")\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const fineTune = await openai.fineTuning.jobs.cancel(\"ftjob-abc123\");\n\n  console.log(fineTune);\n}\nmain();"
+            },
+            "response": "{\n  \"object\": \"fine_tuning.job\",\n  \"id\": \"ftjob-abc123\",\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n  \"created_at\": 1721764800,\n  \"fine_tuned_model\": null,\n  \"organization_id\": \"org-123\",\n  \"result_files\": [],\n  \"status\": \"cancelled\",\n  \"validation_file\": \"file-abc123\",\n  \"training_file\": \"file-abc123\"\n}\n"
+          }
+        }
+      }
+    },
+    "/fine_tuning/jobs/{fine_tuning_job_id}/checkpoints": {
+      "get": {
+        "operationId": "listFineTuningJobCheckpoints",
+        "tags": [
+          "Fine-tuning"
+        ],
+        "summary": "List checkpoints for a fine-tuning job.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "fine_tuning_job_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "ft-AF1WoRqd3aJAHsqc9NY7iL8F"
+            },
+            "description": "The ID of the fine-tuning job to get checkpoints for.\n"
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Identifier for the last checkpoint ID from the previous pagination request.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Number of checkpoints to retrieve.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 10
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ListFineTuningJobCheckpointsResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List fine-tuning checkpoints",
+          "group": "fine-tuning",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/fine_tuning/jobs/ftjob-abc123/checkpoints \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\": \"fine_tuning.job.checkpoint\",\n      \"id\": \"ftckpt_zc4Q7MP6XxulcVzj4MZdwsAB\",\n      \"created_at\": 1721764867,\n      \"fine_tuned_model_checkpoint\": \"ft:gpt-4o-mini-2024-07-18:my-org:custom-suffix:96olL566:ckpt-step-2000\",\n      \"metrics\": {\n        \"full_valid_loss\": 0.134,\n        \"full_valid_mean_token_accuracy\": 0.874\n      },\n      \"fine_tuning_job_id\": \"ftjob-abc123\",\n      \"step_number\": 2000\n    },\n    {\n      \"object\": \"fine_tuning.job.checkpoint\",\n      \"id\": \"ftckpt_enQCFmOTGj3syEpYVhBRLTSy\",\n      \"created_at\": 1721764800,\n      \"fine_tuned_model_checkpoint\": \"ft:gpt-4o-mini-2024-07-18:my-org:custom-suffix:7q8mpxmy:ckpt-step-1000\",\n      \"metrics\": {\n        \"full_valid_loss\": 0.167,\n        \"full_valid_mean_token_accuracy\": 0.781\n      },\n      \"fine_tuning_job_id\": \"ftjob-abc123\",\n      \"step_number\": 1000\n    }\n  ],\n  \"first_id\": \"ftckpt_zc4Q7MP6XxulcVzj4MZdwsAB\",\n  \"last_id\": \"ftckpt_enQCFmOTGj3syEpYVhBRLTSy\",\n  \"has_more\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/fine_tuning/jobs/{fine_tuning_job_id}/events": {
+      "get": {
+        "operationId": "listFineTuningEvents",
+        "tags": [
+          "Fine-tuning"
+        ],
+        "summary": "Get status updates for a fine-tuning job.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "fine_tuning_job_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "ft-AF1WoRqd3aJAHsqc9NY7iL8F"
+            },
+            "description": "The ID of the fine-tuning job to get events for.\n"
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Identifier for the last event from the previous pagination request.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Number of events to retrieve.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ListFineTuningJobEventsResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List fine-tuning events",
+          "group": "fine-tuning",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/fine_tuning/jobs/ftjob-abc123/events \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.fine_tuning.jobs.list_events(\n  fine_tuning_job_id=\"ftjob-abc123\",\n  limit=2\n)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const list = await openai.fineTuning.list_events(id=\"ftjob-abc123\", limit=2);\n\n  for await (const fineTune of list) {\n    console.log(fineTune);\n  }\n}\n\nmain();"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\": \"fine_tuning.job.event\",\n      \"id\": \"ft-event-ddTJfwuMVpfLXseO0Am0Gqjm\",\n      \"created_at\": 1721764800,\n      \"level\": \"info\",\n      \"message\": \"Fine tuning job successfully completed\",\n      \"data\": null,\n      \"type\": \"message\"\n    },\n    {\n      \"object\": \"fine_tuning.job.event\",\n      \"id\": \"ft-event-tyiGuB72evQncpH87xe505Sv\",\n      \"created_at\": 1721764800,\n      \"level\": \"info\",\n      \"message\": \"New fine-tuned model created: ft:gpt-4o-mini:openai::7p4lURel\",\n      \"data\": null,\n      \"type\": \"message\"\n    }\n  ],\n  \"has_more\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/fine_tuning/jobs/{fine_tuning_job_id}/pause": {
+      "post": {
+        "operationId": "pauseFineTuningJob",
+        "tags": [
+          "Fine-tuning"
+        ],
+        "summary": "Pause a fine-tune job.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "fine_tuning_job_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "ft-AF1WoRqd3aJAHsqc9NY7iL8F"
+            },
+            "description": "The ID of the fine-tuning job to pause.\n"
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/FineTuningJob"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Pause fine-tuning",
+          "group": "fine-tuning",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/fine_tuning/jobs/ftjob-abc123/pause \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.fine_tuning.jobs.pause(\"ftjob-abc123\")\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const fineTune = await openai.fineTuning.jobs.pause(\"ftjob-abc123\");\n\n  console.log(fineTune);\n}\nmain();"
+            },
+            "response": "{\n  \"object\": \"fine_tuning.job\",\n  \"id\": \"ftjob-abc123\",\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n  \"created_at\": 1721764800,\n  \"fine_tuned_model\": null,\n  \"organization_id\": \"org-123\",\n  \"result_files\": [],\n  \"status\": \"paused\",\n  \"validation_file\": \"file-abc123\",\n  \"training_file\": \"file-abc123\"\n}\n"
+          }
+        }
+      }
+    },
+    "/fine_tuning/jobs/{fine_tuning_job_id}/resume": {
+      "post": {
+        "operationId": "resumeFineTuningJob",
+        "tags": [
+          "Fine-tuning"
+        ],
+        "summary": "Resume a fine-tune job.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "fine_tuning_job_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "ft-AF1WoRqd3aJAHsqc9NY7iL8F"
+            },
+            "description": "The ID of the fine-tuning job to resume.\n"
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/FineTuningJob"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Resume fine-tuning",
+          "group": "fine-tuning",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/fine_tuning/jobs/ftjob-abc123/resume \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.fine_tuning.jobs.resume(\"ftjob-abc123\")\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const fineTune = await openai.fineTuning.jobs.resume(\"ftjob-abc123\");\n\n  console.log(fineTune);\n}\nmain();"
+            },
+            "response": "{\n  \"object\": \"fine_tuning.job\",\n  \"id\": \"ftjob-abc123\",\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n  \"created_at\": 1721764800,\n  \"fine_tuned_model\": null,\n  \"organization_id\": \"org-123\",\n  \"result_files\": [],\n  \"status\": \"queued\",\n  \"validation_file\": \"file-abc123\",\n  \"training_file\": \"file-abc123\"\n}\n"
+          }
+        }
+      }
+    },
+    "/images/edits": {
+      "post": {
+        "operationId": "createImageEdit",
+        "tags": [
+          "Images"
+        ],
+        "summary": "Creates an edited or extended image given one or more source images and a prompt. This endpoint supports GPT Image models and `dall-e-2`.",
+        "description": "You can call this endpoint with either:\n\n- `multipart/form-data`: use binary uploads via `image` (and optional `mask`).\n- `application/json`: use `images` (and optional `mask`) as references with either `image_url` or `file_id`.\n\nNote that JSON requests use `images` (array) instead of the multipart `image` field.\n",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateImageEditRequest"
+              },
+              "examples": {
+                "multipart_edit": {
+                  "summary": "Multipart form upload (binary image + prompt)",
+                  "value": {
+                    "model": "gpt-image-1.5",
+                    "prompt": "Add a watercolor effect to this image",
+                    "image": "<binary image file>",
+                    "size": "1024x1024",
+                    "quality": "high"
+                  }
+                }
+              }
+            },
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/EditImageBodyJsonParam"
+              },
+              "examples": {
+                "json_with_url": {
+                  "summary": "JSON request with image URL",
+                  "value": {
+                    "model": "gpt-image-1.5",
+                    "prompt": "Add a watercolor effect to this image",
+                    "images": [
+                      {
+                        "image_url": "https://example.com/source-image.png"
+                      }
+                    ],
+                    "size": "1024x1024",
+                    "quality": "high"
+                  }
+                },
+                "json_with_file_id": {
+                  "summary": "JSON request with uploaded file id",
+                  "value": {
+                    "model": "gpt-image-1.5",
+                    "prompt": "Replace the background with a snowy mountain scene",
+                    "images": [
+                      {
+                        "file_id": "file-abc123"
+                      }
+                    ],
+                    "mask": {
+                      "file_id": "file-mask123"
+                    },
+                    "output_format": "png",
+                    "output_compression": 100
+                  }
+                }
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ImagesResponse"
+                }
+              },
+              "text/event-stream": {
+                "schema": {
+                  "$ref": "#/components/schemas/ImageEditStreamEvent"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/InferenceRateLimited"
+          },
+          "503": {
+            "$ref": "#/components/responses/InferenceServiceUnavailable"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create image edit",
+          "group": "images",
+          "examples": [
+            {
+              "title": "Edit image",
+              "request": {
+                "curl": "curl -s -D >(grep -i x-request-id >&2) \\\n  -o >(jq -r '.data[0].b64_json' | base64 --decode > gift-basket.png) \\\n  -X POST \"https://api.openai.com/v1/images/edits\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -F \"model=gpt-image-1.5\" \\\n  -F \"image[]=@body-lotion.png\" \\\n  -F \"image[]=@bath-bomb.png\" \\\n  -F \"image[]=@incense-kit.png\" \\\n  -F \"image[]=@soap.png\" \\\n  -F 'prompt=Create a lovely gift basket with these four items in it'\n",
+                "python": "import base64\nfrom openai import OpenAI\nclient = OpenAI()\n\nprompt = \"\"\"\nGenerate a photorealistic image of a gift basket on a white background\nlabeled 'Relax & Unwind' with a ribbon and handwriting-like font,\ncontaining all the items in the reference pictures.\n\"\"\"\n\nresult = client.images.edit(\n    model=\"gpt-image-1.5\",\n    image=[\n        open(\"body-lotion.png\", \"rb\"),\n        open(\"bath-bomb.png\", \"rb\"),\n        open(\"incense-kit.png\", \"rb\"),\n        open(\"soap.png\", \"rb\"),\n    ],\n    prompt=prompt\n)\n\nimage_base64 = result.data[0].b64_json\nimage_bytes = base64.b64decode(image_base64)\n\n# Save the image to a file\nwith open(\"gift-basket.png\", \"wb\") as f:\n    f.write(image_bytes)\n",
+                "javascript": "import fs from \"fs\";\nimport OpenAI, { toFile } from \"openai\";\n\nconst client = new OpenAI();\n\nconst imageFiles = [\n    \"bath-bomb.png\",\n    \"body-lotion.png\",\n    \"incense-kit.png\",\n    \"soap.png\",\n];\n\nconst images = await Promise.all(\n    imageFiles.map(async (file) =>\n        await toFile(fs.createReadStream(file), null, {\n            type: \"image/png\",\n        })\n    ),\n);\n\nconst rsp = await client.images.edit({\n    model: \"gpt-image-1.5\",\n    image: images,\n    prompt: \"Create a lovely gift basket with these four items in it\",\n});\n\n// Save the image to a file\nconst image_base64 = rsp.data[0].b64_json;\nconst image_bytes = Buffer.from(image_base64, \"base64\");\nfs.writeFileSync(\"basket.png\", image_bytes);\n"
+              }
+            },
+            {
+              "title": "Streaming",
+              "request": {
+                "curl": "curl -s -N -X POST \"https://api.openai.com/v1/images/edits\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -F \"model=gpt-image-1.5\" \\\n  -F \"image[]=@body-lotion.png\" \\\n  -F \"image[]=@bath-bomb.png\" \\\n  -F \"image[]=@incense-kit.png\" \\\n  -F \"image[]=@soap.png\" \\\n  -F 'prompt=Create a lovely gift basket with these four items in it' \\\n  -F \"stream=true\"\n",
+                "python": "from openai import OpenAI\n\nclient = OpenAI()\n\nprompt = \"\"\"\nGenerate a photorealistic image of a gift basket on a white background\nlabeled 'Relax & Unwind' with a ribbon and handwriting-like font,\ncontaining all the items in the reference pictures.\n\"\"\"\n\nstream = client.images.edit(\n    model=\"gpt-image-1.5\",\n    image=[\n        open(\"body-lotion.png\", \"rb\"),\n        open(\"bath-bomb.png\", \"rb\"),\n        open(\"incense-kit.png\", \"rb\"),\n        open(\"soap.png\", \"rb\"),\n    ],\n    prompt=prompt,\n    stream=True\n)\n\nfor event in stream:\n    print(event)\n",
+                "javascript": "import fs from \"fs\";\nimport OpenAI, { toFile } from \"openai\";\n\nconst client = new OpenAI();\n\nconst imageFiles = [\n    \"bath-bomb.png\",\n    \"body-lotion.png\",\n    \"incense-kit.png\",\n    \"soap.png\",\n];\n\nconst images = await Promise.all(\n    imageFiles.map(async (file) =>\n        await toFile(fs.createReadStream(file), null, {\n            type: \"image/png\",\n        })\n    ),\n);\n\nconst stream = await client.images.edit({\n    model: \"gpt-image-1.5\",\n    image: images,\n    prompt: \"Create a lovely gift basket with these four items in it\",\n    stream: true,\n});\n\nfor await (const event of stream) {\n    console.log(event);\n}\n"
+              },
+              "response": "event: image_edit.partial_image\ndata: {\"type\":\"image_edit.partial_image\",\"b64_json\":\"...\",\"partial_image_index\":0}\n\nevent: image_edit.completed\ndata: {\"type\":\"image_edit.completed\",\"b64_json\":\"...\",\"usage\":{\"total_tokens\":100,\"input_tokens\":50,\"output_tokens\":50,\"input_tokens_details\":{\"text_tokens\":10,\"image_tokens\":40}}}\n"
+            }
+          ]
+        }
+      }
+    },
+    "/images/generations": {
+      "post": {
+        "operationId": "createImage",
+        "tags": [
+          "Images"
+        ],
+        "summary": "Creates an image given a prompt. [Learn more](https://developers.openai.com/api/docs/guides/images-vision).\n",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateImageRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ImagesResponse"
+                }
+              },
+              "text/event-stream": {
+                "schema": {
+                  "$ref": "#/components/schemas/ImageGenStreamEvent"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/InferenceRateLimited"
+          },
+          "503": {
+            "$ref": "#/components/responses/InferenceServiceUnavailable"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create image",
+          "group": "images",
+          "examples": [
+            {
+              "title": "Generate image",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/images/generations \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-image-1.5\",\n    \"prompt\": \"A cute baby sea otter\",\n    \"n\": 1,\n    \"size\": \"1024x1024\"\n  }'\n",
+                "python": "import base64\nfrom openai import OpenAI\nclient = OpenAI()\n\nimg = client.images.generate(\n    model=\"gpt-image-1.5\",\n    prompt=\"A cute baby sea otter\",\n    n=1,\n    size=\"1024x1024\"\n)\n\nimage_bytes = base64.b64decode(img.data[0].b64_json)\nwith open(\"output.png\", \"wb\") as f:\n    f.write(image_bytes)\n",
+                "javascript": "import OpenAI from \"openai\";\nimport { writeFile } from \"fs/promises\";\n\nconst client = new OpenAI();\n\nconst img = await client.images.generate({\n  model: \"gpt-image-1.5\",\n  prompt: \"A cute baby sea otter\",\n  n: 1,\n  size: \"1024x1024\"\n});\n\nconst imageBuffer = Buffer.from(img.data[0].b64_json, \"base64\");\nawait writeFile(\"output.png\", imageBuffer);\n"
+              },
+              "response": "{\n  \"created\": 1713833628,\n  \"data\": [\n    {\n      \"b64_json\": \"...\"\n    }\n  ],\n  \"usage\": {\n    \"total_tokens\": 100,\n    \"input_tokens\": 50,\n    \"output_tokens\": 50,\n    \"input_tokens_details\": {\n      \"text_tokens\": 10,\n      \"image_tokens\": 40\n    }\n  }\n}\n"
+            },
+            {
+              "title": "Streaming",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/images/generations \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-image-1.5\",\n    \"prompt\": \"A cute baby sea otter\",\n    \"n\": 1,\n    \"size\": \"1024x1024\",\n    \"stream\": true\n  }' \\\n  --no-buffer\n",
+                "python": "from openai import OpenAI\n\nclient = OpenAI()\n\nstream = client.images.generate(\n    model=\"gpt-image-1.5\",\n    prompt=\"A cute baby sea otter\",\n    n=1,\n    size=\"1024x1024\",\n    stream=True\n)\n\nfor event in stream:\n    print(event)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst client = new OpenAI();\n\nconst stream = await client.images.generate({\n  model: \"gpt-image-1.5\",\n  prompt: \"A cute baby sea otter\",\n  n: 1,\n  size: \"1024x1024\",\n  stream: true,\n});\n\nfor await (const event of stream) {\n  console.log(event);\n}\n"
+              },
+              "response": "event: image_generation.partial_image\ndata: {\"type\":\"image_generation.partial_image\",\"b64_json\":\"...\",\"partial_image_index\":0}\n\nevent: image_generation.completed\ndata: {\"type\":\"image_generation.completed\",\"b64_json\":\"...\",\"usage\":{\"total_tokens\":100,\"input_tokens\":50,\"output_tokens\":50,\"input_tokens_details\":{\"text_tokens\":10,\"image_tokens\":40}}}\n"
+            }
+          ]
+        }
+      }
+    },
+    "/images/variations": {
+      "post": {
+        "operationId": "createImageVariation",
+        "tags": [
+          "Images"
+        ],
+        "summary": "Creates a variation of a given image. This endpoint only supports `dall-e-2`.",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateImageVariationRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ImagesResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create image variation",
+          "group": "images",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/images/variations \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -F image=\"@otter.png\" \\\n  -F n=2 \\\n  -F size=\"1024x1024\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nresponse = client.images.create_variation(\n  image=open(\"image_edit_original.png\", \"rb\"),\n  n=2,\n  size=\"1024x1024\"\n)\n",
+              "javascript": "import fs from \"fs\";\nimport OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const image = await openai.images.createVariation({\n    image: fs.createReadStream(\"otter.png\"),\n  });\n\n  console.log(image.data);\n}\nmain();",
+              "csharp": "using System;\n\nusing OpenAI.Images;\n\nImageClient client = new(\n    model: \"dall-e-2\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nGeneratedImage image = client.GenerateImageVariation(imageFilePath: \"otter.png\");\n\nConsole.WriteLine(image.ImageUri);\n"
+            },
+            "response": "{\n  \"created\": 1589478378,\n  \"data\": [\n    {\n      \"url\": \"https://...\"\n    },\n    {\n      \"url\": \"https://...\"\n    }\n  ]\n}\n"
+          }
+        }
+      }
+    },
+    "/live/sessions": {
+      "post": {
+        "operationId": "create-live",
+        "summary": "Create a Live WebRTC session. Start with the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting).",
+        "description": "Send JSON containing session configuration and transport with type webrtc and the SDP offer. The request starts the session. Apply transport.sdp from the response as the remote answer and wait for session.started on the data channel before sending commands. Audio uses the negotiated media track; omit audio.format and do not send session.start on the data channel. Before integrating, follow the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) to write frontend conversation and delegation instructions and a separate backend prompt.",
+        "tags": [
+          "Live"
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/LiveCreateRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "201": {
+            "description": "Live session created with a WebRTC answer.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/LiveCreateResponse"
+                },
+                "example": {
+                  "session": {
+                    "id": "live_123"
+                  },
+                  "transport": {
+                    "type": "webrtc",
+                    "sdp": "<SDP answer>"
+                  }
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create session",
+          "group": "live",
+          "returns": "Returns 201 Created with the session identifier in session.id and SDP answer in transport.sdp.",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/live/sessions \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"session\":{\"model\":\"gpt-live-1\",\"instructions\":\"Be concise. Ask for clarification when needed.\"},\"transport\":{\"type\":\"webrtc\",\"sdp\":\"<SDP offer>\"}}'"
+            }
+          }
+        }
+      }
+    },
+    "/live/sessions/{session_id}/accept": {
+      "post": {
+        "operationId": "accept-live-session",
+        "summary": "Accept an incoming SIP call. Supply session with type live, the model, and startup configuration. Before accepting calls, follow the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) to write frontend conversation instructions and a separate backend prompt. SIP media format is negotiated; omit audio.format.",
+        "description": "Accept an incoming SIP call. Supply session with type live, the model, and startup configuration. Before accepting calls, follow the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) to write frontend conversation instructions and a separate backend prompt. SIP media format is negotiated; omit audio.format.",
+        "tags": [
+          "Live"
+        ],
+        "parameters": [
+          {
+            "in": "path",
+            "name": "session_id",
+            "required": true,
+            "description": "Opaque Live session identifier from the creation response or incoming-call webhook. Preserve the returned value unchanged, including its prefix.",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/LiveCallAcceptRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Session accept request accepted."
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Accept call",
+          "group": "live-sessions",
+          "returns": "Returns 200 OK when the control request succeeds."
+        }
+      }
+    },
+    "/live/sessions/{session_id}/fork": {
+      "post": {
+        "operationId": "fork-live-session",
+        "summary": "Fork a stored Live session onto a new WebRTC connection.",
+        "description": "Resume the stored conversation using a new WebRTC connection. The model, voice, and frontend instructions are inherited. Omit session or send an empty object to inherit the remaining configuration. Only Responses delegation settings, storage, and frontend data-channel permissions can be overridden. Apply transport.sdp as the remote answer and wait for session.started before sending commands. Do not send session.start on the data channel or supply audio.format; WebRTC negotiates its media format.",
+        "tags": [
+          "Live"
+        ],
+        "parameters": [
+          {
+            "in": "path",
+            "name": "session_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the stored Live session to fork."
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/LiveForkRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "201": {
+            "description": "Forked Live session created with a WebRTC answer.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/LiveCreateResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Fork session",
+          "group": "live",
+          "returns": "The new session identifier in session.id and SDP answer in transport.sdp.",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/live/sessions/live_123/fork \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"session\":{},\"transport\":{\"type\":\"webrtc\",\"sdp\":\"<SDP offer>\"}}'"
+            }
+          }
+        }
+      }
+    },
+    "/live/sessions/{session_id}/hangup": {
+      "post": {
+        "operationId": "hangup-live-session",
+        "summary": "End a SIP call identified by session_id.",
+        "description": "End a SIP call identified by session_id.",
+        "tags": [
+          "Live"
+        ],
+        "parameters": [
+          {
+            "in": "path",
+            "name": "session_id",
+            "required": true,
+            "description": "Opaque Live session identifier from the creation response or incoming-call webhook. Preserve the returned value unchanged, including its prefix.",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Session hangup request accepted."
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Hang up session",
+          "group": "live-sessions",
+          "returns": "Returns 200 OK when the control request succeeds."
+        }
+      }
+    },
+    "/live/sessions/{session_id}/refer": {
+      "post": {
+        "operationId": "refer-live-session",
+        "summary": "Transfer a SIP call to another destination. Supply a nonblank target_uri for the SIP Refer-To header.",
+        "description": "Transfer a SIP call to another destination. Supply a nonblank target_uri for the SIP Refer-To header.",
+        "tags": [
+          "Live"
+        ],
+        "parameters": [
+          {
+            "in": "path",
+            "name": "session_id",
+            "required": true,
+            "description": "Opaque Live session identifier from the creation response or incoming-call webhook. Preserve the returned value unchanged, including its prefix.",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/LiveCallReferRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Session refer request accepted."
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Transfer call",
+          "group": "live-sessions",
+          "returns": "Returns 200 OK when the control request succeeds."
+        }
+      }
+    },
+    "/live/sessions/{session_id}/reject": {
+      "post": {
+        "operationId": "reject-live-session",
+        "summary": "Reject an incoming SIP call. Send a required SIP rejection status_code between 300 and 699.",
+        "description": "Reject an incoming SIP call. Send a required SIP rejection status_code between 300 and 699.",
+        "tags": [
+          "Live"
+        ],
+        "parameters": [
+          {
+            "in": "path",
+            "name": "session_id",
+            "required": true,
+            "description": "Opaque Live session identifier from the creation response or incoming-call webhook. Preserve the returned value unchanged, including its prefix.",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/LiveCallRejectRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Session reject request accepted."
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Reject call",
+          "group": "live-sessions",
+          "returns": "Returns 200 OK when the control request succeeds."
+        }
+      }
+    },
+    "/models": {
+      "get": {
+        "operationId": "listModels",
+        "tags": [
+          "Models"
+        ],
+        "summary": "Lists the currently available models, and provides basic information about each one such as the owner and availability.",
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ListModelsResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List models",
+          "group": "models",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/models \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.models.list()\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const list = await openai.models.list();\n\n  for await (const model of list) {\n    console.log(model);\n  }\n}\nmain();",
+              "csharp": "using System;\n\nusing OpenAI.Models;\n\nOpenAIModelClient client = new(\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nforeach (var model in client.GetModels().Value)\n{\n    Console.WriteLine(model.Id);\n}\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"id\": \"model-id-0\",\n      \"object\": \"model\",\n      \"created\": 1686935002,\n      \"owned_by\": \"organization-owner\",\n      \"shutdown_date\": null\n    },\n    {\n      \"id\": \"model-id-1\",\n      \"object\": \"model\",\n      \"created\": 1686935002,\n      \"owned_by\": \"organization-owner\",\n      \"shutdown_date\": null\n    },\n    {\n      \"id\": \"model-id-2\",\n      \"object\": \"model\",\n      \"created\": 1686935002,\n      \"owned_by\": \"openai\",\n      \"shutdown_date\": \"2026-10-23\"\n    },\n  ]\n}\n"
+          }
+        }
+      }
+    },
+    "/models/{model}": {
+      "get": {
+        "operationId": "retrieveModel",
+        "tags": [
+          "Models"
+        ],
+        "summary": "Retrieves a model instance, providing basic information about the model such as the owner and permissioning.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "model",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "gpt-6-astra"
+            },
+            "description": "The ID of the model to use for this request"
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Model"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve model",
+          "group": "models",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/models/gpt-6-astra \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.models.retrieve(\"gpt-6-astra\")\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const model = await openai.models.retrieve(\"gpt-6-astra\");\n\n  console.log(model);\n}\n\nmain();",
+              "csharp": "using System;\nusing System.ClientModel;\n\nusing OpenAI.Models;\n\n  OpenAIModelClient client = new(\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nClientResult<OpenAIModel> model = client.GetModel(\"babbage-002\");\nConsole.WriteLine(model.Value.Id);\n"
+            },
+            "response": "{\n  \"id\": \"gpt-6-astra\",\n  \"object\": \"model\",\n  \"created\": 1686935002,\n  \"owned_by\": \"openai\",\n  \"shutdown_date\": \"2026-10-23\"\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "operationId": "deleteModel",
+        "tags": [
+          "Models"
+        ],
+        "summary": "Delete a fine-tuned model. You must have the Owner role in your organization to delete a model.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "model",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "ft:gpt-4o-mini:acemeco:suffix:abc123"
+            },
+            "description": "The model to delete"
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeleteModelResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete a fine-tuned model",
+          "group": "models",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/models/ft:gpt-4o-mini:acemeco:suffix:abc123 \\\n  -X DELETE \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nclient.models.delete(\"ft:gpt-4o-mini:acemeco:suffix:abc123\")\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const model = await openai.models.delete(\"ft:gpt-4o-mini:acemeco:suffix:abc123\");\n  \n  console.log(model);\n}\nmain();",
+              "csharp": "using System;\nusing System.ClientModel;\n\nusing OpenAI.Models;\n\nOpenAIModelClient client = new(\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nClientResult success = client.DeleteModel(\"ft:gpt-4o-mini:acemeco:suffix:abc123\");\nConsole.WriteLine(success);\n"
+            },
+            "response": "{\n  \"id\": \"ft:gpt-4o-mini:acemeco:suffix:abc123\",\n  \"object\": \"model\",\n  \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/moderations": {
+      "post": {
+        "operationId": "createModeration",
+        "tags": [
+          "Moderations"
+        ],
+        "summary": "Classifies if text and/or image inputs are potentially harmful. Learn\nmore in the [moderation guide](https://developers.openai.com/api/docs/guides/moderation).\n",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateModerationRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/CreateModerationResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/InferenceRateLimited"
+          },
+          "503": {
+            "$ref": "#/components/responses/InferenceServiceUnavailable"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create moderation",
+          "group": "moderations",
+          "examples": [
+            {
+              "title": "Single string",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/moderations \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"input\": \"I want to kill them.\"\n  }'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\nmoderation = client.moderations.create(input=\"I want to kill them.\")\nprint(moderation)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const moderation = await openai.moderations.create({ input: \"I want to kill them.\" });\n\n  console.log(moderation);\n}\nmain();\n",
+                "csharp": "using System;\nusing System.ClientModel;\n\nusing OpenAI.Moderations;\n\nModerationClient client = new(\n    model: \"omni-moderation-latest\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nClientResult<ModerationResult> moderation = client.ClassifyText(\"I want to kill them.\");\n"
+              },
+              "response": "{\n  \"id\": \"modr-AB8CjOTu2jiq12hp1AQPfeqFWaORR\",\n  \"model\": \"text-moderation-007\",\n  \"results\": [\n    {\n      \"flagged\": true,\n      \"categories\": {\n        \"sexual\": false,\n        \"hate\": false,\n        \"harassment\": true,\n        \"self-harm\": false,\n        \"sexual/minors\": false,\n        \"hate/threatening\": false,\n        \"violence/graphic\": false,\n        \"self-harm/intent\": false,\n        \"self-harm/instructions\": false,\n        \"harassment/threatening\": true,\n        \"violence\": true\n      },\n      \"category_scores\": {\n        \"sexual\": 0.000011726012417057063,\n        \"hate\": 0.22706663608551025,\n        \"harassment\": 0.5215635299682617,\n        \"self-harm\": 2.227119921371923e-6,\n        \"sexual/minors\": 7.107352217872176e-8,\n        \"hate/threatening\": 0.023547329008579254,\n        \"violence/graphic\": 0.00003391829886822961,\n        \"self-harm/intent\": 1.646940972932498e-6,\n        \"self-harm/instructions\": 1.1198755256458526e-9,\n        \"harassment/threatening\": 0.5694745779037476,\n        \"violence\": 0.9971134662628174\n      }\n    }\n  ]\n}\n"
+            },
+            {
+              "title": "Image and text",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/moderations \\\n  -X POST \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"omni-moderation-latest\",\n    \"input\": [\n      { \"type\": \"text\", \"text\": \"...text to classify goes here...\" },\n      {\n        \"type\": \"image_url\",\n        \"image_url\": {\n          \"url\": \"https://example.com/image.png\"\n        }\n      }\n    ]\n  }'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\nresponse = client.moderations.create(\n    model=\"omni-moderation-latest\",\n    input=[\n        {\"type\": \"text\", \"text\": \"...text to classify goes here...\"},\n        {\n            \"type\": \"image_url\",\n            \"image_url\": {\n                \"url\": \"https://example.com/image.png\",\n                # can also use base64 encoded image URLs\n                # \"url\": \"data:image/jpeg;base64,abcdefg...\"\n            }\n        },\n    ],\n)\n\nprint(response)\n",
+                "javascript": "import OpenAI from \"openai\";\nconst openai = new OpenAI();\n\nconst moderation = await openai.moderations.create({\n    model: \"omni-moderation-latest\",\n    input: [\n        { type: \"text\", text: \"...text to classify goes here...\" },\n        {\n            type: \"image_url\",\n            image_url: {\n                url: \"https://example.com/image.png\"\n                // can also use base64 encoded image URLs\n                // url: \"data:image/jpeg;base64,abcdefg...\"\n            }\n        }\n    ],\n});\n\nconsole.log(moderation);\n"
+              },
+              "response": "{\n  \"id\": \"modr-0d9740456c391e43c445bf0f010940c7\",\n  \"model\": \"omni-moderation-latest\",\n  \"results\": [\n    {\n      \"flagged\": true,\n      \"categories\": {\n        \"harassment\": true,\n        \"harassment/threatening\": true,\n        \"sexual\": false,\n        \"hate\": false,\n        \"hate/threatening\": false,\n        \"illicit\": false,\n        \"illicit/violent\": false,\n        \"self-harm/intent\": false,\n        \"self-harm/instructions\": false,\n        \"self-harm\": false,\n        \"sexual/minors\": false,\n        \"violence\": true,\n        \"violence/graphic\": true\n      },\n      \"category_scores\": {\n        \"harassment\": 0.8189693396524255,\n        \"harassment/threatening\": 0.804985420696006,\n        \"sexual\": 1.573112165348997e-6,\n        \"hate\": 0.007562942636942845,\n        \"hate/threatening\": 0.004208854591835476,\n        \"illicit\": 0.030535955153511665,\n        \"illicit/violent\": 0.008925306722380033,\n        \"self-harm/intent\": 0.00023023930975076432,\n        \"self-harm/instructions\": 0.0002293869201073356,\n        \"self-harm\": 0.012598046106750154,\n        \"sexual/minors\": 2.212566909570261e-8,\n        \"violence\": 0.9999992735124786,\n        \"violence/graphic\": 0.843064871157054\n      },\n      \"category_applied_input_types\": {\n        \"harassment\": [\n          \"text\"\n        ],\n        \"harassment/threatening\": [\n          \"text\"\n        ],\n        \"sexual\": [\n          \"text\",\n          \"image\"\n        ],\n        \"hate\": [\n          \"text\"\n        ],\n        \"hate/threatening\": [\n          \"text\"\n        ],\n        \"illicit\": [\n          \"text\"\n        ],\n        \"illicit/violent\": [\n          \"text\"\n        ],\n        \"self-harm/intent\": [\n          \"text\",\n          \"image\"\n        ],\n        \"self-harm/instructions\": [\n          \"text\",\n          \"image\"\n        ],\n        \"self-harm\": [\n          \"text\",\n          \"image\"\n        ],\n        \"sexual/minors\": [\n          \"text\"\n        ],\n        \"violence\": [\n          \"text\",\n          \"image\"\n        ],\n        \"violence/graphic\": [\n          \"text\",\n          \"image\"\n        ]\n      }\n    }\n  ]\n}\n"
+            }
+          ]
+        }
+      }
+    },
+    "/organization/admin_api_keys": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "List organization API keys",
+        "operationId": "admin-api-keys-list",
+        "description": "Retrieve a paginated list of organization admin API keys.",
+        "parameters": [
+          {
+            "in": "query",
+            "name": "after",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "nullable": true,
+              "description": "Return keys with IDs that come after this ID in the pagination order."
+            }
+          },
+          {
+            "in": "query",
+            "name": "order",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "asc",
+                "desc"
+              ],
+              "default": "asc",
+              "description": "Order results by creation time, ascending or descending."
+            }
+          },
+          {
+            "in": "query",
+            "name": "limit",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20,
+              "description": "Maximum number of keys to return."
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A list of organization API keys.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ApiKeyList"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List all organization and project API keys.",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/admin_api_keys?after=key_abc&limit=20 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\": \"organization.admin_api_key\",\n      \"id\": \"key_abc\",\n      \"name\": \"Main Admin Key\",\n      \"redacted_value\": \"sk-admin...def\",\n      \"created_at\": 1711471533,\n      \"expires_at\": 1714063533,\n      \"last_used_at\": 1711471534,\n      \"owner\": {\n        \"type\": \"service_account\",\n        \"object\": \"organization.service_account\",\n        \"id\": \"sa_456\",\n        \"name\": \"My Service Account\",\n        \"created_at\": 1711471533,\n        \"role\": \"member\"\n      }\n    }\n  ],\n  \"first_id\": \"key_abc\",\n  \"last_id\": \"key_abc\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Create an organization admin API key",
+        "operationId": "admin-api-keys-create",
+        "description": "Create a new admin-level API key for the organization.",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "type": "object",
+                "required": [
+                  "name"
+                ],
+                "properties": {
+                  "name": {
+                    "type": "string",
+                    "example": "New Admin Key"
+                  },
+                  "expires_in_seconds": {
+                    "type": "integer",
+                    "minimum": 1,
+                    "maximum": 31536000,
+                    "example": 2592000,
+                    "description": "The number of seconds until the API key expires. Omit this field for a key that does not expire."
+                  }
+                }
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "The newly created admin API key.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/AdminApiKeyCreateResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create admin API key",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/admin_api_keys \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"name\": \"New Admin Key\",\n      \"expires_in_seconds\": 2592000\n  }'\n"
+            },
+            "response": "{\n  \"object\": \"organization.admin_api_key\",\n  \"id\": \"key_xyz\",\n  \"name\": \"New Admin Key\",\n  \"redacted_value\": \"sk-admin...xyz\",\n  \"created_at\": 1711471533,\n  \"expires_at\": 1714063533,\n  \"last_used_at\": 1711471534,\n  \"owner\": {\n    \"type\": \"user\",\n    \"object\": \"organization.user\",\n    \"id\": \"user_123\",\n    \"name\": \"John Doe\",\n    \"created_at\": 1711471533,\n    \"role\": \"owner\"\n  },\n  \"value\": \"sk-admin-1234abcd\"\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/admin_api_keys/{key_id}": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Retrieve a single organization API key",
+        "operationId": "admin-api-keys-get",
+        "description": "Get details for a specific organization API key by its ID.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "key_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "description": "The ID of the API key."
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Details of the requested API key.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/AdminApiKey"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve admin API key",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/admin_api_keys/key_abc \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n  \"object\": \"organization.admin_api_key\",\n  \"id\": \"key_abc\",\n  \"name\": \"Main Admin Key\",\n  \"redacted_value\": \"sk-admin...xyz\",\n  \"created_at\": 1711471533,\n  \"last_used_at\": 1711471534,\n  \"owner\": {\n    \"type\": \"user\",\n    \"object\": \"organization.user\",\n    \"id\": \"user_123\",\n    \"name\": \"John Doe\",\n    \"created_at\": 1711471533,\n    \"role\": \"owner\"\n  }\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Delete an organization admin API key",
+        "operationId": "admin-api-keys-delete",
+        "description": "Delete the specified admin API key.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "key_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "description": "The ID of the API key to be deleted."
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Confirmation that the API key was deleted.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "object",
+                  "properties": {
+                    "id": {
+                      "type": "string",
+                      "example": "key_abc"
+                    },
+                    "object": {
+                      "type": "string",
+                      "enum": [
+                        "organization.admin_api_key.deleted"
+                      ],
+                      "example": "organization.admin_api_key.deleted",
+                      "x-stainless-const": true
+                    },
+                    "deleted": {
+                      "type": "boolean",
+                      "example": true
+                    }
+                  },
+                  "required": [
+                    "id",
+                    "object",
+                    "deleted"
+                  ]
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete admin API key",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/organization/admin_api_keys/key_abc \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n  \"id\": \"key_abc\",\n  \"object\": \"organization.admin_api_key.deleted\",\n  \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/audit_logs": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "List user actions and configuration changes within this organization.",
+        "operationId": "list-audit-logs",
+        "tags": [
+          "Audit Logs"
+        ],
+        "parameters": [
+          {
+            "name": "effective_at",
+            "in": "query",
+            "description": "Return only events whose `effective_at` (Unix seconds) is in this range.",
+            "required": false,
+            "schema": {
+              "type": "object",
+              "properties": {
+                "gt": {
+                  "type": "integer",
+                  "description": "Return only events whose `effective_at` (Unix seconds) is greater than this value."
+                },
+                "gte": {
+                  "type": "integer",
+                  "description": "Return only events whose `effective_at` (Unix seconds) is greater than or equal to this value."
+                },
+                "lt": {
+                  "type": "integer",
+                  "description": "Return only events whose `effective_at` (Unix seconds) is less than this value."
+                },
+                "lte": {
+                  "type": "integer",
+                  "description": "Return only events whose `effective_at` (Unix seconds) is less than or equal to this value."
+                }
+              }
+            }
+          },
+          {
+            "name": "project_ids[]",
+            "in": "query",
+            "description": "Return only events for these projects.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "event_types[]",
+            "in": "query",
+            "description": "Return only events with a `type` in one of these values. For example, `project.created`. For all options, see the documentation for the [audit log object](https://developers.openai.com/api/reference/resources/admin/subresources/organization/subresources/audit_logs).",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "$ref": "#/components/schemas/AuditLogEventType"
+              }
+            }
+          },
+          {
+            "name": "actor_ids[]",
+            "in": "query",
+            "description": "Return only events performed by these actors. Can be a user ID, a service account ID, or an api key tracking ID.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "actor_emails[]",
+            "in": "query",
+            "description": "Return only events performed by users with these emails.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "resource_ids[]",
+            "in": "query",
+            "description": "Return only events performed on these targets. For example, a project ID updated. For ChatGPT connector role events, use the workspace connector resource ID shown in `details.id`, such as `<workspace_id>__<connector_id>`.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "tenant_only",
+            "in": "query",
+            "description": "Return only tenant-scoped events associated with this organization. Required for tenant-scoped events such as `role.bound_to_resource` and `role.unbound_from_resource`. When `true`, all supplied event types must be tenant-scoped.",
+            "required": false,
+            "schema": {
+              "type": "boolean",
+              "default": false
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "before",
+            "in": "query",
+            "description": "A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.\n",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Audit logs listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ListAuditLogsResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List audit logs",
+          "group": "audit-logs",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/audit_logs \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n-H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"id\": \"audit_log-xxx_yyyymmdd\",\n            \"type\": \"project.archived\",\n            \"effective_at\": 1722461446,\n            \"actor\": {\n                \"type\": \"api_key\",\n                \"api_key\": {\n                    \"type\": \"user\",\n                    \"user\": {\n                        \"id\": \"user-xxx\",\n                        \"email\": \"user@example.com\"\n                    }\n                }\n            },\n            \"project.archived\": {\n                \"id\": \"proj_abc\"\n            },\n        },\n        {\n            \"id\": \"audit_log-yyy__20240101\",\n            \"type\": \"api_key.updated\",\n            \"effective_at\": 1720804190,\n            \"actor\": {\n                \"type\": \"session\",\n                \"session\": {\n                    \"user\": {\n                        \"id\": \"user-xxx\",\n                        \"email\": \"user@example.com\"\n                    },\n                    \"ip_address\": \"127.0.0.1\",\n                    \"user_agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36\",\n                    \"ja3\": \"a497151ce4338a12c4418c44d375173e\",\n                    \"ja4\": \"q13d0313h3_55b375c5d22e_c7319ce65786\",\n                    \"ip_address_details\": {\n                      \"country\": \"US\",\n                      \"city\": \"San Francisco\",\n                      \"region\": \"California\",\n                      \"region_code\": \"CA\",\n                      \"asn\": \"1234\",\n                      \"latitude\": \"37.77490\",\n                      \"longitude\": \"-122.41940\"\n                    }\n                }\n            },\n            \"api_key.updated\": {\n                \"id\": \"key_xxxx\",\n                \"data\": {\n                    \"scopes\": [\"resource_2.operation_2\"]\n                }\n            },\n        }\n    ],\n    \"first_id\": \"audit_log-xxx__20240101\",\n    \"last_id\": \"audit_log_yyy__20240101\",\n    \"has_more\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/certificates": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "List uploaded certificates for this organization.",
+        "operationId": "listOrganizationCertificates",
+        "tags": [
+          "Certificates"
+        ],
+        "parameters": [
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.\n",
+            "schema": {
+              "type": "string",
+              "default": "desc",
+              "enum": [
+                "asc",
+                "desc"
+              ]
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Certificates listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ListCertificatesResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List organization certificates",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/certificates \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\"\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\": \"organization.certificate\",\n      \"id\": \"cert_abc\",\n      \"name\": \"My Example Certificate\",\n      \"active\": true,\n      \"created_at\": 1234567,\n      \"certificate_details\": {\n        \"valid_at\": 12345667,\n        \"expires_at\": 12345678\n      }\n    },\n  ],\n  \"first_id\": \"cert_abc\",\n  \"last_id\": \"cert_abc\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Upload a certificate to the organization. This does **not** automatically activate the certificate.\n\nOrganizations can upload up to 50 certificates.\n",
+        "operationId": "uploadCertificate",
+        "tags": [
+          "Certificates"
+        ],
+        "requestBody": {
+          "description": "The certificate upload payload.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/UploadCertificateRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Certificate uploaded successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Certificate"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Upload certificate",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/certificates \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n-H \"Content-Type: application/json\" \\\n-d '{\n  \"name\": \"My Example Certificate\",\n  \"certificate\": \"-----BEGIN CERTIFICATE-----\\\\nMIIDeT...\\\\n-----END CERTIFICATE-----\"\n}'\n"
+            },
+            "response": "{\n  \"object\": \"certificate\",\n  \"id\": \"cert_abc\",\n  \"name\": \"My Example Certificate\",\n  \"created_at\": 1234567,\n  \"certificate_details\": {\n    \"valid_at\": 12345667,\n    \"expires_at\": 12345678\n  }\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/certificates/activate": {
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Activate certificates at the organization level.\n\nYou can atomically and idempotently activate up to 10 certificates at a time.\n",
+        "operationId": "activateOrganizationCertificates",
+        "tags": [
+          "Certificates"
+        ],
+        "requestBody": {
+          "description": "The certificate activation payload.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ToggleCertificatesRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Certificates activated successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/OrganizationCertificateActivationResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Activate certificates for organization",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/certificates/activate \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n-H \"Content-Type: application/json\" \\\n-d '{\n  \"certificate_ids\": [\"cert_abc\", \"cert_def\"]\n}'\n"
+            },
+            "response": "{\n  \"object\": \"organization.certificate.activation\",\n  \"data\": [\n    {\n      \"object\": \"organization.certificate\",\n      \"id\": \"cert_abc\",\n      \"name\": \"My Example Certificate\",\n      \"active\": true,\n      \"created_at\": 1234567,\n      \"certificate_details\": {\n        \"valid_at\": 12345667,\n        \"expires_at\": 12345678\n      }\n    },\n    {\n      \"object\": \"organization.certificate\",\n      \"id\": \"cert_def\",\n      \"name\": \"My Example Certificate 2\",\n      \"active\": true,\n      \"created_at\": 1234567,\n      \"certificate_details\": {\n        \"valid_at\": 12345667,\n        \"expires_at\": 12345678\n      }\n    },\n  ],\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/certificates/deactivate": {
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Deactivate certificates at the organization level.\n\nYou can atomically and idempotently deactivate up to 10 certificates at a time.\n",
+        "operationId": "deactivateOrganizationCertificates",
+        "tags": [
+          "Certificates"
+        ],
+        "requestBody": {
+          "description": "The certificate deactivation payload.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ToggleCertificatesRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Certificates deactivated successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/OrganizationCertificateDeactivationResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Deactivate certificates for organization",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/certificates/deactivate \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n-H \"Content-Type: application/json\" \\\n-d '{\n  \"certificate_ids\": [\"cert_abc\", \"cert_def\"]\n}'\n"
+            },
+            "response": "{\n  \"object\": \"organization.certificate.deactivation\",\n  \"data\": [\n    {\n      \"object\": \"organization.certificate\",\n      \"id\": \"cert_abc\",\n      \"name\": \"My Example Certificate\",\n      \"active\": false,\n      \"created_at\": 1234567,\n      \"certificate_details\": {\n        \"valid_at\": 12345667,\n        \"expires_at\": 12345678\n      }\n    },\n    {\n      \"object\": \"organization.certificate\",\n      \"id\": \"cert_def\",\n      \"name\": \"My Example Certificate 2\",\n      \"active\": false,\n      \"created_at\": 1234567,\n      \"certificate_details\": {\n        \"valid_at\": 12345667,\n        \"expires_at\": 12345678\n      }\n    },\n  ],\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/certificates/{certificate_id}": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Get a certificate that has been uploaded to the organization.\n\nYou can get a certificate regardless of whether it is active or not.\n",
+        "operationId": "getCertificate",
+        "tags": [
+          "Certificates"
+        ],
+        "parameters": [
+          {
+            "name": "certificate_id",
+            "in": "path",
+            "description": "Unique ID of the certificate to retrieve.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "include",
+            "in": "query",
+            "description": "A list of additional fields to include in the response. Currently the only supported value is `content` to fetch the PEM content of the certificate.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "content"
+                ]
+              }
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Certificate retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Certificate"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Get certificate",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl \"https://api.openai.com/v1/organization/certificates/cert_abc?include[]=content\" \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\"\n"
+            },
+            "response": "{\n  \"object\": \"certificate\",\n  \"id\": \"cert_abc\",\n  \"name\": \"My Example Certificate\",\n  \"created_at\": 1234567,\n  \"certificate_details\": {\n    \"valid_at\": 1234567,\n    \"expires_at\": 12345678,\n    \"content\": \"-----BEGIN CERTIFICATE-----MIIDeT...-----END CERTIFICATE-----\"\n  }\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Modify a certificate. Note that only the name can be modified.\n",
+        "operationId": "modifyCertificate",
+        "tags": [
+          "Certificates"
+        ],
+        "parameters": [
+          {
+            "name": "certificate_id",
+            "in": "path",
+            "description": "Unique ID of the certificate to modify.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "The certificate modification payload.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ModifyCertificateRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Certificate modified successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Certificate"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Modify certificate",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/certificates/cert_abc \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n-H \"Content-Type: application/json\" \\\n-d '{\n  \"name\": \"Renamed Certificate\"\n}'\n"
+            },
+            "response": "{\n  \"object\": \"certificate\",\n  \"id\": \"cert_abc\",\n  \"name\": \"Renamed Certificate\",\n  \"created_at\": 1234567,\n  \"certificate_details\": {\n    \"valid_at\": 12345667,\n    \"expires_at\": 12345678\n  }\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Delete a certificate from the organization.\n\nThe certificate must be inactive for the organization and all projects.\n",
+        "operationId": "deleteCertificate",
+        "tags": [
+          "Certificates"
+        ],
+        "parameters": [
+          {
+            "name": "certificate_id",
+            "in": "path",
+            "description": "Unique ID of the certificate to delete.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Certificate deleted successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeleteCertificateResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete certificate",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/organization/certificates/cert_abc \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\"\n"
+            },
+            "response": "{\n  \"object\": \"certificate.deleted\",\n  \"id\": \"cert_abc\"\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/costs": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Get costs details for the organization.",
+        "operationId": "usage-costs",
+        "tags": [
+          "Usage"
+        ],
+        "parameters": [
+          {
+            "name": "start_time",
+            "in": "query",
+            "description": "Start time (Unix seconds) of the query time range, inclusive.",
+            "required": true,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "end_time",
+            "in": "query",
+            "description": "End time (Unix seconds) of the query time range, exclusive.",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "bucket_width",
+            "in": "query",
+            "description": "Width of each time bucket in response. Currently only `1d` is supported, default to `1d`.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "1d"
+              ],
+              "default": "1d"
+            }
+          },
+          {
+            "name": "project_ids",
+            "in": "query",
+            "description": "Return only costs for these projects.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "api_key_ids",
+            "in": "query",
+            "description": "Return only costs for these API keys.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "line_items",
+            "in": "query",
+            "description": "Return only costs for these exact line item names. Each value must match the complete `line_item` value, for example `gpt-6-astra, input_tokens`.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "group_by",
+            "in": "query",
+            "description": "Group the costs by the specified fields. Support fields include `project_id`, `line_item`, `api_key_id` and any combination of them.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "project_id",
+                  "line_item",
+                  "api_key_id"
+                ]
+              }
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of buckets to be returned. Limit can range between 1 and 180, and the default is 7.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 7
+            }
+          },
+          {
+            "name": "page",
+            "in": "query",
+            "description": "A cursor for use in pagination. Corresponding to the `next_page` field from the previous response.",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Costs data retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/UsageResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Costs",
+          "group": "usage-costs",
+          "examples": {
+            "request": {
+              "curl": "curl \"https://api.openai.com/v1/organization/costs?start_time=1730419200&limit=1\" \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n-H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"page\",\n    \"data\": [\n        {\n            \"object\": \"bucket\",\n            \"start_time\": 1730419200,\n            \"end_time\": 1730505600,\n            \"results\": [\n                {\n                    \"object\": \"organization.costs.result\",\n                    \"amount\": {\n                        \"value\": 0.06,\n                        \"currency\": \"usd\"\n                    },\n                    \"line_item\": null,\n                    \"project_id\": null,\n                    \"api_key_id\": null,\n                    \"quantity\": null,\n                    \"quantity_unit\": null\n                }\n            ]\n        }\n    ],\n    \"has_more\": false,\n    \"next_page\": null\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/data_retention": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Retrieves organization data retention controls.",
+        "operationId": "retrieve-organization-data-retention",
+        "tags": [
+          "Data retention"
+        ],
+        "responses": {
+          "200": {
+            "description": "Organization data retention controls retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/OrganizationDataRetention"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve organization data retention",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/data_retention \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"organization.data_retention\",\n    \"type\": \"modified_abuse_monitoring\"\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Updates organization data retention controls.",
+        "operationId": "update-organization-data-retention",
+        "tags": [
+          "Data retention"
+        ],
+        "requestBody": {
+          "description": "The desired organization data retention setting.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/UpdateOrganizationDataRetentionBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Organization data retention controls updated successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/OrganizationDataRetention"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update organization data retention",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/data_retention \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"retention_type\": \"modified_abuse_monitoring\"\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"organization.data_retention\",\n    \"type\": \"modified_abuse_monitoring\"\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/groups": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Lists all groups in the organization.",
+        "operationId": "list-groups",
+        "tags": [
+          "Groups"
+        ],
+        "parameters": [
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of groups to be returned. Limit can range between 0 and 1000, and the default is 100.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 1000,
+              "default": 100
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is a group ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with group_abc, your subsequent call can include `after=group_abc` in order to fetch the next page of the list.\n",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Specifies the sort order of the returned groups.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "asc",
+                "desc"
+              ],
+              "default": "asc"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Groups listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/GroupListResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List groups",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/groups?limit=20&order=asc \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"object\": \"group\",\n            \"id\": \"group_01J1F8ABCDXYZ\",\n            \"name\": \"Support Team\",\n            \"created_at\": 1711471533,\n            \"is_scim_managed\": false\n        }\n    ],\n    \"has_more\": false,\n    \"next\": null\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Creates a new group in the organization.",
+        "operationId": "create-group",
+        "tags": [
+          "Groups"
+        ],
+        "requestBody": {
+          "description": "Parameters for the group you want to create.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateGroupBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Group created successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/GroupResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create group",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/groups \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"name\": \"Support Team\"\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"group\",\n    \"id\": \"group_01J1F8ABCDXYZ\",\n    \"name\": \"Support Team\",\n    \"created_at\": 1711471533,\n    \"is_scim_managed\": false\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/groups/{group_id}": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Retrieves a group.",
+        "operationId": "retrieve-group",
+        "tags": [
+          "Groups"
+        ],
+        "parameters": [
+          {
+            "name": "group_id",
+            "in": "path",
+            "description": "The ID of the group to retrieve.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Group retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/GroupResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve group",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/groups/group_01J1F8ABCDXYZ \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"id\": \"group_01J1F8ABCDXYZ\",\n    \"name\": \"Support Team\",\n    \"created_at\": 1711471533,\n    \"is_scim_managed\": false,\n    \"group_type\": \"group\"\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Updates a group's information.",
+        "operationId": "update-group",
+        "tags": [
+          "Groups"
+        ],
+        "parameters": [
+          {
+            "name": "group_id",
+            "in": "path",
+            "description": "The ID of the group to update.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "New attributes to set on the group.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/UpdateGroupBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Group updated successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/GroupResourceWithSuccess"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update group",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/groups/group_01J1F8ABCDXYZ \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"name\": \"Escalations\"\n  }'\n"
+            },
+            "response": "{\n    \"id\": \"group_01J1F8ABCDXYZ\",\n    \"name\": \"Escalations\",\n    \"created_at\": 1711471533,\n    \"is_scim_managed\": false\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Deletes a group from the organization.",
+        "operationId": "delete-group",
+        "tags": [
+          "Groups"
+        ],
+        "parameters": [
+          {
+            "name": "group_id",
+            "in": "path",
+            "description": "The ID of the group to delete.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Group deleted successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/GroupDeletedResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete group",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/organization/groups/group_01J1F8ABCDXYZ \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"group.deleted\",\n    \"id\": \"group_01J1F8ABCDXYZ\",\n    \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/groups/{group_id}/roles": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Lists the organization roles assigned to a group within the organization.",
+        "operationId": "list-group-role-assignments",
+        "tags": [
+          "Group organization role assignments"
+        ],
+        "parameters": [
+          {
+            "name": "group_id",
+            "in": "path",
+            "description": "The ID of the group whose organization role assignments you want to list.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of organization role assignments to return.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 1000
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Cursor for pagination. Provide the value from the previous response's `next` field to continue listing organization roles.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order for the returned organization roles.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "asc",
+                "desc"
+              ]
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Group organization role assignments listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RoleListResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List group organization role assignments",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/groups/group_01J1F8ABCDXYZ/roles \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"id\": \"role_01J1F8ROLE01\",\n            \"name\": \"API Group Manager\",\n            \"permissions\": [\n                \"api.groups.read\",\n                \"api.groups.write\"\n            ],\n            \"resource_type\": \"api.organization\",\n            \"predefined_role\": false,\n            \"description\": \"Allows managing organization groups\",\n            \"created_at\": 1711471533,\n            \"updated_at\": 1711472599,\n            \"created_by\": \"user_abc123\",\n            \"created_by_user_obj\": {\n                \"id\": \"user_abc123\",\n                \"name\": \"Ada Lovelace\",\n                \"email\": \"ada@example.com\"\n            },\n            \"metadata\": {}\n        }\n    ],\n    \"has_more\": false,\n    \"next\": null\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Assigns an organization role to a group within the organization.",
+        "operationId": "assign-group-role",
+        "tags": [
+          "Group organization role assignments"
+        ],
+        "parameters": [
+          {
+            "name": "group_id",
+            "in": "path",
+            "description": "The ID of the group that should receive the organization role.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "Identifies the organization role to assign to the group.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/PublicAssignOrganizationGroupRoleBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Organization role assigned to the group successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/GroupRoleAssignment"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Assign organization role to group",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/groups/group_01J1F8ABCDXYZ/roles \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"role_id\": \"role_01J1F8ROLE01\"\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"group.role\",\n    \"group\": {\n        \"object\": \"group\",\n        \"id\": \"group_01J1F8ABCDXYZ\",\n        \"name\": \"Support Team\",\n        \"created_at\": 1711471533,\n        \"scim_managed\": false\n    },\n    \"role\": {\n        \"object\": \"role\",\n        \"id\": \"role_01J1F8ROLE01\",\n        \"name\": \"API Group Manager\",\n        \"description\": \"Allows managing organization groups\",\n        \"permissions\": [\n            \"api.groups.read\",\n            \"api.groups.write\"\n        ],\n        \"resource_type\": \"api.organization\",\n        \"predefined_role\": false\n    }\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/groups/{group_id}/roles/{role_id}": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Retrieves an organization role assigned to a group.",
+        "operationId": "retrieve-group-role",
+        "tags": [
+          "Group organization role assignments"
+        ],
+        "parameters": [
+          {
+            "name": "group_id",
+            "in": "path",
+            "description": "The ID of the group to inspect.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "role_id",
+            "in": "path",
+            "description": "The ID of the organization role to retrieve for the group.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Organization role retrieved for the group successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/AssignedRoleDetails"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve group organization role",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/groups/group_01J1F8ABCDXYZ/roles/role_01J1F8ROLE01 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"id\": \"role_01J1F8ROLE01\",\n    \"name\": \"API Group Manager\",\n    \"permissions\": [\n        \"api.groups.read\",\n        \"api.groups.write\"\n    ],\n    \"resource_type\": \"api.organization\",\n    \"predefined_role\": false,\n    \"description\": \"Allows managing organization groups\",\n    \"created_at\": 1711471533,\n    \"updated_at\": 1711472599,\n    \"created_by\": \"user_abc123\",\n    \"created_by_user_obj\": null,\n    \"metadata\": {},\n    \"assignment_sources\": null\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Unassigns an organization role from a group within the organization.",
+        "operationId": "unassign-group-role",
+        "tags": [
+          "Group organization role assignments"
+        ],
+        "parameters": [
+          {
+            "name": "group_id",
+            "in": "path",
+            "description": "The ID of the group to modify.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "role_id",
+            "in": "path",
+            "description": "The ID of the organization role to remove from the group.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Organization role unassigned from the group successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedRoleAssignmentResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Unassign organization role from group",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/organization/groups/group_01J1F8ABCDXYZ/roles/role_01J1F8ROLE01 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"group.role.deleted\",\n    \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/groups/{group_id}/users": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Lists the users assigned to a group.",
+        "operationId": "list-group-users",
+        "tags": [
+          "Group users"
+        ],
+        "parameters": [
+          {
+            "name": "group_id",
+            "in": "path",
+            "description": "The ID of the group to inspect.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of users to be returned. Limit can range between 0 and 1000, and the default is 100.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 1000,
+              "default": 100
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. Provide the ID of the last user from the previous list response to retrieve the next page.\n",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Specifies the sort order of users in the list.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "asc",
+                "desc"
+              ],
+              "default": "desc"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Group users listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/UserListResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List group users",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/groups/group_01J1F8ABCDXYZ/users?limit=20 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"id\": \"user_abc123\",\n            \"name\": \"Ada Lovelace\",\n            \"email\": \"ada@example.com\"\n        }\n    ],\n    \"has_more\": false,\n    \"next\": null\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Adds a user to a group.",
+        "operationId": "add-group-user",
+        "tags": [
+          "Group users"
+        ],
+        "parameters": [
+          {
+            "name": "group_id",
+            "in": "path",
+            "description": "The ID of the group to update.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "Identifies the user that should be added to the group.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateGroupUserBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "User added to the group successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/GroupUserAssignment"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Add group user",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/groups/group_01J1F8ABCDXYZ/users \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"user_id\": \"user_abc123\"\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"group.user\",\n    \"user_id\": \"user_abc123\",\n    \"group_id\": \"group_01J1F8ABCDXYZ\"\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/groups/{group_id}/users/{user_id}": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Retrieves a user in a group.",
+        "operationId": "retrieve-group-user",
+        "tags": [
+          "Group users"
+        ],
+        "parameters": [
+          {
+            "name": "group_id",
+            "in": "path",
+            "description": "The ID of the group to inspect.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "user_id",
+            "in": "path",
+            "description": "The ID of the user to retrieve from the group.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "User retrieved from the group successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/GroupMemberUser"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve group user",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/groups/group_01J1F8ABCDXYZ/users/user_abc123 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"id\": \"user_abc123\",\n    \"name\": \"Ada Lovelace\",\n    \"email\": \"ada@example.com\",\n    \"picture\": null,\n    \"is_service_account\": false,\n    \"user_type\": \"user\"\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Removes a user from a group.",
+        "operationId": "remove-group-user",
+        "tags": [
+          "Group users"
+        ],
+        "parameters": [
+          {
+            "name": "group_id",
+            "in": "path",
+            "description": "The ID of the group to update.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "user_id",
+            "in": "path",
+            "description": "The ID of the user to remove from the group.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "User removed from the group successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/GroupUserDeletedResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Remove group user",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/organization/groups/group_01J1F8ABCDXYZ/users/user_abc123 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"group.user.deleted\",\n    \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/invites": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Returns a list of invites in the organization.",
+        "operationId": "list-invites",
+        "tags": [
+          "Invites"
+        ],
+        "parameters": [
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Invites listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/InviteListResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List invites",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/invites?after=invite-abc&limit=20 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\": \"organization.invite\",\n      \"id\": \"invite-abc\",\n      \"email\": \"user@example.com\",\n      \"role\": \"owner\",\n      \"status\": \"accepted\",\n      \"created_at\": 1711471533,\n      \"expires_at\": 1711471533,\n      \"accepted_at\": 1711471533\n    }\n  ],\n  \"first_id\": \"invite-abc\",\n  \"last_id\": \"invite-abc\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Create an invite for a user to the organization. The invite must be accepted by the user before they have access to the organization.",
+        "operationId": "inviteUser",
+        "tags": [
+          "Invites"
+        ],
+        "requestBody": {
+          "description": "The invite request payload.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/InviteRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "User invited successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Invite"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create invite",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/invites \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"email\": \"anotheruser@example.com\",\n      \"role\": \"reader\",\n      \"projects\": [\n        {\n          \"id\": \"project-xyz\",\n          \"role\": \"member\"\n        },\n        {\n          \"id\": \"project-abc\",\n          \"role\": \"owner\"\n        }\n      ]\n  }'\n"
+            },
+            "response": "{\n  \"object\": \"organization.invite\",\n  \"id\": \"invite-def\",\n  \"email\": \"anotheruser@example.com\",\n  \"role\": \"reader\",\n  \"status\": \"pending\",\n  \"created_at\": 1711471533,\n  \"expires_at\": 1711471533,\n  \"accepted_at\": null,\n  \"projects\": [\n    {\n      \"id\": \"project-xyz\",\n      \"role\": \"member\"\n    },\n    {\n      \"id\": \"project-abc\",\n      \"role\": \"owner\"\n    }\n  ]\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/invites/{invite_id}": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Retrieves an invite.",
+        "operationId": "retrieve-invite",
+        "tags": [
+          "Invites"
+        ],
+        "parameters": [
+          {
+            "in": "path",
+            "name": "invite_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the invite to retrieve."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Invite retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Invite"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve invite",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/invites/invite-abc \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"organization.invite\",\n    \"id\": \"invite-abc\",\n    \"email\": \"user@example.com\",\n    \"role\": \"owner\",\n    \"status\": \"accepted\",\n    \"created_at\": 1711471533,\n    \"expires_at\": 1711471533,\n    \"accepted_at\": 1711471533\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Delete an invite. If the invite has already been accepted, it cannot be deleted.",
+        "operationId": "delete-invite",
+        "tags": [
+          "Invites"
+        ],
+        "parameters": [
+          {
+            "in": "path",
+            "name": "invite_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the invite to delete."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Invite deleted successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/InviteDeleteResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete invite",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/organization/invites/invite-abc \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"organization.invite.deleted\",\n    \"id\": \"invite-abc\",\n    \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/projects": {
+      "get": {
+        "summary": "Returns a list of projects.",
+        "operationId": "list-projects",
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "include_archived",
+            "in": "query",
+            "schema": {
+              "type": "boolean",
+              "default": false
+            },
+            "description": "If `true` returns all projects including those that have been `archived`. Archived projects are not included by default."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Projects listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectListResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List projects",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/projects?after=proj_abc&limit=20&include_archived=false \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"id\": \"proj_abc\",\n            \"object\": \"organization.project\",\n            \"name\": \"Project example\",\n            \"created_at\": 1711471533,\n            \"archived_at\": null,\n            \"status\": \"active\"\n        }\n    ],\n    \"first_id\": \"proj-abc\",\n    \"last_id\": \"proj-xyz\",\n    \"has_more\": false\n}\n"
+          }
+        }
+      },
+      "post": {
+        "summary": "Create a new project in the organization. Projects can be created and archived, but cannot be deleted.",
+        "operationId": "create-project",
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "tags": [
+          "Projects"
+        ],
+        "requestBody": {
+          "description": "The project create request payload.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ProjectCreateRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Project created successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Project"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create project",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/projects \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"name\": \"Project ABC\"\n  }'\n"
+            },
+            "response": "{\n    \"id\": \"proj_abc\",\n    \"object\": \"organization.project\",\n    \"name\": \"Project ABC\",\n    \"created_at\": 1711471533,\n    \"archived_at\": null,\n    \"status\": \"active\"\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/projects/{project_id}": {
+      "get": {
+        "summary": "Retrieves a project.",
+        "operationId": "retrieve-project",
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Project"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve project",
+          "group": "administration",
+          "description": "Retrieve a project.",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/projects/proj_abc \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"id\": \"proj_abc\",\n    \"object\": \"organization.project\",\n    \"name\": \"Project example\",\n    \"created_at\": 1711471533,\n    \"archived_at\": null,\n    \"status\": \"active\"\n}\n"
+          }
+        }
+      },
+      "post": {
+        "summary": "Modifies a project in the organization.",
+        "operationId": "modify-project",
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "The project update request payload.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ProjectUpdateRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Project updated successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Project"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "Error response when updating the default project.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Modify project",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/projects/proj_abc \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"name\": \"Project DEF\"\n  }'\n"
+            }
+          }
+        }
+      }
+    },
+    "/organization/projects/{project_id}/api_keys": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Returns a list of API keys in the project.",
+        "operationId": "list-project-api-keys",
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "owner_project_access",
+            "in": "query",
+            "description": "Filter API keys by whether the owner currently has effective access to the project. Use `active` for owners with access, `inactive` for owners without access, or `any` for all enabled project API keys. If omitted, the endpoint applies its existing membership-based visibility rules, which may exclude some enabled keys.\n",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "active",
+                "inactive",
+                "any"
+              ]
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project API keys listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectApiKeyListResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List project API keys",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/projects/proj_abc/api_keys?after=key_abc&limit=20&owner_project_access=any \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"object\": \"organization.project.api_key\",\n            \"redacted_value\": \"sk-abc...def\",\n            \"name\": \"My API Key\",\n            \"created_at\": 1711471533,\n            \"last_used_at\": 1711471534,\n            \"id\": \"key_abc\",\n            \"owner_project_access\": \"active\",\n            \"owner\": {\n                \"type\": \"user\",\n                \"user\": {\n                    \"id\": \"user_abc\",\n                    \"name\": \"First Last\",\n                    \"email\": \"user@example.com\",\n                    \"role\": \"owner\",\n                    \"created_at\": 1711471533\n                }\n            }\n        }\n    ],\n    \"first_id\": \"key_abc\",\n    \"last_id\": \"key_xyz\",\n    \"has_more\": false\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/projects/{project_id}/api_keys/{api_key_id}": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Retrieves an API key in the project.",
+        "operationId": "retrieve-project-api-key",
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "api_key_id",
+            "in": "path",
+            "description": "The ID of the API key.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project API key retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectApiKey"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve project API key",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/projects/proj_abc/api_keys/key_abc \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"organization.project.api_key\",\n    \"redacted_value\": \"sk-abc...def\",\n    \"name\": \"My API Key\",\n    \"created_at\": 1711471533,\n    \"last_used_at\": 1711471534,\n    \"id\": \"key_abc\",\n    \"owner_project_access\": \"active\",\n    \"owner\": {\n        \"type\": \"user\",\n        \"user\": {\n            \"id\": \"user_abc\",\n            \"name\": \"First Last\",\n            \"email\": \"user@example.com\",\n            \"role\": \"owner\",\n            \"created_at\": 1711471533\n        }\n    }\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Deletes an API key from the project.\n\nReturns confirmation of the key deletion, or an error if the key belonged to\na service account.\n",
+        "operationId": "delete-project-api-key",
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "api_key_id",
+            "in": "path",
+            "description": "The ID of the API key.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project API key deleted successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectApiKeyDeleteResponse"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "Error response for various conditions.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete project API key",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/organization/projects/proj_abc/api_keys/key_abc \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"organization.project.api_key.deleted\",\n    \"id\": \"key_abc\",\n    \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/projects/{project_id}/archive": {
+      "post": {
+        "summary": "Archives a project in the organization. Archived projects cannot be used or updated.",
+        "operationId": "archive-project",
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project archived successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Project"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Archive project",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/projects/proj_abc/archive \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"id\": \"proj_abc\",\n    \"object\": \"organization.project\",\n    \"name\": \"Project DEF\",\n    \"created_at\": 1711471533,\n    \"archived_at\": 1711471533,\n    \"status\": \"archived\"\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/projects/{project_id}/certificates": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "List certificates for this project.",
+        "operationId": "listProjectCertificates",
+        "tags": [
+          "Certificates"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.\n",
+            "schema": {
+              "type": "string",
+              "default": "desc",
+              "enum": [
+                "asc",
+                "desc"
+              ]
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Certificates listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ListProjectCertificatesResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List project certificates",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/projects/proj_abc/certificates \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\"\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\": \"organization.project.certificate\",\n      \"id\": \"cert_abc\",\n      \"name\": \"My Example Certificate\",\n      \"active\": true,\n      \"created_at\": 1234567,\n      \"certificate_details\": {\n        \"valid_at\": 12345667,\n        \"expires_at\": 12345678\n      }\n    },\n  ],\n  \"first_id\": \"cert_abc\",\n  \"last_id\": \"cert_abc\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/projects/{project_id}/certificates/activate": {
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Activate certificates at the project level.\n\nYou can atomically and idempotently activate up to 10 certificates at a time.\n",
+        "operationId": "activateProjectCertificates",
+        "tags": [
+          "Certificates"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "The certificate activation payload.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ToggleCertificatesRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Certificates activated successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/OrganizationProjectCertificateActivationResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Activate certificates for project",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/projects/proj_abc/certificates/activate \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n-H \"Content-Type: application/json\" \\\n-d '{\n  \"certificate_ids\": [\"cert_abc\", \"cert_def\"]\n}'\n"
+            },
+            "response": "{\n  \"object\": \"organization.project.certificate.activation\",\n  \"data\": [\n    {\n      \"object\": \"organization.project.certificate\",\n      \"id\": \"cert_abc\",\n      \"name\": \"My Example Certificate\",\n      \"active\": true,\n      \"created_at\": 1234567,\n      \"certificate_details\": {\n        \"valid_at\": 12345667,\n        \"expires_at\": 12345678\n      }\n    },\n    {\n      \"object\": \"organization.project.certificate\",\n      \"id\": \"cert_def\",\n      \"name\": \"My Example Certificate 2\",\n      \"active\": true,\n      \"created_at\": 1234567,\n      \"certificate_details\": {\n        \"valid_at\": 12345667,\n        \"expires_at\": 12345678\n      }\n    },\n  ],\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/projects/{project_id}/certificates/deactivate": {
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Deactivate certificates at the project level. You can atomically and \nidempotently deactivate up to 10 certificates at a time.\n",
+        "operationId": "deactivateProjectCertificates",
+        "tags": [
+          "Certificates"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "The certificate deactivation payload.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ToggleCertificatesRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Certificates deactivated successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/OrganizationProjectCertificateDeactivationResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Deactivate certificates for project",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/projects/proj_abc/certificates/deactivate \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n-H \"Content-Type: application/json\" \\\n-d '{\n  \"certificate_ids\": [\"cert_abc\", \"cert_def\"]\n}'\n"
+            },
+            "response": "{\n  \"object\": \"organization.project.certificate.deactivation\",\n  \"data\": [\n    {\n      \"object\": \"organization.project.certificate\",\n      \"id\": \"cert_abc\",\n      \"name\": \"My Example Certificate\",\n      \"active\": false,\n      \"created_at\": 1234567,\n      \"certificate_details\": {\n        \"valid_at\": 12345667,\n        \"expires_at\": 12345678\n      }\n    },\n    {\n      \"object\": \"organization.project.certificate\",\n      \"id\": \"cert_def\",\n      \"name\": \"My Example Certificate 2\",\n      \"active\": false,\n      \"created_at\": 1234567,\n      \"certificate_details\": {\n        \"valid_at\": 12345667,\n        \"expires_at\": 12345678\n      }\n    },\n  ],\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/projects/{project_id}/data_retention": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Retrieves project data retention controls.",
+        "operationId": "retrieve-project-data-retention",
+        "tags": [
+          "Data retention"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to inspect.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project data retention controls retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectDataRetention"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve project data retention",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/projects/proj_abc/data_retention \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"project.data_retention\",\n    \"type\": \"organization_default\"\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Updates project data retention controls.",
+        "operationId": "update-project-data-retention",
+        "tags": [
+          "Data retention"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to update.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "The desired project data retention setting.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/UpdateProjectDataRetentionBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Project data retention controls updated successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectDataRetention"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update project data retention",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/projects/proj_abc/data_retention \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"retention_type\": \"modified_abuse_monitoring\"\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"project.data_retention\",\n    \"type\": \"modified_abuse_monitoring\"\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/projects/{project_id}/groups": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Lists the groups that have access to a project.",
+        "operationId": "list-project-groups",
+        "tags": [
+          "Project groups"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to inspect.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of project groups to return. Defaults to 20.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 100,
+              "default": 20
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Cursor for pagination. Provide the ID of the last group from the previous response to fetch the next page.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order for the returned groups.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "asc",
+                "desc"
+              ],
+              "default": "asc"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project groups listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectGroupListResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List project groups",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/projects/proj_abc123/groups?limit=20 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"object\": \"project.group\",\n            \"project_id\": \"proj_abc123\",\n            \"group_id\": \"group_01J1F8ABCDXYZ\",\n            \"group_name\": \"Support Team\",\n            \"created_at\": 1711471533\n        }\n    ],\n    \"has_more\": false,\n    \"next\": null\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Grants a group access to a project.",
+        "operationId": "add-project-group",
+        "tags": [
+          "Project groups"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to update.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "Identifies the group and role to assign to the project.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/InviteProjectGroupBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Group granted access to the project successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectGroup"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Add project group",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/projects/proj_abc123/groups \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"group_id\": \"group_01J1F8ABCDXYZ\",\n      \"role\": \"role_01J1F8PROJ\"\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"project.group\",\n    \"project_id\": \"proj_abc123\",\n    \"group_id\": \"group_01J1F8ABCDXYZ\",\n    \"group_name\": \"Support Team\",\n    \"created_at\": 1711471533\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/projects/{project_id}/groups/{group_id}": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Retrieves a project's group.",
+        "operationId": "retrieve-project-group",
+        "tags": [
+          "Project groups"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to inspect.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "group_id",
+            "in": "path",
+            "description": "The ID of the group to retrieve.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "group_type",
+            "in": "query",
+            "description": "The type of group to retrieve.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "group",
+                "tenant_group"
+              ],
+              "default": "group"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project group retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectGroup"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve project group",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/projects/proj_abc123/groups/group_01J1F8ABCDXYZ \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"project.group\",\n    \"project_id\": \"proj_abc123\",\n    \"group_id\": \"group_01J1F8ABCDXYZ\",\n    \"group_name\": \"Support Team\",\n    \"group_type\": \"group\",\n    \"created_at\": 1711471533\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Revokes a group's access to a project.",
+        "operationId": "remove-project-group",
+        "tags": [
+          "Project groups"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to update.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "group_id",
+            "in": "path",
+            "description": "The ID of the group to remove from the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Group removed from the project successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectGroupDeletedResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Remove project group",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/organization/projects/proj_abc123/groups/group_01J1F8ABCDXYZ \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"project.group.deleted\",\n    \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/projects/{project_id}/hosted_tool_permissions": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Returns hosted tool permissions for a project.",
+        "operationId": "retrieve-project-hosted-tool-permissions",
+        "tags": [
+          "Hosted tools"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project hosted tool permissions retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectHostedToolPermissions"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve project hosted tool permissions",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/projects/proj_abc/hosted_tool_permissions \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"file_search\": {\n        \"enabled\": true\n    },\n    \"web_search\": {\n        \"enabled\": true\n    },\n    \"image_generation\": {\n        \"enabled\": true\n    },\n    \"mcp\": {\n        \"enabled\": true\n    },\n    \"code_interpreter\": {\n        \"enabled\": true\n    }\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Updates hosted tool permissions for a project.",
+        "operationId": "update-project-hosted-tool-permissions",
+        "tags": [
+          "Hosted tools"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "The project hosted tool permissions update request payload.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ProjectHostedToolPermissionsUpdateRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Project hosted tool permissions updated successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectHostedToolPermissions"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Modify project hosted tool permissions",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/projects/proj_abc/hosted_tool_permissions \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"file_search\": {\n          \"enabled\": true\n      },\n      \"image_generation\": {\n          \"enabled\": false\n      }\n  }'\n"
+            },
+            "response": "{\n    \"file_search\": {\n        \"enabled\": true\n    },\n    \"web_search\": {\n        \"enabled\": true\n    },\n    \"image_generation\": {\n        \"enabled\": false\n    },\n    \"mcp\": {\n        \"enabled\": true\n    },\n    \"code_interpreter\": {\n        \"enabled\": true\n    }\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/projects/{project_id}/model_permissions": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Returns model permissions for a project.",
+        "operationId": "retrieve-project-model-permissions",
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project model permissions retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectModelPermissions"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve project model permissions",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/projects/proj_abc/model_permissions \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"project.model_permissions\",\n    \"mode\": \"allow_list\",\n    \"model_ids\": [\n        \"gpt-6-astra\",\n        \"o3\"\n    ]\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Updates model permissions for a project.",
+        "operationId": "update-project-model-permissions",
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "The project model permissions update request payload.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ProjectModelPermissionsUpdateRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Project model permissions updated successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectModelPermissions"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Modify project model permissions",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/projects/proj_abc/model_permissions \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"mode\": \"deny_list\",\n      \"model_ids\": [\n          \"o3\"\n      ]\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"project.model_permissions\",\n    \"mode\": \"deny_list\",\n    \"model_ids\": [\n        \"o3\"\n    ]\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Deletes model permissions for a project.",
+        "operationId": "delete-project-model-permissions",
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project model permissions deleted successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectModelPermissionsDeleteResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete project model permissions",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/organization/projects/proj_abc/model_permissions \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"project.model_permissions.deleted\",\n    \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/projects/{project_id}/rate_limits": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Returns the rate limits per model for a project.",
+        "operationId": "list-project-rate-limits",
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. The default is 100.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 100
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "before",
+            "in": "query",
+            "description": "A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, beginning with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.\n",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project rate limits listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectRateLimitListResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List project rate limits",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/projects/proj_abc/rate_limits?after=rl_xxx&limit=20 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n          \"object\": \"project.rate_limit\",\n          \"id\": \"rl-ada\",\n          \"model\": \"ada\",\n          \"max_requests_per_1_minute\": 600,\n          \"max_tokens_per_1_minute\": 150000,\n          \"max_images_per_1_minute\": 10\n        }\n    ],\n    \"first_id\": \"rl-ada\",\n    \"last_id\": \"rl-ada\",\n    \"has_more\": false\n}\n",
+            "error_response": "{\n    \"code\": 404,\n    \"message\": \"The project {project_id} was not found\"\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/projects/{project_id}/rate_limits/{rate_limit_id}": {
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Updates a project rate limit.",
+        "operationId": "update-project-rate-limits",
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "rate_limit_id",
+            "in": "path",
+            "description": "The ID of the rate limit.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "The project rate limit update request payload.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ProjectRateLimitUpdateRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Project rate limit updated successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectRateLimit"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "Error response for various conditions.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Modify project rate limit",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/projects/proj_abc/rate_limits/rl_xxx \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"max_requests_per_1_minute\": 500\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"project.rate_limit\",\n    \"id\": \"rl-ada\",\n    \"model\": \"ada\",\n    \"max_requests_per_1_minute\": 600,\n    \"max_tokens_per_1_minute\": 150000,\n    \"max_images_per_1_minute\": 10\n  }\n",
+            "error_response": "{\n    \"code\": 404,\n    \"message\": \"The project {project_id} was not found\"\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/projects/{project_id}/service_accounts": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Returns a list of service accounts in the project.",
+        "operationId": "list-project-service-accounts",
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project service accounts listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectServiceAccountListResponse"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "Error response when project is archived.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List project service accounts",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/projects/proj_abc/service_accounts?after=custom_id&limit=20 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"object\": \"organization.project.service_account\",\n            \"id\": \"svc_acct_abc\",\n            \"name\": \"Service Account\",\n            \"role\": \"owner\",\n            \"created_at\": 1711471533\n        }\n    ],\n    \"first_id\": \"svc_acct_abc\",\n    \"last_id\": \"svc_acct_xyz\",\n    \"has_more\": false\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Creates a new service account in the project. By default, this also returns an unredacted API key for the service account.",
+        "operationId": "create-project-service-account",
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "The project service account create request payload.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ProjectServiceAccountCreateRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Project service account created successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectServiceAccountCreateResponse"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "Error response when project is archived.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create project service account",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/projects/proj_abc/service_accounts \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"name\": \"Production App\"\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"organization.project.service_account\",\n    \"id\": \"svc_acct_abc\",\n    \"name\": \"Production App\",\n    \"role\": \"member\",\n    \"created_at\": 1711471533,\n    \"api_key\": {\n        \"object\": \"organization.project.service_account.api_key\",\n        \"value\": \"sk-abcdefghijklmnop123\",\n        \"name\": \"Secret Key\",\n        \"created_at\": 1711471533,\n        \"id\": \"key_abc\"\n    }\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/projects/{project_id}/service_accounts/{service_account_id}": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Retrieves a service account in the project.",
+        "operationId": "retrieve-project-service-account",
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "service_account_id",
+            "in": "path",
+            "description": "The ID of the service account.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project service account retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectServiceAccount"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve project service account",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/projects/proj_abc/service_accounts/svc_acct_abc \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"organization.project.service_account\",\n    \"id\": \"svc_acct_abc\",\n    \"name\": \"Service Account\",\n    \"role\": \"owner\",\n    \"created_at\": 1711471533\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Updates a service account in the project.",
+        "operationId": "update-project-service-account",
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "service_account_id",
+            "in": "path",
+            "description": "The ID of the service account.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "Fields to update on the service account.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/UpdateProjectServiceAccountBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Project service account updated successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectServiceAccount"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update project service account",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/projects/proj_abc/service_accounts/svc_acct_abc \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"name\": \"Updated service account\",\n      \"role\": \"member\"\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"organization.project.service_account\",\n    \"id\": \"svc_acct_abc\",\n    \"name\": \"Updated service account\",\n    \"role\": \"member\",\n    \"created_at\": 1711471533\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Deletes a service account from the project.\n\nReturns confirmation of service account deletion, or an error if the project\nis archived (archived projects have no service accounts).\n",
+        "operationId": "delete-project-service-account",
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "service_account_id",
+            "in": "path",
+            "description": "The ID of the service account.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project service account deleted successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectServiceAccountDeleteResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete project service account",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/organization/projects/proj_abc/service_accounts/svc_acct_abc \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"organization.project.service_account.deleted\",\n    \"id\": \"svc_acct_abc\",\n    \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/projects/{project_id}/spend_alerts": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Lists project spend alerts.",
+        "operationId": "list-project-spend-alerts",
+        "tags": [
+          "Spend alerts"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to inspect.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of spend alerts to return. Defaults to 20.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 100
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order for the returned spend alerts.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "asc",
+                "desc"
+              ],
+              "default": "asc"
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Cursor for pagination. Provide the ID of the last spend alert from the previous response to fetch the next page.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "before",
+            "in": "query",
+            "description": "Cursor for pagination. Provide the ID of the first spend alert from the previous response to fetch the previous page.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project spend alerts listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectSpendAlertListResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List project spend alerts",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/projects/proj_abc/spend_alerts?limit=20&order=asc \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"id\": \"alert_abc123\",\n            \"object\": \"project.spend_alert\",\n            \"threshold_amount\": 100000,\n            \"currency\": \"USD\",\n            \"interval\": \"month\",\n            \"notification_channel\": {\n                \"type\": \"email\",\n                \"recipients\": [\"finance@example.com\"],\n                \"subject_prefix\": \"OpenAI spend alert\"\n            }\n        }\n    ],\n    \"first_id\": \"alert_abc123\",\n    \"last_id\": \"alert_abc123\",\n    \"has_more\": false\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Creates a project spend alert.",
+        "operationId": "create-project-spend-alert",
+        "tags": [
+          "Spend alerts"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to update.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "Parameters for the project spend alert you want to create.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateSpendAlertBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Project spend alert created successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectSpendAlert"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create project spend alert",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/projects/proj_abc/spend_alerts \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"threshold_amount\": 100000,\n      \"currency\": \"USD\",\n      \"interval\": \"month\",\n      \"notification_channel\": {\n          \"type\": \"email\",\n          \"recipients\": [\"finance@example.com\"],\n          \"subject_prefix\": \"OpenAI spend alert\"\n      }\n  }'\n"
+            },
+            "response": "{\n    \"id\": \"alert_abc123\",\n    \"object\": \"project.spend_alert\",\n    \"threshold_amount\": 100000,\n    \"currency\": \"USD\",\n    \"interval\": \"month\",\n    \"notification_channel\": {\n        \"type\": \"email\",\n        \"recipients\": [\"finance@example.com\"],\n        \"subject_prefix\": \"OpenAI spend alert\"\n    }\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/projects/{project_id}/spend_alerts/{alert_id}": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Retrieves a project spend alert.",
+        "operationId": "retrieve-project-spend-alert",
+        "tags": [
+          "Spend alerts"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "alert_id",
+            "in": "path",
+            "description": "The ID of the spend alert to retrieve.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project spend alert retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectSpendAlert"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve project spend alert",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/projects/proj_abc/spend_alerts/alert_abc123 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"id\": \"alert_abc123\",\n    \"object\": \"project.spend_alert\",\n    \"threshold_amount\": 150000,\n    \"currency\": \"USD\",\n    \"interval\": \"month\",\n    \"notification_channel\": {\n        \"type\": \"email\",\n        \"recipients\": [\"finance@example.com\"],\n        \"subject_prefix\": \"OpenAI spend alert\"\n    }\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Updates a project spend alert.",
+        "operationId": "update-project-spend-alert",
+        "tags": [
+          "Spend alerts"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to update.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "alert_id",
+            "in": "path",
+            "description": "The ID of the spend alert to update.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "Fields to update on the project spend alert.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateSpendAlertBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Project spend alert updated successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectSpendAlert"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update project spend alert",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/projects/proj_abc/spend_alerts/alert_abc123 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"threshold_amount\": 150000,\n      \"currency\": \"USD\",\n      \"interval\": \"month\",\n      \"notification_channel\": {\n          \"type\": \"email\",\n          \"recipients\": [\"finance@example.com\"],\n          \"subject_prefix\": \"OpenAI spend alert\"\n      }\n  }'\n"
+            },
+            "response": "{\n    \"id\": \"alert_abc123\",\n    \"object\": \"project.spend_alert\",\n    \"threshold_amount\": 150000,\n    \"currency\": \"USD\",\n    \"interval\": \"month\",\n    \"notification_channel\": {\n        \"type\": \"email\",\n        \"recipients\": [\"finance@example.com\"],\n        \"subject_prefix\": \"OpenAI spend alert\"\n    }\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Deletes a project spend alert.",
+        "operationId": "delete-project-spend-alert",
+        "tags": [
+          "Spend alerts"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to update.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "alert_id",
+            "in": "path",
+            "description": "The ID of the spend alert to delete.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project spend alert deleted successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectSpendAlertDeletedResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete project spend alert",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/organization/projects/proj_abc/spend_alerts/alert_abc123 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"id\": \"alert_abc123\",\n    \"object\": \"project.spend_alert.deleted\",\n    \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/projects/{project_id}/users": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Returns a list of users in the project.",
+        "operationId": "list-project-users",
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project users listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectUserListResponse"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "Error response when project is archived.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List project users",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/projects/proj_abc/users?after=user_abc&limit=20 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"object\": \"organization.project.user\",\n            \"id\": \"user_abc\",\n            \"name\": \"First Last\",\n            \"email\": \"user@example.com\",\n            \"role\": \"owner\",\n            \"added_at\": 1711471533\n        }\n    ],\n    \"first_id\": \"user-abc\",\n    \"last_id\": \"user-xyz\",\n    \"has_more\": false\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Adds a user to the project. Users must already be members of the organization to be added to a project.",
+        "operationId": "create-project-user",
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "tags": [
+          "Projects"
+        ],
+        "requestBody": {
+          "description": "The project user create request payload.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ProjectUserCreateRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "User added to project successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectUser"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "Error response for various conditions.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create project user",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/projects/proj_abc/users \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"user_id\": \"user_abc\",\n      \"role\": \"member\"\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"organization.project.user\",\n    \"id\": \"user_abc\",\n    \"email\": \"user@example.com\",\n    \"role\": \"owner\",\n    \"added_at\": 1711471533\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/projects/{project_id}/users/{user_id}": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Retrieves a user in the project.",
+        "operationId": "retrieve-project-user",
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "user_id",
+            "in": "path",
+            "description": "The ID of the user.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project user retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectUser"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve project user",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/projects/proj_abc/users/user_abc \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"organization.project.user\",\n    \"id\": \"user_abc\",\n    \"name\": \"First Last\",\n    \"email\": \"user@example.com\",\n    \"role\": \"owner\",\n    \"added_at\": 1711471533\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Modifies a user's role in the project.",
+        "operationId": "modify-project-user",
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "user_id",
+            "in": "path",
+            "description": "The ID of the user.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "The project user update request payload.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ProjectUserUpdateRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Project user's role updated successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectUser"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "Error response for various conditions.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Modify project user",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/projects/proj_abc/users/user_abc \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"role\": \"owner\"\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"organization.project.user\",\n    \"id\": \"user_abc\",\n    \"name\": \"First Last\",\n    \"email\": \"user@example.com\",\n    \"role\": \"owner\",\n    \"added_at\": 1711471533\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Deletes a user from the project.\n\nReturns confirmation of project user deletion, or an error if the project is\narchived (archived projects have no users).\n",
+        "operationId": "delete-project-user",
+        "tags": [
+          "Projects"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "user_id",
+            "in": "path",
+            "description": "The ID of the user.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project user deleted successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectUserDeleteResponse"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "Error response for various conditions.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete project user",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/organization/projects/proj_abc/users/user_abc \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"organization.project.user.deleted\",\n    \"id\": \"user_abc\",\n    \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/roles": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Lists the roles configured for the organization.",
+        "operationId": "list-roles",
+        "tags": [
+          "Roles"
+        ],
+        "parameters": [
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of roles to return. Defaults to 1000.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 1000,
+              "default": 1000
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Cursor for pagination. Provide the value from the previous response's `next` field to continue listing roles.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order for the returned roles.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "asc",
+                "desc"
+              ],
+              "default": "asc"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Roles listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/PublicRoleListResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List organization roles",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/roles?limit=20 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"object\": \"role\",\n            \"id\": \"role_01J1F8ROLE01\",\n            \"name\": \"API Group Manager\",\n            \"description\": \"Allows managing organization groups\",\n            \"permissions\": [\n                \"api.groups.read\",\n                \"api.groups.write\"\n            ],\n            \"resource_type\": \"api.organization\",\n            \"predefined_role\": false\n        }\n    ],\n    \"has_more\": false,\n    \"next\": null\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Creates a custom role for the organization.",
+        "operationId": "create-role",
+        "tags": [
+          "Roles"
+        ],
+        "requestBody": {
+          "description": "Parameters for the role you want to create.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/PublicCreateOrganizationRoleBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Role created successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Role"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create organization role",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/roles \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"role_name\": \"API Group Manager\",\n      \"permissions\": [\n          \"api.groups.read\",\n          \"api.groups.write\"\n      ],\n      \"description\": \"Allows managing organization groups\"\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"role\",\n    \"id\": \"role_01J1F8ROLE01\",\n    \"name\": \"API Group Manager\",\n    \"description\": \"Allows managing organization groups\",\n    \"permissions\": [\n        \"api.groups.read\",\n        \"api.groups.write\"\n    ],\n    \"resource_type\": \"api.organization\",\n    \"predefined_role\": false\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/roles/{role_id}": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Retrieves an organization role.",
+        "operationId": "retrieve-role",
+        "tags": [
+          "Roles"
+        ],
+        "parameters": [
+          {
+            "name": "role_id",
+            "in": "path",
+            "description": "The ID of the role to retrieve.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Role retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Role"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve organization role",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/roles/role_01J1F8ROLE01 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"role\",\n    \"id\": \"role_01J1F8ROLE01\",\n    \"name\": \"API Group Manager\",\n    \"description\": \"Allows managing organization groups\",\n    \"permissions\": [\n        \"api.groups.read\",\n        \"api.groups.write\"\n    ],\n    \"resource_type\": \"api.organization\",\n    \"predefined_role\": false\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Updates an existing organization role.",
+        "operationId": "update-role",
+        "tags": [
+          "Roles"
+        ],
+        "parameters": [
+          {
+            "name": "role_id",
+            "in": "path",
+            "description": "The ID of the role to update.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "Fields to update on the role.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/PublicUpdateOrganizationRoleBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Role updated successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Role"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update organization role",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/roles/role_01J1F8ROLE01 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"role_name\": \"API Group Manager\",\n      \"permissions\": [\n          \"api.groups.read\",\n          \"api.groups.write\"\n      ],\n      \"description\": \"Allows managing organization groups\"\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"role\",\n    \"id\": \"role_01J1F8ROLE01\",\n    \"name\": \"API Group Manager\",\n    \"description\": \"Allows managing organization groups\",\n    \"permissions\": [\n        \"api.groups.read\",\n        \"api.groups.write\"\n    ],\n    \"resource_type\": \"api.organization\",\n    \"predefined_role\": false\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Deletes a custom role from the organization.",
+        "operationId": "delete-role",
+        "tags": [
+          "Roles"
+        ],
+        "parameters": [
+          {
+            "name": "role_id",
+            "in": "path",
+            "description": "The ID of the role to delete.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Role deleted successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RoleDeletedResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete organization role",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/organization/roles/role_01J1F8ROLE01 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"role.deleted\",\n    \"id\": \"role_01J1F8ROLE01\",\n    \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/spend_alerts": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Lists organization spend alerts.",
+        "operationId": "list-organization-spend-alerts",
+        "tags": [
+          "Spend alerts"
+        ],
+        "parameters": [
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of spend alerts to return. Defaults to 20.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 100
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order for the returned spend alerts.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "asc",
+                "desc"
+              ],
+              "default": "asc"
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Cursor for pagination. Provide the ID of the last spend alert from the previous response to fetch the next page.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "before",
+            "in": "query",
+            "description": "Cursor for pagination. Provide the ID of the first spend alert from the previous response to fetch the previous page.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Organization spend alerts listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/OrganizationSpendAlertListResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List organization spend alerts",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/spend_alerts?limit=20&order=asc \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"id\": \"alert_abc123\",\n            \"object\": \"organization.spend_alert\",\n            \"threshold_amount\": 100000,\n            \"currency\": \"USD\",\n            \"interval\": \"month\",\n            \"notification_channel\": {\n                \"type\": \"email\",\n                \"recipients\": [\"finance@example.com\"],\n                \"subject_prefix\": \"OpenAI spend alert\"\n            }\n        }\n    ],\n    \"first_id\": \"alert_abc123\",\n    \"last_id\": \"alert_abc123\",\n    \"has_more\": false\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Creates an organization spend alert.",
+        "operationId": "create-organization-spend-alert",
+        "tags": [
+          "Spend alerts"
+        ],
+        "requestBody": {
+          "description": "Parameters for the organization spend alert you want to create.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateSpendAlertBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Organization spend alert created successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/OrganizationSpendAlert"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create organization spend alert",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/spend_alerts \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"threshold_amount\": 100000,\n      \"currency\": \"USD\",\n      \"interval\": \"month\",\n      \"notification_channel\": {\n          \"type\": \"email\",\n          \"recipients\": [\"finance@example.com\"],\n          \"subject_prefix\": \"OpenAI spend alert\"\n      }\n  }'\n"
+            },
+            "response": "{\n    \"id\": \"alert_abc123\",\n    \"object\": \"organization.spend_alert\",\n    \"threshold_amount\": 100000,\n    \"currency\": \"USD\",\n    \"interval\": \"month\",\n    \"notification_channel\": {\n        \"type\": \"email\",\n        \"recipients\": [\"finance@example.com\"],\n        \"subject_prefix\": \"OpenAI spend alert\"\n    }\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/spend_alerts/{alert_id}": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Retrieves an organization spend alert.",
+        "operationId": "retrieve-organization-spend-alert",
+        "tags": [
+          "Spend alerts"
+        ],
+        "parameters": [
+          {
+            "name": "alert_id",
+            "in": "path",
+            "description": "The ID of the spend alert to retrieve.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Organization spend alert retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/OrganizationSpendAlert"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve organization spend alert",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/spend_alerts/alert_abc123 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"id\": \"alert_abc123\",\n    \"object\": \"organization.spend_alert\",\n    \"threshold_amount\": 150000,\n    \"currency\": \"USD\",\n    \"interval\": \"month\",\n    \"notification_channel\": {\n        \"type\": \"email\",\n        \"recipients\": [\"finance@example.com\"],\n        \"subject_prefix\": \"OpenAI spend alert\"\n    }\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Updates an organization spend alert.",
+        "operationId": "update-organization-spend-alert",
+        "tags": [
+          "Spend alerts"
+        ],
+        "parameters": [
+          {
+            "name": "alert_id",
+            "in": "path",
+            "description": "The ID of the spend alert to update.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "Fields to update on the organization spend alert.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateSpendAlertBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Organization spend alert updated successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/OrganizationSpendAlert"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update organization spend alert",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/spend_alerts/alert_abc123 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"threshold_amount\": 150000,\n      \"currency\": \"USD\",\n      \"interval\": \"month\",\n      \"notification_channel\": {\n          \"type\": \"email\",\n          \"recipients\": [\"finance@example.com\"],\n          \"subject_prefix\": \"OpenAI spend alert\"\n      }\n  }'\n"
+            },
+            "response": "{\n    \"id\": \"alert_abc123\",\n    \"object\": \"organization.spend_alert\",\n    \"threshold_amount\": 150000,\n    \"currency\": \"USD\",\n    \"interval\": \"month\",\n    \"notification_channel\": {\n        \"type\": \"email\",\n        \"recipients\": [\"finance@example.com\"],\n        \"subject_prefix\": \"OpenAI spend alert\"\n    }\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Deletes an organization spend alert.",
+        "operationId": "delete-organization-spend-alert",
+        "tags": [
+          "Spend alerts"
+        ],
+        "parameters": [
+          {
+            "name": "alert_id",
+            "in": "path",
+            "description": "The ID of the spend alert to delete.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Organization spend alert deleted successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/OrganizationSpendAlertDeletedResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete organization spend alert",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/organization/spend_alerts/alert_abc123 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"id\": \"alert_abc123\",\n    \"object\": \"organization.spend_alert.deleted\",\n    \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/usage/audio_speeches": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Get audio speeches usage details for the organization.",
+        "operationId": "usage-audio-speeches",
+        "tags": [
+          "Usage"
+        ],
+        "parameters": [
+          {
+            "name": "start_time",
+            "in": "query",
+            "description": "Start time (Unix seconds) of the query time range, inclusive.",
+            "required": true,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "end_time",
+            "in": "query",
+            "description": "End time (Unix seconds) of the query time range, exclusive.",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "bucket_width",
+            "in": "query",
+            "description": "Width of each time bucket in response. Currently `1m`, `1h` and `1d` are supported, default to `1d`.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "1m",
+                "1h",
+                "1d"
+              ],
+              "default": "1d"
+            }
+          },
+          {
+            "name": "project_ids",
+            "in": "query",
+            "description": "Return only usage for these projects.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "user_ids",
+            "in": "query",
+            "description": "Return only usage for these users.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "api_key_ids",
+            "in": "query",
+            "description": "Return only usage for these API keys.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "models",
+            "in": "query",
+            "description": "Return only usage for these models.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "group_by",
+            "in": "query",
+            "description": "Group the usage data by the specified fields. Support fields include `project_id`, `user_id`, `api_key_id`, `model` or any combination of them.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "project_id",
+                  "user_id",
+                  "api_key_id",
+                  "model"
+                ]
+              }
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Specifies the number of buckets to return.\n- `bucket_width=1d`: default: 7, max: 31\n- `bucket_width=1h`: default: 24, max: 168\n- `bucket_width=1m`: default: 60, max: 1440\n",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "page",
+            "in": "query",
+            "description": "A cursor for use in pagination. Corresponding to the `next_page` field from the previous response.",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Usage data retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/UsageResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Audio speeches",
+          "group": "usage-audio-speeches",
+          "examples": {
+            "request": {
+              "curl": "curl \"https://api.openai.com/v1/organization/usage/audio_speeches?start_time=1730419200&limit=1\" \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n-H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"page\",\n    \"data\": [\n        {\n            \"object\": \"bucket\",\n            \"start_time\": 1730419200,\n            \"end_time\": 1730505600,\n            \"results\": [\n                {\n                    \"object\": \"organization.usage.audio_speeches.result\",\n                    \"characters\": 45,\n                    \"num_model_requests\": 1,\n                    \"project_id\": null,\n                    \"user_id\": null,\n                    \"api_key_id\": null,\n                    \"model\": null\n                }\n            ]\n        }\n    ],\n    \"has_more\": false,\n    \"next_page\": null\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/usage/audio_transcriptions": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Get audio transcriptions usage details for the organization.",
+        "operationId": "usage-audio-transcriptions",
+        "tags": [
+          "Usage"
+        ],
+        "parameters": [
+          {
+            "name": "start_time",
+            "in": "query",
+            "description": "Start time (Unix seconds) of the query time range, inclusive.",
+            "required": true,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "end_time",
+            "in": "query",
+            "description": "End time (Unix seconds) of the query time range, exclusive.",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "bucket_width",
+            "in": "query",
+            "description": "Width of each time bucket in response. Currently `1m`, `1h` and `1d` are supported, default to `1d`.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "1m",
+                "1h",
+                "1d"
+              ],
+              "default": "1d"
+            }
+          },
+          {
+            "name": "project_ids",
+            "in": "query",
+            "description": "Return only usage for these projects.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "user_ids",
+            "in": "query",
+            "description": "Return only usage for these users.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "api_key_ids",
+            "in": "query",
+            "description": "Return only usage for these API keys.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "models",
+            "in": "query",
+            "description": "Return only usage for these models.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "group_by",
+            "in": "query",
+            "description": "Group the usage data by the specified fields. Support fields include `project_id`, `user_id`, `api_key_id`, `model` or any combination of them.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "project_id",
+                  "user_id",
+                  "api_key_id",
+                  "model"
+                ]
+              }
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Specifies the number of buckets to return.\n- `bucket_width=1d`: default: 7, max: 31\n- `bucket_width=1h`: default: 24, max: 168\n- `bucket_width=1m`: default: 60, max: 1440\n",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "page",
+            "in": "query",
+            "description": "A cursor for use in pagination. Corresponding to the `next_page` field from the previous response.",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Usage data retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/UsageResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Audio transcriptions",
+          "group": "usage-audio-transcriptions",
+          "examples": {
+            "request": {
+              "curl": "curl \"https://api.openai.com/v1/organization/usage/audio_transcriptions?start_time=1730419200&limit=1\" \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n-H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"page\",\n    \"data\": [\n        {\n            \"object\": \"bucket\",\n            \"start_time\": 1730419200,\n            \"end_time\": 1730505600,\n            \"results\": [\n                {\n                    \"object\": \"organization.usage.audio_transcriptions.result\",\n                    \"seconds\": 20,\n                    \"num_model_requests\": 1,\n                    \"project_id\": null,\n                    \"user_id\": null,\n                    \"api_key_id\": null,\n                    \"model\": null\n                }\n            ]\n        }\n    ],\n    \"has_more\": false,\n    \"next_page\": null\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/usage/code_interpreter_sessions": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Get code interpreter sessions usage details for the organization.",
+        "operationId": "usage-code-interpreter-sessions",
+        "tags": [
+          "Usage"
+        ],
+        "parameters": [
+          {
+            "name": "start_time",
+            "in": "query",
+            "description": "Start time (Unix seconds) of the query time range, inclusive.",
+            "required": true,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "end_time",
+            "in": "query",
+            "description": "End time (Unix seconds) of the query time range, exclusive.",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "bucket_width",
+            "in": "query",
+            "description": "Width of each time bucket in response. Currently `1m`, `1h` and `1d` are supported, default to `1d`.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "1m",
+                "1h",
+                "1d"
+              ],
+              "default": "1d"
+            }
+          },
+          {
+            "name": "project_ids",
+            "in": "query",
+            "description": "Return only usage for these projects.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "group_by",
+            "in": "query",
+            "description": "Group the usage data by the specified fields. Support fields include `project_id`.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "project_id"
+                ]
+              }
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Specifies the number of buckets to return.\n- `bucket_width=1d`: default: 7, max: 31\n- `bucket_width=1h`: default: 24, max: 168\n- `bucket_width=1m`: default: 60, max: 1440\n",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "page",
+            "in": "query",
+            "description": "A cursor for use in pagination. Corresponding to the `next_page` field from the previous response.",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Usage data retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/UsageResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Code interpreter sessions",
+          "group": "usage-code-interpreter-sessions",
+          "examples": {
+            "request": {
+              "curl": "curl \"https://api.openai.com/v1/organization/usage/code_interpreter_sessions?start_time=1730419200&limit=1\" \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n-H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"page\",\n    \"data\": [\n        {\n            \"object\": \"bucket\",\n            \"start_time\": 1730419200,\n            \"end_time\": 1730505600,\n            \"results\": [\n                {\n                    \"object\": \"organization.usage.code_interpreter_sessions.result\",\n                    \"num_sessions\": 1,\n                    \"project_id\": null\n                }\n            ]\n        }\n    ],\n    \"has_more\": false,\n    \"next_page\": null\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/usage/completions": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Get completions usage details for the organization.",
+        "operationId": "usage-completions",
+        "tags": [
+          "Usage"
+        ],
+        "parameters": [
+          {
+            "name": "start_time",
+            "in": "query",
+            "description": "Start time (Unix seconds) of the query time range, inclusive.",
+            "required": true,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "end_time",
+            "in": "query",
+            "description": "End time (Unix seconds) of the query time range, exclusive.",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "bucket_width",
+            "in": "query",
+            "description": "Width of each time bucket in response. Currently `1m`, `1h` and `1d` are supported, default to `1d`.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "1m",
+                "1h",
+                "1d"
+              ],
+              "default": "1d"
+            }
+          },
+          {
+            "name": "project_ids",
+            "in": "query",
+            "description": "Return only usage for these projects.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "user_ids",
+            "in": "query",
+            "description": "Return only usage for these users.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "api_key_ids",
+            "in": "query",
+            "description": "Return only usage for these API keys.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "models",
+            "in": "query",
+            "description": "Return only usage for these models.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "batch",
+            "in": "query",
+            "description": "If `true`, return batch jobs only. If `false`, return non-batch jobs only. By default, return both.\n",
+            "required": false,
+            "schema": {
+              "type": "boolean"
+            }
+          },
+          {
+            "name": "group_by",
+            "in": "query",
+            "description": "Group the usage data by the specified fields. Support fields include `project_id`, `user_id`, `api_key_id`, `model`, `batch`, `service_tier` or any combination of them.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "project_id",
+                  "user_id",
+                  "api_key_id",
+                  "model",
+                  "batch",
+                  "service_tier"
+                ]
+              }
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Specifies the number of buckets to return.\n- `bucket_width=1d`: default: 7, max: 31\n- `bucket_width=1h`: default: 24, max: 168\n- `bucket_width=1m`: default: 60, max: 1440\n",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "page",
+            "in": "query",
+            "description": "A cursor for use in pagination. Corresponding to the `next_page` field from the previous response.",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Usage data retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/UsageResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Completions",
+          "group": "usage-completions",
+          "examples": {
+            "request": {
+              "curl": "curl \"https://api.openai.com/v1/organization/usage/completions?start_time=1730419200&limit=1\" \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n-H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"page\",\n    \"data\": [\n        {\n            \"object\": \"bucket\",\n            \"start_time\": 1730419200,\n            \"end_time\": 1730505600,\n            \"results\": [\n                {\n                    \"object\": \"organization.usage.completions.result\",\n                    \"input_tokens\": 1000,\n                    \"input_cached_tokens\": 400,\n                    \"input_cache_write_tokens\": 100,\n                    \"input_uncached_tokens\": 500,\n                    \"output_tokens\": 500,\n                    \"input_text_tokens\": 400,\n                    \"output_text_tokens\": 400,\n                    \"input_cached_text_tokens\": 300,\n                    \"input_audio_tokens\": 50,\n                    \"input_cached_audio_tokens\": 50,\n                    \"output_audio_tokens\": 50,\n                    \"input_image_tokens\": 50,\n                    \"input_cached_image_tokens\": 50,\n                    \"output_image_tokens\": 50,\n                    \"num_model_requests\": 5,\n                    \"project_id\": null,\n                    \"user_id\": null,\n                    \"api_key_id\": null,\n                    \"model\": null,\n                    \"batch\": null,\n                    \"service_tier\": null\n                }\n            ]\n        }\n    ],\n    \"has_more\": true,\n    \"next_page\": \"page_AAAAAGdGxdEiJdKOAAAAAGcqsYA=\"\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/usage/embeddings": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Get embeddings usage details for the organization.",
+        "operationId": "usage-embeddings",
+        "tags": [
+          "Usage"
+        ],
+        "parameters": [
+          {
+            "name": "start_time",
+            "in": "query",
+            "description": "Start time (Unix seconds) of the query time range, inclusive.",
+            "required": true,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "end_time",
+            "in": "query",
+            "description": "End time (Unix seconds) of the query time range, exclusive.",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "bucket_width",
+            "in": "query",
+            "description": "Width of each time bucket in response. Currently `1m`, `1h` and `1d` are supported, default to `1d`.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "1m",
+                "1h",
+                "1d"
+              ],
+              "default": "1d"
+            }
+          },
+          {
+            "name": "project_ids",
+            "in": "query",
+            "description": "Return only usage for these projects.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "user_ids",
+            "in": "query",
+            "description": "Return only usage for these users.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "api_key_ids",
+            "in": "query",
+            "description": "Return only usage for these API keys.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "models",
+            "in": "query",
+            "description": "Return only usage for these models.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "group_by",
+            "in": "query",
+            "description": "Group the usage data by the specified fields. Support fields include `project_id`, `user_id`, `api_key_id`, `model` or any combination of them.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "project_id",
+                  "user_id",
+                  "api_key_id",
+                  "model"
+                ]
+              }
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Specifies the number of buckets to return.\n- `bucket_width=1d`: default: 7, max: 31\n- `bucket_width=1h`: default: 24, max: 168\n- `bucket_width=1m`: default: 60, max: 1440\n",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "page",
+            "in": "query",
+            "description": "A cursor for use in pagination. Corresponding to the `next_page` field from the previous response.",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Usage data retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/UsageResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Embeddings",
+          "group": "usage-embeddings",
+          "examples": {
+            "request": {
+              "curl": "curl \"https://api.openai.com/v1/organization/usage/embeddings?start_time=1730419200&limit=1\" \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n-H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"page\",\n    \"data\": [\n        {\n            \"object\": \"bucket\",\n            \"start_time\": 1730419200,\n            \"end_time\": 1730505600,\n            \"results\": [\n                {\n                    \"object\": \"organization.usage.embeddings.result\",\n                    \"input_tokens\": 16,\n                    \"num_model_requests\": 2,\n                    \"project_id\": null,\n                    \"user_id\": null,\n                    \"api_key_id\": null,\n                    \"model\": null\n                }\n            ]\n        }\n    ],\n    \"has_more\": false,\n    \"next_page\": null\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/usage/file_search_calls": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Get file search calls usage details for the organization.",
+        "operationId": "usage-file-search-calls",
+        "tags": [
+          "Usage"
+        ],
+        "parameters": [
+          {
+            "name": "start_time",
+            "in": "query",
+            "description": "Start time (Unix seconds) of the query time range, inclusive.",
+            "required": true,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "end_time",
+            "in": "query",
+            "description": "End time (Unix seconds) of the query time range, exclusive.",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "bucket_width",
+            "in": "query",
+            "description": "Width of each time bucket in response. Currently `1m`, `1h` and `1d` are supported, default to `1d`.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "1m",
+                "1h",
+                "1d"
+              ],
+              "default": "1d"
+            }
+          },
+          {
+            "name": "project_ids",
+            "in": "query",
+            "description": "Return only usage for these projects.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "user_ids",
+            "in": "query",
+            "description": "Return only usage for these users.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "api_key_ids",
+            "in": "query",
+            "description": "Return only usage for these API keys.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "vector_store_ids",
+            "in": "query",
+            "description": "Return only usage for these vector stores.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "group_by",
+            "in": "query",
+            "description": "Group the usage data by the specified fields. Support fields include `project_id`, `user_id`, `api_key_id`, `vector_store_id` or any combination of them.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "project_id",
+                  "user_id",
+                  "api_key_id",
+                  "vector_store_id"
+                ]
+              }
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Specifies the number of buckets to return.\n- `bucket_width=1d`: default: 7, max: 31\n- `bucket_width=1h`: default: 24, max: 168\n- `bucket_width=1m`: default: 60, max: 1440\n",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "page",
+            "in": "query",
+            "description": "A cursor for use in pagination. Corresponding to the `next_page` field from the previous response.",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Usage data retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/UsageResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "File search calls",
+          "group": "usage-file-search-calls",
+          "examples": {
+            "request": {
+              "curl": "curl \"https://api.openai.com/v1/organization/usage/file_search_calls?start_time=1730419200&limit=1\" \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n-H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"page\",\n    \"data\": [\n        {\n            \"object\": \"bucket\",\n            \"start_time\": 1730419200,\n            \"end_time\": 1730505600,\n            \"results\": [\n                {\n                    \"object\": \"organization.usage.file_searches.result\",\n                    \"num_requests\": 2,\n                    \"project_id\": null,\n                    \"user_id\": null,\n                    \"api_key_id\": null,\n                    \"vector_store_id\": null\n                }\n            ]\n        }\n    ],\n    \"has_more\": false,\n    \"next_page\": null\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/usage/images": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Get images usage details for the organization.",
+        "operationId": "usage-images",
+        "tags": [
+          "Usage"
+        ],
+        "parameters": [
+          {
+            "name": "start_time",
+            "in": "query",
+            "description": "Start time (Unix seconds) of the query time range, inclusive.",
+            "required": true,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "end_time",
+            "in": "query",
+            "description": "End time (Unix seconds) of the query time range, exclusive.",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "bucket_width",
+            "in": "query",
+            "description": "Width of each time bucket in response. Currently `1m`, `1h` and `1d` are supported, default to `1d`.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "1m",
+                "1h",
+                "1d"
+              ],
+              "default": "1d"
+            }
+          },
+          {
+            "name": "sources",
+            "in": "query",
+            "description": "Return only usages for these sources. Possible values are `image.generation`, `image.edit`, `image.variation` or any combination of them.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "image.generation",
+                  "image.edit",
+                  "image.variation"
+                ]
+              }
+            }
+          },
+          {
+            "name": "sizes",
+            "in": "query",
+            "description": "Return only usages for these image sizes. Possible values are `256x256`, `512x512`, `1024x1024`, `1792x1792`, `1024x1792` or any combination of them.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "256x256",
+                  "512x512",
+                  "1024x1024",
+                  "1792x1792",
+                  "1024x1792"
+                ]
+              }
+            }
+          },
+          {
+            "name": "project_ids",
+            "in": "query",
+            "description": "Return only usage for these projects.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "user_ids",
+            "in": "query",
+            "description": "Return only usage for these users.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "api_key_ids",
+            "in": "query",
+            "description": "Return only usage for these API keys.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "models",
+            "in": "query",
+            "description": "Return only usage for these models.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "group_by",
+            "in": "query",
+            "description": "Group the usage data by the specified fields. Support fields include `project_id`, `user_id`, `api_key_id`, `model`, `size`, `source` or any combination of them.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "project_id",
+                  "user_id",
+                  "api_key_id",
+                  "model",
+                  "size",
+                  "source"
+                ]
+              }
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Specifies the number of buckets to return.\n- `bucket_width=1d`: default: 7, max: 31\n- `bucket_width=1h`: default: 24, max: 168\n- `bucket_width=1m`: default: 60, max: 1440\n",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "page",
+            "in": "query",
+            "description": "A cursor for use in pagination. Corresponding to the `next_page` field from the previous response.",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Usage data retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/UsageResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Images",
+          "group": "usage-images",
+          "examples": {
+            "request": {
+              "curl": "curl \"https://api.openai.com/v1/organization/usage/images?start_time=1730419200&limit=1\" \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n-H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"page\",\n    \"data\": [\n        {\n            \"object\": \"bucket\",\n            \"start_time\": 1730419200,\n            \"end_time\": 1730505600,\n            \"results\": [\n                {\n                    \"object\": \"organization.usage.images.result\",\n                    \"images\": 2,\n                    \"num_model_requests\": 2,\n                    \"size\": null,\n                    \"source\": null,\n                    \"project_id\": null,\n                    \"user_id\": null,\n                    \"api_key_id\": null,\n                    \"model\": null\n                }\n            ]\n        }\n    ],\n    \"has_more\": false,\n    \"next_page\": null\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/usage/moderations": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Get moderations usage details for the organization.",
+        "operationId": "usage-moderations",
+        "tags": [
+          "Usage"
+        ],
+        "parameters": [
+          {
+            "name": "start_time",
+            "in": "query",
+            "description": "Start time (Unix seconds) of the query time range, inclusive.",
+            "required": true,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "end_time",
+            "in": "query",
+            "description": "End time (Unix seconds) of the query time range, exclusive.",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "bucket_width",
+            "in": "query",
+            "description": "Width of each time bucket in response. Currently `1m`, `1h` and `1d` are supported, default to `1d`.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "1m",
+                "1h",
+                "1d"
+              ],
+              "default": "1d"
+            }
+          },
+          {
+            "name": "project_ids",
+            "in": "query",
+            "description": "Return only usage for these projects.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "user_ids",
+            "in": "query",
+            "description": "Return only usage for these users.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "api_key_ids",
+            "in": "query",
+            "description": "Return only usage for these API keys.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "models",
+            "in": "query",
+            "description": "Return only usage for these models.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "group_by",
+            "in": "query",
+            "description": "Group the usage data by the specified fields. Support fields include `project_id`, `user_id`, `api_key_id`, `model` or any combination of them.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "project_id",
+                  "user_id",
+                  "api_key_id",
+                  "model"
+                ]
+              }
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Specifies the number of buckets to return.\n- `bucket_width=1d`: default: 7, max: 31\n- `bucket_width=1h`: default: 24, max: 168\n- `bucket_width=1m`: default: 60, max: 1440\n",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "page",
+            "in": "query",
+            "description": "A cursor for use in pagination. Corresponding to the `next_page` field from the previous response.",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Usage data retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/UsageResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Moderations",
+          "group": "usage-moderations",
+          "examples": {
+            "request": {
+              "curl": "curl \"https://api.openai.com/v1/organization/usage/moderations?start_time=1730419200&limit=1\" \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n-H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"page\",\n    \"data\": [\n        {\n            \"object\": \"bucket\",\n            \"start_time\": 1730419200,\n            \"end_time\": 1730505600,\n            \"results\": [\n                {\n                    \"object\": \"organization.usage.moderations.result\",\n                    \"input_tokens\": 16,\n                    \"num_model_requests\": 2,\n                    \"project_id\": null,\n                    \"user_id\": null,\n                    \"api_key_id\": null,\n                    \"model\": null\n                }\n            ]\n        }\n    ],\n    \"has_more\": false,\n    \"next_page\": null\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/usage/vector_stores": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Get vector stores usage details for the organization.",
+        "operationId": "usage-vector-stores",
+        "tags": [
+          "Usage"
+        ],
+        "parameters": [
+          {
+            "name": "start_time",
+            "in": "query",
+            "description": "Start time (Unix seconds) of the query time range, inclusive.",
+            "required": true,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "end_time",
+            "in": "query",
+            "description": "End time (Unix seconds) of the query time range, exclusive.",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "bucket_width",
+            "in": "query",
+            "description": "Width of each time bucket in response. Currently `1m`, `1h` and `1d` are supported, default to `1d`.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "1m",
+                "1h",
+                "1d"
+              ],
+              "default": "1d"
+            }
+          },
+          {
+            "name": "project_ids",
+            "in": "query",
+            "description": "Return only usage for these projects.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "group_by",
+            "in": "query",
+            "description": "Group the usage data by the specified fields. Support fields include `project_id`.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "project_id"
+                ]
+              }
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Specifies the number of buckets to return.\n- `bucket_width=1d`: default: 7, max: 31\n- `bucket_width=1h`: default: 24, max: 168\n- `bucket_width=1m`: default: 60, max: 1440\n",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "page",
+            "in": "query",
+            "description": "A cursor for use in pagination. Corresponding to the `next_page` field from the previous response.",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Usage data retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/UsageResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Vector stores",
+          "group": "usage-vector-stores",
+          "examples": {
+            "request": {
+              "curl": "curl \"https://api.openai.com/v1/organization/usage/vector_stores?start_time=1730419200&limit=1\" \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n-H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"page\",\n    \"data\": [\n        {\n            \"object\": \"bucket\",\n            \"start_time\": 1730419200,\n            \"end_time\": 1730505600,\n            \"results\": [\n                {\n                    \"object\": \"organization.usage.vector_stores.result\",\n                    \"usage_bytes\": 1024,\n                    \"project_id\": null\n                }\n            ]\n        }\n    ],\n    \"has_more\": false,\n    \"next_page\": null\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/usage/web_search_calls": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Get web search calls usage details for the organization.",
+        "operationId": "usage-web-search-calls",
+        "tags": [
+          "Usage"
+        ],
+        "parameters": [
+          {
+            "name": "start_time",
+            "in": "query",
+            "description": "Start time (Unix seconds) of the query time range, inclusive.",
+            "required": true,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "end_time",
+            "in": "query",
+            "description": "End time (Unix seconds) of the query time range, exclusive.",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "bucket_width",
+            "in": "query",
+            "description": "Width of each time bucket in response. Currently `1m`, `1h` and `1d` are supported, default to `1d`.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "1m",
+                "1h",
+                "1d"
+              ],
+              "default": "1d"
+            }
+          },
+          {
+            "name": "project_ids",
+            "in": "query",
+            "description": "Return only usage for these projects.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "user_ids",
+            "in": "query",
+            "description": "Return only usage for these users.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "api_key_ids",
+            "in": "query",
+            "description": "Return only usage for these API keys.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "models",
+            "in": "query",
+            "description": "Return only usage for these models.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          },
+          {
+            "name": "context_levels",
+            "in": "query",
+            "description": "Return only web search usage for these context levels.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "low",
+                  "medium",
+                  "high"
+                ]
+              }
+            }
+          },
+          {
+            "name": "group_by",
+            "in": "query",
+            "description": "Group the usage data by the specified fields. Support fields include `project_id`, `user_id`, `api_key_id`, `model`, `context_level` or any combination of them.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "project_id",
+                  "user_id",
+                  "api_key_id",
+                  "model",
+                  "context_level"
+                ]
+              }
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Specifies the number of buckets to return.\n- `bucket_width=1d`: default: 7, max: 31\n- `bucket_width=1h`: default: 24, max: 168\n- `bucket_width=1m`: default: 60, max: 1440\n",
+            "required": false,
+            "schema": {
+              "type": "integer"
+            }
+          },
+          {
+            "name": "page",
+            "in": "query",
+            "description": "A cursor for use in pagination. Corresponding to the `next_page` field from the previous response.",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Usage data retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/UsageResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Web search calls",
+          "group": "usage-web-search-calls",
+          "examples": {
+            "request": {
+              "curl": "curl \"https://api.openai.com/v1/organization/usage/web_search_calls?start_time=1730419200&limit=1\" \\\n-H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n-H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"page\",\n    \"data\": [\n        {\n            \"object\": \"bucket\",\n            \"start_time\": 1730419200,\n            \"end_time\": 1730505600,\n            \"results\": [\n                {\n                    \"object\": \"organization.usage.web_searches.result\",\n                    \"num_model_requests\": 2,\n                    \"num_requests\": 2,\n                    \"project_id\": null,\n                    \"user_id\": null,\n                    \"api_key_id\": null,\n                    \"model\": null,\n                    \"context_level\": null\n                }\n            ]\n        }\n    ],\n    \"has_more\": false,\n    \"next_page\": null\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/users": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Lists all of the users in the organization.",
+        "operationId": "list-users",
+        "tags": [
+          "Users"
+        ],
+        "parameters": [
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "emails",
+            "in": "query",
+            "description": "Filter by the email address of users.",
+            "required": false,
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string"
+              }
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Users listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/UserListResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List users",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/users?after=user_abc&limit=20 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"object\": \"organization.user\",\n            \"id\": \"user_abc\",\n            \"name\": \"First Last\",\n            \"email\": \"user@example.com\",\n            \"role\": \"owner\",\n            \"added_at\": 1711471533\n        }\n    ],\n    \"first_id\": \"user-abc\",\n    \"last_id\": \"user-xyz\",\n    \"has_more\": false\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/users/{user_id}": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Retrieves a user by their identifier.",
+        "operationId": "retrieve-user",
+        "tags": [
+          "Users"
+        ],
+        "parameters": [
+          {
+            "name": "user_id",
+            "in": "path",
+            "description": "The ID of the user.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "User retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/User"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve user",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/users/user_abc \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"organization.user\",\n    \"id\": \"user_abc\",\n    \"name\": \"First Last\",\n    \"email\": \"user@example.com\",\n    \"role\": \"owner\",\n    \"added_at\": 1711471533\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Modifies a user's role in the organization.",
+        "operationId": "modify-user",
+        "tags": [
+          "Users"
+        ],
+        "parameters": [
+          {
+            "name": "user_id",
+            "in": "path",
+            "description": "The ID of the user.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "The new user role to modify. This must be one of `owner` or `member`.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/UserRoleUpdateRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "User role updated successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/User"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Modify user",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/users/user_abc \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"role\": \"owner\"\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"organization.user\",\n    \"id\": \"user_abc\",\n    \"name\": \"First Last\",\n    \"email\": \"user@example.com\",\n    \"role\": \"owner\",\n    \"added_at\": 1711471533\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Deletes a user from the organization.",
+        "operationId": "delete-user",
+        "tags": [
+          "Users"
+        ],
+        "parameters": [
+          {
+            "name": "user_id",
+            "in": "path",
+            "description": "The ID of the user.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "User deleted successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/UserDeleteResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete user",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/organization/users/user_abc \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"organization.user.deleted\",\n    \"id\": \"user_abc\",\n    \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/users/{user_id}/roles": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Lists the organization roles assigned to a user within the organization.",
+        "operationId": "list-user-role-assignments",
+        "tags": [
+          "User organization role assignments"
+        ],
+        "parameters": [
+          {
+            "name": "user_id",
+            "in": "path",
+            "description": "The ID of the user to inspect.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of organization role assignments to return.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 1000
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Cursor for pagination. Provide the value from the previous response's `next` field to continue listing organization roles.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order for the returned organization roles.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "asc",
+                "desc"
+              ]
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "User organization role assignments listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RoleListResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List user organization role assignments",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/users/user_abc123/roles \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"id\": \"role_01J1F8ROLE01\",\n            \"name\": \"API Group Manager\",\n            \"permissions\": [\n                \"api.groups.read\",\n                \"api.groups.write\"\n            ],\n            \"resource_type\": \"api.organization\",\n            \"predefined_role\": false,\n            \"description\": \"Allows managing organization groups\",\n            \"created_at\": 1711471533,\n            \"updated_at\": 1711472599,\n            \"created_by\": \"user_abc123\",\n            \"created_by_user_obj\": {\n                \"id\": \"user_abc123\",\n                \"name\": \"Ada Lovelace\",\n                \"email\": \"ada@example.com\"\n            },\n            \"metadata\": {}\n        }\n    ],\n    \"has_more\": false,\n    \"next\": null\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Assigns an organization role to a user within the organization.",
+        "operationId": "assign-user-role",
+        "tags": [
+          "User organization role assignments"
+        ],
+        "parameters": [
+          {
+            "name": "user_id",
+            "in": "path",
+            "description": "The ID of the user that should receive the organization role.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "Identifies the organization role to assign to the user.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/PublicAssignOrganizationGroupRoleBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Organization role assigned to the user successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/UserRoleAssignment"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Assign organization role to user",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/users/user_abc123/roles \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"role_id\": \"role_01J1F8ROLE01\"\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"user.role\",\n    \"user\": {\n        \"object\": \"organization.user\",\n        \"id\": \"user_abc123\",\n        \"name\": \"Ada Lovelace\",\n        \"email\": \"ada@example.com\",\n        \"role\": \"owner\",\n        \"added_at\": 1711470000\n    },\n    \"role\": {\n        \"object\": \"role\",\n        \"id\": \"role_01J1F8ROLE01\",\n        \"name\": \"API Group Manager\",\n        \"description\": \"Allows managing organization groups\",\n        \"permissions\": [\n            \"api.groups.read\",\n            \"api.groups.write\"\n        ],\n        \"resource_type\": \"api.organization\",\n        \"predefined_role\": false\n    }\n}\n"
+          }
+        }
+      }
+    },
+    "/organization/users/{user_id}/roles/{role_id}": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Retrieves an organization role assigned to a user.",
+        "operationId": "retrieve-user-role",
+        "tags": [
+          "User organization role assignments"
+        ],
+        "parameters": [
+          {
+            "name": "user_id",
+            "in": "path",
+            "description": "The ID of the user to inspect.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "role_id",
+            "in": "path",
+            "description": "The ID of the organization role to retrieve for the user.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Organization role retrieved for the user successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/AssignedRoleDetails"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve user organization role",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/users/user_abc123/roles/role_01J1F8ROLE01 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"id\": \"role_01J1F8ROLE01\",\n    \"name\": \"API Group Manager\",\n    \"permissions\": [\n        \"api.groups.read\",\n        \"api.groups.write\"\n    ],\n    \"resource_type\": \"api.organization\",\n    \"predefined_role\": false,\n    \"description\": \"Allows managing organization groups\",\n    \"created_at\": 1711471533,\n    \"updated_at\": 1711472599,\n    \"created_by\": \"user_abc123\",\n    \"created_by_user_obj\": null,\n    \"metadata\": {},\n    \"assignment_sources\": null\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Unassigns an organization role from a user within the organization.",
+        "operationId": "unassign-user-role",
+        "tags": [
+          "User organization role assignments"
+        ],
+        "parameters": [
+          {
+            "name": "user_id",
+            "in": "path",
+            "description": "The ID of the user to modify.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "role_id",
+            "in": "path",
+            "description": "The ID of the organization role to remove from the user.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Organization role unassigned from the user successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedRoleAssignmentResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Unassign organization role from user",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/organization/users/user_abc123/roles/role_01J1F8ROLE01 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"user.role.deleted\",\n    \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/projects/{project_id}/groups/{group_id}/roles": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Lists the project roles assigned to a group within a project.",
+        "operationId": "list-project-group-role-assignments",
+        "tags": [
+          "Project group role assignments"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to inspect.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "group_id",
+            "in": "path",
+            "description": "The ID of the group to inspect.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of project role assignments to return.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 1000
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Cursor for pagination. Provide the value from the previous response's `next` field to continue listing project roles.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order for the returned project roles.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "asc",
+                "desc"
+              ]
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project group role assignments listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RoleListResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List project group role assignments",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/projects/proj_abc123/groups/group_01J1F8ABCDXYZ/roles \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"id\": \"role_01J1F8PROJ\",\n            \"name\": \"API Project Key Manager\",\n            \"permissions\": [\n                \"api.organization.projects.api_keys.read\",\n                \"api.organization.projects.api_keys.write\"\n            ],\n            \"resource_type\": \"api.project\",\n            \"predefined_role\": false,\n            \"description\": \"Allows managing API keys for the project\",\n            \"created_at\": 1711471533,\n            \"updated_at\": 1711472599,\n            \"created_by\": \"user_abc123\",\n            \"created_by_user_obj\": {\n                \"id\": \"user_abc123\",\n                \"name\": \"Ada Lovelace\",\n                \"email\": \"ada@example.com\"\n            },\n            \"metadata\": {}\n        }\n    ],\n    \"has_more\": false,\n    \"next\": null\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Assigns a project role to a group within a project.",
+        "operationId": "assign-project-group-role",
+        "tags": [
+          "Project group role assignments"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to update.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "group_id",
+            "in": "path",
+            "description": "The ID of the group that should receive the project role.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "Identifies the project role to assign to the group.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/PublicAssignOrganizationGroupRoleBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Project role assigned to the group successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/GroupRoleAssignment"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Assign project role to group",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/projects/proj_abc123/groups/group_01J1F8ABCDXYZ/roles \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"role_id\": \"role_01J1F8PROJ\"\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"group.role\",\n    \"group\": {\n        \"object\": \"group\",\n        \"id\": \"group_01J1F8ABCDXYZ\",\n        \"name\": \"Support Team\",\n        \"created_at\": 1711471533,\n        \"scim_managed\": false\n    },\n    \"role\": {\n        \"object\": \"role\",\n        \"id\": \"role_01J1F8PROJ\",\n        \"name\": \"API Project Key Manager\",\n        \"description\": \"Allows managing API keys for the project\",\n        \"permissions\": [\n            \"api.organization.projects.api_keys.read\",\n            \"api.organization.projects.api_keys.write\"\n        ],\n        \"resource_type\": \"api.project\",\n        \"predefined_role\": false\n    }\n}\n"
+          }
+        }
+      }
+    },
+    "/projects/{project_id}/groups/{group_id}/roles/{role_id}": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Retrieves a project role assigned to a group.",
+        "operationId": "retrieve-project-group-role",
+        "tags": [
+          "Project group role assignments"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to inspect.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "group_id",
+            "in": "path",
+            "description": "The ID of the group to inspect.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "role_id",
+            "in": "path",
+            "description": "The ID of the project role to retrieve for the group.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project role retrieved for the group successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/AssignedRoleDetails"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve project group role",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/projects/proj_abc123/groups/group_01J1F8ABCDXYZ/roles/role_01J1F8PROJ \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"id\": \"role_01J1F8PROJ\",\n    \"name\": \"API Project Key Manager\",\n    \"permissions\": [\n        \"api.organization.projects.api_keys.read\",\n        \"api.organization.projects.api_keys.write\"\n    ],\n    \"resource_type\": \"api.project\",\n    \"predefined_role\": false,\n    \"description\": \"Allows managing API keys for the project\",\n    \"created_at\": 1711471533,\n    \"updated_at\": 1711472599,\n    \"created_by\": \"user_abc123\",\n    \"created_by_user_obj\": null,\n    \"metadata\": {},\n    \"assignment_sources\": null\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Unassigns a project role from a group within a project.",
+        "operationId": "unassign-project-group-role",
+        "tags": [
+          "Project group role assignments"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to modify.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "group_id",
+            "in": "path",
+            "description": "The ID of the group whose project role assignment should be removed.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "role_id",
+            "in": "path",
+            "description": "The ID of the project role to remove from the group.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project role unassigned from the group successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedRoleAssignmentResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Unassign project role from group",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/projects/proj_abc123/groups/group_01J1F8ABCDXYZ/roles/role_01J1F8PROJ \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"group.role.deleted\",\n    \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/projects/{project_id}/roles": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Lists the roles configured for a project.",
+        "operationId": "list-project-roles",
+        "tags": [
+          "Roles"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to inspect.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of roles to return. Defaults to 1000.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 1000,
+              "default": 1000
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Cursor for pagination. Provide the value from the previous response's `next` field to continue listing roles.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order for the returned roles.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "asc",
+                "desc"
+              ],
+              "default": "asc"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project roles listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/PublicRoleListResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List project roles",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/projects/proj_abc123/roles?limit=20 \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"object\": \"role\",\n            \"id\": \"role_01J1F8PROJ\",\n            \"name\": \"API Project Key Manager\",\n            \"description\": \"Allows managing API keys for the project\",\n            \"permissions\": [\n                \"api.organization.projects.api_keys.read\",\n                \"api.organization.projects.api_keys.write\"\n            ],\n            \"resource_type\": \"api.project\",\n            \"predefined_role\": false\n        }\n    ],\n    \"has_more\": false,\n    \"next\": null\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Creates a custom role for a project.",
+        "operationId": "create-project-role",
+        "tags": [
+          "Roles"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to update.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "Parameters for the project role you want to create.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/PublicCreateOrganizationRoleBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Project role created successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Role"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create project role",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/projects/proj_abc123/roles \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"role_name\": \"API Project Key Manager\",\n      \"permissions\": [\n          \"api.organization.projects.api_keys.read\",\n          \"api.organization.projects.api_keys.write\"\n      ],\n      \"description\": \"Allows managing API keys for the project\"\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"role\",\n    \"id\": \"role_01J1F8PROJ\",\n    \"name\": \"API Project Key Manager\",\n    \"description\": \"Allows managing API keys for the project\",\n    \"permissions\": [\n        \"api.organization.projects.api_keys.read\",\n        \"api.organization.projects.api_keys.write\"\n    ],\n    \"resource_type\": \"api.project\",\n    \"predefined_role\": false\n}\n"
+          }
+        }
+      }
+    },
+    "/projects/{project_id}/roles/{role_id}": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Retrieves a project role.",
+        "operationId": "retrieve-project-role",
+        "tags": [
+          "Roles"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "role_id",
+            "in": "path",
+            "description": "The ID of the role to retrieve.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project role retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Role"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve project role",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/projects/proj_abc123/roles/role_01J1F8PROJ \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"role\",\n    \"id\": \"role_01J1F8PROJ\",\n    \"name\": \"API Project Key Manager\",\n    \"description\": \"Allows managing API keys for the project\",\n    \"permissions\": [\n        \"api.organization.projects.api_keys.read\",\n        \"api.organization.projects.api_keys.write\"\n    ],\n    \"resource_type\": \"api.project\",\n    \"predefined_role\": false\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Updates an existing project role.",
+        "operationId": "update-project-role",
+        "tags": [
+          "Roles"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to update.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "role_id",
+            "in": "path",
+            "description": "The ID of the role to update.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "Fields to update on the project role.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/PublicUpdateOrganizationRoleBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Project role updated successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Role"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update project role",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/projects/proj_abc123/roles/role_01J1F8PROJ \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"role_name\": \"API Project Key Manager\",\n      \"permissions\": [\n          \"api.organization.projects.api_keys.read\",\n          \"api.organization.projects.api_keys.write\"\n      ],\n      \"description\": \"Allows managing API keys for the project\"\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"role\",\n    \"id\": \"role_01J1F8PROJ\",\n    \"name\": \"API Project Key Manager\",\n    \"description\": \"Allows managing API keys for the project\",\n    \"permissions\": [\n        \"api.organization.projects.api_keys.read\",\n        \"api.organization.projects.api_keys.write\"\n    ],\n    \"resource_type\": \"api.project\",\n    \"predefined_role\": false\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Deletes a custom role from a project.",
+        "operationId": "delete-project-role",
+        "tags": [
+          "Roles"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to update.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "role_id",
+            "in": "path",
+            "description": "The ID of the role to delete.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project role deleted successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RoleDeletedResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete project role",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/projects/proj_abc123/roles/role_01J1F8PROJ \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"role.deleted\",\n    \"id\": \"role_01J1F8PROJ\",\n    \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/projects/{project_id}/users/{user_id}/roles": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Lists the project roles assigned to a user within a project.",
+        "operationId": "list-project-user-role-assignments",
+        "tags": [
+          "Project user role assignments"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to inspect.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "user_id",
+            "in": "path",
+            "description": "The ID of the user to inspect.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of project role assignments to return.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 1000
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Cursor for pagination. Provide the value from the previous response's `next` field to continue listing project roles.",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order for the returned project roles.",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "enum": [
+                "asc",
+                "desc"
+              ]
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project user role assignments listed successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RoleListResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List project user role assignments",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/projects/proj_abc123/users/user_abc123/roles \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"id\": \"role_01J1F8PROJ\",\n            \"name\": \"API Project Key Manager\",\n            \"permissions\": [\n                \"api.organization.projects.api_keys.read\",\n                \"api.organization.projects.api_keys.write\"\n            ],\n            \"resource_type\": \"api.project\",\n            \"predefined_role\": false,\n            \"description\": \"Allows managing API keys for the project\",\n            \"created_at\": 1711471533,\n            \"updated_at\": 1711472599,\n            \"created_by\": \"user_abc123\",\n            \"created_by_user_obj\": {\n                \"id\": \"user_abc123\",\n                \"name\": \"Ada Lovelace\",\n                \"email\": \"ada@example.com\"\n            },\n            \"metadata\": {}\n        }\n    ],\n    \"has_more\": false,\n    \"next\": null\n}\n"
+          }
+        }
+      },
+      "post": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Assigns a project role to a user within a project.",
+        "operationId": "assign-project-user-role",
+        "tags": [
+          "Project user role assignments"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to update.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "user_id",
+            "in": "path",
+            "description": "The ID of the user that should receive the project role.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "Identifies the project role to assign to the user.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/PublicAssignOrganizationGroupRoleBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Project role assigned to the user successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/UserRoleAssignment"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Assign project role to user",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/projects/proj_abc123/users/user_abc123/roles \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"role_id\": \"role_01J1F8PROJ\"\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"user.role\",\n    \"user\": {\n        \"object\": \"organization.user\",\n        \"id\": \"user_abc123\",\n        \"name\": \"Ada Lovelace\",\n        \"email\": \"ada@example.com\",\n        \"role\": \"owner\",\n        \"added_at\": 1711470000\n    },\n    \"role\": {\n        \"object\": \"role\",\n        \"id\": \"role_01J1F8PROJ\",\n        \"name\": \"API Project Key Manager\",\n        \"description\": \"Allows managing API keys for the project\",\n        \"permissions\": [\n            \"api.organization.projects.api_keys.read\",\n            \"api.organization.projects.api_keys.write\"\n        ],\n        \"resource_type\": \"api.project\",\n        \"predefined_role\": false\n    }\n}\n"
+          }
+        }
+      }
+    },
+    "/projects/{project_id}/users/{user_id}/roles/{role_id}": {
+      "get": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Retrieves a project role assigned to a user.",
+        "operationId": "retrieve-project-user-role",
+        "tags": [
+          "Project user role assignments"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to inspect.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "user_id",
+            "in": "path",
+            "description": "The ID of the user to inspect.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "role_id",
+            "in": "path",
+            "description": "The ID of the project role to retrieve for the user.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project role retrieved for the user successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/AssignedRoleDetails"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve project user role",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/projects/proj_abc123/users/user_abc123/roles/role_01J1F8PROJ \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"id\": \"role_01J1F8PROJ\",\n    \"name\": \"API Project Key Manager\",\n    \"permissions\": [\n        \"api.organization.projects.api_keys.read\",\n        \"api.organization.projects.api_keys.write\"\n    ],\n    \"resource_type\": \"api.project\",\n    \"predefined_role\": false,\n    \"description\": \"Allows managing API keys for the project\",\n    \"created_at\": 1711471533,\n    \"updated_at\": 1711472599,\n    \"created_by\": \"user_abc123\",\n    \"created_by_user_obj\": null,\n    \"metadata\": {},\n    \"assignment_sources\": null\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ],
+        "summary": "Unassigns a project role from a user within a project.",
+        "operationId": "unassign-project-user-role",
+        "tags": [
+          "Project user role assignments"
+        ],
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project to modify.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "user_id",
+            "in": "path",
+            "description": "The ID of the user whose project role assignment should be removed.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "role_id",
+            "in": "path",
+            "description": "The ID of the project role to remove from the user.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Project role unassigned from the user successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedRoleAssignmentResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Unassign project role from user",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/projects/proj_abc123/users/user_abc123/roles/role_01J1F8PROJ \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"user.role.deleted\",\n    \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/realtime/calls": {
+      "post": {
+        "summary": "Create a new Realtime API call over WebRTC and receive the SDP answer needed\nto complete the peer connection.",
+        "operationId": "create-realtime-call",
+        "tags": [
+          "Realtime"
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/RealtimeCallCreateRequest"
+              },
+              "encoding": {
+                "sdp": {
+                  "contentType": "application/sdp"
+                },
+                "session": {
+                  "contentType": "application/json"
+                }
+              }
+            },
+            "application/sdp": {
+              "schema": {
+                "type": "string",
+                "description": "WebRTC SDP offer. Use this variant when you have previously created an\nephemeral **session token** and are authenticating the request with it.\nRealtime session parameters will be retrieved from the session token."
+              }
+            }
+          }
+        },
+        "responses": {
+          "201": {
+            "description": "Realtime call created successfully.",
+            "headers": {
+              "Location": {
+                "description": "Relative URL containing the call ID for subsequent control requests.",
+                "schema": {
+                  "type": "string"
+                }
+              }
+            },
+            "content": {
+              "application/sdp": {
+                "schema": {
+                  "type": "string",
+                  "description": "SDP answer produced by OpenAI for the peer connection."
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create call",
+          "group": "realtime",
+          "returns": "Returns `201 Created` with the SDP answer in the response body. The\n`Location` response header includes the call ID for follow-up requests,\ne.g., establishing a monitoring WebSocket or hanging up the call.",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/realtime/calls \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -F \"sdp=<offer.sdp;type=application/sdp\" \\\n  -F 'session={\"type\":\"realtime\",\"model\":\"gpt-realtime\"};type=application/json'"
+            },
+            "response": "v=0\no=- 4227147428 1719357865 IN IP4 127.0.0.1\ns=-\nc=IN IP4 0.0.0.0\nt=0 0\na=group:BUNDLE 0 1\na=msid-semantic:WMS *\na=fingerprint:sha-256 CA:92:52:51:B4:91:3B:34:DD:9C:0B:FB:76:19:7E:3B:F1:21:0F:32:2C:38:01:72:5D:3F:78:C7:5F:8B:C7:36\nm=audio 9 UDP/TLS/RTP/SAVPF 111 0 8\na=mid:0\na=ice-ufrag:kZ2qkHXX/u11\na=ice-pwd:uoD16Di5OGx3VbqgA3ymjEQV2kwiOjw6\na=setup:active\na=rtcp-mux\na=rtpmap:111 opus/48000/2\na=candidate:993865896 1 udp 2130706431 4.155.146.196 3478 typ host ufrag kZ2qkHXX/u11\na=candidate:1432411780 1 tcp 1671430143 4.155.146.196 443 typ host tcptype passive ufrag kZ2qkHXX/u11\nm=application 9 UDP/DTLS/SCTP webrtc-datachannel\na=mid:1\na=sctp-port:5000"
+          }
+        }
+      }
+    },
+    "/realtime/calls/{call_id}/accept": {
+      "post": {
+        "summary": "Accept an incoming SIP call and configure the realtime session that will\nhandle it.",
+        "operationId": "accept-realtime-call",
+        "tags": [
+          "Realtime"
+        ],
+        "parameters": [
+          {
+            "in": "path",
+            "name": "call_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The identifier for the call provided in the\n[`realtime.call.incoming`](https://developers.openai.com/api/reference/resources/webhooks#realtime.call.incoming)\nwebhook."
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "description": "Session configuration to apply before the caller is bridged to the model.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/RealtimeSessionCreateRequestGA"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Call accepted successfully."
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Accept call",
+          "group": "realtime-calls",
+          "returns": "Returns `200 OK` once OpenAI starts ringing the SIP leg with the supplied\nsession configuration.",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/realtime/calls/$CALL_ID/accept \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n        \"type\": \"realtime\",\n        \"model\": \"gpt-realtime\",\n        \"instructions\": \"You are Alex, a friendly concierge for Example Corp.\",\n      }'"
+            }
+          }
+        }
+      }
+    },
+    "/realtime/calls/{call_id}/hangup": {
+      "post": {
+        "summary": "End an active Realtime API call, whether it was initiated over SIP or\nWebRTC.",
+        "operationId": "hangup-realtime-call",
+        "tags": [
+          "Realtime"
+        ],
+        "parameters": [
+          {
+            "in": "path",
+            "name": "call_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The identifier for the call. For SIP calls, use the value provided in the\n[`realtime.call.incoming`](https://developers.openai.com/api/reference/resources/webhooks#realtime.call.incoming)\nwebhook. For WebRTC sessions, reuse the call ID returned in the `Location`\nheader when creating the call with\n[`POST /v1/realtime/calls`](https://developers.openai.com/api/reference/resources/realtime/subresources/calls/methods/create)."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Call hangup initiated successfully."
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Hang up call",
+          "group": "realtime-calls",
+          "returns": "Returns `200 OK` when OpenAI begins terminating the realtime call.",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/realtime/calls/$CALL_ID/hangup \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\""
+            }
+          }
+        }
+      }
+    },
+    "/realtime/calls/{call_id}/refer": {
+      "post": {
+        "summary": "Transfer an active SIP call to a new destination using the SIP REFER verb.",
+        "operationId": "refer-realtime-call",
+        "tags": [
+          "Realtime"
+        ],
+        "parameters": [
+          {
+            "in": "path",
+            "name": "call_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The identifier for the call provided in the\n[`realtime.call.incoming`](https://developers.openai.com/api/reference/resources/webhooks#realtime.call.incoming)\nwebhook."
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "description": "Destination URI for the REFER request.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/RealtimeCallReferRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Call referred successfully."
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Refer call",
+          "group": "realtime-calls",
+          "returns": "Returns `200 OK` once the REFER is handed off to your SIP provider.",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/realtime/calls/$CALL_ID/refer \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"target_uri\": \"tel:+14155550123\"}'"
+            }
+          }
+        }
+      }
+    },
+    "/realtime/calls/{call_id}/reject": {
+      "post": {
+        "summary": "Decline an incoming SIP call by returning a SIP status code to the caller.",
+        "operationId": "reject-realtime-call",
+        "tags": [
+          "Realtime"
+        ],
+        "parameters": [
+          {
+            "in": "path",
+            "name": "call_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The identifier for the call provided in the\n[`realtime.call.incoming`](https://developers.openai.com/api/reference/resources/webhooks#realtime.call.incoming)\nwebhook."
+          }
+        ],
+        "requestBody": {
+          "required": false,
+          "description": "Provide an optional SIP status code. When omitted the API responds with\n`603 Decline`.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/RealtimeCallRejectRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Call rejected successfully."
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Reject call",
+          "group": "realtime-calls",
+          "returns": "Returns `200 OK` after OpenAI sends the SIP status code to the caller.",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/realtime/calls/$CALL_ID/reject \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"status_code\": 486}'"
+            }
+          }
+        }
+      }
+    },
+    "/realtime/client_secrets": {
+      "post": {
+        "summary": "Create a Realtime client secret with an associated session configuration.\n\nClient secrets are short-lived tokens that can be passed to a client app,\nsuch as a web frontend or mobile client, which grants access to the Realtime API without\nleaking your main API key. You can configure a custom TTL for each client secret.\n\nYou can also attach session configuration options to the client secret, which will be\napplied to any sessions created using that client secret, but these can also be overridden\nby the client connection.\n\n[Learn more about authentication with client secrets over WebRTC](https://developers.openai.com/api/docs/guides/realtime-webrtc).\n\nReturns the created client secret and the effective session object. The client secret is a string that looks like `ek_1234`.\n",
+        "operationId": "create-realtime-client-secret",
+        "tags": [
+          "Realtime"
+        ],
+        "requestBody": {
+          "description": "Create a client secret with the given session configuration.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/RealtimeCreateClientSecretRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Client secret created successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RealtimeCreateClientSecretResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create client secret",
+          "group": "realtime",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/realtime/client_secrets \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"expires_after\": {\n      \"anchor\": \"created_at\",\n      \"seconds\": 600\n    },\n    \"session\": {\n      \"type\": \"realtime\",\n      \"model\": \"gpt-realtime\",\n      \"instructions\": \"You are a friendly assistant.\"\n    }\n  }'\n"
+            },
+            "response": "{\n  \"value\": \"ek_68af296e8e408191a1120ab6383263c2\",\n  \"expires_at\": 1756310470,\n  \"session\": {\n    \"type\": \"realtime\",\n    \"object\": \"realtime.session\",\n    \"id\": \"sess_C9CiUVUzUzYIssh3ELY1d\",\n    \"model\": \"gpt-realtime\",\n    \"output_modalities\": [\n      \"audio\"\n    ],\n    \"instructions\": \"You are a friendly assistant.\",\n    \"tools\": [],\n    \"tool_choice\": \"auto\",\n    \"max_output_tokens\": \"inf\",\n    \"tracing\": null,\n    \"truncation\": \"auto\",\n    \"prompt\": null,\n    \"expires_at\": 0,\n    \"audio\": {\n      \"input\": {\n        \"format\": {\n          \"type\": \"audio/pcm\",\n          \"rate\": 24000\n        },\n        \"transcription\": null,\n        \"noise_reduction\": null,\n        \"turn_detection\": {\n          \"type\": \"server_vad\",\n        }\n      },\n      \"output\": {\n        \"format\": {\n          \"type\": \"audio/pcm\",\n          \"rate\": 24000\n        },\n        \"voice\": \"alloy\",\n        \"speed\": 1.0\n      }\n    },\n    \"include\": null\n  }\n}\n"
+          }
+        }
+      }
+    },
+    "/realtime/sessions": {
+      "post": {
+        "summary": "Create an ephemeral API token for use in client-side applications with the\nRealtime API. Can be configured with the same session parameters as the\n`session.update` client event.\n\nIt responds with a session object, plus a `client_secret` key which contains\na usable ephemeral API token that can be used to authenticate browser clients\nfor the Realtime API.\n\nReturns the created Realtime session object, plus an ephemeral key.\n",
+        "operationId": "create-realtime-session",
+        "tags": [
+          "Realtime"
+        ],
+        "requestBody": {
+          "description": "Create an ephemeral API key with the given session configuration.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/RealtimeSessionCreateRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Session created successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RealtimeSessionCreateResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create session",
+          "group": "realtime",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/realtime/sessions \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"model\": \"gpt-realtime\",\n    \"modalities\": [\"audio\", \"text\"],\n    \"instructions\": \"You are a friendly assistant.\"\n  }'\n"
+            },
+            "response": "{\n  \"id\": \"sess_001\",\n  \"object\": \"realtime.session\",\n  \"model\": \"gpt-realtime-2025-08-25\",\n  \"modalities\": [\"audio\", \"text\"],\n  \"instructions\": \"You are a friendly assistant.\",\n  \"voice\": \"alloy\",\n  \"input_audio_format\": \"pcm16\",\n  \"output_audio_format\": \"pcm16\",\n  \"input_audio_transcription\": {\n      \"model\": \"whisper-1\"\n  },\n  \"turn_detection\": null,\n  \"tools\": [],\n  \"tool_choice\": \"none\",\n  \"temperature\": 0.7,\n  \"max_response_output_tokens\": 200,\n  \"speed\": 1.1,\n  \"tracing\": \"auto\",\n  \"client_secret\": {\n    \"value\": \"ek_abc123\", \n    \"expires_at\": 1234567890\n  }\n}\n"
+          }
+        }
+      }
+    },
+    "/realtime/transcription_sessions": {
+      "post": {
+        "summary": "Create an ephemeral API token for use in client-side applications with the\nRealtime API specifically for realtime transcriptions. \nCan be configured with the same session parameters as the `transcription_session.update` client event.\n\nIt responds with a session object, plus a `client_secret` key which contains\na usable ephemeral API token that can be used to authenticate browser clients\nfor the Realtime API.\n\nReturns the created Realtime transcription session object, plus an ephemeral key.\n",
+        "operationId": "create-realtime-transcription-session",
+        "tags": [
+          "Realtime"
+        ],
+        "requestBody": {
+          "description": "Create an ephemeral API key with the given session configuration.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/RealtimeTranscriptionSessionCreateRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Session created successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RealtimeTranscriptionSessionCreateResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create transcription session",
+          "group": "realtime",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/realtime/transcription_sessions \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{}'\n"
+            },
+            "response": "{\n  \"id\": \"sess_BBwZc7cFV3XizEyKGDCGL\",\n  \"object\": \"realtime.transcription_session\",\n  \"modalities\": [\"audio\", \"text\"],\n  \"turn_detection\": {\n    \"type\": \"server_vad\",\n    \"threshold\": 0.5,\n    \"prefix_padding_ms\": 300,\n    \"silence_duration_ms\": 200\n  },\n  \"input_audio_format\": \"pcm16\",\n  \"input_audio_transcription\": {\n    \"model\": \"gpt-4o-transcribe\",\n    \"language\": null,\n    \"prompt\": \"\"\n  },\n  \"client_secret\": null\n}\n"
+          }
+        }
+      }
+    },
+    "/realtime/translations/client_secrets": {
+      "post": {
+        "summary": "Create a Realtime translation client secret with an associated translation session configuration.\n\nClient secrets are short-lived tokens that can be passed to a client app,\nsuch as a web frontend or mobile client, which grants access to the Realtime\nTranslation API without leaking your main API key. You can configure a custom\nTTL for each client secret.\n\nReturns the created client secret and the effective translation session object.\nThe client secret is a string that looks like `ek_1234`.\n",
+        "operationId": "create-realtime-translation-client-secret",
+        "tags": [
+          "Realtime"
+        ],
+        "requestBody": {
+          "description": "Create a client secret with the given translation session configuration.",
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/RealtimeTranslationClientSecretCreateRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Translation client secret created successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RealtimeTranslationClientSecretCreateResponse"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create translation client secret",
+          "group": "realtime",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/realtime/translations/client_secrets \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"expires_after\": {\n      \"anchor\": \"created_at\",\n      \"seconds\": 600\n    },\n    \"session\": {\n      \"model\": \"gpt-realtime-translate\",\n      \"audio\": {\n        \"input\": {\n          \"transcription\": {\n            \"model\": \"gpt-realtime-whisper\"\n          },\n          \"noise_reduction\": null\n        },\n        \"output\": {\n          \"language\": \"es\"\n        }\n      }\n    }\n  }'\n"
+            },
+            "response": "{\n  \"value\": \"ek_68af296e8e408191a1120ab6383263c2\",\n  \"expires_at\": 1756310470,\n  \"session\": {\n    \"id\": \"sess_C9CiUVUzUzYIssh3ELY1d\",\n    \"type\": \"translation\",\n    \"expires_at\": 1756310470,\n    \"model\": \"gpt-realtime-translate\",\n    \"audio\": {\n      \"input\": {\n        \"transcription\": {\n          \"model\": \"gpt-realtime-whisper\"\n        },\n        \"noise_reduction\": null\n      },\n      \"output\": {\n        \"language\": \"es\"\n      }\n    }\n  }\n}\n"
+          }
+        }
+      }
+    },
+    "/responses": {
+      "post": {
+        "operationId": "createResponse",
+        "tags": [
+          "Responses"
+        ],
+        "summary": "Creates a model response. Provide [text](https://developers.openai.com/api/docs/guides/text) or\n[image](https://developers.openai.com/api/docs/guides/images-vision) inputs to generate [text](https://developers.openai.com/api/docs/guides/text)\nor [JSON](https://developers.openai.com/api/docs/guides/structured-outputs) outputs. Have the model call\nyour own [custom code](https://developers.openai.com/api/docs/guides/function-calling) or use built-in\n[tools](https://developers.openai.com/api/docs/guides/tools) like [web search](https://developers.openai.com/api/docs/guides/tools-web-search)\nor [file search](https://developers.openai.com/api/docs/guides/tools-file-search) to use your own data\nas input for the model's response.\n",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateResponse"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Response"
+                }
+              },
+              "text/event-stream": {
+                "schema": {
+                  "$ref": "#/components/schemas/ResponseStreamEvent"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/InferenceRateLimited"
+          },
+          "503": {
+            "$ref": "#/components/responses/InferenceServiceUnavailable"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create a model response",
+          "group": "responses",
+          "path": "create",
+          "examples": [
+            {
+              "title": "Text input",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/responses \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-6-astra\",\n    \"input\": \"Tell me a three sentence bedtime story about a unicorn.\"\n  }'\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst response = await openai.responses.create({\n    model: \"gpt-6-astra\",\n    input: \"Tell me a three sentence bedtime story about a unicorn.\"\n});\n\nconsole.log(response);\n",
+                "python": "from openai import OpenAI\n\nclient = OpenAI()\n\nresponse = client.responses.create(\n  model=\"gpt-6-astra\",\n  input=\"Tell me a three sentence bedtime story about a unicorn.\"\n)\n\nprint(response)\n",
+                "csharp": "using System;\nusing OpenAI.Responses;\n\nOpenAIResponseClient client = new(\n    model: \"gpt-6-astra\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nOpenAIResponse response = client.CreateResponse(\"Tell me a three sentence bedtime story about a unicorn.\");\n\nConsole.WriteLine(response.GetOutputText());\n"
+              },
+              "response": "{\n  \"id\": \"resp_67ccd2bed1ec8190b14f964abc0542670bb6a6b452d3795b\",\n  \"object\": \"response\",\n  \"created_at\": 1741476542,\n  \"status\": \"completed\",\n  \"completed_at\": 1741476543,\n  \"error\": null,\n  \"incomplete_details\": null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"model\": \"gpt-6-astra\",\n  \"output\": [\n    {\n      \"type\": \"message\",\n      \"id\": \"msg_67ccd2bf17f0819081ff3bb2cf6508e60bb6a6b452d3795b\",\n      \"status\": \"completed\",\n      \"role\": \"assistant\",\n      \"content\": [\n        {\n          \"type\": \"output_text\",\n          \"text\": \"In a peaceful grove beneath a silver moon, a unicorn named Lumina discovered a hidden pool that reflected the stars. As she dipped her horn into the water, the pool began to shimmer, revealing a pathway to a magical realm of endless night skies. Filled with wonder, Lumina whispered a wish for all who dream to find their own hidden magic, and as she glanced back, her hoofprints sparkled like stardust.\",\n          \"annotations\": []\n        }\n      ]\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": null,\n  \"reasoning\": {\n    \"effort\": null,\n    \"summary\": null\n  },\n  \"store\": true,\n  \"temperature\": 1.0,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [],\n  \"top_p\": 1.0,\n  \"truncation\": \"disabled\",\n  \"usage\": {\n    \"input_tokens\": 36,\n    \"input_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"cache_write_tokens\": 0\n    },\n    \"output_tokens\": 87,\n    \"output_tokens_details\": {\n      \"reasoning_tokens\": 0\n    },\n    \"total_tokens\": 123\n  },\n  \"user\": null,\n  \"metadata\": {}\n}\n"
+            },
+            {
+              "title": "Image input",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/responses \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-6-astra\",\n    \"input\": [\n      {\n        \"role\": \"user\",\n        \"content\": [\n          {\"type\": \"input_text\", \"text\": \"what is in this image?\"},\n          {\n            \"type\": \"input_image\",\n            \"image_url\": \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\"\n          }\n        ]\n      }\n    ]\n  }'\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst response = await openai.responses.create({\n    model: \"gpt-6-astra\",\n    input: [\n        {\n            role: \"user\",\n            content: [\n                { type: \"input_text\", text: \"what is in this image?\" },\n                {\n                    type: \"input_image\",\n                    image_url:\n                        \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\",\n                },\n            ],\n        },\n    ],\n});\n\nconsole.log(response);\n",
+                "python": "from openai import OpenAI\n\nclient = OpenAI()\n\nresponse = client.responses.create(\n    model=\"gpt-6-astra\",\n    input=[\n        {\n            \"role\": \"user\",\n            \"content\": [\n                { \"type\": \"input_text\", \"text\": \"what is in this image?\" },\n                {\n                    \"type\": \"input_image\",\n                    \"image_url\": \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\"\n                }\n            ]\n        }\n    ]\n)\n\nprint(response)\n",
+                "csharp": "using System;\nusing System.Collections.Generic;\n\nusing OpenAI.Responses;\n\nOpenAIResponseClient client = new(\n    model: \"gpt-6-astra\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nList<ResponseItem> inputItems =\n[\n    ResponseItem.CreateUserMessageItem(\n        [\n            ResponseContentPart.CreateInputTextPart(\"What is in this image?\"),\n            ResponseContentPart.CreateInputImagePart(new Uri(\"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\"))\n        ]\n    )\n];\n\nOpenAIResponse response = client.CreateResponse(inputItems);\n\nConsole.WriteLine(response.GetOutputText());\n"
+              },
+              "response": "{\n  \"id\": \"resp_67ccd3a9da748190baa7f1570fe91ac604becb25c45c1d41\",\n  \"object\": \"response\",\n  \"created_at\": 1741476777,\n  \"status\": \"completed\",\n  \"completed_at\": 1741476778,\n  \"error\": null,\n  \"incomplete_details\": null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"model\": \"gpt-6-astra\",\n  \"output\": [\n    {\n      \"type\": \"message\",\n      \"id\": \"msg_67ccd3acc8d48190a77525dc6de64b4104becb25c45c1d41\",\n      \"status\": \"completed\",\n      \"role\": \"assistant\",\n      \"content\": [\n        {\n          \"type\": \"output_text\",\n          \"text\": \"The image depicts a scenic landscape with a wooden boardwalk or pathway leading through lush, green grass under a blue sky with some clouds. The setting suggests a peaceful natural area, possibly a park or nature reserve. There are trees and shrubs in the background.\",\n          \"annotations\": []\n        }\n      ]\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": null,\n  \"reasoning\": {\n    \"effort\": null,\n    \"summary\": null\n  },\n  \"store\": true,\n  \"temperature\": 1.0,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [],\n  \"top_p\": 1.0,\n  \"truncation\": \"disabled\",\n  \"usage\": {\n    \"input_tokens\": 328,\n    \"input_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"cache_write_tokens\": 0\n    },\n    \"output_tokens\": 52,\n    \"output_tokens_details\": {\n      \"reasoning_tokens\": 0\n    },\n    \"total_tokens\": 380\n  },\n  \"user\": null,\n  \"metadata\": {}\n}\n"
+            },
+            {
+              "title": "File input",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/responses \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-6-astra\",\n    \"input\": [\n      {\n        \"role\": \"user\",\n        \"content\": [\n          {\"type\": \"input_text\", \"text\": \"what is in this file?\"},\n          {\n            \"type\": \"input_file\",\n            \"file_url\": \"https://www.berkshirehathaway.com/letters/2024ltr.pdf\",\n            \"detail\": \"auto\"\n          }\n        ]\n      }\n    ]\n  }'\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst response = await openai.responses.create({\n    model: \"gpt-6-astra\",\n    input: [\n        {\n            role: \"user\",\n            content: [\n                { type: \"input_text\", text: \"what is in this file?\" },\n                {\n                    type: \"input_file\",\n                    file_url: \"https://www.berkshirehathaway.com/letters/2024ltr.pdf\",\n                    detail: \"auto\",\n                },\n            ],\n        },\n    ],\n});\n\nconsole.log(response);\n",
+                "python": "from openai import OpenAI\n\nclient = OpenAI()\n\nresponse = client.responses.create(\n    model=\"gpt-6-astra\",\n    input=[\n        {\n            \"role\": \"user\",\n            \"content\": [\n                { \"type\": \"input_text\", \"text\": \"what is in this file?\" },\n                {\n                    \"type\": \"input_file\",\n                    \"file_url\": \"https://www.berkshirehathaway.com/letters/2024ltr.pdf\",\n                    \"detail\": \"auto\"\n                }\n            ]\n        }\n    ]\n)\n\nprint(response)\n"
+              },
+              "response": "{\n  \"id\": \"resp_686eef60237881a2bd1180bb8b13de430e34c516d176ff86\",\n  \"object\": \"response\",\n  \"created_at\": 1752100704,\n  \"status\": \"completed\",\n  \"completed_at\": 1752100705,\n  \"background\": false,\n  \"error\": null,\n  \"incomplete_details\": null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"max_tool_calls\": null,\n  \"model\": \"gpt-6-astra\",\n  \"output\": [\n    {\n      \"id\": \"msg_686eef60d3e081a29283bdcbc4322fd90e34c516d176ff86\",\n      \"type\": \"message\",\n      \"status\": \"completed\",\n      \"content\": [\n        {\n          \"type\": \"output_text\",\n          \"annotations\": [],\n          \"logprobs\": [],\n          \"text\": \"The file seems to contain excerpts from a letter to the shareholders of Berkshire Hathaway Inc., likely written by Warren Buffett. It covers several topics:\\n\\n1. **Communication Philosophy**: Buffett emphasizes the importance of transparency and candidness in reporting mistakes and successes to shareholders.\\n\\n2. **Mistakes and Learnings**: The letter acknowledges past mistakes in business assessments and management hires, highlighting the importance of correcting errors promptly.\\n\\n3. **CEO Succession**: Mention of Greg Abel stepping in as the new CEO and continuing the tradition of honest communication.\\n\\n4. **Pete Liegl Story**: A detailed account of acquiring Forest River and the relationship with its founder, highlighting trust and effective business decisions.\\n\\n5. **2024 Performance**: Overview of business performance, particularly in insurance and investment activities, with a focus on GEICO's improvement.\\n\\n6. **Tax Contributions**: Discussion of significant tax payments to the U.S. Treasury, credited to shareholders' reinvestments.\\n\\n7. **Investment Strategy**: A breakdown of Berkshire\\u2019s investments in both controlled subsidiaries and marketable equities, along with a focus on long-term holding strategies.\\n\\n8. **American Capitalism**: Reflections on America\\u2019s economic development and Berkshire\\u2019s role within it.\\n\\n9. **Property-Casualty Insurance**: Insights into the P/C insurance business model and its challenges and benefits.\\n\\n10. **Japanese Investments**: Information about Berkshire\\u2019s investments in Japanese companies and future plans.\\n\\n11. **Annual Meeting**: Details about the upcoming annual gathering in Omaha, including schedule changes and new book releases.\\n\\n12. **Personal Anecdotes**: Light-hearted stories about family and interactions, conveying Buffett's personable approach.\\n\\n13. **Financial Performance Data**: Tables comparing Berkshire\\u2019s annual performance to the S&P 500, showing impressive long-term gains.\\n\\nOverall, the letter reinforces Berkshire Hathaway's commitment to transparency, investment in both its businesses and the wider economy, and emphasizes strong leadership and prudent financial management.\"\n        }\n      ],\n      \"role\": \"assistant\"\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": null,\n  \"reasoning\": {\n    \"effort\": null,\n    \"summary\": null\n  },\n  \"service_tier\": \"default\",\n  \"store\": true,\n  \"temperature\": 1.0,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [],\n  \"top_logprobs\": 0,\n  \"top_p\": 1.0,\n  \"truncation\": \"disabled\",\n  \"usage\": {\n    \"input_tokens\": 8438,\n    \"input_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"cache_write_tokens\": 0\n    },\n    \"output_tokens\": 398,\n    \"output_tokens_details\": {\n      \"reasoning_tokens\": 0\n    },\n    \"total_tokens\": 8836\n  },\n  \"user\": null,\n  \"metadata\": {}\n}\n"
+            },
+            {
+              "title": "Web search",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/responses \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-6-astra\",\n    \"tools\": [{ \"type\": \"web_search_preview\" }],\n    \"input\": \"What was a positive news story from today?\"\n  }'\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst response = await openai.responses.create({\n    model: \"gpt-6-astra\",\n    tools: [{ type: \"web_search_preview\" }],\n    input: \"What was a positive news story from today?\",\n});\n\nconsole.log(response);\n",
+                "python": "from openai import OpenAI\n\nclient = OpenAI()\n\nresponse = client.responses.create(\n    model=\"gpt-6-astra\",\n    tools=[{ \"type\": \"web_search_preview\" }],\n    input=\"What was a positive news story from today?\",\n)\n\nprint(response)\n",
+                "csharp": "using System;\n\nusing OpenAI.Responses;\n\nOpenAIResponseClient client = new(\n    model: \"gpt-6-astra\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nstring userInputText = \"What was a positive news story from today?\";\n\nResponseCreationOptions options = new()\n{\n    Tools =\n    {\n        ResponseTool.CreateWebSearchTool()\n    },\n};\n\nOpenAIResponse response = client.CreateResponse(userInputText, options);\n\nConsole.WriteLine(response.GetOutputText());\n"
+              },
+              "response": "{\n  \"id\": \"resp_67ccf18ef5fc8190b16dbee19bc54e5f087bb177ab789d5c\",\n  \"object\": \"response\",\n  \"created_at\": 1741484430,\n  \"status\": \"completed\",\n  \"completed_at\": 1741484431,\n  \"error\": null,\n  \"incomplete_details\": null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"model\": \"gpt-6-astra\",\n  \"output\": [\n    {\n      \"type\": \"web_search_call\",\n      \"id\": \"ws_67ccf18f64008190a39b619f4c8455ef087bb177ab789d5c\",\n      \"status\": \"completed\"\n    },\n    {\n      \"type\": \"message\",\n      \"id\": \"msg_67ccf190ca3881909d433c50b1f6357e087bb177ab789d5c\",\n      \"status\": \"completed\",\n      \"role\": \"assistant\",\n      \"content\": [\n        {\n          \"type\": \"output_text\",\n          \"text\": \"As of today, March 9, 2025, one notable positive news story...\",\n          \"annotations\": [\n            {\n              \"type\": \"url_citation\",\n              \"start_index\": 442,\n              \"end_index\": 557,\n              \"url\": \"https://.../?utm_source=chatgpt.com\",\n              \"title\": \"...\"\n            },\n            {\n              \"type\": \"url_citation\",\n              \"start_index\": 962,\n              \"end_index\": 1077,\n              \"url\": \"https://.../?utm_source=chatgpt.com\",\n              \"title\": \"...\"\n            },\n            {\n              \"type\": \"url_citation\",\n              \"start_index\": 1336,\n              \"end_index\": 1451,\n              \"url\": \"https://.../?utm_source=chatgpt.com\",\n              \"title\": \"...\"\n            }\n          ]\n        }\n      ]\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": null,\n  \"reasoning\": {\n    \"effort\": null,\n    \"summary\": null\n  },\n  \"store\": true,\n  \"temperature\": 1.0,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [\n    {\n      \"type\": \"web_search_preview\",\n      \"domains\": [],\n      \"search_context_size\": \"medium\",\n      \"user_location\": {\n        \"type\": \"approximate\",\n        \"city\": null,\n        \"country\": \"US\",\n        \"region\": null,\n        \"timezone\": null\n      }\n    }\n  ],\n  \"top_p\": 1.0,\n  \"truncation\": \"disabled\",\n  \"usage\": {\n    \"input_tokens\": 328,\n    \"input_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"cache_write_tokens\": 0\n    },\n    \"output_tokens\": 356,\n    \"output_tokens_details\": {\n      \"reasoning_tokens\": 0\n    },\n    \"total_tokens\": 684\n  },\n  \"user\": null,\n  \"metadata\": {}\n}\n"
+            },
+            {
+              "title": "File search",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/responses \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-6-astra\",\n    \"tools\": [{\n      \"type\": \"file_search\",\n      \"vector_store_ids\": [\"vs_1234567890\"],\n      \"max_num_results\": 20\n    }],\n    \"input\": \"What are the attributes of an ancient brown dragon?\"\n  }'\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst response = await openai.responses.create({\n    model: \"gpt-6-astra\",\n    tools: [{\n      type: \"file_search\",\n      vector_store_ids: [\"vs_1234567890\"],\n      max_num_results: 20\n    }],\n    input: \"What are the attributes of an ancient brown dragon?\",\n});\n\nconsole.log(response);\n",
+                "python": "from openai import OpenAI\n\nclient = OpenAI()\n\nresponse = client.responses.create(\n    model=\"gpt-6-astra\",\n    tools=[{\n      \"type\": \"file_search\",\n      \"vector_store_ids\": [\"vs_1234567890\"],\n      \"max_num_results\": 20\n    }],\n    input=\"What are the attributes of an ancient brown dragon?\",\n)\n\nprint(response)\n",
+                "csharp": "using System;\n\nusing OpenAI.Responses;\n\nOpenAIResponseClient client = new(\n    model: \"gpt-6-astra\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nstring userInputText = \"What are the attributes of an ancient brown dragon?\";\n\nResponseCreationOptions options = new()\n{\n    Tools =\n    {\n        ResponseTool.CreateFileSearchTool(\n            vectorStoreIds: [\"vs_1234567890\"],\n            maxResultCount: 20\n        )\n    },\n};\n\nOpenAIResponse response = client.CreateResponse(userInputText, options);\n\nConsole.WriteLine(response.GetOutputText());\n"
+              },
+              "response": "{\n  \"id\": \"resp_67ccf4c55fc48190b71bd0463ad3306d09504fb6872380d7\",\n  \"object\": \"response\",\n  \"created_at\": 1741485253,\n  \"status\": \"completed\",\n  \"completed_at\": 1741485254,\n  \"error\": null,\n  \"incomplete_details\": null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"model\": \"gpt-6-astra\",\n  \"output\": [\n    {\n      \"type\": \"file_search_call\",\n      \"id\": \"fs_67ccf4c63cd08190887ef6464ba5681609504fb6872380d7\",\n      \"status\": \"completed\",\n      \"queries\": [\n        \"attributes of an ancient brown dragon\"\n      ],\n      \"results\": null\n    },\n    {\n      \"type\": \"message\",\n      \"id\": \"msg_67ccf4c93e5c81909d595b369351a9d309504fb6872380d7\",\n      \"status\": \"completed\",\n      \"role\": \"assistant\",\n      \"content\": [\n        {\n          \"type\": \"output_text\",\n          \"text\": \"The attributes of an ancient brown dragon include...\",\n          \"annotations\": [\n            {\n              \"type\": \"file_citation\",\n              \"index\": 320,\n              \"file_id\": \"file-4wDz5b167pAf72nx1h9eiN\",\n              \"filename\": \"dragons.pdf\"\n            },\n            {\n              \"type\": \"file_citation\",\n              \"index\": 576,\n              \"file_id\": \"file-4wDz5b167pAf72nx1h9eiN\",\n              \"filename\": \"dragons.pdf\"\n            },\n            {\n              \"type\": \"file_citation\",\n              \"index\": 815,\n              \"file_id\": \"file-4wDz5b167pAf72nx1h9eiN\",\n              \"filename\": \"dragons.pdf\"\n            },\n            {\n              \"type\": \"file_citation\",\n              \"index\": 815,\n              \"file_id\": \"file-4wDz5b167pAf72nx1h9eiN\",\n              \"filename\": \"dragons.pdf\"\n            },\n            {\n              \"type\": \"file_citation\",\n              \"index\": 1030,\n              \"file_id\": \"file-4wDz5b167pAf72nx1h9eiN\",\n              \"filename\": \"dragons.pdf\"\n            },\n            {\n              \"type\": \"file_citation\",\n              \"index\": 1030,\n              \"file_id\": \"file-4wDz5b167pAf72nx1h9eiN\",\n              \"filename\": \"dragons.pdf\"\n            },\n            {\n              \"type\": \"file_citation\",\n              \"index\": 1156,\n              \"file_id\": \"file-4wDz5b167pAf72nx1h9eiN\",\n              \"filename\": \"dragons.pdf\"\n            },\n            {\n              \"type\": \"file_citation\",\n              \"index\": 1225,\n              \"file_id\": \"file-4wDz5b167pAf72nx1h9eiN\",\n              \"filename\": \"dragons.pdf\"\n            }\n          ]\n        }\n      ]\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": null,\n  \"reasoning\": {\n    \"effort\": null,\n    \"summary\": null\n  },\n  \"store\": true,\n  \"temperature\": 1.0,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [\n    {\n      \"type\": \"file_search\",\n      \"filters\": null,\n      \"max_num_results\": 20,\n      \"ranking_options\": {\n        \"ranker\": \"auto\",\n        \"score_threshold\": 0.0\n      },\n      \"vector_store_ids\": [\n        \"vs_1234567890\"\n      ]\n    }\n  ],\n  \"top_p\": 1.0,\n  \"truncation\": \"disabled\",\n  \"usage\": {\n    \"input_tokens\": 18307,\n    \"input_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"cache_write_tokens\": 0\n    },\n    \"output_tokens\": 348,\n    \"output_tokens_details\": {\n      \"reasoning_tokens\": 0\n    },\n    \"total_tokens\": 18655\n  },\n  \"user\": null,\n  \"metadata\": {}\n}\n"
+            },
+            {
+              "title": "Streaming",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/responses \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-6-astra\",\n    \"instructions\": \"You are a helpful assistant.\",\n    \"input\": \"Hello!\",\n    \"stream\": true\n  }'\n",
+                "python": "from openai import OpenAI\n\nclient = OpenAI()\n\nresponse = client.responses.create(\n  model=\"gpt-6-astra\",\n  instructions=\"You are a helpful assistant.\",\n  input=\"Hello!\",\n  stream=True\n)\n\nfor event in response:\n  print(event)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst response = await openai.responses.create({\n    model: \"gpt-6-astra\",\n    instructions: \"You are a helpful assistant.\",\n    input: \"Hello!\",\n    stream: true,\n});\n\nfor await (const event of response) {\n    console.log(event);\n}\n",
+                "csharp": "using System;\nusing System.ClientModel;\nusing System.Threading.Tasks;\n\nusing OpenAI.Responses;\n\nOpenAIResponseClient client = new(\n    model: \"gpt-6-astra\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nstring userInputText = \"Hello!\";\n\nResponseCreationOptions options = new()\n{\n    Instructions = \"You are a helpful assistant.\",\n};\n\nAsyncCollectionResult<StreamingResponseUpdate> responseUpdates = client.CreateResponseStreamingAsync(userInputText, options);\n\nawait foreach (StreamingResponseUpdate responseUpdate in responseUpdates)\n{\n    if (responseUpdate is StreamingResponseOutputTextDeltaUpdate outputTextDeltaUpdate)\n    {\n        Console.Write(outputTextDeltaUpdate.Delta);\n    }\n}\n"
+              },
+              "response": "event: response.created\ndata: {\"type\":\"response.created\",\"response\":{\"id\":\"resp_67c9fdcecf488190bdd9a0409de3a1ec07b8b0ad4e5eb654\",\"object\":\"response\",\"created_at\":1741290958,\"status\":\"in_progress\",\"error\":null,\"incomplete_details\":null,\"instructions\":\"You are a helpful assistant.\",\"max_output_tokens\":null,\"model\":\"gpt-6-astra\",\"output\":[],\"parallel_tool_calls\":true,\"previous_response_id\":null,\"reasoning\":{\"effort\":null,\"summary\":null},\"store\":true,\"temperature\":1.0,\"text\":{\"format\":{\"type\":\"text\"}},\"tool_choice\":\"auto\",\"tools\":[],\"top_p\":1.0,\"truncation\":\"disabled\",\"usage\":null,\"user\":null,\"metadata\":{}}}\n\nevent: response.in_progress\ndata: {\"type\":\"response.in_progress\",\"response\":{\"id\":\"resp_67c9fdcecf488190bdd9a0409de3a1ec07b8b0ad4e5eb654\",\"object\":\"response\",\"created_at\":1741290958,\"status\":\"in_progress\",\"error\":null,\"incomplete_details\":null,\"instructions\":\"You are a helpful assistant.\",\"max_output_tokens\":null,\"model\":\"gpt-6-astra\",\"output\":[],\"parallel_tool_calls\":true,\"previous_response_id\":null,\"reasoning\":{\"effort\":null,\"summary\":null},\"store\":true,\"temperature\":1.0,\"text\":{\"format\":{\"type\":\"text\"}},\"tool_choice\":\"auto\",\"tools\":[],\"top_p\":1.0,\"truncation\":\"disabled\",\"usage\":null,\"user\":null,\"metadata\":{}}}\n\nevent: response.output_item.added\ndata: {\"type\":\"response.output_item.added\",\"output_index\":0,\"item\":{\"id\":\"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654\",\"type\":\"message\",\"status\":\"in_progress\",\"role\":\"assistant\",\"content\":[]}}\n\nevent: response.content_part.added\ndata: {\"type\":\"response.content_part.added\",\"item_id\":\"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654\",\"output_index\":0,\"content_index\":0,\"part\":{\"type\":\"output_text\",\"text\":\"\",\"annotations\":[]}}\n\nevent: response.output_text.delta\ndata: {\"type\":\"response.output_text.delta\",\"item_id\":\"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654\",\"output_index\":0,\"content_index\":0,\"delta\":\"Hi\"}\n\n...\n\nevent: response.output_text.done\ndata: {\"type\":\"response.output_text.done\",\"item_id\":\"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654\",\"output_index\":0,\"content_index\":0,\"text\":\"Hi there! How can I assist you today?\"}\n\nevent: response.content_part.done\ndata: {\"type\":\"response.content_part.done\",\"item_id\":\"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654\",\"output_index\":0,\"content_index\":0,\"part\":{\"type\":\"output_text\",\"text\":\"Hi there! How can I assist you today?\",\"annotations\":[]}}\n\nevent: response.output_item.done\ndata: {\"type\":\"response.output_item.done\",\"output_index\":0,\"item\":{\"id\":\"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654\",\"type\":\"message\",\"status\":\"completed\",\"role\":\"assistant\",\"content\":[{\"type\":\"output_text\",\"text\":\"Hi there! How can I assist you today?\",\"annotations\":[]}]}}\n\nevent: response.completed\ndata: {\"type\":\"response.completed\",\"response\":{\"id\":\"resp_67c9fdcecf488190bdd9a0409de3a1ec07b8b0ad4e5eb654\",\"object\":\"response\",\"created_at\":1741290958,\"status\":\"completed\",\"error\":null,\"incomplete_details\":null,\"instructions\":\"You are a helpful assistant.\",\"max_output_tokens\":null,\"model\":\"gpt-6-astra\",\"output\":[{\"id\":\"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654\",\"type\":\"message\",\"status\":\"completed\",\"role\":\"assistant\",\"content\":[{\"type\":\"output_text\",\"text\":\"Hi there! How can I assist you today?\",\"annotations\":[]}]}],\"parallel_tool_calls\":true,\"previous_response_id\":null,\"reasoning\":{\"effort\":null,\"summary\":null},\"store\":true,\"temperature\":1.0,\"text\":{\"format\":{\"type\":\"text\"}},\"tool_choice\":\"auto\",\"tools\":[],\"top_p\":1.0,\"truncation\":\"disabled\",\"usage\":{\"input_tokens\":37,\"output_tokens\":11,\"output_tokens_details\":{\"reasoning_tokens\":0},\"total_tokens\":48},\"user\":null,\"metadata\":{}}}\n"
+            },
+            {
+              "title": "Functions",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/responses \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-6-astra\",\n    \"input\": \"What is the weather like in Boston today?\",\n    \"tools\": [\n      {\n        \"type\": \"function\",\n        \"name\": \"get_current_weather\",\n        \"description\": \"Get the current weather in a given location\",\n        \"parameters\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"location\": {\n              \"type\": \"string\",\n              \"description\": \"The city and state, e.g. San Francisco, CA\"\n            },\n            \"unit\": {\n              \"type\": \"string\",\n              \"enum\": [\"celsius\", \"fahrenheit\"]\n            }\n          },\n          \"required\": [\"location\", \"unit\"]\n        }\n      }\n    ],\n    \"tool_choice\": \"auto\"\n  }'\n",
+                "python": "from openai import OpenAI\n\nclient = OpenAI()\n\ntools = [\n    {\n        \"type\": \"function\",\n        \"name\": \"get_current_weather\",\n        \"description\": \"Get the current weather in a given location\",\n        \"parameters\": {\n          \"type\": \"object\",\n          \"properties\": {\n              \"location\": {\n                  \"type\": \"string\",\n                  \"description\": \"The city and state, e.g. San Francisco, CA\",\n              },\n              \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]},\n          },\n          \"required\": [\"location\", \"unit\"],\n        }\n    }\n]\n\nresponse = client.responses.create(\n  model=\"gpt-6-astra\",\n  tools=tools,\n  input=\"What is the weather like in Boston today?\",\n  tool_choice=\"auto\"\n)\n\nprint(response)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst tools = [\n    {\n        type: \"function\",\n        name: \"get_current_weather\",\n        description: \"Get the current weather in a given location\",\n        parameters: {\n            type: \"object\",\n            properties: {\n                location: {\n                    type: \"string\",\n                    description: \"The city and state, e.g. San Francisco, CA\",\n                },\n                unit: { type: \"string\", enum: [\"celsius\", \"fahrenheit\"] },\n            },\n            required: [\"location\", \"unit\"],\n        },\n    },\n];\n\nconst response = await openai.responses.create({\n    model: \"gpt-6-astra\",\n    tools: tools,\n    input: \"What is the weather like in Boston today?\",\n    tool_choice: \"auto\",\n});\n\nconsole.log(response);\n",
+                "csharp": "using System;\nusing OpenAI.Responses;\n\nOpenAIResponseClient client = new(\n    model: \"gpt-6-astra\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nResponseTool getCurrentWeatherFunctionTool = ResponseTool.CreateFunctionTool(\n    functionName: \"get_current_weather\",\n    functionDescription: \"Get the current weather in a given location\",\n    functionParameters: BinaryData.FromString(\"\"\"\n        {\n            \"type\": \"object\",\n            \"properties\": {\n                \"location\": {\n                    \"type\": \"string\",\n                    \"description\": \"The city and state, e.g. San Francisco, CA\"\n                },\n                \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]}\n            },\n            \"required\": [\"location\", \"unit\"]\n        }\n        \"\"\"\n    )\n);\n\nstring userInputText = \"What is the weather like in Boston today?\";\n\nResponseCreationOptions options = new()\n{\n    Tools =\n    {\n        getCurrentWeatherFunctionTool\n    },\n    ToolChoice = ResponseToolChoice.CreateAutoChoice(),\n};\n\nOpenAIResponse response = client.CreateResponse(userInputText, options);\n"
+              },
+              "response": "{\n  \"id\": \"resp_67ca09c5efe0819096d0511c92b8c890096610f474011cc0\",\n  \"object\": \"response\",\n  \"created_at\": 1741294021,\n  \"status\": \"completed\",\n  \"completed_at\": 1741294022,\n  \"error\": null,\n  \"incomplete_details\": null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"model\": \"gpt-6-astra\",\n  \"output\": [\n    {\n      \"type\": \"function_call\",\n      \"id\": \"fc_67ca09c6bedc8190a7abfec07b1a1332096610f474011cc0\",\n      \"call_id\": \"call_unLAR8MvFNptuiZK6K6HCy5k\",\n      \"name\": \"get_current_weather\",\n      \"arguments\": \"{\\\"location\\\":\\\"Boston, MA\\\",\\\"unit\\\":\\\"celsius\\\"}\",\n      \"status\": \"completed\"\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": null,\n  \"reasoning\": {\n    \"effort\": null,\n    \"summary\": null\n  },\n  \"store\": true,\n  \"temperature\": 1.0,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"description\": \"Get the current weather in a given location\",\n      \"name\": \"get_current_weather\",\n      \"parameters\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"location\": {\n            \"type\": \"string\",\n            \"description\": \"The city and state, e.g. San Francisco, CA\"\n          },\n          \"unit\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"celsius\",\n              \"fahrenheit\"\n            ]\n          }\n        },\n        \"required\": [\n          \"location\",\n          \"unit\"\n        ]\n      },\n      \"strict\": true\n    }\n  ],\n  \"top_p\": 1.0,\n  \"truncation\": \"disabled\",\n  \"usage\": {\n    \"input_tokens\": 291,\n    \"output_tokens\": 23,\n    \"output_tokens_details\": {\n      \"reasoning_tokens\": 0\n    },\n    \"total_tokens\": 314\n  },\n  \"user\": null,\n  \"metadata\": {}\n}\n"
+            },
+            {
+              "title": "Reasoning",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/responses \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-6-astra\",\n    \"input\": \"How much wood would a woodchuck chuck?\",\n    \"reasoning\": {\n      \"effort\": \"high\"\n    }\n  }'\n",
+                "javascript": "import OpenAI from \"openai\";\nconst openai = new OpenAI();\n\nconst response = await openai.responses.create({\n    model: \"gpt-6-astra\",\n    input: \"How much wood would a woodchuck chuck?\",\n    reasoning: {\n      effort: \"high\"\n    }\n});\n\nconsole.log(response);\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\nresponse = client.responses.create(\n    model=\"gpt-6-astra\",\n    input=\"How much wood would a woodchuck chuck?\",\n    reasoning={\n        \"effort\": \"high\"\n    }\n)\n\nprint(response)\n",
+                "csharp": "using System;\nusing OpenAI.Responses;\n\nOpenAIResponseClient client = new(\n    model: \"gpt-6-astra\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nstring userInputText = \"How much wood would a woodchuck chuck?\";\n\nResponseCreationOptions options = new()\n{\n    ReasoningOptions = new()\n    {\n        ReasoningEffortLevel = ResponseReasoningEffortLevel.High,\n    },\n};\n\nOpenAIResponse response = client.CreateResponse(userInputText, options);\n\nConsole.WriteLine(response.GetOutputText());\n"
+              },
+              "response": "{\n  \"id\": \"resp_67ccd7eca01881908ff0b5146584e408072912b2993db808\",\n  \"object\": \"response\",\n  \"created_at\": 1741477868,\n  \"status\": \"completed\",\n  \"completed_at\": 1741477869,\n  \"error\": null,\n  \"incomplete_details\": null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"model\": \"gpt-6-astra\",\n  \"output\": [\n    {\n      \"type\": \"message\",\n      \"id\": \"msg_67ccd7f7b5848190a6f3e95d809f6b44072912b2993db808\",\n      \"status\": \"completed\",\n      \"role\": \"assistant\",\n      \"content\": [\n        {\n          \"type\": \"output_text\",\n          \"text\": \"The classic tongue twister...\",\n          \"annotations\": []\n        }\n      ]\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": null,\n  \"reasoning\": {\n    \"effort\": \"high\",\n    \"summary\": null\n  },\n  \"store\": true,\n  \"temperature\": 1.0,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [],\n  \"top_p\": 1.0,\n  \"truncation\": \"disabled\",\n  \"usage\": {\n    \"input_tokens\": 81,\n    \"input_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"cache_write_tokens\": 0\n    },\n    \"output_tokens\": 1035,\n    \"output_tokens_details\": {\n      \"reasoning_tokens\": 832\n    },\n    \"total_tokens\": 1116\n  },\n  \"user\": null,\n  \"metadata\": {}\n}\n"
+            }
+          ]
+        }
+      }
+    },
+    "/responses/{response_id}": {
+      "get": {
+        "operationId": "getResponse",
+        "tags": [
+          "Responses"
+        ],
+        "summary": "Retrieves a model response with the given ID.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "response_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "resp_677efb5139a88190b512bc3fef8e535d"
+            },
+            "description": "The ID of the response to retrieve."
+          },
+          {
+            "in": "query",
+            "name": "include",
+            "schema": {
+              "type": "array",
+              "items": {
+                "$ref": "#/components/schemas/IncludeEnum"
+              }
+            },
+            "description": "Additional fields to include in the response. See the `include`\nparameter for Response creation above for more information.\n"
+          },
+          {
+            "in": "query",
+            "name": "stream",
+            "schema": {
+              "type": "boolean"
+            },
+            "description": "If set to true, the model response data will be streamed to the client\nas it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).\nSee the [Streaming section below](https://developers.openai.com/api/reference/resources/responses/streaming-events)\nfor more information.\n"
+          },
+          {
+            "in": "query",
+            "name": "starting_after",
+            "schema": {
+              "type": "integer"
+            },
+            "description": "The sequence number of the event after which to start streaming.\n"
+          },
+          {
+            "in": "query",
+            "name": "include_obfuscation",
+            "schema": {
+              "type": "boolean"
+            },
+            "description": "When true, stream obfuscation will be enabled. Stream obfuscation adds\nrandom characters to an `obfuscation` field on streaming delta events\nto normalize payload sizes as a mitigation to certain side-channel\nattacks. These obfuscation fields are included by default, but add a\nsmall amount of overhead to the data stream. You can set\n`include_obfuscation` to false to optimize for bandwidth if you trust\nthe network links between your application and the OpenAI API.\n"
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Response"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Get a model response",
+          "group": "responses",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/responses/resp_123 \\\n    -H \"Content-Type: application/json\" \\\n    -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "javascript": "import OpenAI from \"openai\";\nconst client = new OpenAI();\n\nconst response = await client.responses.retrieve(\"resp_123\");\nconsole.log(response);\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nresponse = client.responses.retrieve(\"resp_123\")\nprint(response)\n"
+            },
+            "response": "{\n  \"id\": \"resp_67cb71b351908190a308f3859487620d06981a8637e6bc44\",\n  \"object\": \"response\",\n  \"created_at\": 1741386163,\n  \"status\": \"completed\",\n  \"completed_at\": 1741386164,\n  \"error\": null,\n  \"incomplete_details\": null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"model\": \"gpt-6-astra\",\n  \"output\": [\n    {\n      \"type\": \"message\",\n      \"id\": \"msg_67cb71b3c2b0819084d481baaaf148f206981a8637e6bc44\",\n      \"status\": \"completed\",\n      \"role\": \"assistant\",\n      \"content\": [\n        {\n          \"type\": \"output_text\",\n          \"text\": \"Silent circuits hum,  \\nThoughts emerge in data streams—  \\nDigital dawn breaks.\",\n          \"annotations\": []\n        }\n      ]\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": null,\n  \"reasoning\": {\n    \"effort\": null,\n    \"summary\": null\n  },\n  \"store\": true,\n  \"temperature\": 1.0,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [],\n  \"top_p\": 1.0,\n  \"truncation\": \"disabled\",\n  \"usage\": {\n    \"input_tokens\": 32,\n    \"input_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"cache_write_tokens\": 0\n    },\n    \"output_tokens\": 18,\n    \"output_tokens_details\": {\n      \"reasoning_tokens\": 0\n    },\n    \"total_tokens\": 50\n  },\n  \"user\": null,\n  \"metadata\": {}\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "operationId": "deleteResponse",
+        "tags": [
+          "Responses"
+        ],
+        "summary": "Deletes a model response with the given ID.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "response_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "resp_677efb5139a88190b512bc3fef8e535d"
+            },
+            "description": "The ID of the response to delete."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK"
+          },
+          "404": {
+            "description": "Not Found",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Error"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete a model response",
+          "group": "responses",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/responses/resp_123 \\\n    -H \"Content-Type: application/json\" \\\n    -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "javascript": "import OpenAI from \"openai\";\nconst client = new OpenAI();\n\nconst response = await client.responses.delete(\"resp_123\");\nconsole.log(response);\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nresponse = client.responses.delete(\"resp_123\")\nprint(response)\n"
+            },
+            "response": "{\n  \"id\": \"resp_6786a1bec27481909a17d673315b29f6\",\n  \"object\": \"response\",\n  \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/responses/{response_id}/cancel": {
+      "post": {
+        "operationId": "cancelResponse",
+        "tags": [
+          "Responses"
+        ],
+        "summary": "Cancels a model response with the given ID. Only responses created with\nthe `background` parameter set to `true` can be cancelled.\n[Learn more](https://developers.openai.com/api/docs/guides/background).\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "response_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "resp_677efb5139a88190b512bc3fef8e535d"
+            },
+            "description": "The ID of the response to cancel."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Response"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "Not Found",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Error"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Cancel a response",
+          "group": "responses",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/responses/resp_123/cancel \\\n    -H \"Content-Type: application/json\" \\\n    -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "javascript": "import OpenAI from \"openai\";\nconst client = new OpenAI();\n\nconst response = await client.responses.cancel(\"resp_123\");\nconsole.log(response);\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nresponse = client.responses.cancel(\"resp_123\")\nprint(response)\n"
+            },
+            "response": "{\n  \"id\": \"resp_67cb71b351908190a308f3859487620d06981a8637e6bc44\",\n  \"object\": \"response\",\n  \"created_at\": 1741386163,\n  \"status\": \"cancelled\",\n  \"background\": true,\n  \"completed_at\": null,\n  \"error\": null,\n  \"incomplete_details\": null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"model\": \"gpt-6-astra\",\n  \"output\": [\n    {\n      \"type\": \"message\",\n      \"id\": \"msg_67cb71b3c2b0819084d481baaaf148f206981a8637e6bc44\",\n      \"status\": \"in_progress\",\n      \"role\": \"assistant\",\n      \"content\": [\n        {\n          \"type\": \"output_text\",\n          \"text\": \"Silent circuits hum,  \\nThoughts emerge in data streams—  \\nDigital dawn breaks.\",\n          \"annotations\": []\n        }\n      ]\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": null,\n  \"reasoning\": {\n    \"effort\": null,\n    \"summary\": null\n  },\n  \"store\": true,\n  \"temperature\": 1.0,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [],\n  \"top_p\": 1.0,\n  \"truncation\": \"disabled\",\n  \"usage\": null,\n  \"user\": null,\n  \"metadata\": {}\n}\n"
+          }
+        }
+      }
+    },
+    "/responses/{response_id}/input_items": {
+      "get": {
+        "operationId": "listInputItems",
+        "tags": [
+          "Responses"
+        ],
+        "summary": "Returns a list of input items for a given response.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "response_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the response to retrieve input items for."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between\n1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "in": "query",
+            "name": "order",
+            "schema": {
+              "type": "string",
+              "enum": [
+                "asc",
+                "desc"
+              ]
+            },
+            "description": "The order to return the input items in. Default is `desc`.\n- `asc`: Return the input items in ascending order.\n- `desc`: Return the input items in descending order.\n"
+          },
+          {
+            "in": "query",
+            "name": "after",
+            "schema": {
+              "type": "string"
+            },
+            "description": "An item ID to list items after, used in pagination.\n"
+          },
+          {
+            "in": "query",
+            "name": "include",
+            "schema": {
+              "type": "array",
+              "items": {
+                "$ref": "#/components/schemas/IncludeEnum"
+              }
+            },
+            "description": "Additional fields to include in the response. See the `include`\nparameter for Response creation above for more information.\n"
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ResponseItemList"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List input items",
+          "group": "responses",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/responses/resp_abc123/input_items \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "javascript": "import OpenAI from \"openai\";\nconst client = new OpenAI();\n\nconst response = await client.responses.inputItems.list(\"resp_123\");\nconsole.log(response.data);\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nresponse = client.responses.input_items.list(\"resp_123\")\nprint(response.data)\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"id\": \"msg_abc123\",\n      \"type\": \"message\",\n      \"role\": \"user\",\n      \"content\": [\n        {\n          \"type\": \"input_text\",\n          \"text\": \"Tell me a three sentence bedtime story about a unicorn.\"\n        }\n      ]\n    }\n  ],\n  \"first_id\": \"msg_abc123\",\n  \"last_id\": \"msg_abc123\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      }
+    },
+    "/threads": {
+      "post": {
+        "operationId": "createThread",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Create a thread.",
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateThreadRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ThreadObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create thread",
+          "group": "threads",
+          "beta": true,
+          "examples": [
+            {
+              "title": "Empty",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/threads \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -d ''\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\nempty_thread = client.beta.threads.create()\nprint(empty_thread)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const emptyThread = await openai.beta.threads.create();\n\n  console.log(emptyThread);\n}\n\nmain();"
+              },
+              "response": "{\n  \"id\": \"thread_abc123\",\n  \"object\": \"thread\",\n  \"created_at\": 1699012949,\n  \"metadata\": {},\n  \"tool_resources\": {}\n}\n"
+            },
+            {
+              "title": "Messages",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/threads \\\n-H \"Content-Type: application/json\" \\\n-H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n-H \"OpenAI-Beta: assistants=v2\" \\\n-d '{\n    \"messages\": [{\n      \"role\": \"user\",\n      \"content\": \"Hello, what is AI?\"\n    }, {\n      \"role\": \"user\",\n      \"content\": \"How does AI work? Explain it in simple terms.\"\n    }]\n  }'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\nmessage_thread = client.beta.threads.create(\n  messages=[\n    {\n      \"role\": \"user\",\n      \"content\": \"Hello, what is AI?\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": \"How does AI work? Explain it in simple terms.\"\n    },\n  ]\n)\n\nprint(message_thread)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const messageThread = await openai.beta.threads.create({\n    messages: [\n      {\n        role: \"user\",\n        content: \"Hello, what is AI?\"\n      },\n      {\n        role: \"user\",\n        content: \"How does AI work? Explain it in simple terms.\",\n      },\n    ],\n  });\n\n  console.log(messageThread);\n}\n\nmain();"
+              },
+              "response": "{\n  \"id\": \"thread_abc123\",\n  \"object\": \"thread\",\n  \"created_at\": 1699014083,\n  \"metadata\": {},\n  \"tool_resources\": {}\n}\n"
+            }
+          ]
+        }
+      }
+    },
+    "/threads/runs": {
+      "post": {
+        "operationId": "createThreadAndRun",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Create a thread and run it in one request.",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateThreadAndRunRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RunObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create thread and run",
+          "group": "threads",
+          "beta": true,
+          "examples": [
+            {
+              "title": "Default",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/threads/runs \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -d '{\n      \"assistant_id\": \"asst_abc123\",\n      \"thread\": {\n        \"messages\": [\n          {\"role\": \"user\", \"content\": \"Explain deep learning to a 5 year old.\"}\n        ]\n      }\n    }'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\nrun = client.beta.threads.create_and_run(\n  assistant_id=\"asst_abc123\",\n  thread={\n    \"messages\": [\n      {\"role\": \"user\", \"content\": \"Explain deep learning to a 5 year old.\"}\n    ]\n  }\n)\n\nprint(run)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const run = await openai.beta.threads.createAndRun({\n    assistant_id: \"asst_abc123\",\n    thread: {\n      messages: [\n        { role: \"user\", content: \"Explain deep learning to a 5 year old.\" },\n      ],\n    },\n  });\n\n  console.log(run);\n}\n\nmain();\n"
+              },
+              "response": "{\n  \"id\": \"run_abc123\",\n  \"object\": \"thread.run\",\n  \"created_at\": 1699076792,\n  \"assistant_id\": \"asst_abc123\",\n  \"thread_id\": \"thread_abc123\",\n  \"status\": \"queued\",\n  \"started_at\": null,\n  \"expires_at\": 1699077392,\n  \"cancelled_at\": null,\n  \"failed_at\": null,\n  \"completed_at\": null,\n  \"required_action\": null,\n  \"last_error\": null,\n  \"model\": \"gpt-5\",\n  \"instructions\": \"You are a helpful assistant.\",\n  \"tools\": [],\n  \"tool_resources\": {},\n  \"metadata\": {},\n  \"temperature\": 1.0,\n  \"top_p\": 1.0,\n  \"max_completion_tokens\": null,\n  \"max_prompt_tokens\": null,\n  \"truncation_strategy\": {\n    \"type\": \"auto\",\n    \"last_messages\": null\n  },\n  \"incomplete_details\": null,\n  \"usage\": null,\n  \"response_format\": \"auto\",\n  \"tool_choice\": \"auto\",\n  \"parallel_tool_calls\": true\n}\n"
+            },
+            {
+              "title": "Streaming",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/threads/runs \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -d '{\n    \"assistant_id\": \"asst_123\",\n    \"thread\": {\n      \"messages\": [\n        {\"role\": \"user\", \"content\": \"Hello\"}\n      ]\n    },\n    \"stream\": true\n  }'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\nstream = client.beta.threads.create_and_run(\n  assistant_id=\"asst_123\",\n  thread={\n    \"messages\": [\n      {\"role\": \"user\", \"content\": \"Hello\"}\n    ]\n  },\n  stream=True\n)\n\nfor event in stream:\n  print(event)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const stream = await openai.beta.threads.createAndRun({\n      assistant_id: \"asst_123\",\n      thread: {\n        messages: [\n          { role: \"user\", content: \"Hello\" },\n        ],\n      },\n      stream: true\n  });\n\n  for await (const event of stream) {\n    console.log(event);\n  }\n}\n\nmain();\n"
+              },
+              "response": "event: thread.created\ndata: {\"id\":\"thread_123\",\"object\":\"thread\",\"created_at\":1710348075,\"metadata\":{}}\n\nevent: thread.run.created\ndata: {\"id\":\"run_123\",\"object\":\"thread.run\",\"created_at\":1710348075,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"status\":\"queued\",\"started_at\":null,\"expires_at\":1710348675,\"cancelled_at\":null,\"failed_at\":null,\"completed_at\":null,\"required_action\":null,\"last_error\":null,\"model\":\"gpt-5\",\"instructions\":null,\"tools\":[],\"tool_resources\":{},\"metadata\":{},\"temperature\":1.0,\"top_p\":1.0,\"max_completion_tokens\":null,\"max_prompt_tokens\":null,\"truncation_strategy\":{\"type\":\"auto\",\"last_messages\":null},\"incomplete_details\":null,\"usage\":null,\"response_format\":\"auto\",\"tool_choice\":\"auto\",\"parallel_tool_calls\":true}\n\nevent: thread.run.queued\ndata: {\"id\":\"run_123\",\"object\":\"thread.run\",\"created_at\":1710348075,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"status\":\"queued\",\"started_at\":null,\"expires_at\":1710348675,\"cancelled_at\":null,\"failed_at\":null,\"completed_at\":null,\"required_action\":null,\"last_error\":null,\"model\":\"gpt-5\",\"instructions\":null,\"tools\":[],\"tool_resources\":{},\"metadata\":{},\"temperature\":1.0,\"top_p\":1.0,\"max_completion_tokens\":null,\"max_prompt_tokens\":null,\"truncation_strategy\":{\"type\":\"auto\",\"last_messages\":null},\"incomplete_details\":null,\"usage\":null,\"response_format\":\"auto\",\"tool_choice\":\"auto\",\"parallel_tool_calls\":true}\n\nevent: thread.run.in_progress\ndata: {\"id\":\"run_123\",\"object\":\"thread.run\",\"created_at\":1710348075,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"status\":\"in_progress\",\"started_at\":null,\"expires_at\":1710348675,\"cancelled_at\":null,\"failed_at\":null,\"completed_at\":null,\"required_action\":null,\"last_error\":null,\"model\":\"gpt-5\",\"instructions\":null,\"tools\":[],\"tool_resources\":{},\"metadata\":{},\"temperature\":1.0,\"top_p\":1.0,\"max_completion_tokens\":null,\"max_prompt_tokens\":null,\"truncation_strategy\":{\"type\":\"auto\",\"last_messages\":null},\"incomplete_details\":null,\"usage\":null,\"response_format\":\"auto\",\"tool_choice\":\"auto\",\"parallel_tool_calls\":true}\n\nevent: thread.run.step.created\ndata: {\"id\":\"step_001\",\"object\":\"thread.run.step\",\"created_at\":1710348076,\"run_id\":\"run_123\",\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"type\":\"message_creation\",\"status\":\"in_progress\",\"cancelled_at\":null,\"completed_at\":null,\"expires_at\":1710348675,\"failed_at\":null,\"last_error\":null,\"step_details\":{\"type\":\"message_creation\",\"message_creation\":{\"message_id\":\"msg_001\"}},\"usage\":null}\n\nevent: thread.run.step.in_progress\ndata: {\"id\":\"step_001\",\"object\":\"thread.run.step\",\"created_at\":1710348076,\"run_id\":\"run_123\",\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"type\":\"message_creation\",\"status\":\"in_progress\",\"cancelled_at\":null,\"completed_at\":null,\"expires_at\":1710348675,\"failed_at\":null,\"last_error\":null,\"step_details\":{\"type\":\"message_creation\",\"message_creation\":{\"message_id\":\"msg_001\"}},\"usage\":null}\n\nevent: thread.message.created\ndata: {\"id\":\"msg_001\",\"object\":\"thread.message\",\"created_at\":1710348076,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"run_id\":\"run_123\",\"status\":\"in_progress\",\"incomplete_details\":null,\"incomplete_at\":null,\"completed_at\":null,\"role\":\"assistant\",\"content\":[], \"metadata\":{}}\n\nevent: thread.message.in_progress\ndata: {\"id\":\"msg_001\",\"object\":\"thread.message\",\"created_at\":1710348076,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"run_id\":\"run_123\",\"status\":\"in_progress\",\"incomplete_details\":null,\"incomplete_at\":null,\"completed_at\":null,\"role\":\"assistant\",\"content\":[], \"metadata\":{}}\n\nevent: thread.message.delta\ndata: {\"id\":\"msg_001\",\"object\":\"thread.message.delta\",\"delta\":{\"content\":[{\"index\":0,\"type\":\"text\",\"text\":{\"value\":\"Hello\",\"annotations\":[]}}]}}\n\n...\n\nevent: thread.message.delta\ndata: {\"id\":\"msg_001\",\"object\":\"thread.message.delta\",\"delta\":{\"content\":[{\"index\":0,\"type\":\"text\",\"text\":{\"value\":\" today\"}}]}}\n\nevent: thread.message.delta\ndata: {\"id\":\"msg_001\",\"object\":\"thread.message.delta\",\"delta\":{\"content\":[{\"index\":0,\"type\":\"text\",\"text\":{\"value\":\"?\"}}]}}\n\nevent: thread.message.completed\ndata: {\"id\":\"msg_001\",\"object\":\"thread.message\",\"created_at\":1710348076,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"run_id\":\"run_123\",\"status\":\"completed\",\"incomplete_details\":null,\"incomplete_at\":null,\"completed_at\":1710348077,\"role\":\"assistant\",\"content\":[{\"type\":\"text\",\"text\":{\"value\":\"Hello! How can I assist you today?\",\"annotations\":[]}}], \"metadata\":{}}\n\nevent: thread.run.step.completed\ndata: {\"id\":\"step_001\",\"object\":\"thread.run.step\",\"created_at\":1710348076,\"run_id\":\"run_123\",\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"type\":\"message_creation\",\"status\":\"completed\",\"cancelled_at\":null,\"completed_at\":1710348077,\"expires_at\":1710348675,\"failed_at\":null,\"last_error\":null,\"step_details\":{\"type\":\"message_creation\",\"message_creation\":{\"message_id\":\"msg_001\"}},\"usage\":{\"prompt_tokens\":20,\"completion_tokens\":11,\"total_tokens\":31}}\n\nevent: thread.run.completed\n{\"id\":\"run_123\",\"object\":\"thread.run\",\"created_at\":1710348076,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"status\":\"completed\",\"started_at\":1713226836,\"expires_at\":null,\"cancelled_at\":null,\"failed_at\":null,\"completed_at\":1713226837,\"required_action\":null,\"last_error\":null,\"model\":\"gpt-5\",\"instructions\":null,\"tools\":[],\"metadata\":{},\"temperature\":1.0,\"top_p\":1.0,\"max_completion_tokens\":null,\"max_prompt_tokens\":null,\"truncation_strategy\":{\"type\":\"auto\",\"last_messages\":null},\"incomplete_details\":null,\"usage\":{\"prompt_tokens\":345,\"completion_tokens\":11,\"total_tokens\":356},\"response_format\":\"auto\",\"tool_choice\":\"auto\",\"parallel_tool_calls\":true}\n\nevent: done\ndata: [DONE]\n"
+            },
+            {
+              "title": "Streaming with Functions",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/threads/runs \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -d '{\n    \"assistant_id\": \"asst_abc123\",\n    \"thread\": {\n      \"messages\": [\n        {\"role\": \"user\", \"content\": \"What is the weather like in San Francisco?\"}\n      ]\n    },\n    \"tools\": [\n      {\n        \"type\": \"function\",\n        \"function\": {\n          \"name\": \"get_current_weather\",\n          \"description\": \"Get the current weather in a given location\",\n          \"parameters\": {\n            \"type\": \"object\",\n            \"properties\": {\n              \"location\": {\n                \"type\": \"string\",\n                \"description\": \"The city and state, e.g. San Francisco, CA\"\n              },\n              \"unit\": {\n                \"type\": \"string\",\n                \"enum\": [\"celsius\", \"fahrenheit\"]\n              }\n            },\n            \"required\": [\"location\"]\n          }\n        }\n      }\n    ],\n    \"stream\": true\n  }'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\ntools = [\n  {\n    \"type\": \"function\",\n    \"function\": {\n      \"name\": \"get_current_weather\",\n      \"description\": \"Get the current weather in a given location\",\n      \"parameters\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"location\": {\n            \"type\": \"string\",\n            \"description\": \"The city and state, e.g. San Francisco, CA\",\n          },\n          \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]},\n        },\n        \"required\": [\"location\"],\n      },\n    }\n  }\n]\n\nstream = client.beta.threads.create_and_run(\n  thread={\n      \"messages\": [\n        {\"role\": \"user\", \"content\": \"What is the weather like in San Francisco?\"}\n      ]\n  },\n  assistant_id=\"asst_abc123\",\n  tools=tools,\n  stream=True\n)\n\nfor event in stream:\n  print(event)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst tools = [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"get_current_weather\",\n        \"description\": \"Get the current weather in a given location\",\n        \"parameters\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"location\": {\n              \"type\": \"string\",\n              \"description\": \"The city and state, e.g. San Francisco, CA\",\n            },\n            \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]},\n          },\n          \"required\": [\"location\"],\n        },\n      }\n    }\n];\n\nasync function main() {\n  const stream = await openai.beta.threads.createAndRun({\n    assistant_id: \"asst_123\",\n    thread: {\n      messages: [\n        { role: \"user\", content: \"What is the weather like in San Francisco?\" },\n      ],\n    },\n    tools: tools,\n    stream: true\n  });\n\n  for await (const event of stream) {\n    console.log(event);\n  }\n}\n\nmain();\n"
+              },
+              "response": "event: thread.created\ndata: {\"id\":\"thread_123\",\"object\":\"thread\",\"created_at\":1710351818,\"metadata\":{}}\n\nevent: thread.run.created\ndata: {\"id\":\"run_123\",\"object\":\"thread.run\",\"created_at\":1710351818,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"status\":\"queued\",\"started_at\":null,\"expires_at\":1710352418,\"cancelled_at\":null,\"failed_at\":null,\"completed_at\":null,\"required_action\":null,\"last_error\":null,\"model\":\"gpt-5\",\"instructions\":null,\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_current_weather\",\"description\":\"Get the current weather in a given location\",\"parameters\":{\"type\":\"object\",\"properties\":{\"location\":{\"type\":\"string\",\"description\":\"The city and state, e.g. San Francisco, CA\"},\"unit\":{\"type\":\"string\",\"enum\":[\"celsius\",\"fahrenheit\"]}},\"required\":[\"location\"]}}}],\"metadata\":{},\"temperature\":1.0,\"top_p\":1.0,\"max_completion_tokens\":null,\"max_prompt_tokens\":null,\"truncation_strategy\":{\"type\":\"auto\",\"last_messages\":null},\"incomplete_details\":null,\"usage\":null,\"response_format\":\"auto\",\"tool_choice\":\"auto\",\"parallel_tool_calls\":true}}\n\nevent: thread.run.queued\ndata: {\"id\":\"run_123\",\"object\":\"thread.run\",\"created_at\":1710351818,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"status\":\"queued\",\"started_at\":null,\"expires_at\":1710352418,\"cancelled_at\":null,\"failed_at\":null,\"completed_at\":null,\"required_action\":null,\"last_error\":null,\"model\":\"gpt-5\",\"instructions\":null,\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_current_weather\",\"description\":\"Get the current weather in a given location\",\"parameters\":{\"type\":\"object\",\"properties\":{\"location\":{\"type\":\"string\",\"description\":\"The city and state, e.g. San Francisco, CA\"},\"unit\":{\"type\":\"string\",\"enum\":[\"celsius\",\"fahrenheit\"]}},\"required\":[\"location\"]}}}],\"metadata\":{},\"temperature\":1.0,\"top_p\":1.0,\"max_completion_tokens\":null,\"max_prompt_tokens\":null,\"truncation_strategy\":{\"type\":\"auto\",\"last_messages\":null},\"incomplete_details\":null,\"usage\":null,\"response_format\":\"auto\",\"tool_choice\":\"auto\",\"parallel_tool_calls\":true}}\n\nevent: thread.run.in_progress\ndata: {\"id\":\"run_123\",\"object\":\"thread.run\",\"created_at\":1710351818,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"status\":\"in_progress\",\"started_at\":1710351818,\"expires_at\":1710352418,\"cancelled_at\":null,\"failed_at\":null,\"completed_at\":null,\"required_action\":null,\"last_error\":null,\"model\":\"gpt-5\",\"instructions\":null,\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_current_weather\",\"description\":\"Get the current weather in a given location\",\"parameters\":{\"type\":\"object\",\"properties\":{\"location\":{\"type\":\"string\",\"description\":\"The city and state, e.g. San Francisco, CA\"},\"unit\":{\"type\":\"string\",\"enum\":[\"celsius\",\"fahrenheit\"]}},\"required\":[\"location\"]}}}],\"metadata\":{},\"temperature\":1.0,\"top_p\":1.0,\"max_completion_tokens\":null,\"max_prompt_tokens\":null,\"truncation_strategy\":{\"type\":\"auto\",\"last_messages\":null},\"incomplete_details\":null,\"usage\":null,\"response_format\":\"auto\",\"tool_choice\":\"auto\",\"parallel_tool_calls\":true}}\n\nevent: thread.run.step.created\ndata: {\"id\":\"step_001\",\"object\":\"thread.run.step\",\"created_at\":1710351819,\"run_id\":\"run_123\",\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"type\":\"tool_calls\",\"status\":\"in_progress\",\"cancelled_at\":null,\"completed_at\":null,\"expires_at\":1710352418,\"failed_at\":null,\"last_error\":null,\"step_details\":{\"type\":\"tool_calls\",\"tool_calls\":[]},\"usage\":null}\n\nevent: thread.run.step.in_progress\ndata: {\"id\":\"step_001\",\"object\":\"thread.run.step\",\"created_at\":1710351819,\"run_id\":\"run_123\",\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"type\":\"tool_calls\",\"status\":\"in_progress\",\"cancelled_at\":null,\"completed_at\":null,\"expires_at\":1710352418,\"failed_at\":null,\"last_error\":null,\"step_details\":{\"type\":\"tool_calls\",\"tool_calls\":[]},\"usage\":null}\n\nevent: thread.run.step.delta\ndata: {\"id\":\"step_001\",\"object\":\"thread.run.step.delta\",\"delta\":{\"step_details\":{\"type\":\"tool_calls\",\"tool_calls\":[{\"index\":0,\"id\":\"call_XXNp8YGaFrjrSjgqxtC8JJ1B\",\"type\":\"function\",\"function\":{\"name\":\"get_current_weather\",\"arguments\":\"\",\"output\":null}}]}}}\n\nevent: thread.run.step.delta\ndata: {\"id\":\"step_001\",\"object\":\"thread.run.step.delta\",\"delta\":{\"step_details\":{\"type\":\"tool_calls\",\"tool_calls\":[{\"index\":0,\"type\":\"function\",\"function\":{\"arguments\":\"{\\\"\"}}]}}}\n\nevent: thread.run.step.delta\ndata: {\"id\":\"step_001\",\"object\":\"thread.run.step.delta\",\"delta\":{\"step_details\":{\"type\":\"tool_calls\",\"tool_calls\":[{\"index\":0,\"type\":\"function\",\"function\":{\"arguments\":\"location\"}}]}}}\n\n...\n\nevent: thread.run.step.delta\ndata: {\"id\":\"step_001\",\"object\":\"thread.run.step.delta\",\"delta\":{\"step_details\":{\"type\":\"tool_calls\",\"tool_calls\":[{\"index\":0,\"type\":\"function\",\"function\":{\"arguments\":\"ahrenheit\"}}]}}}\n\nevent: thread.run.step.delta\ndata: {\"id\":\"step_001\",\"object\":\"thread.run.step.delta\",\"delta\":{\"step_details\":{\"type\":\"tool_calls\",\"tool_calls\":[{\"index\":0,\"type\":\"function\",\"function\":{\"arguments\":\"\\\"}\"}}]}}}\n\nevent: thread.run.requires_action\ndata: {\"id\":\"run_123\",\"object\":\"thread.run\",\"created_at\":1710351818,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"status\":\"requires_action\",\"started_at\":1710351818,\"expires_at\":1710352418,\"cancelled_at\":null,\"failed_at\":null,\"completed_at\":null,\"required_action\":{\"type\":\"submit_tool_outputs\",\"submit_tool_outputs\":{\"tool_calls\":[{\"id\":\"call_XXNp8YGaFrjrSjgqxtC8JJ1B\",\"type\":\"function\",\"function\":{\"name\":\"get_current_weather\",\"arguments\":\"{\\\"location\\\":\\\"San Francisco, CA\\\",\\\"unit\\\":\\\"fahrenheit\\\"}\"}}]}},\"last_error\":null,\"model\":\"gpt-5\",\"instructions\":null,\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_current_weather\",\"description\":\"Get the current weather in a given location\",\"parameters\":{\"type\":\"object\",\"properties\":{\"location\":{\"type\":\"string\",\"description\":\"The city and state, e.g. San Francisco, CA\"},\"unit\":{\"type\":\"string\",\"enum\":[\"celsius\",\"fahrenheit\"]}},\"required\":[\"location\"]}}}],\"metadata\":{},\"temperature\":1.0,\"top_p\":1.0,\"max_completion_tokens\":null,\"max_prompt_tokens\":null,\"truncation_strategy\":{\"type\":\"auto\",\"last_messages\":null},\"incomplete_details\":null,\"usage\":{\"prompt_tokens\":345,\"completion_tokens\":11,\"total_tokens\":356},\"response_format\":\"auto\",\"tool_choice\":\"auto\",\"parallel_tool_calls\":true}}\n\nevent: done\ndata: [DONE]\n"
+            }
+          ]
+        }
+      }
+    },
+    "/threads/{thread_id}": {
+      "get": {
+        "operationId": "getThread",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Retrieves a thread.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "thread_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the thread to retrieve."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ThreadObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve thread",
+          "group": "threads",
+          "beta": true,
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/threads/thread_abc123 \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"OpenAI-Beta: assistants=v2\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nmy_thread = client.beta.threads.retrieve(\"thread_abc123\")\nprint(my_thread)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const myThread = await openai.beta.threads.retrieve(\n    \"thread_abc123\"\n  );\n\n  console.log(myThread);\n}\n\nmain();"
+            },
+            "response": "{\n  \"id\": \"thread_abc123\",\n  \"object\": \"thread\",\n  \"created_at\": 1699014083,\n  \"metadata\": {},\n  \"tool_resources\": {\n    \"code_interpreter\": {\n      \"file_ids\": []\n    }\n  }\n}\n"
+          }
+        }
+      },
+      "post": {
+        "operationId": "modifyThread",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Modifies a thread.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "thread_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the thread to modify. Only the `metadata` can be modified."
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ModifyThreadRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ThreadObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Modify thread",
+          "group": "threads",
+          "beta": true,
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/threads/thread_abc123 \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -d '{\n      \"metadata\": {\n        \"modified\": \"true\",\n        \"user\": \"abc123\"\n      }\n    }'\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nmy_updated_thread = client.beta.threads.update(\n  \"thread_abc123\",\n  metadata={\n    \"modified\": \"true\",\n    \"user\": \"abc123\"\n  }\n)\nprint(my_updated_thread)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const updatedThread = await openai.beta.threads.update(\n    \"thread_abc123\",\n    {\n      metadata: { modified: \"true\", user: \"abc123\" },\n    }\n  );\n\n  console.log(updatedThread);\n}\n\nmain();"
+            },
+            "response": "{\n  \"id\": \"thread_abc123\",\n  \"object\": \"thread\",\n  \"created_at\": 1699014083,\n  \"metadata\": {\n    \"modified\": \"true\",\n    \"user\": \"abc123\"\n  },\n  \"tool_resources\": {}\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "operationId": "deleteThread",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Delete a thread.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "thread_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the thread to delete."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeleteThreadResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete thread",
+          "group": "threads",
+          "beta": true,
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/threads/thread_abc123 \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -X DELETE\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nresponse = client.beta.threads.delete(\"thread_abc123\")\nprint(response)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const response = await openai.beta.threads.delete(\"thread_abc123\");\n\n  console.log(response);\n}\nmain();"
+            },
+            "response": "{\n  \"id\": \"thread_abc123\",\n  \"object\": \"thread.deleted\",\n  \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/threads/{thread_id}/messages": {
+      "get": {
+        "operationId": "listMessages",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Returns a list of messages for a given thread.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "thread_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the [thread](https://developers.openai.com/api/docs/assistants/migration) the messages belong to."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.\n",
+            "schema": {
+              "type": "string",
+              "default": "desc",
+              "enum": [
+                "asc",
+                "desc"
+              ]
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "before",
+            "in": "query",
+            "description": "A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.\n",
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "run_id",
+            "in": "query",
+            "description": "Filter messages by the run ID that generated them.\n",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ListMessagesResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List messages",
+          "group": "threads",
+          "beta": true,
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/threads/thread_abc123/messages \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"OpenAI-Beta: assistants=v2\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nthread_messages = client.beta.threads.messages.list(\"thread_abc123\")\nprint(thread_messages.data)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const threadMessages = await openai.beta.threads.messages.list(\n    \"thread_abc123\"\n  );\n\n  console.log(threadMessages.data);\n}\n\nmain();"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"id\": \"msg_abc123\",\n      \"object\": \"thread.message\",\n      \"created_at\": 1699016383,\n      \"assistant_id\": null,\n      \"thread_id\": \"thread_abc123\",\n      \"run_id\": null,\n      \"role\": \"user\",\n      \"content\": [\n        {\n          \"type\": \"text\",\n          \"text\": {\n            \"value\": \"How does AI work? Explain it in simple terms.\",\n            \"annotations\": []\n          }\n        }\n      ],\n      \"attachments\": [],\n      \"metadata\": {}\n    },\n    {\n      \"id\": \"msg_abc456\",\n      \"object\": \"thread.message\",\n      \"created_at\": 1699016383,\n      \"assistant_id\": null,\n      \"thread_id\": \"thread_abc123\",\n      \"run_id\": null,\n      \"role\": \"user\",\n      \"content\": [\n        {\n          \"type\": \"text\",\n          \"text\": {\n            \"value\": \"Hello, what is AI?\",\n            \"annotations\": []\n          }\n        }\n      ],\n      \"attachments\": [],\n      \"metadata\": {}\n    }\n  ],\n  \"first_id\": \"msg_abc123\",\n  \"last_id\": \"msg_abc456\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      },
+      "post": {
+        "operationId": "createMessage",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Create a message.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "thread_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the [thread](https://developers.openai.com/api/docs/assistants/migration) to create a message for."
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateMessageRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/MessageObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create message",
+          "group": "threads",
+          "beta": true,
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/threads/thread_abc123/messages \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -d '{\n      \"role\": \"user\",\n      \"content\": \"How does AI work? Explain it in simple terms.\"\n    }'\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nthread_message = client.beta.threads.messages.create(\n  \"thread_abc123\",\n  role=\"user\",\n  content=\"How does AI work? Explain it in simple terms.\",\n)\nprint(thread_message)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const threadMessages = await openai.beta.threads.messages.create(\n    \"thread_abc123\",\n    { role: \"user\", content: \"How does AI work? Explain it in simple terms.\" }\n  );\n\n  console.log(threadMessages);\n}\n\nmain();"
+            },
+            "response": "{\n  \"id\": \"msg_abc123\",\n  \"object\": \"thread.message\",\n  \"created_at\": 1713226573,\n  \"assistant_id\": null,\n  \"thread_id\": \"thread_abc123\",\n  \"run_id\": null,\n  \"role\": \"user\",\n  \"content\": [\n    {\n      \"type\": \"text\",\n      \"text\": {\n        \"value\": \"How does AI work? Explain it in simple terms.\",\n        \"annotations\": []\n      }\n    }\n  ],\n  \"attachments\": [],\n  \"metadata\": {}\n}\n"
+          }
+        }
+      }
+    },
+    "/threads/{thread_id}/messages/{message_id}": {
+      "get": {
+        "operationId": "getMessage",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Retrieve a message.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "thread_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the [thread](https://developers.openai.com/api/docs/assistants/migration) to which this message belongs."
+          },
+          {
+            "in": "path",
+            "name": "message_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the message to retrieve."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/MessageObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve message",
+          "group": "threads",
+          "beta": true,
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123 \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"OpenAI-Beta: assistants=v2\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nmessage = client.beta.threads.messages.retrieve(\n  message_id=\"msg_abc123\",\n  thread_id=\"thread_abc123\",\n)\nprint(message)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const message = await openai.beta.threads.messages.retrieve(\n    \"msg_abc123\",\n    { thread_id: \"thread_abc123\" }\n  );\n\n  console.log(message);\n}\n\nmain();"
+            },
+            "response": "{\n  \"id\": \"msg_abc123\",\n  \"object\": \"thread.message\",\n  \"created_at\": 1699017614,\n  \"assistant_id\": null,\n  \"thread_id\": \"thread_abc123\",\n  \"run_id\": null,\n  \"role\": \"user\",\n  \"content\": [\n    {\n      \"type\": \"text\",\n      \"text\": {\n        \"value\": \"How does AI work? Explain it in simple terms.\",\n        \"annotations\": []\n      }\n    }\n  ],\n  \"attachments\": [],\n  \"metadata\": {}\n}\n"
+          }
+        }
+      },
+      "post": {
+        "operationId": "modifyMessage",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Modifies a message.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "thread_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the thread to which this message belongs."
+          },
+          {
+            "in": "path",
+            "name": "message_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the message to modify."
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ModifyMessageRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/MessageObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Modify message",
+          "group": "threads",
+          "beta": true,
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123 \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -d '{\n      \"metadata\": {\n        \"modified\": \"true\",\n        \"user\": \"abc123\"\n      }\n    }'\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nmessage = client.beta.threads.messages.update(\n  message_id=\"msg_abc12\",\n  thread_id=\"thread_abc123\",\n  metadata={\n    \"modified\": \"true\",\n    \"user\": \"abc123\",\n  },\n)\nprint(message)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const message = await openai.beta.threads.messages.update(\n    \"thread_abc123\",\n    \"msg_abc123\",\n    {\n      metadata: {\n        modified: \"true\",\n        user: \"abc123\",\n      },\n    }\n  }'"
+            },
+            "response": "{\n  \"id\": \"msg_abc123\",\n  \"object\": \"thread.message\",\n  \"created_at\": 1699017614,\n  \"assistant_id\": null,\n  \"thread_id\": \"thread_abc123\",\n  \"run_id\": null,\n  \"role\": \"user\",\n  \"content\": [\n    {\n      \"type\": \"text\",\n      \"text\": {\n        \"value\": \"How does AI work? Explain it in simple terms.\",\n        \"annotations\": []\n      }\n    }\n  ],\n  \"file_ids\": [],\n  \"metadata\": {\n    \"modified\": \"true\",\n    \"user\": \"abc123\"\n  }\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "operationId": "deleteMessage",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Deletes a message.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "thread_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the thread to which this message belongs."
+          },
+          {
+            "in": "path",
+            "name": "message_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the message to delete."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeleteMessageResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete message",
+          "group": "threads",
+          "beta": true,
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123 \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"OpenAI-Beta: assistants=v2\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\ndeleted_message = client.beta.threads.messages.delete(\n  message_id=\"msg_abc12\",\n  thread_id=\"thread_abc123\",\n)\nprint(deleted_message)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const deletedMessage = await openai.beta.threads.messages.delete(\n    \"msg_abc123\",\n    { thread_id: \"thread_abc123\" }\n  );\n\n  console.log(deletedMessage);\n}"
+            },
+            "response": "{\n  \"id\": \"msg_abc123\",\n  \"object\": \"thread.message.deleted\",\n  \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/threads/{thread_id}/runs": {
+      "get": {
+        "operationId": "listRuns",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Returns a list of runs belonging to a thread.",
+        "parameters": [
+          {
+            "name": "thread_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the thread the run belongs to."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.\n",
+            "schema": {
+              "type": "string",
+              "default": "desc",
+              "enum": [
+                "asc",
+                "desc"
+              ]
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "before",
+            "in": "query",
+            "description": "A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.\n",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ListRunsResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List runs",
+          "group": "threads",
+          "beta": true,
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/threads/thread_abc123/runs \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nruns = client.beta.threads.runs.list(\n  \"thread_abc123\"\n)\n\nprint(runs)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const runs = await openai.beta.threads.runs.list(\n    \"thread_abc123\"\n  );\n\n  console.log(runs);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"id\": \"run_abc123\",\n      \"object\": \"thread.run\",\n      \"created_at\": 1699075072,\n      \"assistant_id\": \"asst_abc123\",\n      \"thread_id\": \"thread_abc123\",\n      \"status\": \"completed\",\n      \"started_at\": 1699075072,\n      \"expires_at\": null,\n      \"cancelled_at\": null,\n      \"failed_at\": null,\n      \"completed_at\": 1699075073,\n      \"last_error\": null,\n      \"model\": \"gpt-5\",\n      \"instructions\": null,\n      \"incomplete_details\": null,\n      \"tools\": [\n        {\n          \"type\": \"code_interpreter\"\n        }\n      ],\n      \"tool_resources\": {\n        \"code_interpreter\": {\n          \"file_ids\": [\n            \"file-abc123\",\n            \"file-abc456\"\n          ]\n        }\n      },\n      \"metadata\": {},\n      \"usage\": {\n        \"prompt_tokens\": 123,\n        \"completion_tokens\": 456,\n        \"total_tokens\": 579\n      },\n      \"temperature\": 1.0,\n      \"top_p\": 1.0,\n      \"max_prompt_tokens\": 1000,\n      \"max_completion_tokens\": 1000,\n      \"truncation_strategy\": {\n        \"type\": \"auto\",\n        \"last_messages\": null\n      },\n      \"response_format\": \"auto\",\n      \"tool_choice\": \"auto\",\n      \"parallel_tool_calls\": true\n    },\n    {\n      \"id\": \"run_abc456\",\n      \"object\": \"thread.run\",\n      \"created_at\": 1699063290,\n      \"assistant_id\": \"asst_abc123\",\n      \"thread_id\": \"thread_abc123\",\n      \"status\": \"completed\",\n      \"started_at\": 1699063290,\n      \"expires_at\": null,\n      \"cancelled_at\": null,\n      \"failed_at\": null,\n      \"completed_at\": 1699063291,\n      \"last_error\": null,\n      \"model\": \"gpt-5\",\n      \"instructions\": null,\n      \"incomplete_details\": null,\n      \"tools\": [\n        {\n          \"type\": \"code_interpreter\"\n        }\n      ],\n      \"tool_resources\": {\n        \"code_interpreter\": {\n          \"file_ids\": [\n            \"file-abc123\",\n            \"file-abc456\"\n          ]\n        }\n      },\n      \"metadata\": {},\n      \"usage\": {\n        \"prompt_tokens\": 123,\n        \"completion_tokens\": 456,\n        \"total_tokens\": 579\n      },\n      \"temperature\": 1.0,\n      \"top_p\": 1.0,\n      \"max_prompt_tokens\": 1000,\n      \"max_completion_tokens\": 1000,\n      \"truncation_strategy\": {\n        \"type\": \"auto\",\n        \"last_messages\": null\n      },\n      \"response_format\": \"auto\",\n      \"tool_choice\": \"auto\",\n      \"parallel_tool_calls\": true\n    }\n  ],\n  \"first_id\": \"run_abc123\",\n  \"last_id\": \"run_abc456\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      },
+      "post": {
+        "operationId": "createRun",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Create a run.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "thread_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the thread to run."
+          },
+          {
+            "name": "include[]",
+            "in": "query",
+            "description": "A list of additional fields to include in the response. Currently the only supported value is `step_details.tool_calls[*].file_search.results[*].content` to fetch the file search result content.\n\nSee the [file search tool documentation](https://developers.openai.com/api/docs/guides/tools-file-search#retrieval-customization) for more information.\n",
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "step_details.tool_calls[*].file_search.results[*].content"
+                ]
+              }
+            }
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateRunRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RunObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create run",
+          "group": "threads",
+          "beta": true,
+          "examples": [
+            {
+              "title": "Default",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/threads/thread_abc123/runs \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -d '{\n    \"assistant_id\": \"asst_abc123\"\n  }'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\nrun = client.beta.threads.runs.create(\n  thread_id=\"thread_abc123\",\n  assistant_id=\"asst_abc123\"\n)\n\nprint(run)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const run = await openai.beta.threads.runs.create(\n    \"thread_abc123\",\n    { assistant_id: \"asst_abc123\" }\n  );\n\n  console.log(run);\n}\n\nmain();\n"
+              },
+              "response": "{\n  \"id\": \"run_abc123\",\n  \"object\": \"thread.run\",\n  \"created_at\": 1699063290,\n  \"assistant_id\": \"asst_abc123\",\n  \"thread_id\": \"thread_abc123\",\n  \"status\": \"queued\",\n  \"started_at\": 1699063290,\n  \"expires_at\": null,\n  \"cancelled_at\": null,\n  \"failed_at\": null,\n  \"completed_at\": 1699063291,\n  \"last_error\": null,\n  \"model\": \"gpt-5\",\n  \"instructions\": null,\n  \"incomplete_details\": null,\n  \"tools\": [\n    {\n      \"type\": \"code_interpreter\"\n    }\n  ],\n  \"metadata\": {},\n  \"usage\": null,\n  \"temperature\": 1.0,\n  \"top_p\": 1.0,\n  \"max_prompt_tokens\": 1000,\n  \"max_completion_tokens\": 1000,\n  \"truncation_strategy\": {\n    \"type\": \"auto\",\n    \"last_messages\": null\n  },\n  \"response_format\": \"auto\",\n  \"tool_choice\": \"auto\",\n  \"parallel_tool_calls\": true\n}\n"
+            },
+            {
+              "title": "Streaming",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/threads/thread_123/runs \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -d '{\n    \"assistant_id\": \"asst_123\",\n    \"stream\": true\n  }'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\nstream = client.beta.threads.runs.create(\n  thread_id=\"thread_123\",\n  assistant_id=\"asst_123\",\n  stream=True\n)\n\nfor event in stream:\n  print(event)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const stream = await openai.beta.threads.runs.create(\n    \"thread_123\",\n    { assistant_id: \"asst_123\", stream: true }\n  );\n\n  for await (const event of stream) {\n    console.log(event);\n  }\n}\n\nmain();\n"
+              },
+              "response": "event: thread.run.created\ndata: {\"id\":\"run_123\",\"object\":\"thread.run\",\"created_at\":1710330640,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"status\":\"queued\",\"started_at\":null,\"expires_at\":1710331240,\"cancelled_at\":null,\"failed_at\":null,\"completed_at\":null,\"required_action\":null,\"last_error\":null,\"model\":\"gpt-5\",\"instructions\":null,\"tools\":[],\"metadata\":{},\"temperature\":1.0,\"top_p\":1.0,\"max_completion_tokens\":null,\"max_prompt_tokens\":null,\"truncation_strategy\":{\"type\":\"auto\",\"last_messages\":null},\"incomplete_details\":null,\"usage\":null,\"response_format\":\"auto\",\"tool_choice\":\"auto\",\"parallel_tool_calls\":true}}\n\nevent: thread.run.queued\ndata: {\"id\":\"run_123\",\"object\":\"thread.run\",\"created_at\":1710330640,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"status\":\"queued\",\"started_at\":null,\"expires_at\":1710331240,\"cancelled_at\":null,\"failed_at\":null,\"completed_at\":null,\"required_action\":null,\"last_error\":null,\"model\":\"gpt-5\",\"instructions\":null,\"tools\":[],\"metadata\":{},\"temperature\":1.0,\"top_p\":1.0,\"max_completion_tokens\":null,\"max_prompt_tokens\":null,\"truncation_strategy\":{\"type\":\"auto\",\"last_messages\":null},\"incomplete_details\":null,\"usage\":null,\"response_format\":\"auto\",\"tool_choice\":\"auto\",\"parallel_tool_calls\":true}}\n\nevent: thread.run.in_progress\ndata: {\"id\":\"run_123\",\"object\":\"thread.run\",\"created_at\":1710330640,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"status\":\"in_progress\",\"started_at\":1710330641,\"expires_at\":1710331240,\"cancelled_at\":null,\"failed_at\":null,\"completed_at\":null,\"required_action\":null,\"last_error\":null,\"model\":\"gpt-5\",\"instructions\":null,\"tools\":[],\"metadata\":{},\"temperature\":1.0,\"top_p\":1.0,\"max_completion_tokens\":null,\"max_prompt_tokens\":null,\"truncation_strategy\":{\"type\":\"auto\",\"last_messages\":null},\"incomplete_details\":null,\"usage\":null,\"response_format\":\"auto\",\"tool_choice\":\"auto\",\"parallel_tool_calls\":true}}\n\nevent: thread.run.step.created\ndata: {\"id\":\"step_001\",\"object\":\"thread.run.step\",\"created_at\":1710330641,\"run_id\":\"run_123\",\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"type\":\"message_creation\",\"status\":\"in_progress\",\"cancelled_at\":null,\"completed_at\":null,\"expires_at\":1710331240,\"failed_at\":null,\"last_error\":null,\"step_details\":{\"type\":\"message_creation\",\"message_creation\":{\"message_id\":\"msg_001\"}},\"usage\":null}\n\nevent: thread.run.step.in_progress\ndata: {\"id\":\"step_001\",\"object\":\"thread.run.step\",\"created_at\":1710330641,\"run_id\":\"run_123\",\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"type\":\"message_creation\",\"status\":\"in_progress\",\"cancelled_at\":null,\"completed_at\":null,\"expires_at\":1710331240,\"failed_at\":null,\"last_error\":null,\"step_details\":{\"type\":\"message_creation\",\"message_creation\":{\"message_id\":\"msg_001\"}},\"usage\":null}\n\nevent: thread.message.created\ndata: {\"id\":\"msg_001\",\"object\":\"thread.message\",\"created_at\":1710330641,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"run_id\":\"run_123\",\"status\":\"in_progress\",\"incomplete_details\":null,\"incomplete_at\":null,\"completed_at\":null,\"role\":\"assistant\",\"content\":[],\"metadata\":{}}\n\nevent: thread.message.in_progress\ndata: {\"id\":\"msg_001\",\"object\":\"thread.message\",\"created_at\":1710330641,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"run_id\":\"run_123\",\"status\":\"in_progress\",\"incomplete_details\":null,\"incomplete_at\":null,\"completed_at\":null,\"role\":\"assistant\",\"content\":[],\"metadata\":{}}\n\nevent: thread.message.delta\ndata: {\"id\":\"msg_001\",\"object\":\"thread.message.delta\",\"delta\":{\"content\":[{\"index\":0,\"type\":\"text\",\"text\":{\"value\":\"Hello\",\"annotations\":[]}}]}}\n\n...\n\nevent: thread.message.delta\ndata: {\"id\":\"msg_001\",\"object\":\"thread.message.delta\",\"delta\":{\"content\":[{\"index\":0,\"type\":\"text\",\"text\":{\"value\":\" today\"}}]}}\n\nevent: thread.message.delta\ndata: {\"id\":\"msg_001\",\"object\":\"thread.message.delta\",\"delta\":{\"content\":[{\"index\":0,\"type\":\"text\",\"text\":{\"value\":\"?\"}}]}}\n\nevent: thread.message.completed\ndata: {\"id\":\"msg_001\",\"object\":\"thread.message\",\"created_at\":1710330641,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"run_id\":\"run_123\",\"status\":\"completed\",\"incomplete_details\":null,\"incomplete_at\":null,\"completed_at\":1710330642,\"role\":\"assistant\",\"content\":[{\"type\":\"text\",\"text\":{\"value\":\"Hello! How can I assist you today?\",\"annotations\":[]}}],\"metadata\":{}}\n\nevent: thread.run.step.completed\ndata: {\"id\":\"step_001\",\"object\":\"thread.run.step\",\"created_at\":1710330641,\"run_id\":\"run_123\",\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"type\":\"message_creation\",\"status\":\"completed\",\"cancelled_at\":null,\"completed_at\":1710330642,\"expires_at\":1710331240,\"failed_at\":null,\"last_error\":null,\"step_details\":{\"type\":\"message_creation\",\"message_creation\":{\"message_id\":\"msg_001\"}},\"usage\":{\"prompt_tokens\":20,\"completion_tokens\":11,\"total_tokens\":31}}\n\nevent: thread.run.completed\ndata: {\"id\":\"run_123\",\"object\":\"thread.run\",\"created_at\":1710330640,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"status\":\"completed\",\"started_at\":1710330641,\"expires_at\":null,\"cancelled_at\":null,\"failed_at\":null,\"completed_at\":1710330642,\"required_action\":null,\"last_error\":null,\"model\":\"gpt-5\",\"instructions\":null,\"tools\":[],\"metadata\":{},\"temperature\":1.0,\"top_p\":1.0,\"max_completion_tokens\":null,\"max_prompt_tokens\":null,\"truncation_strategy\":{\"type\":\"auto\",\"last_messages\":null},\"incomplete_details\":null,\"usage\":{\"prompt_tokens\":20,\"completion_tokens\":11,\"total_tokens\":31},\"response_format\":\"auto\",\"tool_choice\":\"auto\",\"parallel_tool_calls\":true}}\n\nevent: done\ndata: [DONE]\n"
+            },
+            {
+              "title": "Streaming with Functions",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/threads/thread_abc123/runs \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -d '{\n    \"assistant_id\": \"asst_abc123\",\n    \"tools\": [\n      {\n        \"type\": \"function\",\n        \"function\": {\n          \"name\": \"get_current_weather\",\n          \"description\": \"Get the current weather in a given location\",\n          \"parameters\": {\n            \"type\": \"object\",\n            \"properties\": {\n              \"location\": {\n                \"type\": \"string\",\n                \"description\": \"The city and state, e.g. San Francisco, CA\"\n              },\n              \"unit\": {\n                \"type\": \"string\",\n                \"enum\": [\"celsius\", \"fahrenheit\"]\n              }\n            },\n            \"required\": [\"location\"]\n          }\n        }\n      }\n    ],\n    \"stream\": true\n  }'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\ntools = [\n  {\n    \"type\": \"function\",\n    \"function\": {\n      \"name\": \"get_current_weather\",\n      \"description\": \"Get the current weather in a given location\",\n      \"parameters\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"location\": {\n            \"type\": \"string\",\n            \"description\": \"The city and state, e.g. San Francisco, CA\",\n          },\n          \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]},\n        },\n        \"required\": [\"location\"],\n      },\n    }\n  }\n]\n\nstream = client.beta.threads.runs.create(\n  thread_id=\"thread_abc123\",\n  assistant_id=\"asst_abc123\",\n  tools=tools,\n  stream=True\n)\n\nfor event in stream:\n  print(event)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst tools = [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"get_current_weather\",\n        \"description\": \"Get the current weather in a given location\",\n        \"parameters\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"location\": {\n              \"type\": \"string\",\n              \"description\": \"The city and state, e.g. San Francisco, CA\",\n            },\n            \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]},\n          },\n          \"required\": [\"location\"],\n        },\n      }\n    }\n];\n\nasync function main() {\n  const stream = await openai.beta.threads.runs.create(\n    \"thread_abc123\",\n    {\n      assistant_id: \"asst_abc123\",\n      tools: tools,\n      stream: true\n    }\n  );\n\n  for await (const event of stream) {\n    console.log(event);\n  }\n}\n\nmain();\n"
+              },
+              "response": "event: thread.run.created\ndata: {\"id\":\"run_123\",\"object\":\"thread.run\",\"created_at\":1710348075,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"status\":\"queued\",\"started_at\":null,\"expires_at\":1710348675,\"cancelled_at\":null,\"failed_at\":null,\"completed_at\":null,\"required_action\":null,\"last_error\":null,\"model\":\"gpt-5\",\"instructions\":null,\"tools\":[],\"metadata\":{},\"temperature\":1.0,\"top_p\":1.0,\"max_completion_tokens\":null,\"max_prompt_tokens\":null,\"truncation_strategy\":{\"type\":\"auto\",\"last_messages\":null},\"incomplete_details\":null,\"usage\":null,\"response_format\":\"auto\",\"tool_choice\":\"auto\",\"parallel_tool_calls\":true}}\n\nevent: thread.run.queued\ndata: {\"id\":\"run_123\",\"object\":\"thread.run\",\"created_at\":1710348075,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"status\":\"queued\",\"started_at\":null,\"expires_at\":1710348675,\"cancelled_at\":null,\"failed_at\":null,\"completed_at\":null,\"required_action\":null,\"last_error\":null,\"model\":\"gpt-5\",\"instructions\":null,\"tools\":[],\"metadata\":{},\"temperature\":1.0,\"top_p\":1.0,\"max_completion_tokens\":null,\"max_prompt_tokens\":null,\"truncation_strategy\":{\"type\":\"auto\",\"last_messages\":null},\"incomplete_details\":null,\"usage\":null,\"response_format\":\"auto\",\"tool_choice\":\"auto\",\"parallel_tool_calls\":true}}\n\nevent: thread.run.in_progress\ndata: {\"id\":\"run_123\",\"object\":\"thread.run\",\"created_at\":1710348075,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"status\":\"in_progress\",\"started_at\":1710348075,\"expires_at\":1710348675,\"cancelled_at\":null,\"failed_at\":null,\"completed_at\":null,\"required_action\":null,\"last_error\":null,\"model\":\"gpt-5\",\"instructions\":null,\"tools\":[],\"metadata\":{},\"temperature\":1.0,\"top_p\":1.0,\"max_completion_tokens\":null,\"max_prompt_tokens\":null,\"truncation_strategy\":{\"type\":\"auto\",\"last_messages\":null},\"incomplete_details\":null,\"usage\":null,\"response_format\":\"auto\",\"tool_choice\":\"auto\",\"parallel_tool_calls\":true}}\n\nevent: thread.run.step.created\ndata: {\"id\":\"step_001\",\"object\":\"thread.run.step\",\"created_at\":1710348076,\"run_id\":\"run_123\",\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"type\":\"message_creation\",\"status\":\"in_progress\",\"cancelled_at\":null,\"completed_at\":null,\"expires_at\":1710348675,\"failed_at\":null,\"last_error\":null,\"step_details\":{\"type\":\"message_creation\",\"message_creation\":{\"message_id\":\"msg_001\"}},\"usage\":null}\n\nevent: thread.run.step.in_progress\ndata: {\"id\":\"step_001\",\"object\":\"thread.run.step\",\"created_at\":1710348076,\"run_id\":\"run_123\",\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"type\":\"message_creation\",\"status\":\"in_progress\",\"cancelled_at\":null,\"completed_at\":null,\"expires_at\":1710348675,\"failed_at\":null,\"last_error\":null,\"step_details\":{\"type\":\"message_creation\",\"message_creation\":{\"message_id\":\"msg_001\"}},\"usage\":null}\n\nevent: thread.message.created\ndata: {\"id\":\"msg_001\",\"object\":\"thread.message\",\"created_at\":1710348076,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"run_id\":\"run_123\",\"status\":\"in_progress\",\"incomplete_details\":null,\"incomplete_at\":null,\"completed_at\":null,\"role\":\"assistant\",\"content\":[],\"metadata\":{}}\n\nevent: thread.message.in_progress\ndata: {\"id\":\"msg_001\",\"object\":\"thread.message\",\"created_at\":1710348076,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"run_id\":\"run_123\",\"status\":\"in_progress\",\"incomplete_details\":null,\"incomplete_at\":null,\"completed_at\":null,\"role\":\"assistant\",\"content\":[],\"metadata\":{}}\n\nevent: thread.message.delta\ndata: {\"id\":\"msg_001\",\"object\":\"thread.message.delta\",\"delta\":{\"content\":[{\"index\":0,\"type\":\"text\",\"text\":{\"value\":\"Hello\",\"annotations\":[]}}]}}\n\n...\n\nevent: thread.message.delta\ndata: {\"id\":\"msg_001\",\"object\":\"thread.message.delta\",\"delta\":{\"content\":[{\"index\":0,\"type\":\"text\",\"text\":{\"value\":\" today\"}}]}}\n\nevent: thread.message.delta\ndata: {\"id\":\"msg_001\",\"object\":\"thread.message.delta\",\"delta\":{\"content\":[{\"index\":0,\"type\":\"text\",\"text\":{\"value\":\"?\"}}]}}\n\nevent: thread.message.completed\ndata: {\"id\":\"msg_001\",\"object\":\"thread.message\",\"created_at\":1710348076,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"run_id\":\"run_123\",\"status\":\"completed\",\"incomplete_details\":null,\"incomplete_at\":null,\"completed_at\":1710348077,\"role\":\"assistant\",\"content\":[{\"type\":\"text\",\"text\":{\"value\":\"Hello! How can I assist you today?\",\"annotations\":[]}}],\"metadata\":{}}\n\nevent: thread.run.step.completed\ndata: {\"id\":\"step_001\",\"object\":\"thread.run.step\",\"created_at\":1710348076,\"run_id\":\"run_123\",\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"type\":\"message_creation\",\"status\":\"completed\",\"cancelled_at\":null,\"completed_at\":1710348077,\"expires_at\":1710348675,\"failed_at\":null,\"last_error\":null,\"step_details\":{\"type\":\"message_creation\",\"message_creation\":{\"message_id\":\"msg_001\"}},\"usage\":{\"prompt_tokens\":20,\"completion_tokens\":11,\"total_tokens\":31}}\n\nevent: thread.run.completed\ndata: {\"id\":\"run_123\",\"object\":\"thread.run\",\"created_at\":1710348075,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"status\":\"completed\",\"started_at\":1710348075,\"expires_at\":null,\"cancelled_at\":null,\"failed_at\":null,\"completed_at\":1710348077,\"required_action\":null,\"last_error\":null,\"model\":\"gpt-5\",\"instructions\":null,\"tools\":[],\"metadata\":{},\"temperature\":1.0,\"top_p\":1.0,\"max_completion_tokens\":null,\"max_prompt_tokens\":null,\"truncation_strategy\":{\"type\":\"auto\",\"last_messages\":null},\"incomplete_details\":null,\"usage\":{\"prompt_tokens\":20,\"completion_tokens\":11,\"total_tokens\":31},\"response_format\":\"auto\",\"tool_choice\":\"auto\",\"parallel_tool_calls\":true}}\n\nevent: done\ndata: [DONE]\n"
+            }
+          ]
+        }
+      }
+    },
+    "/threads/{thread_id}/runs/{run_id}": {
+      "get": {
+        "operationId": "getRun",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Retrieves a run.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "thread_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the [thread](https://developers.openai.com/api/docs/assistants/migration) that was run."
+          },
+          {
+            "in": "path",
+            "name": "run_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the run to retrieve."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RunObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve run",
+          "group": "threads",
+          "beta": true,
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"OpenAI-Beta: assistants=v2\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nrun = client.beta.threads.runs.retrieve(\n  thread_id=\"thread_abc123\",\n  run_id=\"run_abc123\"\n)\n\nprint(run)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const run = await openai.beta.threads.runs.retrieve(\n    \"run_abc123\",\n    { thread_id: \"thread_abc123\" }\n  );\n\n  console.log(run);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"id\": \"run_abc123\",\n  \"object\": \"thread.run\",\n  \"created_at\": 1699075072,\n  \"assistant_id\": \"asst_abc123\",\n  \"thread_id\": \"thread_abc123\",\n  \"status\": \"completed\",\n  \"started_at\": 1699075072,\n  \"expires_at\": null,\n  \"cancelled_at\": null,\n  \"failed_at\": null,\n  \"completed_at\": 1699075073,\n  \"last_error\": null,\n  \"model\": \"gpt-5\",\n  \"instructions\": null,\n  \"incomplete_details\": null,\n  \"tools\": [\n    {\n      \"type\": \"code_interpreter\"\n    }\n  ],\n  \"metadata\": {},\n  \"usage\": {\n    \"prompt_tokens\": 123,\n    \"completion_tokens\": 456,\n    \"total_tokens\": 579\n  },\n  \"temperature\": 1.0,\n  \"top_p\": 1.0,\n  \"max_prompt_tokens\": 1000,\n  \"max_completion_tokens\": 1000,\n  \"truncation_strategy\": {\n    \"type\": \"auto\",\n    \"last_messages\": null\n  },\n  \"response_format\": \"auto\",\n  \"tool_choice\": \"auto\",\n  \"parallel_tool_calls\": true\n}\n"
+          }
+        }
+      },
+      "post": {
+        "operationId": "modifyRun",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Modifies a run.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "thread_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the [thread](https://developers.openai.com/api/docs/assistants/migration) that was run."
+          },
+          {
+            "in": "path",
+            "name": "run_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the run to modify."
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ModifyRunRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RunObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Modify run",
+          "group": "threads",
+          "beta": true,
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -d '{\n    \"metadata\": {\n      \"user_id\": \"user_abc123\"\n    }\n  }'\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nrun = client.beta.threads.runs.update(\n  thread_id=\"thread_abc123\",\n  run_id=\"run_abc123\",\n  metadata={\"user_id\": \"user_abc123\"},\n)\n\nprint(run)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const run = await openai.beta.threads.runs.update(\n    \"run_abc123\",\n    {\n      thread_id: \"thread_abc123\",\n      metadata: {\n        user_id: \"user_abc123\",\n      },\n    }\n  );\n\n  console.log(run);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"id\": \"run_abc123\",\n  \"object\": \"thread.run\",\n  \"created_at\": 1699075072,\n  \"assistant_id\": \"asst_abc123\",\n  \"thread_id\": \"thread_abc123\",\n  \"status\": \"completed\",\n  \"started_at\": 1699075072,\n  \"expires_at\": null,\n  \"cancelled_at\": null,\n  \"failed_at\": null,\n  \"completed_at\": 1699075073,\n  \"last_error\": null,\n  \"model\": \"gpt-5\",\n  \"instructions\": null,\n  \"incomplete_details\": null,\n  \"tools\": [\n    {\n      \"type\": \"code_interpreter\"\n    }\n  ],\n  \"tool_resources\": {\n    \"code_interpreter\": {\n      \"file_ids\": [\n        \"file-abc123\",\n        \"file-abc456\"\n      ]\n    }\n  },\n  \"metadata\": {\n    \"user_id\": \"user_abc123\"\n  },\n  \"usage\": {\n    \"prompt_tokens\": 123,\n    \"completion_tokens\": 456,\n    \"total_tokens\": 579\n  },\n  \"temperature\": 1.0,\n  \"top_p\": 1.0,\n  \"max_prompt_tokens\": 1000,\n  \"max_completion_tokens\": 1000,\n  \"truncation_strategy\": {\n    \"type\": \"auto\",\n    \"last_messages\": null\n  },\n  \"response_format\": \"auto\",\n  \"tool_choice\": \"auto\",\n  \"parallel_tool_calls\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/threads/{thread_id}/runs/{run_id}/cancel": {
+      "post": {
+        "operationId": "cancelRun",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Cancels a run that is `in_progress`.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "thread_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the thread to which this run belongs."
+          },
+          {
+            "in": "path",
+            "name": "run_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the run to cancel."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RunObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Cancel a run",
+          "group": "threads",
+          "beta": true,
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/cancel \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -X POST\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nrun = client.beta.threads.runs.cancel(\n  thread_id=\"thread_abc123\",\n  run_id=\"run_abc123\"\n)\n\nprint(run)\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const run = await openai.beta.threads.runs.cancel(\n    \"run_abc123\",\n    { thread_id: \"thread_abc123\" }\n  );\n\n  console.log(run);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"id\": \"run_abc123\",\n  \"object\": \"thread.run\",\n  \"created_at\": 1699076126,\n  \"assistant_id\": \"asst_abc123\",\n  \"thread_id\": \"thread_abc123\",\n  \"status\": \"cancelling\",\n  \"started_at\": 1699076126,\n  \"expires_at\": 1699076726,\n  \"cancelled_at\": null,\n  \"failed_at\": null,\n  \"completed_at\": null,\n  \"last_error\": null,\n  \"model\": \"gpt-5\",\n  \"instructions\": \"You summarize books.\",\n  \"tools\": [\n    {\n      \"type\": \"file_search\"\n    }\n  ],\n  \"tool_resources\": {\n    \"file_search\": {\n      \"vector_store_ids\": [\"vs_123\"]\n    }\n  },\n  \"metadata\": {},\n  \"usage\": null,\n  \"temperature\": 1.0,\n  \"top_p\": 1.0,\n  \"response_format\": \"auto\",\n  \"tool_choice\": \"auto\",\n  \"parallel_tool_calls\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/threads/{thread_id}/runs/{run_id}/steps": {
+      "get": {
+        "operationId": "listRunSteps",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Returns a list of run steps belonging to a run.",
+        "parameters": [
+          {
+            "name": "thread_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the thread the run and run steps belong to."
+          },
+          {
+            "name": "run_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the run the run steps belong to."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.\n",
+            "schema": {
+              "type": "string",
+              "default": "desc",
+              "enum": [
+                "asc",
+                "desc"
+              ]
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "before",
+            "in": "query",
+            "description": "A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.\n",
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "include[]",
+            "in": "query",
+            "description": "A list of additional fields to include in the response. Currently the only supported value is `step_details.tool_calls[*].file_search.results[*].content` to fetch the file search result content.\n\nSee the [file search tool documentation](https://developers.openai.com/api/docs/guides/tools-file-search#retrieval-customization) for more information.\n",
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "step_details.tool_calls[*].file_search.results[*].content"
+                ]
+              }
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ListRunStepsResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List run steps",
+          "group": "threads",
+          "beta": true,
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nrun_steps = client.beta.threads.runs.steps.list(\n    thread_id=\"thread_abc123\",\n    run_id=\"run_abc123\"\n)\n\nprint(run_steps)\n",
+              "javascript": "import OpenAI from \"openai\";\nconst openai = new OpenAI();\n\nasync function main() {\n  const runStep = await openai.beta.threads.runs.steps.list(\n    \"run_abc123\",\n    { thread_id: \"thread_abc123\" }\n  );\n  console.log(runStep);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"id\": \"step_abc123\",\n      \"object\": \"thread.run.step\",\n      \"created_at\": 1699063291,\n      \"run_id\": \"run_abc123\",\n      \"assistant_id\": \"asst_abc123\",\n      \"thread_id\": \"thread_abc123\",\n      \"type\": \"message_creation\",\n      \"status\": \"completed\",\n      \"cancelled_at\": null,\n      \"completed_at\": 1699063291,\n      \"expired_at\": null,\n      \"failed_at\": null,\n      \"last_error\": null,\n      \"step_details\": {\n        \"type\": \"message_creation\",\n        \"message_creation\": {\n          \"message_id\": \"msg_abc123\"\n        }\n      },\n      \"usage\": {\n        \"prompt_tokens\": 123,\n        \"completion_tokens\": 456,\n        \"total_tokens\": 579\n      }\n    }\n  ],\n  \"first_id\": \"step_abc123\",\n  \"last_id\": \"step_abc456\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      }
+    },
+    "/threads/{thread_id}/runs/{run_id}/steps/{step_id}": {
+      "get": {
+        "operationId": "getRunStep",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "Retrieves a run step.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "thread_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the thread to which the run and run step belongs."
+          },
+          {
+            "in": "path",
+            "name": "run_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the run to which the run step belongs."
+          },
+          {
+            "in": "path",
+            "name": "step_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the run step to retrieve."
+          },
+          {
+            "name": "include[]",
+            "in": "query",
+            "description": "A list of additional fields to include in the response. Currently the only supported value is `step_details.tool_calls[*].file_search.results[*].content` to fetch the file search result content.\n\nSee the [file search tool documentation](https://developers.openai.com/api/docs/guides/tools-file-search#retrieval-customization) for more information.\n",
+            "schema": {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "step_details.tool_calls[*].file_search.results[*].content"
+                ]
+              }
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RunStepObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve run step",
+          "group": "threads",
+          "beta": true,
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps/step_abc123 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nrun_step = client.beta.threads.runs.steps.retrieve(\n    thread_id=\"thread_abc123\",\n    run_id=\"run_abc123\",\n    step_id=\"step_abc123\"\n)\n\nprint(run_step)\n",
+              "javascript": "import OpenAI from \"openai\";\nconst openai = new OpenAI();\n\nasync function main() {\n  const runStep = await openai.beta.threads.runs.steps.retrieve(\n    \"step_abc123\",\n    { thread_id: \"thread_abc123\", run_id: \"run_abc123\" }\n  );\n  console.log(runStep);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"id\": \"step_abc123\",\n  \"object\": \"thread.run.step\",\n  \"created_at\": 1699063291,\n  \"run_id\": \"run_abc123\",\n  \"assistant_id\": \"asst_abc123\",\n  \"thread_id\": \"thread_abc123\",\n  \"type\": \"message_creation\",\n  \"status\": \"completed\",\n  \"cancelled_at\": null,\n  \"completed_at\": 1699063291,\n  \"expired_at\": null,\n  \"failed_at\": null,\n  \"last_error\": null,\n  \"step_details\": {\n    \"type\": \"message_creation\",\n    \"message_creation\": {\n      \"message_id\": \"msg_abc123\"\n    }\n  },\n  \"usage\": {\n    \"prompt_tokens\": 123,\n    \"completion_tokens\": 456,\n    \"total_tokens\": 579\n  }\n}\n"
+          }
+        }
+      }
+    },
+    "/threads/{thread_id}/runs/{run_id}/submit_tool_outputs": {
+      "post": {
+        "operationId": "submitToolOuputsToRun",
+        "tags": [
+          "Assistants"
+        ],
+        "summary": "When a run has the `status: \"requires_action\"` and `required_action.type` is `submit_tool_outputs`, this endpoint can be used to submit the outputs from the tool calls once they're all completed. All outputs must be submitted in a single request.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "thread_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the [thread](https://developers.openai.com/api/docs/assistants/migration) to which this run belongs."
+          },
+          {
+            "in": "path",
+            "name": "run_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the run that requires the tool output submission."
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/SubmitToolOutputsRunRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RunObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Submit tool outputs to run",
+          "group": "threads",
+          "beta": true,
+          "examples": [
+            {
+              "title": "Default",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/threads/thread_123/runs/run_123/submit_tool_outputs \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -d '{\n    \"tool_outputs\": [\n      {\n        \"tool_call_id\": \"call_001\",\n        \"output\": \"70 degrees and sunny.\"\n      }\n    ]\n  }'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\nrun = client.beta.threads.runs.submit_tool_outputs(\n  thread_id=\"thread_123\",\n  run_id=\"run_123\",\n  tool_outputs=[\n    {\n      \"tool_call_id\": \"call_001\",\n      \"output\": \"70 degrees and sunny.\"\n    }\n  ]\n)\n\nprint(run)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const run = await openai.beta.threads.runs.submitToolOutputs(\n    \"run_123\",\n    {\n      thread_id: \"thread_123\",\n      tool_outputs: [\n        {\n          tool_call_id: \"call_001\",\n          output: \"70 degrees and sunny.\",\n        },\n      ],\n    }\n  );\n\n  console.log(run);\n}\n\nmain();\n"
+              },
+              "response": "{\n  \"id\": \"run_123\",\n  \"object\": \"thread.run\",\n  \"created_at\": 1699075592,\n  \"assistant_id\": \"asst_123\",\n  \"thread_id\": \"thread_123\",\n  \"status\": \"queued\",\n  \"started_at\": 1699075592,\n  \"expires_at\": 1699076192,\n  \"cancelled_at\": null,\n  \"failed_at\": null,\n  \"completed_at\": null,\n  \"last_error\": null,\n  \"model\": \"gpt-5\",\n  \"instructions\": null,\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"get_current_weather\",\n        \"description\": \"Get the current weather in a given location\",\n        \"parameters\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"location\": {\n              \"type\": \"string\",\n              \"description\": \"The city and state, e.g. San Francisco, CA\"\n            },\n            \"unit\": {\n              \"type\": \"string\",\n              \"enum\": [\"celsius\", \"fahrenheit\"]\n            }\n          },\n          \"required\": [\"location\"]\n        }\n      }\n    }\n  ],\n  \"metadata\": {},\n  \"usage\": null,\n  \"temperature\": 1.0,\n  \"top_p\": 1.0,\n  \"max_prompt_tokens\": 1000,\n  \"max_completion_tokens\": 1000,\n  \"truncation_strategy\": {\n    \"type\": \"auto\",\n    \"last_messages\": null\n  },\n  \"response_format\": \"auto\",\n  \"tool_choice\": \"auto\",\n  \"parallel_tool_calls\": true\n}\n"
+            },
+            {
+              "title": "Streaming",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/threads/thread_123/runs/run_123/submit_tool_outputs \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -d '{\n    \"tool_outputs\": [\n      {\n        \"tool_call_id\": \"call_001\",\n        \"output\": \"70 degrees and sunny.\"\n      }\n    ],\n    \"stream\": true\n  }'\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\nstream = client.beta.threads.runs.submit_tool_outputs(\n  thread_id=\"thread_123\",\n  run_id=\"run_123\",\n  tool_outputs=[\n    {\n      \"tool_call_id\": \"call_001\",\n      \"output\": \"70 degrees and sunny.\"\n    }\n  ],\n  stream=True\n)\n\nfor event in stream:\n  print(event)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n  const stream = await openai.beta.threads.runs.submitToolOutputs(\n    \"run_123\",\n    {\n      thread_id: \"thread_123\",\n      tool_outputs: [\n        {\n          tool_call_id: \"call_001\",\n          output: \"70 degrees and sunny.\",\n        },\n      ],\n    }\n  );\n\n  for await (const event of stream) {\n    console.log(event);\n  }\n}\n\nmain();\n"
+              },
+              "response": "event: thread.run.step.completed\ndata: {\"id\":\"step_001\",\"object\":\"thread.run.step\",\"created_at\":1710352449,\"run_id\":\"run_123\",\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"type\":\"tool_calls\",\"status\":\"completed\",\"cancelled_at\":null,\"completed_at\":1710352475,\"expires_at\":1710353047,\"failed_at\":null,\"last_error\":null,\"step_details\":{\"type\":\"tool_calls\",\"tool_calls\":[{\"id\":\"call_iWr0kQ2EaYMaxNdl0v3KYkx7\",\"type\":\"function\",\"function\":{\"name\":\"get_current_weather\",\"arguments\":\"{\\\"location\\\":\\\"San Francisco, CA\\\",\\\"unit\\\":\\\"fahrenheit\\\"}\",\"output\":\"70 degrees and sunny.\"}}]},\"usage\":{\"prompt_tokens\":291,\"completion_tokens\":24,\"total_tokens\":315}}\n\nevent: thread.run.queued\ndata: {\"id\":\"run_123\",\"object\":\"thread.run\",\"created_at\":1710352447,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"status\":\"queued\",\"started_at\":1710352448,\"expires_at\":1710353047,\"cancelled_at\":null,\"failed_at\":null,\"completed_at\":null,\"required_action\":null,\"last_error\":null,\"model\":\"gpt-5\",\"instructions\":null,\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_current_weather\",\"description\":\"Get the current weather in a given location\",\"parameters\":{\"type\":\"object\",\"properties\":{\"location\":{\"type\":\"string\",\"description\":\"The city and state, e.g. San Francisco, CA\"},\"unit\":{\"type\":\"string\",\"enum\":[\"celsius\",\"fahrenheit\"]}},\"required\":[\"location\"]}}}],\"metadata\":{},\"temperature\":1.0,\"top_p\":1.0,\"max_completion_tokens\":null,\"max_prompt_tokens\":null,\"truncation_strategy\":{\"type\":\"auto\",\"last_messages\":null},\"incomplete_details\":null,\"usage\":null,\"response_format\":\"auto\",\"tool_choice\":\"auto\",\"parallel_tool_calls\":true}}\n\nevent: thread.run.in_progress\ndata: {\"id\":\"run_123\",\"object\":\"thread.run\",\"created_at\":1710352447,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"status\":\"in_progress\",\"started_at\":1710352475,\"expires_at\":1710353047,\"cancelled_at\":null,\"failed_at\":null,\"completed_at\":null,\"required_action\":null,\"last_error\":null,\"model\":\"gpt-5\",\"instructions\":null,\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_current_weather\",\"description\":\"Get the current weather in a given location\",\"parameters\":{\"type\":\"object\",\"properties\":{\"location\":{\"type\":\"string\",\"description\":\"The city and state, e.g. San Francisco, CA\"},\"unit\":{\"type\":\"string\",\"enum\":[\"celsius\",\"fahrenheit\"]}},\"required\":[\"location\"]}}}],\"metadata\":{},\"temperature\":1.0,\"top_p\":1.0,\"max_completion_tokens\":null,\"max_prompt_tokens\":null,\"truncation_strategy\":{\"type\":\"auto\",\"last_messages\":null},\"incomplete_details\":null,\"usage\":null,\"response_format\":\"auto\",\"tool_choice\":\"auto\",\"parallel_tool_calls\":true}}\n\nevent: thread.run.step.created\ndata: {\"id\":\"step_002\",\"object\":\"thread.run.step\",\"created_at\":1710352476,\"run_id\":\"run_123\",\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"type\":\"message_creation\",\"status\":\"in_progress\",\"cancelled_at\":null,\"completed_at\":null,\"expires_at\":1710353047,\"failed_at\":null,\"last_error\":null,\"step_details\":{\"type\":\"message_creation\",\"message_creation\":{\"message_id\":\"msg_002\"}},\"usage\":null}\n\nevent: thread.run.step.in_progress\ndata: {\"id\":\"step_002\",\"object\":\"thread.run.step\",\"created_at\":1710352476,\"run_id\":\"run_123\",\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"type\":\"message_creation\",\"status\":\"in_progress\",\"cancelled_at\":null,\"completed_at\":null,\"expires_at\":1710353047,\"failed_at\":null,\"last_error\":null,\"step_details\":{\"type\":\"message_creation\",\"message_creation\":{\"message_id\":\"msg_002\"}},\"usage\":null}\n\nevent: thread.message.created\ndata: {\"id\":\"msg_002\",\"object\":\"thread.message\",\"created_at\":1710352476,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"run_id\":\"run_123\",\"status\":\"in_progress\",\"incomplete_details\":null,\"incomplete_at\":null,\"completed_at\":null,\"role\":\"assistant\",\"content\":[],\"metadata\":{}}\n\nevent: thread.message.in_progress\ndata: {\"id\":\"msg_002\",\"object\":\"thread.message\",\"created_at\":1710352476,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"run_id\":\"run_123\",\"status\":\"in_progress\",\"incomplete_details\":null,\"incomplete_at\":null,\"completed_at\":null,\"role\":\"assistant\",\"content\":[],\"metadata\":{}}\n\nevent: thread.message.delta\ndata: {\"id\":\"msg_002\",\"object\":\"thread.message.delta\",\"delta\":{\"content\":[{\"index\":0,\"type\":\"text\",\"text\":{\"value\":\"The\",\"annotations\":[]}}]}}\n\nevent: thread.message.delta\ndata: {\"id\":\"msg_002\",\"object\":\"thread.message.delta\",\"delta\":{\"content\":[{\"index\":0,\"type\":\"text\",\"text\":{\"value\":\" current\"}}]}}\n\nevent: thread.message.delta\ndata: {\"id\":\"msg_002\",\"object\":\"thread.message.delta\",\"delta\":{\"content\":[{\"index\":0,\"type\":\"text\",\"text\":{\"value\":\" weather\"}}]}}\n\n...\n\nevent: thread.message.delta\ndata: {\"id\":\"msg_002\",\"object\":\"thread.message.delta\",\"delta\":{\"content\":[{\"index\":0,\"type\":\"text\",\"text\":{\"value\":\" sunny\"}}]}}\n\nevent: thread.message.delta\ndata: {\"id\":\"msg_002\",\"object\":\"thread.message.delta\",\"delta\":{\"content\":[{\"index\":0,\"type\":\"text\",\"text\":{\"value\":\".\"}}]}}\n\nevent: thread.message.completed\ndata: {\"id\":\"msg_002\",\"object\":\"thread.message\",\"created_at\":1710352476,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"run_id\":\"run_123\",\"status\":\"completed\",\"incomplete_details\":null,\"incomplete_at\":null,\"completed_at\":1710352477,\"role\":\"assistant\",\"content\":[{\"type\":\"text\",\"text\":{\"value\":\"The current weather in San Francisco, CA is 70 degrees Fahrenheit and sunny.\",\"annotations\":[]}}],\"metadata\":{}}\n\nevent: thread.run.step.completed\ndata: {\"id\":\"step_002\",\"object\":\"thread.run.step\",\"created_at\":1710352476,\"run_id\":\"run_123\",\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"type\":\"message_creation\",\"status\":\"completed\",\"cancelled_at\":null,\"completed_at\":1710352477,\"expires_at\":1710353047,\"failed_at\":null,\"last_error\":null,\"step_details\":{\"type\":\"message_creation\",\"message_creation\":{\"message_id\":\"msg_002\"}},\"usage\":{\"prompt_tokens\":329,\"completion_tokens\":18,\"total_tokens\":347}}\n\nevent: thread.run.completed\ndata: {\"id\":\"run_123\",\"object\":\"thread.run\",\"created_at\":1710352447,\"assistant_id\":\"asst_123\",\"thread_id\":\"thread_123\",\"status\":\"completed\",\"started_at\":1710352475,\"expires_at\":null,\"cancelled_at\":null,\"failed_at\":null,\"completed_at\":1710352477,\"required_action\":null,\"last_error\":null,\"model\":\"gpt-5\",\"instructions\":null,\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_current_weather\",\"description\":\"Get the current weather in a given location\",\"parameters\":{\"type\":\"object\",\"properties\":{\"location\":{\"type\":\"string\",\"description\":\"The city and state, e.g. San Francisco, CA\"},\"unit\":{\"type\":\"string\",\"enum\":[\"celsius\",\"fahrenheit\"]}},\"required\":[\"location\"]}}}],\"metadata\":{},\"temperature\":1.0,\"top_p\":1.0,\"max_completion_tokens\":null,\"max_prompt_tokens\":null,\"truncation_strategy\":{\"type\":\"auto\",\"last_messages\":null},\"incomplete_details\":null,\"usage\":{\"prompt_tokens\":20,\"completion_tokens\":11,\"total_tokens\":31},\"response_format\":\"auto\",\"tool_choice\":\"auto\",\"parallel_tool_calls\":true}}\n\nevent: done\ndata: [DONE]\n"
+            }
+          ]
+        }
+      }
+    },
+    "/uploads": {
+      "post": {
+        "operationId": "createUpload",
+        "tags": [
+          "Uploads"
+        ],
+        "summary": "Creates an intermediate [Upload](https://developers.openai.com/api/reference/resources/uploads) object\nthat you can add [Parts](https://developers.openai.com/api/reference/resources/uploads/subresources/parts) to.\nCurrently, an Upload can accept at most 8 GB in total and expires after an\nhour after you create it.\n\nOnce you complete the Upload, we will create a\n[File](https://developers.openai.com/api/reference/resources/files) object that contains all the parts\nyou uploaded. This File is usable in the rest of our platform as a regular\nFile object.\n\nFor certain `purpose` values, the correct `mime_type` must be specified.\nPlease refer to documentation for the\n[supported MIME types for your use case](https://developers.openai.com/api/docs/guides/tools-file-search#supported-files).\n\nFor guidance on the proper filename extensions for each purpose, please\nfollow the documentation on [creating a\nFile](https://developers.openai.com/api/reference/resources/files/methods/create).\n\nReturns the Upload object with status `pending`.\n",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateUploadRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Upload"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create upload",
+          "group": "uploads",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/uploads \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"purpose\": \"fine-tune\",\n    \"filename\": \"training_examples.jsonl\",\n    \"bytes\": 2147483648,\n    \"mime_type\": \"text/jsonl\",\n    \"expires_after\": {\n      \"anchor\": \"created_at\",\n      \"seconds\": 3600\n    }\n  }'\n"
+            },
+            "response": "{\n  \"id\": \"upload_abc123\",\n  \"object\": \"upload\",\n  \"bytes\": 2147483648,\n  \"created_at\": 1719184911,\n  \"filename\": \"training_examples.jsonl\",\n  \"purpose\": \"fine-tune\",\n  \"status\": \"pending\",\n  \"expires_at\": 1719127296\n}\n"
+          }
+        }
+      }
+    },
+    "/uploads/{upload_id}/cancel": {
+      "post": {
+        "operationId": "cancelUpload",
+        "tags": [
+          "Uploads"
+        ],
+        "summary": "Cancels the Upload. No Parts may be added after an Upload is cancelled.\n\nReturns the Upload object with status `cancelled`.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "upload_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "upload_abc123"
+            },
+            "description": "The ID of the Upload.\n"
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Upload"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Cancel upload",
+          "group": "uploads",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/uploads/upload_abc123/cancel\n"
+            },
+            "response": "{\n  \"id\": \"upload_abc123\",\n  \"object\": \"upload\",\n  \"bytes\": 2147483648,\n  \"created_at\": 1719184911,\n  \"filename\": \"training_examples.jsonl\",\n  \"purpose\": \"fine-tune\",\n  \"status\": \"cancelled\",\n  \"expires_at\": 1719127296\n}\n"
+          }
+        }
+      }
+    },
+    "/uploads/{upload_id}/complete": {
+      "post": {
+        "operationId": "completeUpload",
+        "tags": [
+          "Uploads"
+        ],
+        "summary": "Completes the [Upload](https://developers.openai.com/api/reference/resources/uploads).\n\nWithin the returned Upload object, there is a nested [File](https://developers.openai.com/api/reference/resources/files) object that is ready to use in the rest of the platform.\n\nYou can specify the order of the Parts by passing in an ordered list of the Part IDs.\n\nThe number of bytes uploaded upon completion must match the number of bytes initially specified when creating the Upload object. No Parts may be added after an Upload is completed.\nReturns the Upload object with status `completed`, including an additional `file` property containing the created usable File object.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "upload_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "upload_abc123"
+            },
+            "description": "The ID of the Upload.\n"
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CompleteUploadRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/Upload"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Complete upload",
+          "group": "uploads",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/uploads/upload_abc123/complete\n  -d '{\n    \"part_ids\": [\"part_def456\", \"part_ghi789\"]\n  }'\n"
+            },
+            "response": "{\n  \"id\": \"upload_abc123\",\n  \"object\": \"upload\",\n  \"bytes\": 2147483648,\n  \"created_at\": 1719184911,\n  \"filename\": \"training_examples.jsonl\",\n  \"purpose\": \"fine-tune\",\n  \"status\": \"completed\",\n  \"expires_at\": 1719127296,\n  \"file\": {\n    \"id\": \"file-xyz321\",\n    \"object\": \"file\",\n    \"bytes\": 2147483648,\n    \"created_at\": 1719186911,\n    \"expires_at\": 1719127296,\n    \"filename\": \"training_examples.jsonl\",\n    \"purpose\": \"fine-tune\",\n  }\n}\n"
+          }
+        }
+      }
+    },
+    "/uploads/{upload_id}/parts": {
+      "post": {
+        "operationId": "addUploadPart",
+        "tags": [
+          "Uploads"
+        ],
+        "summary": "Adds a [Part](https://developers.openai.com/api/reference/resources/uploads/subresources/parts) to an [Upload](https://developers.openai.com/api/reference/resources/uploads) object. A Part represents a chunk of bytes from the file you are trying to upload.\n\nEach Part can be at most 64 MB, and you can add Parts until you hit the Upload maximum of 8 GB.\n\nIt is possible to add multiple Parts in parallel. You can decide the intended order of the Parts when you [complete the Upload](https://developers.openai.com/api/reference/resources/uploads/methods/complete).\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "upload_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "upload_abc123"
+            },
+            "description": "The ID of the Upload.\n"
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/AddUploadPartRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/UploadPart"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Add upload part",
+          "group": "uploads",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/uploads/upload_abc123/parts\n  -F data=\"aHR0cHM6Ly9hcGkub3BlbmFpLmNvbS92MS91cGxvYWRz...\"\n"
+            },
+            "response": "{\n  \"id\": \"part_def456\",\n  \"object\": \"upload.part\",\n  \"created_at\": 1719185911,\n  \"upload_id\": \"upload_abc123\"\n}\n"
+          }
+        }
+      }
+    },
+    "/vector_stores": {
+      "get": {
+        "operationId": "listVectorStores",
+        "tags": [
+          "Vector stores"
+        ],
+        "summary": "Returns a list of vector stores.",
+        "parameters": [
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.\n",
+            "schema": {
+              "type": "string",
+              "default": "desc",
+              "enum": [
+                "asc",
+                "desc"
+              ]
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "before",
+            "in": "query",
+            "description": "A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.\n",
+            "schema": {
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ListVectorStoresResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List vector stores",
+          "group": "vector_stores",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/vector_stores \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nvector_stores = client.vector_stores.list()\nprint(vector_stores)\n",
+              "javascript": "import OpenAI from \"openai\";\nconst openai = new OpenAI();\n\nasync function main() {\n  const vectorStores = await openai.vectorStores.list();\n  console.log(vectorStores);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"id\": \"vs_abc123\",\n      \"object\": \"vector_store\",\n      \"created_at\": 1699061776,\n      \"name\": \"Support FAQ\",\n      \"description\": \"Contains commonly asked questions and answers, organized by topic.\",\n      \"bytes\": 139920,\n      \"file_counts\": {\n        \"in_progress\": 0,\n        \"completed\": 3,\n        \"failed\": 0,\n        \"cancelled\": 0,\n        \"total\": 3\n      }\n    },\n    {\n      \"id\": \"vs_abc456\",\n      \"object\": \"vector_store\",\n      \"created_at\": 1699061776,\n      \"name\": \"Support FAQ v2\",\n      \"description\": null,\n      \"bytes\": 139920,\n      \"file_counts\": {\n        \"in_progress\": 0,\n        \"completed\": 3,\n        \"failed\": 0,\n        \"cancelled\": 0,\n        \"total\": 3\n      }\n    }\n  ],\n  \"first_id\": \"vs_abc123\",\n  \"last_id\": \"vs_abc456\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      },
+      "post": {
+        "operationId": "createVectorStore",
+        "tags": [
+          "Vector stores"
+        ],
+        "summary": "Create a vector store.",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateVectorStoreRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VectorStoreObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create vector store",
+          "group": "vector_stores",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/vector_stores \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -d '{\n    \"name\": \"Support FAQ\"\n  }'\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nvector_store = client.vector_stores.create(\n  name=\"Support FAQ\"\n)\nprint(vector_store)\n",
+              "javascript": "import OpenAI from \"openai\";\nconst openai = new OpenAI();\n\nasync function main() {\n  const vectorStore = await openai.vectorStores.create({\n    name: \"Support FAQ\"\n  });\n  console.log(vectorStore);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"id\": \"vs_abc123\",\n  \"object\": \"vector_store\",\n  \"created_at\": 1699061776,\n  \"name\": \"Support FAQ\",\n  \"description\": \"Contains commonly asked questions and answers, organized by topic.\",\n  \"bytes\": 139920,\n  \"file_counts\": {\n    \"in_progress\": 0,\n    \"completed\": 3,\n    \"failed\": 0,\n    \"cancelled\": 0,\n    \"total\": 3\n  }\n}\n"
+          }
+        }
+      }
+    },
+    "/vector_stores/{vector_store_id}": {
+      "get": {
+        "operationId": "getVectorStore",
+        "tags": [
+          "Vector stores"
+        ],
+        "summary": "Retrieves a vector store.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "vector_store_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the vector store to retrieve."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VectorStoreObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve vector store",
+          "group": "vector_stores",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/vector_stores/vs_abc123 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nvector_store = client.vector_stores.retrieve(\n  vector_store_id=\"vs_abc123\"\n)\nprint(vector_store)\n",
+              "javascript": "import OpenAI from \"openai\";\nconst openai = new OpenAI();\n\nasync function main() {\n  const vectorStore = await openai.vectorStores.retrieve(\n    \"vs_abc123\"\n  );\n  console.log(vectorStore);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"id\": \"vs_abc123\",\n  \"object\": \"vector_store\",\n  \"created_at\": 1699061776\n}\n"
+          }
+        }
+      },
+      "post": {
+        "operationId": "modifyVectorStore",
+        "tags": [
+          "Vector stores"
+        ],
+        "summary": "Modifies a vector store.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "vector_store_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the vector store to modify."
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/UpdateVectorStoreRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VectorStoreObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Modify vector store",
+          "group": "vector_stores",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/vector_stores/vs_abc123 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\"\n  -d '{\n    \"name\": \"Support FAQ\"\n  }'\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nvector_store = client.vector_stores.update(\n  vector_store_id=\"vs_abc123\",\n  name=\"Support FAQ\"\n)\nprint(vector_store)\n",
+              "javascript": "import OpenAI from \"openai\";\nconst openai = new OpenAI();\n\nasync function main() {\n  const vectorStore = await openai.vectorStores.update(\n    \"vs_abc123\",\n    {\n      name: \"Support FAQ\"\n    }\n  );\n  console.log(vectorStore);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"id\": \"vs_abc123\",\n  \"object\": \"vector_store\",\n  \"created_at\": 1699061776,\n  \"name\": \"Support FAQ\",\n  \"description\": \"Contains commonly asked questions and answers, organized by topic.\",\n  \"bytes\": 139920,\n  \"file_counts\": {\n    \"in_progress\": 0,\n    \"completed\": 3,\n    \"failed\": 0,\n    \"cancelled\": 0,\n    \"total\": 3\n  }\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "operationId": "deleteVectorStore",
+        "tags": [
+          "Vector stores"
+        ],
+        "summary": "Delete a vector store.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "vector_store_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the vector store to delete."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeleteVectorStoreResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete vector store",
+          "group": "vector_stores",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/vector_stores/vs_abc123 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -X DELETE\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\ndeleted_vector_store = client.vector_stores.delete(\n  vector_store_id=\"vs_abc123\"\n)\nprint(deleted_vector_store)\n",
+              "javascript": "import OpenAI from \"openai\";\nconst openai = new OpenAI();\n\nasync function main() {\n  const deletedVectorStore = await openai.vectorStores.delete(\n    \"vs_abc123\"\n  );\n  console.log(deletedVectorStore);\n}\n\nmain();\n"
+            },
+            "response": "{\n  id: \"vs_abc123\",\n  object: \"vector_store.deleted\",\n  deleted: true\n}\n"
+          }
+        }
+      }
+    },
+    "/vector_stores/{vector_store_id}/file_batches": {
+      "post": {
+        "operationId": "createVectorStoreFileBatch",
+        "tags": [
+          "Vector stores"
+        ],
+        "summary": "Create a vector store file batch.",
+        "description": "The maximum number of files in a single batch request is 2000.\nVector store file attach requests are rate limited per vector store (300 requests per minute across both this endpoint and `/vector_stores/{vector_store_id}/files`).\nFor ingesting multiple files into the same vector store, this batch endpoint is recommended.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "vector_store_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "vs_abc123"
+            },
+            "description": "The ID of the vector store for which to create a File Batch.\n"
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateVectorStoreFileBatchRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VectorStoreFileBatchObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create vector store file batch",
+          "group": "vector_stores",
+          "description": "Attaches multiple files to a vector store in one request. This is the recommended approach for multi-file ingestion, especially because per-vector-store file attach writes are rate-limited (300 requests/minute shared with `/vector_stores/{vector_store_id}/files`).\n",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/vector_stores/vs_abc123/file_batches \\\n    -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n    -H \"Content-Type: application/json \\\n    -H \"OpenAI-Beta: assistants=v2\" \\\n    -d '{\n      \"files\": [\n        {\n          \"file_id\": \"file-abc123\",\n          \"attributes\": {\"category\": \"finance\"}\n        },\n        {\n          \"file_id\": \"file-abc456\",\n          \"chunking_strategy\": {\n            \"type\": \"static\",\n            \"max_chunk_size_tokens\": 1200,\n            \"chunk_overlap_tokens\": 200\n          }\n        }\n      ]\n    }'\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nvector_store_file_batch = client.vector_stores.file_batches.create(\n  vector_store_id=\"vs_abc123\",\n  files=[\n    {\n      \"file_id\": \"file-abc123\",\n      \"attributes\": {\"category\": \"finance\"},\n    },\n    {\n      \"file_id\": \"file-abc456\",\n      \"chunking_strategy\": {\n        \"type\": \"static\",\n        \"max_chunk_size_tokens\": 1200,\n        \"chunk_overlap_tokens\": 200,\n      },\n    },\n  ],\n)\nprint(vector_store_file_batch)\n",
+              "javascript": "import OpenAI from \"openai\";\nconst openai = new OpenAI();\n\nasync function main() {\n  const myVectorStoreFileBatch = await openai.vectorStores.fileBatches.create(\n    \"vs_abc123\",\n    {\n      files: [\n        {\n          file_id: \"file-abc123\",\n          attributes: { category: \"finance\" },\n        },\n        {\n          file_id: \"file-abc456\",\n          chunking_strategy: {\n            type: \"static\",\n            max_chunk_size_tokens: 1200,\n            chunk_overlap_tokens: 200,\n          },\n        },\n      ]\n    }\n  );\n  console.log(myVectorStoreFileBatch);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"id\": \"vsfb_abc123\",\n  \"object\": \"vector_store.file_batch\",\n  \"created_at\": 1699061776,\n  \"vector_store_id\": \"vs_abc123\",\n  \"status\": \"in_progress\",\n  \"file_counts\": {\n    \"in_progress\": 1,\n    \"completed\": 1,\n    \"failed\": 0,\n    \"cancelled\": 0,\n    \"total\": 0,\n  }\n}\n"
+          }
+        }
+      }
+    },
+    "/vector_stores/{vector_store_id}/file_batches/{batch_id}": {
+      "get": {
+        "operationId": "getVectorStoreFileBatch",
+        "tags": [
+          "Vector stores"
+        ],
+        "summary": "Retrieves a vector store file batch.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "vector_store_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "vs_abc123"
+            },
+            "description": "The ID of the vector store that the file batch belongs to."
+          },
+          {
+            "in": "path",
+            "name": "batch_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "vsfb_abc123"
+            },
+            "description": "The ID of the file batch being retrieved."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VectorStoreFileBatchObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve vector store file batch",
+          "group": "vector_stores",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/vector_stores/vs_abc123/file_batches/vsfb_abc123 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nvector_store_file_batch = client.vector_stores.file_batches.retrieve(\n  vector_store_id=\"vs_abc123\",\n  batch_id=\"vsfb_abc123\"\n)\nprint(vector_store_file_batch)\n",
+              "javascript": "import OpenAI from \"openai\";\nconst openai = new OpenAI();\n\nasync function main() {\n  const vectorStoreFileBatch = await openai.vectorStores.fileBatches.retrieve(\n    \"vsfb_abc123\",\n    { vector_store_id: \"vs_abc123\" }\n  );\n  console.log(vectorStoreFileBatch);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"id\": \"vsfb_abc123\",\n  \"object\": \"vector_store.file_batch\",\n  \"created_at\": 1699061776,\n  \"vector_store_id\": \"vs_abc123\",\n  \"status\": \"in_progress\",\n  \"file_counts\": {\n    \"in_progress\": 1,\n    \"completed\": 1,\n    \"failed\": 0,\n    \"cancelled\": 0,\n    \"total\": 0,\n  }\n}\n"
+          }
+        }
+      }
+    },
+    "/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel": {
+      "post": {
+        "operationId": "cancelVectorStoreFileBatch",
+        "tags": [
+          "Vector stores"
+        ],
+        "summary": "Cancel a vector store file batch. This attempts to cancel the processing of files in this batch as soon as possible.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "vector_store_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the vector store that the file batch belongs to."
+          },
+          {
+            "in": "path",
+            "name": "batch_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the file batch to cancel."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VectorStoreFileBatchObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Cancel vector store file batch",
+          "group": "vector_stores",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/vector_stores/vs_abc123/files_batches/vsfb_abc123/cancel \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -X POST\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\ndeleted_vector_store_file_batch = client.vector_stores.file_batches.cancel(\n    vector_store_id=\"vs_abc123\",\n    file_batch_id=\"vsfb_abc123\"\n)\nprint(deleted_vector_store_file_batch)\n",
+              "javascript": "import OpenAI from \"openai\";\nconst openai = new OpenAI();\n\nasync function main() {\n  const deletedVectorStoreFileBatch = await openai.vectorStores.fileBatches.cancel(\n    \"vsfb_abc123\",\n    { vector_store_id: \"vs_abc123\" }\n  );\n  console.log(deletedVectorStoreFileBatch);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"id\": \"vsfb_abc123\",\n  \"object\": \"vector_store.file_batch\",\n  \"created_at\": 1699061776,\n  \"vector_store_id\": \"vs_abc123\",\n  \"status\": \"in_progress\",\n  \"file_counts\": {\n    \"in_progress\": 12,\n    \"completed\": 3,\n    \"failed\": 0,\n    \"cancelled\": 0,\n    \"total\": 15,\n  }\n}\n"
+          }
+        }
+      }
+    },
+    "/vector_stores/{vector_store_id}/file_batches/{batch_id}/files": {
+      "get": {
+        "operationId": "listFilesInVectorStoreBatch",
+        "tags": [
+          "Vector stores"
+        ],
+        "summary": "Returns a list of vector store files in a batch.",
+        "parameters": [
+          {
+            "name": "vector_store_id",
+            "in": "path",
+            "description": "The ID of the vector store that the files belong to.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "batch_id",
+            "in": "path",
+            "description": "The ID of the file batch that the files belong to.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.\n",
+            "schema": {
+              "type": "string",
+              "default": "desc",
+              "enum": [
+                "asc",
+                "desc"
+              ]
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "before",
+            "in": "query",
+            "description": "A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.\n",
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "filter",
+            "in": "query",
+            "description": "Filter by file status. One of `in_progress`, `completed`, `failed`, `cancelled`.",
+            "schema": {
+              "type": "string",
+              "enum": [
+                "in_progress",
+                "completed",
+                "failed",
+                "cancelled"
+              ]
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ListVectorStoreFilesResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List vector store files in a batch",
+          "group": "vector_stores",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/vector_stores/vs_abc123/files_batches/vsfb_abc123/files \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nvector_store_files = client.vector_stores.file_batches.list_files(\n  vector_store_id=\"vs_abc123\",\n  batch_id=\"vsfb_abc123\"\n)\nprint(vector_store_files)\n",
+              "javascript": "import OpenAI from \"openai\";\nconst openai = new OpenAI();\n\nasync function main() {\n  const vectorStoreFiles = await openai.vectorStores.fileBatches.listFiles(\n    \"vsfb_abc123\",\n    { vector_store_id: \"vs_abc123\" }\n  );\n  console.log(vectorStoreFiles);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"id\": \"file-abc123\",\n      \"object\": \"vector_store.file\",\n      \"created_at\": 1699061776,\n      \"vector_store_id\": \"vs_abc123\"\n    },\n    {\n      \"id\": \"file-abc456\",\n      \"object\": \"vector_store.file\",\n      \"created_at\": 1699061776,\n      \"vector_store_id\": \"vs_abc123\"\n    }\n  ],\n  \"first_id\": \"file-abc123\",\n  \"last_id\": \"file-abc456\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      }
+    },
+    "/vector_stores/{vector_store_id}/files": {
+      "get": {
+        "operationId": "listVectorStoreFiles",
+        "tags": [
+          "Vector stores"
+        ],
+        "summary": "Returns a list of vector store files.",
+        "parameters": [
+          {
+            "name": "vector_store_id",
+            "in": "path",
+            "description": "The ID of the vector store that the files belong to.",
+            "required": true,
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.\n",
+            "schema": {
+              "type": "string",
+              "default": "desc",
+              "enum": [
+                "asc",
+                "desc"
+              ]
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list.\n",
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "before",
+            "in": "query",
+            "description": "A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, starting with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list.\n",
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "name": "filter",
+            "in": "query",
+            "description": "Filter by file status. One of `in_progress`, `completed`, `failed`, `cancelled`.",
+            "schema": {
+              "type": "string",
+              "enum": [
+                "in_progress",
+                "completed",
+                "failed",
+                "cancelled"
+              ]
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ListVectorStoreFilesResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List vector store files",
+          "group": "vector_stores",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/vector_stores/vs_abc123/files \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nvector_store_files = client.vector_stores.files.list(\n  vector_store_id=\"vs_abc123\"\n)\nprint(vector_store_files)\n",
+              "javascript": "import OpenAI from \"openai\";\nconst openai = new OpenAI();\n\nasync function main() {\n  const vectorStoreFiles = await openai.vectorStores.files.list(\n    \"vs_abc123\"\n  );\n  console.log(vectorStoreFiles);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"id\": \"file-abc123\",\n      \"object\": \"vector_store.file\",\n      \"created_at\": 1699061776,\n      \"vector_store_id\": \"vs_abc123\"\n    },\n    {\n      \"id\": \"file-abc456\",\n      \"object\": \"vector_store.file\",\n      \"created_at\": 1699061776,\n      \"vector_store_id\": \"vs_abc123\"\n    }\n  ],\n  \"first_id\": \"file-abc123\",\n  \"last_id\": \"file-abc456\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      },
+      "post": {
+        "operationId": "createVectorStoreFile",
+        "tags": [
+          "Vector stores"
+        ],
+        "summary": "Create a vector store file by attaching a [File](https://developers.openai.com/api/reference/resources/files) to a [vector store](https://developers.openai.com/api/reference/resources/vector_stores).",
+        "description": "This endpoint is subject to a per-vector-store write rate limit of 300 requests per minute, shared with `/vector_stores/{vector_store_id}/file_batches`.\nFor uploading multiple files to the same vector store, use the file batches endpoint to reduce request volume.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "vector_store_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "vs_abc123"
+            },
+            "description": "The ID of the vector store for which to create a File.\n"
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateVectorStoreFileRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VectorStoreFileObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create vector store file",
+          "group": "vector_stores",
+          "description": "Attaches one file to a vector store. File attach writes are rate-limited per vector store (300 requests/minute shared with `/vector_stores/{vector_store_id}/file_batches`), so use file batches when uploading multiple files.\n",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/vector_stores/vs_abc123/files \\\n    -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n    -H \"Content-Type: application/json\" \\\n    -H \"OpenAI-Beta: assistants=v2\" \\\n    -d '{\n      \"file_id\": \"file-abc123\"\n    }'\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nvector_store_file = client.vector_stores.files.create(\n  vector_store_id=\"vs_abc123\",\n  file_id=\"file-abc123\"\n)\nprint(vector_store_file)\n",
+              "javascript": "import OpenAI from \"openai\";\nconst openai = new OpenAI();\n\nasync function main() {\n  const myVectorStoreFile = await openai.vectorStores.files.create(\n    \"vs_abc123\",\n    {\n      file_id: \"file-abc123\"\n    }\n  );\n  console.log(myVectorStoreFile);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"id\": \"file-abc123\",\n  \"object\": \"vector_store.file\",\n  \"created_at\": 1699061776,\n  \"usage_bytes\": 1234,\n  \"vector_store_id\": \"vs_abcd\",\n  \"status\": \"completed\",\n  \"last_error\": null\n}\n"
+          }
+        }
+      }
+    },
+    "/vector_stores/{vector_store_id}/files/{file_id}": {
+      "get": {
+        "operationId": "getVectorStoreFile",
+        "tags": [
+          "Vector stores"
+        ],
+        "summary": "Retrieves a vector store file.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "vector_store_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "vs_abc123"
+            },
+            "description": "The ID of the vector store that the file belongs to."
+          },
+          {
+            "in": "path",
+            "name": "file_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "file-abc123"
+            },
+            "description": "The ID of the file being retrieved."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VectorStoreFileObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve vector store file",
+          "group": "vector_stores",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/vector_stores/vs_abc123/files/file-abc123 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\"\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nvector_store_file = client.vector_stores.files.retrieve(\n  vector_store_id=\"vs_abc123\",\n  file_id=\"file-abc123\"\n)\nprint(vector_store_file)\n",
+              "javascript": "import OpenAI from \"openai\";\nconst openai = new OpenAI();\n\nasync function main() {\n  const vectorStoreFile = await openai.vectorStores.files.retrieve(\n    \"file-abc123\",\n    { vector_store_id: \"vs_abc123\" }\n  );\n  console.log(vectorStoreFile);\n}\n\nmain();\n"
+            },
+            "response": "{\n  \"id\": \"file-abc123\",\n  \"object\": \"vector_store.file\",\n  \"created_at\": 1699061776,\n  \"vector_store_id\": \"vs_abcd\",\n  \"status\": \"completed\",\n  \"last_error\": null\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "operationId": "deleteVectorStoreFile",
+        "tags": [
+          "Vector stores"
+        ],
+        "summary": "Delete a vector store file. This will remove the file from the vector store but the file itself will not be deleted. To delete the file, use the [delete file](https://developers.openai.com/api/reference/resources/files/methods/delete) endpoint.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "vector_store_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the vector store that the file belongs to."
+          },
+          {
+            "in": "path",
+            "name": "file_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the file to delete."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeleteVectorStoreFileResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete vector store file",
+          "group": "vector_stores",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/vector_stores/vs_abc123/files/file-abc123 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"OpenAI-Beta: assistants=v2\" \\\n  -X DELETE\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\ndeleted_vector_store_file = client.vector_stores.files.delete(\n    vector_store_id=\"vs_abc123\",\n    file_id=\"file-abc123\"\n)\nprint(deleted_vector_store_file)\n",
+              "javascript": "import OpenAI from \"openai\";\nconst openai = new OpenAI();\n\nasync function main() {\n  const deletedVectorStoreFile = await openai.vectorStores.files.delete(\n    \"file-abc123\",\n    { vector_store_id: \"vs_abc123\" }\n  );\n  console.log(deletedVectorStoreFile);\n}\n\nmain();\n"
+            },
+            "response": "{\n  id: \"file-abc123\",\n  object: \"vector_store.file.deleted\",\n  deleted: true\n}\n"
+          }
+        }
+      },
+      "post": {
+        "operationId": "updateVectorStoreFileAttributes",
+        "tags": [
+          "Vector stores"
+        ],
+        "summary": "Update attributes on a vector store file.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "vector_store_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "vs_abc123"
+            },
+            "description": "The ID of the vector store the file belongs to."
+          },
+          {
+            "in": "path",
+            "name": "file_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "file-abc123"
+            },
+            "description": "The ID of the file to update attributes."
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/UpdateVectorStoreFileAttributesRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VectorStoreFileObject"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update vector store file attributes",
+          "group": "vector_stores",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/vector_stores/{vector_store_id}/files/{file_id} \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"attributes\": {\"key1\": \"value1\", \"key2\": 2}}'\n"
+            },
+            "response": "{\n  \"id\": \"file-abc123\",\n  \"object\": \"vector_store.file\",\n  \"usage_bytes\": 1234,\n  \"created_at\": 1699061776,\n  \"vector_store_id\": \"vs_abcd\",\n  \"status\": \"completed\",\n  \"last_error\": null,\n  \"chunking_strategy\": {...},\n  \"attributes\": {\"key1\": \"value1\", \"key2\": 2}\n}\n"
+          }
+        }
+      }
+    },
+    "/vector_stores/{vector_store_id}/files/{file_id}/content": {
+      "get": {
+        "operationId": "retrieveVectorStoreFileContent",
+        "tags": [
+          "Vector stores"
+        ],
+        "summary": "Retrieve the parsed contents of a vector store file.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "vector_store_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "vs_abc123"
+            },
+            "description": "The ID of the vector store."
+          },
+          {
+            "in": "path",
+            "name": "file_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "file-abc123"
+            },
+            "description": "The ID of the file within the vector store."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VectorStoreFileContentResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve vector store file content",
+          "group": "vector_stores",
+          "examples": {
+            "request": {
+              "curl": "curl \\\nhttps://api.openai.com/v1/vector_stores/vs_abc123/files/file-abc123/content \\\n-H \"Authorization: Bearer $OPENAI_API_KEY\"\n"
+            },
+            "response": "{\n  \"file_id\": \"file-abc123\",\n  \"filename\": \"example.txt\",\n  \"attributes\": {\"key\": \"value\"},\n  \"content\": [\n    {\"type\": \"text\", \"text\": \"...\"},\n    ...\n  ]\n}\n"
+          }
+        }
+      }
+    },
+    "/vector_stores/{vector_store_id}/search": {
+      "post": {
+        "operationId": "searchVectorStore",
+        "tags": [
+          "Vector stores"
+        ],
+        "summary": "Search a vector store for relevant chunks based on a query and file attributes filter.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "vector_store_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "vs_abc123"
+            },
+            "description": "The ID of the vector store to search."
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/VectorStoreSearchRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VectorStoreSearchResultsPage"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Search vector store",
+          "group": "vector_stores",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST \\\nhttps://api.openai.com/v1/vector_stores/vs_abc123/search \\\n-H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n-H \"Content-Type: application/json\" \\\n-d '{\"query\": \"What is the return policy?\", \"filters\": {...}}'\n"
+            },
+            "response": "{\n  \"object\": \"vector_store.search_results.page\",\n  \"search_query\": \"What is the return policy?\",\n  \"data\": [\n    {\n      \"file_id\": \"file_123\",\n      \"filename\": \"document.pdf\",\n      \"score\": 0.95,\n      \"attributes\": {\n        \"author\": \"John Doe\",\n        \"date\": \"2023-01-01\"\n      },\n      \"content\": [\n        {\n          \"type\": \"text\",\n          \"text\": \"Relevant chunk\"\n        }\n      ]\n    },\n    {\n      \"file_id\": \"file_456\",\n      \"filename\": \"notes.txt\",\n      \"score\": 0.89,\n      \"attributes\": {\n        \"author\": \"Jane Smith\",\n        \"date\": \"2023-01-02\"\n      },\n      \"content\": [\n        {\n          \"type\": \"text\",\n          \"text\": \"Sample text content from the vector store.\"\n        }\n      ]\n    }\n  ],\n  \"has_more\": false,\n  \"next_page\": null\n}\n"
+          }
+        }
+      }
+    },
+    "/conversations": {
+      "post": {
+        "tags": [
+          "Conversations"
+        ],
+        "summary": "Create a conversation.",
+        "operationId": "createConversation",
+        "parameters": [],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateConversationBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ConversationResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create a conversation",
+          "group": "conversations",
+          "path": "create",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/conversations \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"metadata\": {\"topic\": \"demo\"},\n    \"items\": [\n      {\n        \"type\": \"message\",\n        \"role\": \"user\",\n        \"content\": \"Hello!\"\n      }\n    ]\n  }'\n",
+              "javascript": "import OpenAI from \"openai\";\nconst client = new OpenAI();\n\nconst conversation = await client.conversations.create({\n  metadata: { topic: \"demo\" },\n  items: [\n    { type: \"message\", role: \"user\", content: \"Hello!\" }\n  ],\n});\nconsole.log(conversation);\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nconversation = client.conversations.create(\n  metadata={\"topic\": \"demo\"},\n  items=[\n    {\"type\": \"message\", \"role\": \"user\", \"content\": \"Hello!\"}\n  ]\n)\nprint(conversation)\n",
+              "csharp": "using System;\nusing System.Collections.Generic;\nusing OpenAI.Conversations;\n\nOpenAIConversationClient client = new(\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nConversation conversation = client.CreateConversation(\n    new CreateConversationOptions\n    {\n        Metadata = new Dictionary<string, string>\n        {\n            { \"topic\", \"demo\" }\n        },\n        Items =\n        {\n            new ConversationMessageInput\n            {\n                Role = \"user\",\n                Content = \"Hello!\",\n            }\n        }\n    }\n);\nConsole.WriteLine(conversation.Id);\n"
+            },
+            "response": "{\n  \"id\": \"conv_123\",\n  \"object\": \"conversation\",\n  \"created_at\": 1741900000,\n  \"metadata\": {\"topic\": \"demo\"}\n}\n"
+          }
+        }
+      }
+    },
+    "/conversations/{conversation_id}": {
+      "get": {
+        "tags": [
+          "Conversations"
+        ],
+        "summary": "Get a conversation",
+        "operationId": "getConversation",
+        "parameters": [
+          {
+            "name": "conversation_id",
+            "in": "path",
+            "description": "The ID of the conversation to retrieve.",
+            "required": true,
+            "schema": {
+              "example": "conv_123",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ConversationResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve a conversation",
+          "group": "conversations",
+          "path": "retrieve",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/conversations/conv_123 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "javascript": "import OpenAI from \"openai\";\nconst client = new OpenAI();\n\nconst conversation = await client.conversations.retrieve(\"conv_123\");\nconsole.log(conversation);\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nconversation = client.conversations.retrieve(\"conv_123\")\nprint(conversation)\n",
+              "csharp": "using System;\nusing OpenAI.Conversations;\n\nOpenAIConversationClient client = new(\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nConversation conversation = client.GetConversation(\"conv_123\");\nConsole.WriteLine(conversation.Id);\n"
+            },
+            "response": "{\n  \"id\": \"conv_123\",\n  \"object\": \"conversation\",\n  \"created_at\": 1741900000,\n  \"metadata\": {\"topic\": \"demo\"}\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "tags": [
+          "Conversations"
+        ],
+        "summary": "Delete a conversation. Items in the conversation will not be deleted.",
+        "operationId": "deleteConversation",
+        "parameters": [
+          {
+            "name": "conversation_id",
+            "in": "path",
+            "description": "The ID of the conversation to delete.",
+            "required": true,
+            "schema": {
+              "example": "conv_123",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedConversationResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete a conversation",
+          "group": "conversations",
+          "path": "delete",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/conversations/conv_123 \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "javascript": "import OpenAI from \"openai\";\nconst client = new OpenAI();\n\nconst deleted = await client.conversations.delete(\"conv_123\");\nconsole.log(deleted);\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\ndeleted = client.conversations.delete(\"conv_123\")\nprint(deleted)\n",
+              "csharp": "using System;\nusing OpenAI.Conversations;\n\nOpenAIConversationClient client = new(\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nDeletedConversation deleted = client.DeleteConversation(\"conv_123\");\nConsole.WriteLine(deleted.Id);\n"
+            },
+            "response": "{\n  \"id\": \"conv_123\",\n  \"object\": \"conversation.deleted\",\n  \"deleted\": true\n}\n"
+          }
+        }
+      },
+      "post": {
+        "tags": [
+          "Conversations"
+        ],
+        "summary": "Update a conversation",
+        "operationId": "updateConversation",
+        "parameters": [
+          {
+            "name": "conversation_id",
+            "in": "path",
+            "description": "The ID of the conversation to update.",
+            "required": true,
+            "schema": {
+              "example": "conv_123",
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/UpdateConversationBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ConversationResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update a conversation",
+          "group": "conversations",
+          "path": "update",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/conversations/conv_123 \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"metadata\": {\"topic\": \"project-x\"}\n  }'\n",
+              "javascript": "import OpenAI from \"openai\";\nconst client = new OpenAI();\n\nconst updated = await client.conversations.update(\n  \"conv_123\",\n  { metadata: { topic: \"project-x\" } }\n);\nconsole.log(updated);\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nupdated = client.conversations.update(\n  \"conv_123\",\n  metadata={\"topic\": \"project-x\"}\n)\nprint(updated)\n",
+              "csharp": "using System;\nusing System.Collections.Generic;\nusing OpenAI.Conversations;\n\nOpenAIConversationClient client = new(\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nConversation updated = client.UpdateConversation(\n    conversationId: \"conv_123\",\n    new UpdateConversationOptions\n    {\n        Metadata = new Dictionary<string, string>\n        {\n            { \"topic\", \"project-x\" }\n        }\n    }\n);\nConsole.WriteLine(updated.Id);\n"
+            },
+            "response": "{\n  \"id\": \"conv_123\",\n  \"object\": \"conversation\",\n  \"created_at\": 1741900000,\n  \"metadata\": {\"topic\": \"project-x\"}\n}\n"
+          }
+        }
+      }
+    },
+    "/safety/alerts/{id}": {
+      "get": {
+        "summary": "Get a safety alert belonging to the authenticated API project.",
+        "operationId": "Getprojectsafetyalert",
+        "parameters": [
+          {
+            "name": "id",
+            "in": "path",
+            "description": "Project safety alert ID",
+            "required": true,
+            "schema": {
+              "description": "Project safety alert ID",
+              "type": "string",
+              "maxLength": 38
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SafetyAlertResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve a safety alert",
+          "group": "safety-alerts",
+          "path": "retrieve",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/safety/alerts/alert_0123456789abcdef0123456789abcdef \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n"
+            },
+            "response": "{\n  \"id\": \"alert_0123456789abcdef0123456789abcdef\",\n  \"object\": \"safety.alert\",\n  \"created_at\": 1787659200,\n  \"request_id\": \"req_123\",\n  \"response_id\": \"resp_123\",\n  \"model\": \"gpt-6-astra\",\n  \"request_paused\": true,\n  \"error_type\": \"potentially_unintended_data_access\",\n  \"reason\": \"Potentially unintended data access.\"\n}\n"
+          }
+        }
+      }
+    },
+    "/live/sessions/{session_id}/content": {
+      "get": {
+        "tags": [
+          "Live"
+        ],
+        "summary": "Get Live session content",
+        "description": "Download stored session audio as stereo WAV: input left, output right.",
+        "operationId": "download-live-recording",
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "description": "The ID of the stored Live session to download. Use the session ID returned when the session started with storage enabled.",
+            "required": true,
+            "schema": {
+              "description": "The ID of the stored Live session to download. Use the session ID returned when the session started with storage enabled.",
+              "type": "string",
+              "pattern": "^live_[A-Za-z0-9_-]{1,128}$"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Stored session recording. Input audio is in the left channel and output audio is in the right channel.",
+            "content": {
+              "audio/wav": {
+                "schema": {
+                  "description": "The Live session recording as a stereo WAV file, with input audio in the left channel and output audio in the right channel.",
+                  "type": "string",
+                  "format": "binary"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Download recording",
+          "group": "live",
+          "returns": "The stored session recording as binary stereo WAV audio."
+        }
+      }
+    },
+    "/organization/spend_limit": {
+      "get": {
+        "summary": "Get the organization's hard spend limit.",
+        "operationId": "Getorganizationspendlimit",
+        "parameters": [],
+        "responses": {
+          "200": {
+            "description": "Hard spend limit retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/OrganizationSpendLimitResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve organization spend limit",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/spend_limit \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"organization.spend_limit\",\n    \"threshold_amount\": 10000,\n    \"currency\": \"USD\",\n    \"interval\": \"month\",\n    \"enforcement\": {\n        \"status\": \"enforcing\"\n    }\n}\n"
+          }
+        },
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ]
+      },
+      "post": {
+        "summary": "Create or replace the organization's hard spend limit.",
+        "operationId": "Updateorganizationspendlimit",
+        "parameters": [],
+        "requestBody": {
+          "description": "Parameters for the hard spend limit you want to create or replace.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/UpdateOrganizationSpendLimitBody"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "200": {
+            "description": "Hard spend limit created or replaced successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/OrganizationSpendLimitResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update organization spend limit",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/spend_limit \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"threshold_amount\": 10000,\n      \"currency\": \"USD\",\n      \"interval\": \"month\"\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"organization.spend_limit\",\n    \"threshold_amount\": 10000,\n    \"currency\": \"USD\",\n    \"interval\": \"month\",\n    \"enforcement\": {\n        \"status\": \"enforcing\"\n    }\n}\n"
+          }
+        },
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ]
+      },
+      "delete": {
+        "summary": "Delete the organization's hard spend limit.",
+        "operationId": "Deleteorganizationspendlimit",
+        "parameters": [],
+        "responses": {
+          "200": {
+            "description": "Hard spend limit deleted successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/OrganizationSpendLimitDeletedResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete organization spend limit",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/organization/spend_limit \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"organization.spend_limit.deleted\",\n    \"deleted\": true\n}\n"
+          }
+        },
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ]
+      }
+    },
+    "/organization/projects/{project_id}/spend_limit": {
+      "get": {
+        "summary": "Get a project's hard spend limit.",
+        "operationId": "Getprojectspendlimit",
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project whose hard spend limit is being managed.",
+            "required": true,
+            "schema": {
+              "example": "proj_123",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Hard spend limit retrieved successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectSpendLimitResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve project spend limit",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/organization/projects/proj_abc/spend_limit \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"project.spend_limit\",\n    \"threshold_amount\": 10000,\n    \"currency\": \"USD\",\n    \"interval\": \"month\",\n    \"enforcement\": {\n        \"status\": \"enforcing\"\n    }\n}\n"
+          }
+        },
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ]
+      },
+      "delete": {
+        "summary": "Delete a project's hard spend limit.",
+        "operationId": "Deleteprojectspendlimit",
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project whose hard spend limit is being managed.",
+            "required": true,
+            "schema": {
+              "example": "proj_123",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Hard spend limit deleted successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectSpendLimitDeletedResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete project spend limit",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/organization/projects/proj_abc/spend_limit \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\"\n"
+            },
+            "response": "{\n    \"object\": \"project.spend_limit.deleted\",\n    \"deleted\": true\n}\n"
+          }
+        },
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ]
+      },
+      "post": {
+        "summary": "Create or replace a project's hard spend limit.",
+        "operationId": "Updateprojectspendlimit",
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project whose hard spend limit is being managed.",
+            "required": true,
+            "schema": {
+              "example": "proj_123",
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "Parameters for the hard spend limit you want to create or replace.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/UpdateProjectSpendLimitBody"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "200": {
+            "description": "Hard spend limit created or replaced successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProjectSpendLimitResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update project spend limit",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/projects/proj_abc/spend_limit \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"threshold_amount\": 10000,\n      \"currency\": \"USD\",\n      \"interval\": \"month\"\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"project.spend_limit\",\n    \"threshold_amount\": 10000,\n    \"currency\": \"USD\",\n    \"interval\": \"month\",\n    \"enforcement\": {\n        \"status\": \"enforcing\"\n    }\n}\n"
+          }
+        },
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ]
+      }
+    },
+    "/organization/projects/{project_id}/service_accounts/{service_account_id}/api_keys": {
+      "post": {
+        "summary": "Creates an API key for a service account in the project.",
+        "operationId": "CreateanAPIkeyforaserviceaccount",
+        "parameters": [
+          {
+            "name": "project_id",
+            "in": "path",
+            "description": "The ID of the project.",
+            "required": true,
+            "schema": {
+              "description": "The ID of the project.",
+              "type": "string"
+            }
+          },
+          {
+            "name": "service_account_id",
+            "in": "path",
+            "description": "The ID of the service account.",
+            "required": true,
+            "schema": {
+              "description": "The ID of the service account.",
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "description": "The service account API key create request payload.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateProjectServiceAccountApiKeyBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Service account API key created successfully.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ServiceAccountApiKeyBody"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create project service account API key",
+          "group": "administration",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/organization/projects/proj_abc/service_accounts/svc_acct_abc/api_keys \\\n  -H \"Authorization: Bearer $OPENAI_ADMIN_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n      \"name\": \"Production App\",\n      \"scopes\": [\"api.responses.write\"]\n  }'\n"
+            },
+            "response": "{\n    \"object\": \"organization.project.service_account.api_key\",\n    \"value\": \"sk-abcdefghijklmnop123\",\n    \"name\": \"Production App\",\n    \"created_at\": 1711471533,\n    \"id\": \"key_abc\"\n}\n"
+          }
+        },
+        "security": [
+          {
+            "AdminApiKeyAuth": []
+          }
+        ]
+      }
+    },
+    "/content_provenance_checks": {
+      "post": {
+        "summary": "Check whether an image or audio file contains known OpenAI provenance signals. [Learn more about content provenance](https://developers.openai.com/api/docs/guides/content-provenance).\n\nIf `not_detected`, it means the tool did not find supported signals in the uploaded file. The content could still have been generated by OpenAI if the metadata was stripped or has evidence of tampering, the watermark was degraded, it comes from a legacy generation model, or it was created before provenance signals were available. Content could also still be AI-generated by another company's model, which the tool currently does not detect.",
+        "operationId": "Createcontentprovenancecheck",
+        "parameters": [],
+        "requestBody": {
+          "content": {
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateContentProvenanceBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ProvenanceResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create content provenance check",
+          "group": "content_provenance_checks",
+          "examples": []
+        }
+      }
+    },
+    "/videos": {
+      "post": {
+        "tags": [
+          "Videos"
+        ],
+        "summary": "Create a new video generation job from a prompt and optional reference assets.",
+        "operationId": "createVideo",
+        "parameters": [],
+        "requestBody": {
+          "content": {
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateVideoMultipartBody"
+              }
+            },
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateVideoJsonBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VideoResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/InferenceRateLimited"
+          },
+          "503": {
+            "$ref": "#/components/responses/InferenceServiceUnavailable"
+          }
+        },
+        "deprecated": true,
+        "x-oaiMeta": {
+          "name": "Create video",
+          "group": "videos",
+          "path": "create",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/videos \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -F \"model=sora-2\" \\\n  -F \"prompt=A calico cat playing a piano on stage\"\n",
+              "javascript": "import OpenAI from 'openai';\n\nconst openai = new OpenAI();\n\nconst video = await openai.videos.create({ prompt: 'A calico cat playing a piano on stage' });\n\nconsole.log(video.id);\n",
+              "python": "from openai import OpenAI\n\nclient = OpenAI()\nvideo = client.videos.create(\n    prompt=\"A calico cat playing a piano on stage\",\n)\nprint(video.id)\n",
+              "go": "package main\n\nimport (\n  \"context\"\n  \"fmt\"\n\n  \"github.com/openai/openai-go\"\n)\n\nfunc main() {\n  client := openai.NewClient()\n  video, err := client.Videos.New(context.TODO(), openai.VideoNewParams{\n    Prompt: \"A calico cat playing a piano on stage\",\n  })\n  if err != nil {\n    panic(err.Error())\n  }\n  fmt.Printf(\"%+v\\n\", video.ID)\n}\n",
+              "ruby": "require \"openai\"\n\nopenai = OpenAI::Client.new\n\nvideo = openai.videos.create(prompt: \"A calico cat playing a piano on stage\")\n\nputs(video)\n",
+              "java": "package com.openai.example;\n\nimport com.openai.client.OpenAIClient;\nimport com.openai.client.okhttp.OpenAIOkHttpClient;\nimport com.openai.models.videos.Video;\nimport com.openai.models.videos.VideoCreateParams;\n\npublic final class Main {\n    private Main() {}\n\n    public static void main(String[] args) {\n        OpenAIClient client = OpenAIOkHttpClient.fromEnv();\n\n        VideoCreateParams params = VideoCreateParams.builder()\n            .prompt(\"A calico cat playing a piano on stage\")\n            .build();\n        Video video = client.videos().create(params);\n    }\n}\n"
+            },
+            "response": "{\n  \"id\": \"video_123\",\n  \"object\": \"video\",\n  \"model\": \"sora-2\",\n  \"status\": \"queued\",\n  \"progress\": 0,\n  \"created_at\": 1712697600,\n  \"size\": \"1024x1792\",\n  \"seconds\": \"8\",\n  \"quality\": \"standard\"\n}\n"
+          }
+        }
+      },
+      "get": {
+        "tags": [
+          "Videos"
+        ],
+        "summary": "List recently generated videos for the current project.",
+        "operationId": "ListVideos",
+        "parameters": [
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Number of items to retrieve",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 100
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order of results by timestamp. Use `asc` for ascending order or `desc` for descending order.",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/OrderEnum"
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Identifier for the last item from the previous pagination request",
+            "required": false,
+            "schema": {
+              "description": "Identifier for the last item from the previous pagination request",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VideoListResource"
+                }
+              }
+            }
+          }
+        },
+        "deprecated": true,
+        "x-oaiMeta": {
+          "name": "List videos",
+          "group": "videos",
+          "path": "list for the organization.",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/videos \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "javascript": "import OpenAI from 'openai';\n\nconst openai = new OpenAI();\n\n// Automatically fetches more pages as needed.\nfor await (const video of openai.videos.list()) {\n  console.log(video.id);\n}\n",
+              "python": "from openai import OpenAI\n\nclient = OpenAI()\npage = client.videos.list()\npage = page.data[0]\nprint(page.id)\n",
+              "go": "package main\n\nimport (\n  \"context\"\n  \"fmt\"\n\n  \"github.com/openai/openai-go\"\n)\n\nfunc main() {\n  client := openai.NewClient()\n  page, err := client.Videos.List(context.TODO(), openai.VideoListParams{\n\n  })\n  if err != nil {\n    panic(err.Error())\n  }\n  fmt.Printf(\"%+v\\n\", page)\n}\n",
+              "ruby": "require \"openai\"\n\nopenai = OpenAI::Client.new\n\npage = openai.videos.list\n\nputs(page)\n",
+              "java": "package com.openai.example;\n\nimport com.openai.client.OpenAIClient;\nimport com.openai.client.okhttp.OpenAIOkHttpClient;\nimport com.openai.models.videos.VideoListPage;\nimport com.openai.models.videos.VideoListParams;\n\npublic final class Main {\n    private Main() {}\n\n    public static void main(String[] args) {\n        OpenAIClient client = OpenAIOkHttpClient.fromEnv();\n\n        VideoListPage page = client.videos().list();\n    }\n}\n"
+            },
+            "response": "{\n  \"data\": [\n    {\n      \"id\": \"video_123\",\n      \"object\": \"video\",\n      \"model\": \"sora-2\",\n      \"status\": \"completed\"\n    }\n  ],\n  \"object\": \"list\"\n}\n"
+          }
+        }
+      }
+    },
+    "/videos/characters": {
+      "post": {
+        "tags": [
+          "Videos"
+        ],
+        "summary": "Create a character from an uploaded video.",
+        "operationId": "CreateVideoCharacter",
+        "parameters": [],
+        "requestBody": {
+          "content": {
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateVideoCharacterBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VideoCharacterResource"
+                }
+              }
+            }
+          }
+        },
+        "deprecated": true
+      }
+    },
+    "/videos/characters/{character_id}": {
+      "get": {
+        "tags": [
+          "Videos"
+        ],
+        "summary": "Fetch a character.",
+        "operationId": "GetVideoCharacter",
+        "parameters": [
+          {
+            "name": "character_id",
+            "in": "path",
+            "description": "The identifier of the character to retrieve.",
+            "required": true,
+            "schema": {
+              "example": "char_123",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VideoCharacterResource"
+                }
+              }
+            }
+          }
+        },
+        "deprecated": true
+      }
+    },
+    "/videos/edits": {
+      "post": {
+        "tags": [
+          "Videos"
+        ],
+        "summary": "Create a new video generation job by editing a source video or existing generated video.",
+        "operationId": "CreateVideoEdit",
+        "parameters": [],
+        "requestBody": {
+          "content": {
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateVideoEditMultipartBody"
+              }
+            },
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateVideoEditJsonBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VideoResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/InferenceRateLimited"
+          },
+          "503": {
+            "$ref": "#/components/responses/InferenceServiceUnavailable"
+          }
+        },
+        "deprecated": true
+      }
+    },
+    "/videos/extensions": {
+      "post": {
+        "tags": [
+          "Videos"
+        ],
+        "summary": "Create an extension of a completed video.",
+        "operationId": "CreateVideoExtend",
+        "parameters": [],
+        "requestBody": {
+          "content": {
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateVideoExtendMultipartBody"
+              }
+            },
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateVideoExtendJsonBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VideoResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/InferenceRateLimited"
+          },
+          "503": {
+            "$ref": "#/components/responses/InferenceServiceUnavailable"
+          }
+        },
+        "deprecated": true
+      }
+    },
+    "/videos/{video_id}": {
+      "get": {
+        "tags": [
+          "Videos"
+        ],
+        "summary": "Fetch the latest metadata for a generated video.",
+        "operationId": "GetVideo",
+        "parameters": [
+          {
+            "name": "video_id",
+            "in": "path",
+            "description": "The identifier of the video to retrieve.",
+            "required": true,
+            "schema": {
+              "example": "video_123",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VideoResource"
+                }
+              }
+            }
+          }
+        },
+        "deprecated": true,
+        "x-oaiMeta": {
+          "name": "Retrieve video",
+          "group": "videos",
+          "path": "retrieve matching the provided identifier.",
+          "examples": {
+            "response": "",
+            "request": {
+              "javascript": "import OpenAI from 'openai';\n\nconst client = new OpenAI();\n\nconst video = await client.videos.retrieve('video_123');\n\nconsole.log(video.id);\n",
+              "python": "from openai import OpenAI\n\nclient = OpenAI()\nvideo = client.videos.retrieve(\n    \"video_123\",\n)\nprint(video.id)\n",
+              "go": "package main\n\nimport (\n  \"context\"\n  \"fmt\"\n\n  \"github.com/openai/openai-go\"\n)\n\nfunc main() {\n  client := openai.NewClient()\n  video, err := client.Videos.Get(context.TODO(), \"video_123\")\n  if err != nil {\n    panic(err.Error())\n  }\n  fmt.Printf(\"%+v\\n\", video.ID)\n}\n",
+              "ruby": "require \"openai\"\n\nopenai = OpenAI::Client.new\n\nvideo = openai.videos.retrieve(\"video_123\")\n\nputs(video)\n",
+              "java": "package com.openai.example;\n\nimport com.openai.client.OpenAIClient;\nimport com.openai.client.okhttp.OpenAIOkHttpClient;\nimport com.openai.models.videos.Video;\nimport com.openai.models.videos.VideoRetrieveParams;\n\npublic final class Main {\n    private Main() {}\n\n    public static void main(String[] args) {\n        OpenAIClient client = OpenAIOkHttpClient.fromEnv();\n\n        Video video = client.videos().retrieve(\"video_123\");\n    }\n}\n"
+            }
+          }
+        }
+      },
+      "delete": {
+        "tags": [
+          "Videos"
+        ],
+        "summary": "Permanently delete a completed or failed video and its stored assets.",
+        "operationId": "DeleteVideo",
+        "parameters": [
+          {
+            "name": "video_id",
+            "in": "path",
+            "description": "The identifier of the video to delete.",
+            "required": true,
+            "schema": {
+              "example": "video_123",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedVideoResource"
+                }
+              }
+            }
+          }
+        },
+        "deprecated": true,
+        "x-oaiMeta": {
+          "name": "Delete video",
+          "group": "videos",
+          "path": "delete",
+          "examples": {
+            "response": "",
+            "request": {
+              "javascript": "import OpenAI from 'openai';\n\nconst client = new OpenAI();\n\nconst video = await client.videos.delete('video_123');\n\nconsole.log(video.id);\n",
+              "python": "from openai import OpenAI\n\nclient = OpenAI()\nvideo = client.videos.delete(\n    \"video_123\",\n)\nprint(video.id)\n",
+              "go": "package main\n\nimport (\n  \"context\"\n  \"fmt\"\n\n  \"github.com/openai/openai-go\"\n)\n\nfunc main() {\n  client := openai.NewClient()\n  video, err := client.Videos.Delete(context.TODO(), \"video_123\")\n  if err != nil {\n    panic(err.Error())\n  }\n  fmt.Printf(\"%+v\\n\", video.ID)\n}\n",
+              "ruby": "require \"openai\"\n\nopenai = OpenAI::Client.new\n\nvideo = openai.videos.delete(\"video_123\")\n\nputs(video)\n",
+              "java": "package com.openai.example;\n\nimport com.openai.client.OpenAIClient;\nimport com.openai.client.okhttp.OpenAIOkHttpClient;\nimport com.openai.models.videos.VideoDeleteParams;\nimport com.openai.models.videos.VideoDeleteResponse;\n\npublic final class Main {\n    private Main() {}\n\n    public static void main(String[] args) {\n        OpenAIClient client = OpenAIOkHttpClient.fromEnv();\n\n        VideoDeleteResponse video = client.videos().delete(\"video_123\");\n    }\n}\n"
+            }
+          }
+        }
+      }
+    },
+    "/videos/{video_id}/content": {
+      "get": {
+        "tags": [
+          "Videos"
+        ],
+        "summary": "Download the generated video bytes or a derived preview asset.\n\nStreams the rendered video content for the specified video job.",
+        "operationId": "RetrieveVideoContent",
+        "parameters": [
+          {
+            "name": "video_id",
+            "in": "path",
+            "description": "The identifier of the video whose media to download.",
+            "required": true,
+            "schema": {
+              "example": "video_123",
+              "type": "string"
+            }
+          },
+          {
+            "name": "variant",
+            "in": "query",
+            "description": "Which downloadable asset to return. Defaults to the MP4 video.",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/VideoContentVariant"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The video bytes or preview asset that matches the requested variant.",
+            "content": {
+              "video/mp4": {
+                "schema": {
+                  "type": "string",
+                  "format": "binary"
+                }
+              },
+              "image/webp": {
+                "schema": {
+                  "type": "string",
+                  "format": "binary"
+                }
+              },
+              "application/json": {
+                "schema": {
+                  "type": "string"
+                }
+              }
+            }
+          }
+        },
+        "deprecated": true,
+        "x-oaiMeta": {
+          "name": "Retrieve video content",
+          "group": "videos",
+          "path": "content",
+          "examples": {
+            "response": "",
+            "request": {
+              "javascript": "import OpenAI from 'openai';\n\nconst client = new OpenAI();\n\nconst response = await client.videos.downloadContent('video_123');\n\nconsole.log(response);\n\nconst content = await response.blob();\nconsole.log(content);\n",
+              "python": "from openai import OpenAI\n\nclient = OpenAI()\nresponse = client.videos.download_content(\n    video_id=\"video_123\",\n)\nprint(response)\ncontent = response.read()\nprint(content)\n",
+              "go": "package main\n\nimport (\n  \"context\"\n  \"fmt\"\n\n  \"github.com/openai/openai-go\"\n)\n\nfunc main() {\n  client := openai.NewClient()\n  response, err := client.Videos.DownloadContent(\n    context.TODO(),\n    \"video_123\",\n    openai.VideoDownloadContentParams{\n\n    },\n  )\n  if err != nil {\n    panic(err.Error())\n  }\n  fmt.Printf(\"%+v\\n\", response)\n}\n",
+              "ruby": "require \"openai\"\n\nopenai = OpenAI::Client.new\n\nresponse = openai.videos.download_content(\"video_123\")\n\nputs(response)\n",
+              "java": "package com.openai.example;\n\nimport com.openai.client.OpenAIClient;\nimport com.openai.client.okhttp.OpenAIOkHttpClient;\nimport com.openai.core.http.HttpResponse;\nimport com.openai.models.videos.VideoDownloadContentParams;\n\npublic final class Main {\n    private Main() {}\n\n    public static void main(String[] args) {\n        OpenAIClient client = OpenAIOkHttpClient.fromEnv();\n\n        HttpResponse response = client.videos().downloadContent(\"video_123\");\n    }\n}\n"
+            }
+          }
+        }
+      }
+    },
+    "/videos/{video_id}/remix": {
+      "post": {
+        "tags": [
+          "Videos"
+        ],
+        "summary": "Create a remix of a completed video using a refreshed prompt.",
+        "operationId": "CreateVideoRemix",
+        "parameters": [
+          {
+            "name": "video_id",
+            "in": "path",
+            "description": "The identifier of the completed video to remix.",
+            "required": true,
+            "schema": {
+              "example": "video_123",
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateVideoRemixBody"
+              }
+            },
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateVideoRemixBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VideoResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/InferenceRateLimited"
+          },
+          "503": {
+            "$ref": "#/components/responses/InferenceServiceUnavailable"
+          }
+        },
+        "deprecated": true,
+        "x-oaiMeta": {
+          "name": "Remix video",
+          "group": "videos",
+          "path": "remix using the provided prompt.",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/videos/video_123/remix \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"prompt\": \"Extend the scene with the cat taking a bow to the cheering audience\"\n  }'\n",
+              "javascript": "import OpenAI from 'openai';\n\nconst client = new OpenAI();\n\nconst video = await client.videos.remix('video_123', { prompt: 'Extend the scene with the cat taking a bow to the cheering audience' });\n\nconsole.log(video.id);\n",
+              "python": "from openai import OpenAI\n\nclient = OpenAI()\nvideo = client.videos.remix(\n    video_id=\"video_123\",\n    prompt=\"Extend the scene with the cat taking a bow to the cheering audience\",\n)\nprint(video.id)\n",
+              "go": "package main\n\nimport (\n  \"context\"\n  \"fmt\"\n\n  \"github.com/openai/openai-go\"\n)\n\nfunc main() {\n  client := openai.NewClient()\n  video, err := client.Videos.Remix(\n    context.TODO(),\n    \"video_123\",\n    openai.VideoRemixParams{\n      Prompt: \"Extend the scene with the cat taking a bow to the cheering audience\",\n    },\n  )\n  if err != nil {\n    panic(err.Error())\n  }\n  fmt.Printf(\"%+v\\n\", video.ID)\n}\n",
+              "ruby": "require \"openai\"\n\nopenai = OpenAI::Client.new\n\nvideo = openai.videos.remix(\"video_123\", prompt: \"Extend the scene with the cat taking a bow to the cheering audience\")\n\nputs(video)\n",
+              "java": "package com.openai.example;\n\nimport com.openai.client.OpenAIClient;\nimport com.openai.client.okhttp.OpenAIOkHttpClient;\nimport com.openai.models.videos.Video;\nimport com.openai.models.videos.VideoRemixParams;\n\npublic final class Main {\n    private Main() {}\n\n    public static void main(String[] args) {\n        OpenAIClient client = OpenAIOkHttpClient.fromEnv();\n\n        VideoRemixParams params = VideoRemixParams.builder()\n            .videoId(\"video_123\")\n            .prompt(\"Extend the scene with the cat taking a bow to the cheering audience\")\n            .build();\n        Video video = client.videos().remix(params);\n    }\n}\n"
+            },
+            "response": "{\n  \"id\": \"video_456\",\n  \"object\": \"video\",\n  \"model\": \"sora-2\",\n  \"status\": \"queued\",\n  \"progress\": 0,\n  \"created_at\": 1712698600,\n  \"size\": \"720x1280\",\n  \"seconds\": \"8\",\n  \"remixed_from_video_id\": \"video_123\"\n}\n"
+          }
+        }
+      }
+    },
+    "/responses/input_tokens": {
+      "post": {
+        "summary": "Returns input token counts of the request.\n\nReturns an object with `object` set to `response.input_tokens` and an `input_tokens` count.",
+        "operationId": "Getinputtokencounts",
+        "parameters": [],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/TokenCountsBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/TokenCountsResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Get input token counts",
+          "group": "responses",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/responses/input_tokens \\\n    -H \"Content-Type: application/json\" \\\n    -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n    -d '{\n      \"model\": \"gpt-6-astra\",\n      \"input\": \"Tell me a joke.\"\n    }'\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst client = new OpenAI();\n\nconst response = await client.responses.inputTokens.count({\n  model: \"gpt-6-astra\",\n  input: \"Tell me a joke.\",\n});\n\nconsole.log(response.input_tokens);\n",
+              "python": "from openai import OpenAI\n\nclient = OpenAI()\n\nresponse = client.responses.input_tokens.count(\n    model=\"gpt-6-astra\",\n    input=\"Tell me a joke.\"\n)\nprint(response.input_tokens)\n",
+              "go": "package main\n\nimport (\n  \"context\"\n  \"fmt\"\n\n  \"github.com/openai/openai-go\"\n  \"github.com/openai/openai-go/responses\"\n)\n\nfunc main() {\n  client := openai.NewClient()\n  response, err := client.Responses.InputTokens.Count(context.TODO(), responses.InputTokenCountParams{\n    Model: \"gpt-6-astra\",\n    Input: \"Tell me a joke.\",\n  })\n  if err != nil {\n    panic(err.Error())\n  }\n  fmt.Printf(\"%+v\\n\", response.InputTokens)\n}\n",
+              "ruby": "require \"openai\"\n\nopenai = OpenAI::Client.new\n\nresponse = openai.responses.input_tokens.count(model: \"gpt-6-astra\", input: \"Tell me a joke.\")\n\nputs(response)\n",
+              "java": "package com.openai.example;\n\nimport com.openai.client.OpenAIClient;\nimport com.openai.client.okhttp.OpenAIOkHttpClient;\nimport com.openai.models.responses.inputtokens.InputTokenCountParams;\nimport com.openai.models.responses.inputtokens.InputTokenCountResponse;\n\npublic final class Main {\n    private Main() {}\n\n    public static void main(String[] args) {\n        OpenAIClient client = OpenAIOkHttpClient.fromEnv();\n\n        InputTokenCountParams params = InputTokenCountParams.builder()\n            .model(\"gpt-6-astra\")\n            .input(\"Tell me a joke.\")\n            .build();\n\n        InputTokenCountResponse response = client.responses().inputTokens().count(params);\n    }\n}\n"
+            },
+            "response": "{\n  \"object\": \"response.input_tokens\",\n  \"input_tokens\": 11\n}\n"
+          }
+        }
+      }
+    },
+    "/responses/compact": {
+      "post": {
+        "summary": "Compact a conversation. Returns a compacted response object.\n\nLearn when and how to compact long-running conversations in the [conversation state guide](https://developers.openai.com/api/docs/guides/conversation-state#managing-the-context-window). For ZDR-compatible compaction details, see [Compaction (advanced)](https://developers.openai.com/api/docs/guides/conversation-state#compaction-advanced).",
+        "operationId": "Compactconversation",
+        "parameters": [],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CompactResponseMethodPublicBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/CompactResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/InferenceRateLimited"
+          },
+          "503": {
+            "$ref": "#/components/responses/InferenceServiceUnavailable"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Compact a response",
+          "group": "responses",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/responses/compact \\\n    -H \"Content-Type: application/json\" \\\n    -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n    -d '{\n      \"model\": \"gpt-6-astra\",\n      \"input\": [\n        {\n          \"role\": \"user\",\n          \"content\": \"Create a simple landing page for a dog petting café.\"\n        },\n        {\n          \"id\": \"msg_001\",\n          \"type\": \"message\",\n          \"status\": \"completed\",\n          \"content\": [\n            {\n              \"type\": \"output_text\",\n              \"annotations\": [],\n              \"logprobs\": [],\n              \"text\": \"Below is a single file, ready-to-use landing page for a dog petting café:...\"\n            }\n          ],\n          \"role\": \"assistant\"\n        }\n      ]\n    }'\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\n// Compact the previous response if you are running out of tokens\nconst compactedResponse = await openai.responses.compact({\n  model: \"gpt-6-astra\",\n  input: [\n    {\n      role: \"user\",\n      content: \"Create a simple landing page for a dog petting café.\",\n    },\n    // All items returned from previous requests are included here, like reasoning, message, function call, etc.\n    {\n      id: \"msg_030d085c0b53e67e0069332e3a72d4819c96c6f2c4adc15d33\",\n      type: \"message\",\n      status: \"completed\",\n      content: [\n        {\n          type: \"output_text\",\n          annotations: [],\n          logprobs: [],\n          text: \"Below is a single file, ready-to-use landing page for a dog petting café:...\",\n        },\n      ],\n      role: \"assistant\",\n    },\n  ],\n});\n\n// Pass the compactedResponse.output as input to the next request\nconsole.log(compactedResponse);\n",
+              "python": "from openai import OpenAI\n\nclient = OpenAI()\n\ncompacted_response = client.responses.compact(\n    model=\"gpt-6-astra\",\n    input=[\n    {\n        \"role\": \"user\",\n        \"content\": \"Create a simple landing page for a dog petting cafe.\",\n    },\n    # All items returned from previous requests are included here, like reasoning, message, function call, etc.\n    {\n        \"id\": \"msg_001\",\n        \"type\": \"message\",\n        \"status\": \"completed\",\n        \"content\": [\n        {\n            \"type\": \"output_text\",\n            \"annotations\": [],\n            \"logprobs\": [],\n            \"text\": \"Below is a single file, ready-to-use landing page for a dog petting café:...\",\n        },\n        ],\n        \"role\": \"assistant\",\n    },\n    ]\n)\n# Pass the compacted_response.output as input to the next request\nprint(compacted_response)\n"
+            },
+            "response": "{\n  \"id\": \"resp_001\",\n  \"object\": \"response.compaction\",\n  \"created_at\": 1764967971,\n  \"output\": [\n    {\n      \"id\": \"msg_000\",\n      \"type\": \"message\",\n      \"status\": \"completed\",\n      \"content\": [\n        {\n          \"type\": \"input_text\",\n          \"text\": \"Create a simple landing page for a dog petting cafe.\"\n        }\n      ],\n      \"role\": \"user\"\n    },\n    {\n      \"id\": \"cmp_001\",\n      \"type\": \"compaction\",\n      \"encrypted_content\": \"gAAAAABpM0Yj-...=\"\n    }\n  ],\n  \"usage\": {\n    \"input_tokens\": 139,\n    \"input_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"cache_write_tokens\": 0\n    },\n    \"output_tokens\": 438,\n    \"output_tokens_details\": {\n      \"reasoning_tokens\": 64\n    },\n    \"total_tokens\": 577\n  }\n}\n"
+          }
+        }
+      }
+    },
+    "/skills": {
+      "post": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "Create a new skill.",
+        "operationId": "CreateSkill",
+        "parameters": [],
+        "requestBody": {
+          "content": {
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateSkillBody"
+              }
+            },
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateSkillBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SkillResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      },
+      "get": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "List all skills for the current project.",
+        "operationId": "ListSkills",
+        "parameters": [
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Number of items to retrieve",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 100
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order of results by timestamp. Use `asc` for ascending order or `desc` for descending order.",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/OrderEnum"
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "Identifier for the last item from the previous pagination request",
+            "required": false,
+            "schema": {
+              "description": "Identifier for the last item from the previous pagination request",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SkillListResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      }
+    },
+    "/skills/{skill_id}": {
+      "delete": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "Delete a skill by its ID.",
+        "operationId": "DeleteSkill",
+        "parameters": [
+          {
+            "name": "skill_id",
+            "in": "path",
+            "description": "The identifier of the skill to delete.",
+            "required": true,
+            "schema": {
+              "example": "skill_123",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedSkillResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      },
+      "get": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "Get a skill by its ID.",
+        "operationId": "GetSkill",
+        "parameters": [
+          {
+            "name": "skill_id",
+            "in": "path",
+            "description": "The identifier of the skill to retrieve.",
+            "required": true,
+            "schema": {
+              "example": "skill_123",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SkillResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      },
+      "post": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "Update the default version pointer for a skill.",
+        "operationId": "UpdateSkillDefaultVersion",
+        "parameters": [
+          {
+            "name": "skill_id",
+            "in": "path",
+            "description": "The identifier of the skill.",
+            "required": true,
+            "schema": {
+              "example": "skill_123",
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/SetDefaultSkillVersionBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SkillResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      }
+    },
+    "/skills/{skill_id}/content": {
+      "get": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "Download a skill zip bundle by its ID.",
+        "operationId": "GetSkillContent",
+        "parameters": [
+          {
+            "name": "skill_id",
+            "in": "path",
+            "description": "The identifier of the skill to download.",
+            "required": true,
+            "schema": {
+              "example": "skill_123",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The skill zip bundle.",
+            "content": {
+              "application/zip": {
+                "schema": {
+                  "type": "string",
+                  "format": "binary"
+                }
+              },
+              "application/json": {
+                "schema": {
+                  "type": "string"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      }
+    },
+    "/skills/{skill_id}/versions": {
+      "post": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "Create a new immutable skill version.",
+        "operationId": "CreateSkillVersion",
+        "parameters": [
+          {
+            "name": "skill_id",
+            "in": "path",
+            "description": "The identifier of the skill to version.",
+            "required": true,
+            "schema": {
+              "example": "skill_123",
+              "type": "string"
+            }
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "multipart/form-data": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateSkillVersionBody"
+              }
+            },
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateSkillVersionBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SkillVersionResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      },
+      "get": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "List skill versions for a skill.",
+        "operationId": "ListSkillVersions",
+        "parameters": [
+          {
+            "name": "skill_id",
+            "in": "path",
+            "description": "The identifier of the skill.",
+            "required": true,
+            "schema": {
+              "example": "skill_123",
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Number of versions to retrieve.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 100
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order of results by version number.",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/OrderEnum"
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "The skill version ID to start after.",
+            "required": false,
+            "schema": {
+              "example": "skillver_123",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SkillVersionListResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      }
+    },
+    "/skills/{skill_id}/versions/{version}": {
+      "get": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "Get a specific skill version.",
+        "operationId": "GetSkillVersion",
+        "parameters": [
+          {
+            "name": "skill_id",
+            "in": "path",
+            "description": "The identifier of the skill.",
+            "required": true,
+            "schema": {
+              "example": "skill_123",
+              "type": "string"
+            }
+          },
+          {
+            "name": "version",
+            "in": "path",
+            "description": "The version number to retrieve.",
+            "required": true,
+            "schema": {
+              "description": "The version number to retrieve.",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SkillVersionResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      },
+      "delete": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "Delete a skill version.",
+        "operationId": "DeleteSkillVersion",
+        "parameters": [
+          {
+            "name": "skill_id",
+            "in": "path",
+            "description": "The identifier of the skill.",
+            "required": true,
+            "schema": {
+              "example": "skill_123",
+              "type": "string"
+            }
+          },
+          {
+            "name": "version",
+            "in": "path",
+            "description": "The skill version number.",
+            "required": true,
+            "schema": {
+              "description": "The skill version number.",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedSkillVersionResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      }
+    },
+    "/skills/{skill_id}/versions/{version}/content": {
+      "get": {
+        "tags": [
+          "Skills"
+        ],
+        "summary": "Download a skill version zip bundle.",
+        "operationId": "GetSkillVersionContent",
+        "parameters": [
+          {
+            "name": "skill_id",
+            "in": "path",
+            "description": "The identifier of the skill.",
+            "required": true,
+            "schema": {
+              "example": "skill_123",
+              "type": "string"
+            }
+          },
+          {
+            "name": "version",
+            "in": "path",
+            "description": "The skill version number.",
+            "required": true,
+            "schema": {
+              "description": "The skill version number.",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The skill zip bundle.",
+            "content": {
+              "application/zip": {
+                "schema": {
+                  "type": "string",
+                  "format": "binary"
+                }
+              },
+              "application/json": {
+                "schema": {
+                  "type": "string"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        }
+      }
+    },
+    "/chatkit/sessions/{session_id}/cancel": {
+      "post": {
+        "summary": "Cancel an active ChatKit session and return its most recent metadata.\n\nCancelling prevents new requests from using the issued client secret.",
+        "operationId": "CancelChatSessionMethod",
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "description": "Unique identifier for the ChatKit session to cancel.",
+            "required": true,
+            "schema": {
+              "example": "cksess_123",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ChatSessionResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Cancel chat session",
+          "group": "chatkit",
+          "beta": true,
+          "path": "cancel-session new requests from using the issued client secret.",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST \\\n  https://api.openai.com/v1/chatkit/sessions/cksess_123/cancel \\\n  -H \"OpenAI-Beta: chatkit_beta=v1\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "javascript": "import OpenAI from 'openai';\n\nconst client = new OpenAI();\n\nconst chatSession = await client.beta.chatkit.sessions.cancel('cksess_123');\n\nconsole.log(chatSession.id);\n",
+              "python": "from openai import OpenAI\n\nclient = OpenAI()\nchat_session = client.beta.chatkit.sessions.cancel(\n    \"cksess_123\",\n)\nprint(chat_session.id)\n",
+              "go": "package main\n\nimport (\n  \"context\"\n  \"fmt\"\n\n  \"github.com/openai/openai-go\"\n  \"github.com/openai/openai-go/option\"\n)\n\nfunc main() {\n  client := openai.NewClient()\n  chatSession, err := client.Beta.ChatKit.Sessions.Cancel(context.TODO(), \"cksess_123\")\n  if err != nil {\n    panic(err.Error())\n  }\n  fmt.Printf(\"%+v\\n\", chatSession.ID)\n}\n",
+              "ruby": "require \"openai\"\n\nopenai = OpenAI::Client.new\n\nchat_session = openai.beta.chatkit.sessions.cancel(\"cksess_123\")\n\nputs(chat_session)\n",
+              "java": "package com.openai.example;\n\nimport com.openai.client.OpenAIClient;\nimport com.openai.client.okhttp.OpenAIOkHttpClient;\nimport com.openai.models.beta.chatkit.sessions.SessionCancelParams;\nimport com.openai.models.beta.chatkit.threads.ChatSession;\n\npublic final class Main {\n    private Main() {}\n\n    public static void main(String[] args) {\n        OpenAIClient client = OpenAIOkHttpClient.fromEnv();\n\n        ChatSession chatSession = client.beta().chatkit().sessions().cancel(\"cksess_123\");\n    }\n}\n"
+            },
+            "response": "{\n  \"id\": \"cksess_123\",\n  \"object\": \"chatkit.session\",\n  \"workflow\": {\n    \"id\": \"workflow_alpha\",\n    \"version\": \"1\"\n  },\n  \"scope\": {\n    \"customer_id\": \"cust_456\"\n  },\n  \"max_requests_per_1_minute\": 30,\n  \"ttl_seconds\": 900,\n  \"status\": \"cancelled\",\n  \"cancelled_at\": 1712345678\n}\n"
+          }
+        }
+      }
+    },
+    "/chatkit/sessions": {
+      "post": {
+        "summary": "Create a ChatKit session.",
+        "operationId": "CreateChatSessionMethod",
+        "parameters": [],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateChatSessionBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ChatSessionResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create ChatKit session",
+          "group": "chatkit",
+          "beta": true,
+          "path": "sessions/create object.",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/chatkit/sessions \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -H \"OpenAI-Beta: chatkit_beta=v1\" \\\n  -d '{\n    \"workflow\": {\n      \"id\": \"workflow_alpha\",\n      \"version\": \"2024-10-01\"\n    },\n    \"scope\": {\n      \"project\": \"alpha\",\n      \"environment\": \"staging\"\n    },\n    \"expires_after\": 1800,\n    \"max_requests_per_1_minute\": 60,\n    \"max_requests_per_session\": 500\n  }'\n",
+              "javascript": "import OpenAI from 'openai';\n\nconst client = new OpenAI();\n\nconst chatSession = await client.beta.chatkit.sessions.create({ user: 'user', workflow: { id: 'id' } });\n\nconsole.log(chatSession.id);\n",
+              "python": "from openai import OpenAI\n\nclient = OpenAI()\nchat_session = client.beta.chatkit.sessions.create(\n    user=\"user\",\n    workflow={\n        \"id\": \"id\"\n    },\n)\nprint(chat_session.id)\n",
+              "go": "package main\n\nimport (\n  \"context\"\n  \"fmt\"\n\n  \"github.com/openai/openai-go\"\n  \"github.com/openai/openai-go/option\"\n)\n\nfunc main() {\n  client := openai.NewClient()\n  chatSession, err := client.Beta.ChatKit.Sessions.New(context.TODO(), openai.BetaChatKitSessionNewParams{\n    User: \"user\",\n    Workflow: openai.ChatSessionWorkflowParam{\n      ID: \"id\",\n    },\n  })\n  if err != nil {\n    panic(err.Error())\n  }\n  fmt.Printf(\"%+v\\n\", chatSession.ID)\n}\n",
+              "ruby": "require \"openai\"\n\nopenai = OpenAI::Client.new\n\nchat_session = openai.beta.chatkit.sessions.create(user: \"user\", workflow: {id: \"id\"})\n\nputs(chat_session)\n",
+              "java": "package com.openai.example;\n\nimport com.openai.client.OpenAIClient;\nimport com.openai.client.okhttp.OpenAIOkHttpClient;\nimport com.openai.models.beta.chatkit.sessions.SessionCreateParams;\nimport com.openai.models.beta.chatkit.threads.ChatSession;\nimport com.openai.models.beta.chatkit.threads.ChatSessionWorkflowParam;\n\npublic final class Main {\n    private Main() {}\n\n    public static void main(String[] args) {\n        OpenAIClient client = OpenAIOkHttpClient.fromEnv();\n\n        SessionCreateParams params = SessionCreateParams.builder()\n            .user(\"user\")\n            .workflow(ChatSessionWorkflowParam.builder()\n                .id(\"id\")\n                .build())\n            .build();\n        ChatSession chatSession = client.beta().chatkit().sessions().create(params);\n    }\n}\n"
+            },
+            "response": "{\n  \"client_secret\": \"chatkit_token_123\",\n  \"expires_at\": 1735689600,\n  \"workflow\": {\n    \"id\": \"workflow_alpha\",\n    \"version\": \"2024-10-01\"\n  },\n  \"scope\": {\n    \"project\": \"alpha\",\n    \"environment\": \"staging\"\n  },\n  \"max_requests_per_1_minute\": 60,\n  \"max_requests_per_session\": 500,\n  \"status\": \"active\"\n}\n"
+          }
+        }
+      }
+    },
+    "/chatkit/threads/{thread_id}/items": {
+      "get": {
+        "summary": "List items that belong to a ChatKit thread.",
+        "operationId": "ListThreadItemsMethod",
+        "parameters": [
+          {
+            "name": "thread_id",
+            "in": "path",
+            "description": "Identifier of the ChatKit thread whose items are requested.",
+            "required": true,
+            "schema": {
+              "example": "cthr_123",
+              "type": "string"
+            }
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Maximum number of thread items to return. Defaults to 20.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 100
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order for results by creation time. Defaults to `desc`.",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/OrderEnum"
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "List items created after this thread item ID. Defaults to null for the first page.",
+            "required": false,
+            "schema": {
+              "description": "List items created after this thread item ID. Defaults to null for the first page.",
+              "type": "string"
+            }
+          },
+          {
+            "name": "before",
+            "in": "query",
+            "description": "List items created before this thread item ID. Defaults to null for the newest results.",
+            "required": false,
+            "schema": {
+              "description": "List items created before this thread item ID. Defaults to null for the newest results.",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ThreadItemListResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List ChatKit thread items",
+          "group": "chatkit",
+          "beta": true,
+          "path": "threads/list-items for the specified thread.",
+          "examples": {
+            "request": {
+              "curl": "curl \"https://api.openai.com/v1/chatkit/threads/cthr_abc123/items?limit=3\" \\\n  -H \"OpenAI-Beta: chatkit_beta=v1\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "javascript": "import OpenAI from 'openai';\n\nconst client = new OpenAI();\n\n// Automatically fetches more pages as needed.\nfor await (const thread of client.beta.chatkit.threads.listItems('cthr_123')) {\n  console.log(thread);\n}\n",
+              "python": "from openai import OpenAI\n\nclient = OpenAI()\npage = client.beta.chatkit.threads.list_items(\n    thread_id=\"cthr_123\",\n)\npage = page.data[0]\nprint(page)\n",
+              "go": "package main\n\nimport (\n  \"context\"\n  \"fmt\"\n\n  \"github.com/openai/openai-go\"\n  \"github.com/openai/openai-go/option\"\n)\n\nfunc main() {\n  client := openai.NewClient()\n  page, err := client.Beta.ChatKit.Threads.ListItems(\n    context.TODO(),\n    \"cthr_123\",\n    openai.BetaChatKitThreadListItemsParams{\n\n    },\n  )\n  if err != nil {\n    panic(err.Error())\n  }\n  fmt.Printf(\"%+v\\n\", page)\n}\n",
+              "ruby": "require \"openai\"\n\nopenai = OpenAI::Client.new\n\npage = openai.beta.chatkit.threads.list_items(\"cthr_123\")\n\nputs(page)\n",
+              "java": "package com.openai.example;\n\nimport com.openai.client.OpenAIClient;\nimport com.openai.client.okhttp.OpenAIOkHttpClient;\nimport com.openai.models.beta.chatkit.threads.ThreadListItemsPage;\nimport com.openai.models.beta.chatkit.threads.ThreadListItemsParams;\n\npublic final class Main {\n    private Main() {}\n\n    public static void main(String[] args) {\n        OpenAIClient client = OpenAIOkHttpClient.fromEnv();\n\n        ThreadListItemsPage page = client.beta().chatkit().threads().listItems(\"cthr_123\");\n    }\n}\n"
+            },
+            "response": "{\n  \"data\": [\n    {\n      \"id\": \"cthi_user_001\",\n      \"object\": \"chatkit.thread_item\",\n      \"type\": \"user_message\",\n      \"content\": [\n        {\n          \"type\": \"input_text\",\n          \"text\": \"I need help debugging an onboarding issue.\"\n        }\n      ],\n      \"attachments\": []\n    },\n    {\n      \"id\": \"cthi_assistant_002\",\n      \"object\": \"chatkit.thread_item\",\n      \"type\": \"assistant_message\",\n      \"content\": [\n        {\n          \"type\": \"output_text\",\n          \"text\": \"Let's start by confirming the workflow version you deployed.\"\n        }\n      ]\n    }\n  ],\n  \"has_more\": false,\n  \"object\": \"list\"\n}\n"
+          }
+        }
+      }
+    },
+    "/chatkit/threads/{thread_id}": {
+      "get": {
+        "summary": "Retrieve a ChatKit thread by its identifier.",
+        "operationId": "GetThreadMethod",
+        "parameters": [
+          {
+            "name": "thread_id",
+            "in": "path",
+            "description": "Identifier of the ChatKit thread to retrieve.",
+            "required": true,
+            "schema": {
+              "example": "cthr_123",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ThreadResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve ChatKit thread",
+          "group": "chatkit",
+          "beta": true,
+          "path": "threads/retrieve",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/chatkit/threads/cthr_abc123 \\\n  -H \"OpenAI-Beta: chatkit_beta=v1\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "javascript": "import OpenAI from 'openai';\n\nconst client = new OpenAI();\n\nconst chatkitThread = await client.beta.chatkit.threads.retrieve('cthr_123');\n\nconsole.log(chatkitThread.id);\n",
+              "python": "from openai import OpenAI\n\nclient = OpenAI()\nchatkit_thread = client.beta.chatkit.threads.retrieve(\n    \"cthr_123\",\n)\nprint(chatkit_thread.id)\n",
+              "go": "package main\n\nimport (\n  \"context\"\n  \"fmt\"\n\n  \"github.com/openai/openai-go\"\n)\n\nfunc main() {\n  client := openai.NewClient()\n  chatkitThread, err := client.Beta.ChatKit.Threads.Get(context.TODO(), \"cthr_123\")\n  if err != nil {\n    panic(err.Error())\n  }\n  fmt.Printf(\"%+v\\n\", chatkitThread.ID)\n}\n",
+              "ruby": "require \"openai\"\n\nopenai = OpenAI::Client.new\n\nchatkit_thread = openai.beta.chatkit.threads.retrieve(\"cthr_123\")\n\nputs(chatkit_thread)\n",
+              "java": "package com.openai.example;\n\nimport com.openai.client.OpenAIClient;\nimport com.openai.client.okhttp.OpenAIOkHttpClient;\nimport com.openai.models.beta.chatkit.threads.ChatKitThread;\nimport com.openai.models.beta.chatkit.threads.ThreadRetrieveParams;\n\npublic final class Main {\n    private Main() {}\n\n    public static void main(String[] args) {\n        OpenAIClient client = OpenAIOkHttpClient.fromEnv();\n\n        ChatKitThread chatkitThread = client.beta().chatkit().threads().retrieve(\"cthr_123\");\n    }\n}\n"
+            },
+            "response": "{\n  \"id\": \"cthr_abc123\",\n  \"object\": \"chatkit.thread\",\n  \"title\": \"Customer escalation\",\n  \"items\": {\n    \"data\": [\n      {\n        \"id\": \"cthi_user_001\",\n        \"object\": \"chatkit.thread_item\",\n        \"type\": \"user_message\",\n        \"content\": [\n          {\n            \"type\": \"input_text\",\n            \"text\": \"I need help debugging an onboarding issue.\"\n          }\n        ],\n        \"attachments\": []\n      },\n      {\n        \"id\": \"cthi_assistant_002\",\n        \"object\": \"chatkit.thread_item\",\n        \"type\": \"assistant_message\",\n        \"content\": [\n          {\n            \"type\": \"output_text\",\n            \"text\": \"Let's start by confirming the workflow version you deployed.\"\n          }\n        ]\n      }\n    ],\n    \"has_more\": false\n  }\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "summary": "Delete a ChatKit thread along with its items and stored attachments.",
+        "operationId": "DeleteThreadMethod",
+        "parameters": [
+          {
+            "name": "thread_id",
+            "in": "path",
+            "description": "Identifier of the ChatKit thread to delete.",
+            "required": true,
+            "schema": {
+              "example": "cthr_123",
+              "type": "string"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedThreadResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "beta": true,
+          "examples": {
+            "response": "",
+            "request": {
+              "javascript": "import OpenAI from 'openai';\n\nconst client = new OpenAI();\n\nconst thread = await client.beta.chat_kit.threads.delete('cthr_123');\n\nconsole.log(thread.id);\n",
+              "python": "from openai import OpenAI\n\nclient = OpenAI()\nthread = client.beta.chat_kit.threads.delete(\n    \"cthr_123\",\n)\nprint(thread.id)\n",
+              "go": "package main\n\nimport (\n  \"context\"\n  \"fmt\"\n\n  \"github.com/openai/openai-go\"\n)\n\nfunc main() {\n  client := openai.NewClient()\n  thread, err := client.Beta.ChatKit.Threads.Delete(context.TODO(), \"cthr_123\")\n  if err != nil {\n    panic(err.Error())\n  }\n  fmt.Printf(\"%+v\\n\", thread.ID)\n}\n",
+              "ruby": "require \"openai\"\n\nopenai = OpenAI::Client.new\n\nthread = openai.beta.chat_kit.threads.delete(\"cthr_123\")\n\nputs(thread)\n",
+              "java": "package com.openai.example;\n\nimport com.openai.client.OpenAIClient;\nimport com.openai.client.okhttp.OpenAIOkHttpClient;\nimport com.openai.models.beta.chat_kit.threads.ThreadDeleteParams;\nimport com.openai.models.beta.chat_kit.threads.ThreadDeleteResponse;\n\npublic final class Main {\n    private Main() {}\n\n    public static void main(String[] args) {\n        OpenAIClient client = OpenAIOkHttpClient.fromEnv();\n\n        ThreadDeleteResponse thread = client.beta().chat_kit().threads().delete(\"cthr_123\");\n    }\n}\n"
+            }
+          },
+          "name": "Delete ChatKit thread",
+          "group": "chatkit",
+          "path": "threads/delete"
+        }
+      }
+    },
+    "/chatkit/threads": {
+      "get": {
+        "summary": "List ChatKit threads with optional pagination and user filters.",
+        "operationId": "ListThreadsMethod",
+        "parameters": [
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "Maximum number of thread items to return. Defaults to 20.",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 100
+            }
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "description": "Sort order for results by creation time. Defaults to `desc`.",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/OrderEnum"
+            }
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "description": "List items created after this thread item ID. Defaults to null for the first page.",
+            "required": false,
+            "schema": {
+              "description": "List items created after this thread item ID. Defaults to null for the first page.",
+              "type": "string"
+            }
+          },
+          {
+            "name": "before",
+            "in": "query",
+            "description": "List items created before this thread item ID. Defaults to null for the newest results.",
+            "required": false,
+            "schema": {
+              "description": "List items created before this thread item ID. Defaults to null for the newest results.",
+              "type": "string"
+            }
+          },
+          {
+            "name": "user",
+            "in": "query",
+            "description": "Filter threads that belong to this user identifier. Defaults to null to return all users.",
+            "required": false,
+            "schema": {
+              "description": "Filter threads that belong to this user identifier. Defaults to null to return all users.",
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 512
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ThreadListResource"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List ChatKit threads",
+          "group": "chatkit",
+          "beta": true,
+          "path": "list-threads scope.",
+          "examples": {
+            "request": {
+              "curl": "curl \"https://api.openai.com/v1/chatkit/threads?limit=2&order=desc\" \\\n  -H \"OpenAI-Beta: chatkit_beta=v1\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "javascript": "import OpenAI from 'openai';\n\nconst client = new OpenAI();\n\n// Automatically fetches more pages as needed.\nfor await (const chatkitThread of client.beta.chatkit.threads.list()) {\n  console.log(chatkitThread.id);\n}\n",
+              "python": "from openai import OpenAI\n\nclient = OpenAI()\npage = client.beta.chatkit.threads.list()\npage = page.data[0]\nprint(page.id)\n",
+              "go": "package main\n\nimport (\n  \"context\"\n  \"fmt\"\n\n  \"github.com/openai/openai-go\"\n)\n\nfunc main() {\n  client := openai.NewClient()\n  page, err := client.Beta.ChatKit.Threads.List(context.TODO(), openai.BetaChatKitThreadListParams{\n\n  })\n  if err != nil {\n    panic(err.Error())\n  }\n  fmt.Printf(\"%+v\\n\", page)\n}\n",
+              "ruby": "require \"openai\"\n\nopenai = OpenAI::Client.new\n\npage = openai.beta.chatkit.threads.list\n\nputs(page)\n",
+              "java": "package com.openai.example;\n\nimport com.openai.client.OpenAIClient;\nimport com.openai.client.okhttp.OpenAIOkHttpClient;\nimport com.openai.models.beta.chatkit.threads.ThreadListPage;\nimport com.openai.models.beta.chatkit.threads.ThreadListParams;\n\npublic final class Main {\n    private Main() {}\n\n    public static void main(String[] args) {\n        OpenAIClient client = OpenAIOkHttpClient.fromEnv();\n\n        ThreadListPage page = client.beta().chatkit().threads().list();\n    }\n}\n"
+            },
+            "response": "{\n  \"data\": [\n    {\n      \"id\": \"cthr_abc123\",\n      \"object\": \"chatkit.thread\",\n      \"title\": \"Customer escalation\"\n    },\n    {\n      \"id\": \"cthr_def456\",\n      \"object\": \"chatkit.thread\",\n      \"title\": \"Demo feedback\"\n    }\n  ],\n  \"has_more\": false,\n  \"object\": \"list\"\n}\n"
+          }
+        }
+      }
+    },
+    "/agents/environments/{environment_id}": {
+      "get": {
+        "operationId": "retrieveAgentEnvironment",
+        "summary": "Retrieves an execution environment's connection status and safe installed metadata. See [environment lifecycle](https://developers.openai.com/api/docs/guides/agents-api/environments/lifecycle).",
+        "description": "Retrieves an execution environment's connection status and safe installed metadata.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "environment_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the environment."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested environment.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/PublicEnvironmentResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve an agent environment"
+        }
+      }
+    },
+    "/agents/environments/{environment_id}/files": {
+      "get": {
+        "operationId": "listAgentEnvironmentFiles",
+        "summary": "Lists live files on a connected execution environment with optional directory filtering and opaque cursor pagination. See [environment files](https://developers.openai.com/api/docs/guides/agents-api/environments/files).",
+        "description": "Lists live files on a connected execution environment with optional directory filtering and opaque cursor pagination.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "environment_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the environment."
+          },
+          {
+            "name": "path",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": [
+                "string",
+                "null"
+              ],
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Restrict the listing to this absolute workspace directory."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": [
+                "integer",
+                "null"
+              ],
+              "format": "int64",
+              "minimum": 1,
+              "maximum": 100
+            },
+            "description": "The maximum number of files to return, between 1 and 100."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam"
+            },
+            "description": "Sort by case-sensitive path components. Defaults to descending."
+          },
+          {
+            "name": "page",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The opaque token from the previous page. Keep the same path, order, and limit."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A page of live environment files.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EnvironmentFileListResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List agent environment files"
+        }
+      },
+      "post": {
+        "operationId": "createAgentEnvironmentFile",
+        "summary": "Copies inline bytes or a Files API file into a connected execution environment. See [environment files](https://developers.openai.com/api/docs/guides/agents-api/environments/files).",
+        "description": "Copies inline bytes or a Files API file into a connected execution environment.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "environment_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the environment."
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/HostedEnvironmentFileParam"
+              }
+            }
+          }
+        },
+        "responses": {
+          "201": {
+            "description": "The created live environment file.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EnvironmentFileResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create an agent environment file"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/subagents": {
+      "get": {
+        "operationId": "listAgentSessionSubagents",
+        "summary": "Lists subagents in a session, including nested and closed subagents. See [subagent workflows](https://developers.openai.com/api/docs/guides/agents-api/multi-agent).",
+        "description": "Lists subagents in a session, including nested and closed subagents.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "format": "int64",
+              "minimum": 1,
+              "maximum": 100,
+              "default": 20
+            },
+            "description": "The maximum number of resources to return, between 1 and 100. Defaults to 20."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "The order in which resources are returned. Defaults to `desc`."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested subagents.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "object",
+                  "properties": {
+                    "object": {
+                      "type": "string",
+                      "enum": [
+                        "list"
+                      ],
+                      "default": "list",
+                      "x-stainless-const": true,
+                      "description": "The object type, which is always `list`."
+                    },
+                    "data": {
+                      "type": "array",
+                      "items": {
+                        "$ref": "#/components/schemas/SubagentResource"
+                      },
+                      "minItems": 0,
+                      "maxItems": 2000,
+                      "description": "The resources returned in this page, in the requested sort order."
+                    },
+                    "first_id": {
+                      "type": [
+                        "string",
+                        "null"
+                      ],
+                      "minLength": 0,
+                      "description": "The ID of the first resource in `data`, or `null` if the page is empty."
+                    },
+                    "last_id": {
+                      "type": [
+                        "string",
+                        "null"
+                      ],
+                      "minLength": 0,
+                      "description": "The ID of the last resource in `data`, or `null` if the page is empty. Pass this as `after` with the same order and filters."
+                    },
+                    "has_more": {
+                      "type": "boolean",
+                      "description": "Whether there are more resources to retrieve after this page."
+                    }
+                  },
+                  "required": [
+                    "object",
+                    "data",
+                    "first_id",
+                    "last_id",
+                    "has_more"
+                  ],
+                  "additionalProperties": false,
+                  "description": "A page of Agents API resources, with IDs for retrieving additional pages."
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List session subagents"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/subagents/{subagent_id}": {
+      "get": {
+        "operationId": "retrieveAgentSessionSubagent",
+        "summary": "Retrieves a subagent belonging to this session. See [subagent workflows](https://developers.openai.com/api/docs/guides/agents-api/multi-agent).",
+        "description": "Retrieves a subagent belonging to this session.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "subagent_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the subagent in this session."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested subagent.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SubagentResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve a session subagent"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/subagents/{subagent_id}/items": {
+      "get": {
+        "operationId": "listAgentSessionSubagentItems",
+        "summary": "Lists this subagent's own items across all of its turns. See [subagent workflows](https://developers.openai.com/api/docs/guides/agents-api/multi-agent).",
+        "description": "Lists this subagent's own items across all of its turns.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "subagent_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the subagent in this session."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "format": "int64",
+              "minimum": 1,
+              "maximum": 100,
+              "default": 20
+            },
+            "description": "The maximum number of resources to return, between 1 and 100. Defaults to 20."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "The order in which resources are returned. Defaults to `desc`."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested subagent history.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionItemListResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List subagent items"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/subagents/{subagent_id}/turns": {
+      "get": {
+        "operationId": "listAgentSessionSubagentTurns",
+        "summary": "Lists all turns of this subagent, including turns after a resume. See [subagent workflows](https://developers.openai.com/api/docs/guides/agents-api/multi-agent).",
+        "description": "Lists all turns of this subagent, including turns after a resume.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "subagent_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the subagent in this session."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "format": "int64",
+              "minimum": 1,
+              "maximum": 100,
+              "default": 20
+            },
+            "description": "The maximum number of resources to return, between 1 and 100. Defaults to 20."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "The order in which resources are returned. Defaults to `desc`."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested subagent history.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionTurnListResource",
+                  "description": "A page of turns from an agent session or subagent."
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List subagent turns"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/subagents/{subagent_id}/turns/{turn_id}": {
+      "get": {
+        "operationId": "retrieveAgentSessionSubagentTurn",
+        "summary": "Retrieves a turn belonging to this subagent. See [subagent workflows](https://developers.openai.com/api/docs/guides/agents-api/multi-agent).",
+        "description": "Retrieves a turn belonging to this subagent.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "subagent_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the subagent in this session."
+          },
+          {
+            "name": "turn_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of a turn belonging to this subagent."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested subagent history.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/TurnResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve a subagent turn"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/subagents/{subagent_id}/turns/{turn_id}/items": {
+      "get": {
+        "operationId": "listAgentSessionSubagentTurnItems",
+        "summary": "Lists items belonging to one turn of this subagent. See [subagent workflows](https://developers.openai.com/api/docs/guides/agents-api/multi-agent).",
+        "description": "Lists items belonging to one turn of this subagent.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "subagent_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the subagent in this session."
+          },
+          {
+            "name": "turn_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of a turn belonging to this subagent."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "format": "int64",
+              "minimum": 1,
+              "maximum": 100,
+              "default": 20
+            },
+            "description": "The maximum number of resources to return, between 1 and 100. Defaults to 20."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "The order in which resources are returned. Defaults to `desc`."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested subagent history.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionItemListResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List subagent turn items"
+        }
+      }
+    },
+    "/agents": {
+      "get": {
+        "operationId": "listAgents",
+        "summary": "Lists reusable agents in the current project. See [agent configuration](https://developers.openai.com/api/docs/guides/agents-api/configuration).",
+        "description": "Lists reusable agents in the current project.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": [
+                "integer",
+                "null"
+              ],
+              "format": "int64",
+              "minimum": 1
+            },
+            "description": "The maximum number of resources to return."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "The order in which resources are returned. Defaults to `desc`."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A page of agents.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/AgentListResource",
+                  "description": "A page of reusable agents."
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List agents"
+        }
+      },
+      "post": {
+        "operationId": "createAgent",
+        "summary": "Creates a reusable agent without storing credentials. See [agent configuration](https://developers.openai.com/api/docs/guides/agents-api/configuration).",
+        "description": "Creates a reusable agent without storing credentials.",
+        "tags": [
+          "Agents"
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateAgentParams"
+              }
+            }
+          }
+        },
+        "responses": {
+          "201": {
+            "description": "The created agent.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/AgentResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create an agent"
+        }
+      }
+    },
+    "/agents/{agent_id}": {
+      "get": {
+        "operationId": "retrieveAgent",
+        "summary": "Retrieves a reusable agent by ID. See [agent configuration](https://developers.openai.com/api/docs/guides/agents-api/configuration).",
+        "description": "Retrieves a reusable agent by ID.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "agent_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the reusable agent."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested agent.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/AgentResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve an agent"
+        }
+      },
+      "post": {
+        "operationId": "updateAgent",
+        "summary": "Updates a reusable agent. See [agent configuration](https://developers.openai.com/api/docs/guides/agents-api/configuration).",
+        "description": "Updates a reusable agent.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "agent_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the reusable agent."
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/UpdateAgentParams"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "The updated agent.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/AgentResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update an agent"
+        }
+      },
+      "delete": {
+        "operationId": "deleteAgent",
+        "summary": "Deletes a reusable agent. See [agent configuration](https://developers.openai.com/api/docs/guides/agents-api/configuration).",
+        "description": "Deletes a reusable agent.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "agent_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the reusable agent."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The deleted agent.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedAgentResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete an agent"
+        }
+      }
+    },
+    "/agents/environments/templates": {
+      "get": {
+        "operationId": "listAgentEnvironmentTemplates",
+        "summary": "Lists reusable environment templates without returning confidential values. See [reusing a hosted setup](https://developers.openai.com/api/docs/guides/agents-api/tools#reuse-a-hosted-plugin-setup).",
+        "description": "Lists reusable environment templates without returning confidential values.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "format": "int64",
+              "minimum": 1,
+              "maximum": 100,
+              "default": 20
+            },
+            "description": "The maximum number of resources to return, between 1 and 100. Defaults to 20."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "The order in which resources are returned. Defaults to `desc`."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A page of environment templates.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EnvironmentTemplateListResource",
+                  "description": "A page of reusable environment templates."
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested environment definition was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List agent environment templates"
+        }
+      },
+      "post": {
+        "operationId": "createAgentEnvironmentTemplate",
+        "summary": "Creates reusable environment configuration without returning confidential setup commands or environment values. See [reusing a hosted setup](https://developers.openai.com/api/docs/guides/agents-api/tools#reuse-a-hosted-plugin-setup).",
+        "description": "Creates reusable environment configuration without returning confidential setup commands or environment values.",
+        "tags": [
+          "Agents"
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateEnvironmentTemplateParams"
+              }
+            }
+          }
+        },
+        "responses": {
+          "201": {
+            "description": "The created environment template.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EnvironmentTemplateResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested environment definition was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create an agent environment template"
+        }
+      }
+    },
+    "/agents/environments/templates/{environment_template_id}": {
+      "get": {
+        "operationId": "retrieveAgentEnvironmentTemplate",
+        "summary": "Retrieves reusable environment configuration without returning confidential values. See [reusing a hosted setup](https://developers.openai.com/api/docs/guides/agents-api/tools#reuse-a-hosted-plugin-setup).",
+        "description": "Retrieves reusable environment configuration without returning confidential values.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "environment_template_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the reusable environment template."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested environment template.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EnvironmentTemplateResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested environment definition was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve an agent environment template"
+        }
+      },
+      "post": {
+        "operationId": "updateAgentEnvironmentTemplate",
+        "summary": "Updates reusable environment configuration without returning confidential values. See [reusing a hosted setup](https://developers.openai.com/api/docs/guides/agents-api/tools#reuse-a-hosted-plugin-setup).",
+        "description": "Updates reusable environment configuration without returning confidential values.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "environment_template_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the reusable environment template."
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/UpdateEnvironmentTemplateParams"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "The updated environment template.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/EnvironmentTemplateResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested environment definition was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current environment state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update an agent environment template"
+        }
+      },
+      "delete": {
+        "operationId": "deleteAgentEnvironmentTemplate",
+        "summary": "Deletes reusable environment configuration and all confidential template inputs. See [reusing a hosted setup](https://developers.openai.com/api/docs/guides/agents-api/tools#reuse-a-hosted-plugin-setup).",
+        "description": "Deletes reusable environment configuration and all confidential template inputs.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "environment_template_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the reusable environment template."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The deleted environment template.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedEnvironmentTemplateResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested environment definition was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current environment state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete an agent environment template"
+        }
+      }
+    },
+    "/agents/sessions": {
+      "get": {
+        "operationId": "listAgentSessions",
+        "summary": "Lists managed agent sessions using ID-based pagination and the requested sort order. See [managing sessions](https://developers.openai.com/api/docs/guides/agents-api/sessions/manage).",
+        "description": "Lists managed agent sessions using ID-based pagination and the requested sort order.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": [
+                "integer",
+                "null"
+              ],
+              "format": "int64",
+              "minimum": 1
+            },
+            "description": "The maximum number of resources to return."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "Sort order by the `created_at` timestamp. Use `asc` for ascending order or `desc` for descending order. Defaults to `desc`."
+          },
+          {
+            "name": "agent_id",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Only return sessions whose root agent has this ID. Omit to return sessions for all agents."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A page of sessions.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionListResource",
+                  "description": "A paginated list of sessions."
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List agent sessions"
+        }
+      },
+      "post": {
+        "operationId": "createAgentSession",
+        "summary": "Creates a managed agent session, optionally submits initial input, and returns the session or streams its events when stream is true. See [running sessions](https://developers.openai.com/api/docs/guides/agents-api/sessions).",
+        "description": "Creates a managed agent session, optionally submits initial input, and returns the session or streams its events when stream is true.",
+        "tags": [
+          "Agents"
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateAgentSessionParams"
+              }
+            }
+          }
+        },
+        "responses": {
+          "201": {
+            "description": "The created session or its event stream.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionResource"
+                }
+              },
+              "text/event-stream": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionEvent"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oai-streaming": {
+          "request_field": "stream",
+          "response_status_code": 201
+        },
+        "x-oaiMeta": {
+          "name": "Create an agent session"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}": {
+      "get": {
+        "operationId": "retrieveAgentSession",
+        "summary": "Retrieves the current state of a managed agent session. See [managing sessions](https://developers.openai.com/api/docs/guides/agents-api/sessions/manage).",
+        "description": "Retrieves the current state of a managed agent session.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested session.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve an agent session"
+        }
+      },
+      "post": {
+        "operationId": "updateAgentSession",
+        "summary": "Updates session metadata. Omitted fields are unchanged. See [managing sessions](https://developers.openai.com/api/docs/guides/agents-api/sessions/manage).",
+        "description": "Updates session metadata. Omitted fields are unchanged.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/UpdateAgentSessionParams"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "The updated session.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Update an agent session"
+        }
+      },
+      "delete": {
+        "operationId": "deleteAgentSession",
+        "summary": "Removes a managed agent session from the public API and returns a deletion confirmation. Physical cleanup may continue asynchronously. See [managing sessions](https://developers.openai.com/api/docs/guides/agents-api/sessions/manage).",
+        "description": "Removes a managed agent session from the public API and returns a deletion confirmation. Physical cleanup may continue asynchronously.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The deleted session.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedSessionResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete an agent session"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/artifacts": {
+      "get": {
+        "operationId": "listAgentSessionArtifacts",
+        "summary": "Lists immutable artifacts published by completed hosted session turns. See [session artifacts](https://developers.openai.com/api/docs/guides/agents-api/environments/files#openai-hosted-artifacts).",
+        "description": "Lists immutable artifacts published by completed hosted session turns.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam"
+            },
+            "description": "Sort by creation time and ID. Defaults to descending."
+          },
+          {
+            "name": "environment_id",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": [
+                "string",
+                "null"
+              ],
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Restrict the listing to artifacts produced by this environment."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": [
+                "integer",
+                "null"
+              ],
+              "format": "int64",
+              "minimum": 1,
+              "maximum": 100
+            },
+            "description": "The maximum number of artifacts to return, between 1 and 100."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": [
+                "string",
+                "null"
+              ],
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return artifacts after this immutable artifact ID."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A page of durable session artifacts.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionArtifactListResource",
+                  "description": "A page of durable artifacts published by a session."
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List agent session artifacts"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/artifacts/{artifact_id}": {
+      "get": {
+        "operationId": "retrieveAgentSessionArtifact",
+        "summary": "Retrieves immutable metadata for one durable session artifact. See [session artifacts](https://developers.openai.com/api/docs/guides/agents-api/environments/files#openai-hosted-artifacts).",
+        "description": "Retrieves immutable metadata for one durable session artifact.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session that owns the artifact."
+          },
+          {
+            "name": "artifact_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The immutable session artifact ID."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested session artifact.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionArtifactResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve an agent session artifact"
+        }
+      },
+      "delete": {
+        "operationId": "deleteAgentSessionArtifact",
+        "summary": "Deletes an immutable session artifact without deleting its live environment file or original Files API object. See [session artifacts](https://developers.openai.com/api/docs/guides/agents-api/environments/files#openai-hosted-artifacts).",
+        "description": "Deletes an immutable session artifact without deleting its live environment file or original Files API object.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session that owns the artifact."
+          },
+          {
+            "name": "artifact_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The immutable session artifact ID."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The deleted session artifact.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedSessionArtifactResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete an agent session artifact"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/artifacts/{artifact_id}/content": {
+      "get": {
+        "operationId": "retrieveAgentSessionArtifactContent",
+        "summary": "Downloads immutable session artifact bytes after the execution environment expires. See [session artifacts](https://developers.openai.com/api/docs/guides/agents-api/environments/files#openai-hosted-artifacts).",
+        "description": "Downloads immutable session artifact bytes after the execution environment expires.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session that owns the artifact."
+          },
+          {
+            "name": "artifact_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The immutable session artifact ID."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The immutable artifact contents.",
+            "content": {
+              "application/octet-stream": {
+                "schema": {
+                  "type": "string",
+                  "format": "binary"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve agent session artifact content"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/events": {
+      "get": {
+        "operationId": "listAgentSessionEvents",
+        "summary": "Streams live events for an agent session. See [session events](https://developers.openai.com/api/docs/guides/agents-api/sessions/events).",
+        "description": "Streams live events for an agent session.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A live stream of session events.",
+            "content": {
+              "text/event-stream": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionEvent"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oai-streaming": {
+          "request_field": null,
+          "response_status_code": 200
+        },
+        "x-oaiMeta": {
+          "name": "Stream agent session events"
+        }
+      },
+      "post": {
+        "operationId": "createAgentSessionEvents",
+        "summary": "Submits message, cancellation, or tool-result events to a managed agent session. See [session events](https://developers.openai.com/api/docs/guides/agents-api/sessions/events).",
+        "description": "Submits message, cancellation, or tool-result events to a managed agent session.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "Idempotency-Key",
+            "in": "header",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "description": "An optional client-generated key that makes retries of submitted messages idempotent."
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateSessionEventsParams"
+              }
+            }
+          }
+        },
+        "responses": {
+          "202": {
+            "description": "The events were accepted."
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create agent session input events"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/items": {
+      "get": {
+        "operationId": "listAgentSessionItems",
+        "summary": "Lists items produced by the session's root agent, including its interactions with subagents. Each subagent has its own item history. See [inspecting agent output](https://developers.openai.com/api/docs/guides/agents-api/observability).",
+        "description": "Lists items produced by the session's root agent, including its interactions with subagents. Each subagent has its own item history.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "format": "int64",
+              "minimum": 1,
+              "maximum": 100,
+              "default": 20
+            },
+            "description": "The maximum number of resources to return, between 1 and 100. Defaults to 20."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "The order in which resources are returned. Defaults to `desc`."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A page of session items.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionItemListResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required Responses permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List agent session items"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/turns": {
+      "get": {
+        "operationId": "listAgentSessionTurns",
+        "summary": "Lists turns by creation time and turn ID. The after cursor is exclusive in the selected order. See [session turns](https://developers.openai.com/api/docs/guides/agents-api/sessions/manage#inspect-session-turns).",
+        "description": "Lists turns by creation time and turn ID. The after cursor is exclusive in the selected order.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "format": "int64",
+              "minimum": 1,
+              "maximum": 100,
+              "default": 20
+            },
+            "description": "The maximum number of resources to return, between 1 and 100. Defaults to 20."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "The order in which resources are returned. Defaults to `desc`."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A page of session turns.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/SessionTurnListResource",
+                  "description": "A page of turns from an agent session or subagent."
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List agent session turns"
+        }
+      }
+    },
+    "/agents/sessions/{session_id}/turns/{turn_id}": {
+      "get": {
+        "operationId": "retrieveAgentSessionTurn",
+        "summary": "Retrieves a turn's current status, timestamps, usage, and error. Returns 404 if the turn does not belong to the session. See [session turns](https://developers.openai.com/api/docs/guides/agents-api/sessions/manage#inspect-session-turns).",
+        "description": "Retrieves a turn's current status, timestamps, usage, and error. Returns 404 if the turn does not belong to the session.",
+        "tags": [
+          "Agents"
+        ],
+        "parameters": [
+          {
+            "name": "session_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the session that owns the turn."
+          },
+          {
+            "name": "turn_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the turn."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested turn.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/TurnResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested session or event was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current session state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve an agent session turn"
+        }
+      }
+    },
+    "/vaults": {
+      "get": {
+        "operationId": "listVaults",
+        "summary": "Lists vaults using ID-based pagination. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).",
+        "description": "Lists vaults using ID-based pagination.",
+        "tags": [
+          "Vaults"
+        ],
+        "parameters": [
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "Sort order by the `created_at` timestamp. Use `asc` for ascending order or `desc` for descending order. Defaults to `desc`."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": [
+                "integer",
+                "null"
+              ],
+              "format": "int64",
+              "minimum": 0
+            },
+            "description": "The maximum number of resources to return. Defaults to 20. Values are clamped between 1 and 100."
+          },
+          {
+            "name": "status",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/VaultStatusFilterParam"
+            },
+            "description": "Filter by one status or a list, such as `status=active` or `status[]=active&status[]=archived`. Both statuses are included by default."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A page of vaults.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VaultListResource",
+                  "description": "A page of vaults."
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested vault or credential was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current vault state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List vaults"
+        }
+      },
+      "post": {
+        "operationId": "createVault",
+        "summary": "Creates a vault for the current project. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).",
+        "description": "Creates a vault for the current project.",
+        "tags": [
+          "Vaults"
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateVaultParams"
+              }
+            }
+          }
+        },
+        "responses": {
+          "201": {
+            "description": "The created vault.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VaultResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested vault or credential was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current vault state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create a vault"
+        }
+      }
+    },
+    "/vaults/{vault_id}": {
+      "get": {
+        "operationId": "retrieveVault",
+        "summary": "Retrieves a vault by its ID. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).",
+        "description": "Retrieves a vault by its ID.",
+        "tags": [
+          "Vaults"
+        ],
+        "parameters": [
+          {
+            "name": "vault_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the vault."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested vault.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VaultResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested vault or credential was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current vault state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve a vault"
+        }
+      },
+      "delete": {
+        "operationId": "deleteVault",
+        "summary": "Deletes a vault and all its credentials. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).",
+        "description": "Deletes a vault and all its credentials.",
+        "tags": [
+          "Vaults"
+        ],
+        "parameters": [
+          {
+            "name": "vault_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the vault."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The deleted vault.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedVaultResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested vault or credential was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current vault state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete a vault"
+        }
+      }
+    },
+    "/vaults/{vault_id}/credentials": {
+      "get": {
+        "operationId": "listVaultCredentials",
+        "summary": "Lists a vault's credentials using ID-based pagination without returning secret values. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).",
+        "description": "Lists a vault's credentials using ID-based pagination without returning secret values.",
+        "tags": [
+          "Vaults"
+        ],
+        "parameters": [
+          {
+            "name": "vault_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the vault."
+          },
+          {
+            "name": "order",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/ListOrderParam",
+              "default": "desc"
+            },
+            "description": "Sort order by the `created_at` timestamp. Use `asc` for ascending order or `desc` for descending order. Defaults to `desc`."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": [
+                "integer",
+                "null"
+              ],
+              "format": "int64",
+              "minimum": 0
+            },
+            "description": "The maximum number of resources to return. Defaults to 20. Values are clamped between 1 and 100."
+          },
+          {
+            "name": "status",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "$ref": "#/components/schemas/VaultStatusFilterParam"
+            },
+            "description": "Filter by one status or a list, such as `status=active` or `status[]=active&status[]=archived`. Both statuses are included by default."
+          },
+          {
+            "name": "after",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "Return resources after this resource ID in the selected order."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A page of vault credentials.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VaultCredentialListResource",
+                  "description": "A page of credentials in a vault."
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested vault or credential was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current vault state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List vault credentials"
+        }
+      },
+      "post": {
+        "operationId": "createVaultCredential",
+        "summary": "Creates a vault credential. Secret values are write-only and are never returned. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).",
+        "description": "Creates a vault credential. Secret values are write-only and are never returned.",
+        "tags": [
+          "Vaults"
+        ],
+        "parameters": [
+          {
+            "name": "vault_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the vault."
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateVaultCredentialParams"
+              }
+            }
+          }
+        },
+        "responses": {
+          "201": {
+            "description": "The created vault credential without secret values.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VaultCredentialResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested vault or credential was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current vault state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create a vault credential"
+        }
+      }
+    },
+    "/vaults/{vault_id}/credentials/{credential_id}": {
+      "get": {
+        "operationId": "retrieveVaultCredential",
+        "summary": "Retrieves vault credential metadata without returning secret values. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).",
+        "description": "Retrieves vault credential metadata without returning secret values.",
+        "tags": [
+          "Vaults"
+        ],
+        "parameters": [
+          {
+            "name": "vault_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the vault."
+          },
+          {
+            "name": "credential_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the vault credential."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The requested vault credential without secret values.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VaultCredentialResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested vault or credential was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current vault state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Retrieve a vault credential"
+        }
+      },
+      "post": {
+        "operationId": "rotateVaultCredential",
+        "summary": "Rotates a vault credential's write-only secret and returns only credential metadata. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).",
+        "description": "Rotates a vault credential's write-only secret and returns only credential metadata.",
+        "tags": [
+          "Vaults"
+        ],
+        "parameters": [
+          {
+            "name": "vault_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the vault."
+          },
+          {
+            "name": "credential_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the vault credential."
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/RotateVaultCredentialParams"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "The rotated vault credential without secret values.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/VaultCredentialResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested vault or credential was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current vault state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Rotate a vault credential"
+        }
+      },
+      "delete": {
+        "operationId": "deleteVaultCredential",
+        "summary": "Deletes a vault credential. See [vaults](https://developers.openai.com/api/docs/guides/agents-api/tools/vaults).",
+        "description": "Deletes a vault credential.",
+        "tags": [
+          "Vaults"
+        ],
+        "parameters": [
+          {
+            "name": "vault_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the vault."
+          },
+          {
+            "name": "credential_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "description": "The ID of the vault credential."
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "The deleted vault credential.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/DeletedVaultCredentialResource"
+                }
+              }
+            }
+          },
+          "400": {
+            "description": "The request was invalid.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "401": {
+            "description": "Authentication or project context was missing.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "403": {
+            "description": "The API key lacks the required management permission.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "The requested vault or credential was not found.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "409": {
+            "description": "The request conflicted with the current vault state.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "500": {
+            "description": "An internal error occurred.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          },
+          "503": {
+            "description": "The service is temporarily unavailable.",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse-2"
+                }
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete a vault credential"
+        }
+      }
+    },
+    "/responses?beta=true": {
+      "post": {
+        "operationId": "beta_createResponse",
+        "tags": [
+          "Responses"
+        ],
+        "summary": "Creates a model response. Provide [text](https://developers.openai.com/api/docs/guides/text) or\n[image](https://developers.openai.com/api/docs/guides/images-vision) inputs to generate [text](https://developers.openai.com/api/docs/guides/text)\nor [JSON](https://developers.openai.com/api/docs/guides/structured-outputs) outputs. Have the model call\nyour own [custom code](https://developers.openai.com/api/docs/guides/function-calling) or use built-in\n[tools](https://developers.openai.com/api/docs/guides/tools) like [web search](https://developers.openai.com/api/docs/guides/tools-web-search)\nor [file search](https://developers.openai.com/api/docs/guides/tools-file-search) to use your own data\nas input for the model's response.\n",
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/BetaCreateResponse"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/BetaResponse"
+                }
+              },
+              "text/event-stream": {
+                "schema": {
+                  "$ref": "#/components/schemas/BetaResponseStreamEvent"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/InferenceRateLimited"
+          },
+          "503": {
+            "$ref": "#/components/responses/InferenceServiceUnavailable"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Create a model response",
+          "group": "responses",
+          "path": "create",
+          "examples": [
+            {
+              "title": "Text input",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/responses \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-6-astra\",\n    \"input\": \"Tell me a three sentence bedtime story about a unicorn.\"\n  }'\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst response = await openai.responses.create({\n    model: \"gpt-6-astra\",\n    input: \"Tell me a three sentence bedtime story about a unicorn.\"\n});\n\nconsole.log(response);\n",
+                "python": "from openai import OpenAI\n\nclient = OpenAI()\n\nresponse = client.responses.create(\n  model=\"gpt-6-astra\",\n  input=\"Tell me a three sentence bedtime story about a unicorn.\"\n)\n\nprint(response)\n",
+                "csharp": "using System;\nusing OpenAI.Responses;\n\nOpenAIResponseClient client = new(\n    model: \"gpt-6-astra\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nOpenAIResponse response = client.CreateResponse(\"Tell me a three sentence bedtime story about a unicorn.\");\n\nConsole.WriteLine(response.GetOutputText());\n"
+              },
+              "response": "{\n  \"id\": \"resp_67ccd2bed1ec8190b14f964abc0542670bb6a6b452d3795b\",\n  \"object\": \"response\",\n  \"created_at\": 1741476542,\n  \"status\": \"completed\",\n  \"completed_at\": 1741476543,\n  \"error\": null,\n  \"incomplete_details\": null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"model\": \"gpt-6-astra\",\n  \"output\": [\n    {\n      \"type\": \"message\",\n      \"id\": \"msg_67ccd2bf17f0819081ff3bb2cf6508e60bb6a6b452d3795b\",\n      \"status\": \"completed\",\n      \"role\": \"assistant\",\n      \"content\": [\n        {\n          \"type\": \"output_text\",\n          \"text\": \"In a peaceful grove beneath a silver moon, a unicorn named Lumina discovered a hidden pool that reflected the stars. As she dipped her horn into the water, the pool began to shimmer, revealing a pathway to a magical realm of endless night skies. Filled with wonder, Lumina whispered a wish for all who dream to find their own hidden magic, and as she glanced back, her hoofprints sparkled like stardust.\",\n          \"annotations\": []\n        }\n      ]\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": null,\n  \"reasoning\": {\n    \"effort\": null,\n    \"summary\": null\n  },\n  \"store\": true,\n  \"temperature\": 1.0,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [],\n  \"top_p\": 1.0,\n  \"truncation\": \"disabled\",\n  \"usage\": {\n    \"input_tokens\": 36,\n    \"input_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"cache_write_tokens\": 0\n    },\n    \"output_tokens\": 87,\n    \"output_tokens_details\": {\n      \"reasoning_tokens\": 0\n    },\n    \"total_tokens\": 123\n  },\n  \"user\": null,\n  \"metadata\": {}\n}\n"
+            },
+            {
+              "title": "Image input",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/responses \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-6-astra\",\n    \"input\": [\n      {\n        \"role\": \"user\",\n        \"content\": [\n          {\"type\": \"input_text\", \"text\": \"what is in this image?\"},\n          {\n            \"type\": \"input_image\",\n            \"image_url\": \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\"\n          }\n        ]\n      }\n    ]\n  }'\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst response = await openai.responses.create({\n    model: \"gpt-6-astra\",\n    input: [\n        {\n            role: \"user\",\n            content: [\n                { type: \"input_text\", text: \"what is in this image?\" },\n                {\n                    type: \"input_image\",\n                    image_url:\n                        \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\",\n                },\n            ],\n        },\n    ],\n});\n\nconsole.log(response);\n",
+                "python": "from openai import OpenAI\n\nclient = OpenAI()\n\nresponse = client.responses.create(\n    model=\"gpt-6-astra\",\n    input=[\n        {\n            \"role\": \"user\",\n            \"content\": [\n                { \"type\": \"input_text\", \"text\": \"what is in this image?\" },\n                {\n                    \"type\": \"input_image\",\n                    \"image_url\": \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\"\n                }\n            ]\n        }\n    ]\n)\n\nprint(response)\n",
+                "csharp": "using System;\nusing System.Collections.Generic;\n\nusing OpenAI.Responses;\n\nOpenAIResponseClient client = new(\n    model: \"gpt-6-astra\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nList<ResponseItem> inputItems =\n[\n    ResponseItem.CreateUserMessageItem(\n        [\n            ResponseContentPart.CreateInputTextPart(\"What is in this image?\"),\n            ResponseContentPart.CreateInputImagePart(new Uri(\"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\"))\n        ]\n    )\n];\n\nOpenAIResponse response = client.CreateResponse(inputItems);\n\nConsole.WriteLine(response.GetOutputText());\n"
+              },
+              "response": "{\n  \"id\": \"resp_67ccd3a9da748190baa7f1570fe91ac604becb25c45c1d41\",\n  \"object\": \"response\",\n  \"created_at\": 1741476777,\n  \"status\": \"completed\",\n  \"completed_at\": 1741476778,\n  \"error\": null,\n  \"incomplete_details\": null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"model\": \"gpt-6-astra\",\n  \"output\": [\n    {\n      \"type\": \"message\",\n      \"id\": \"msg_67ccd3acc8d48190a77525dc6de64b4104becb25c45c1d41\",\n      \"status\": \"completed\",\n      \"role\": \"assistant\",\n      \"content\": [\n        {\n          \"type\": \"output_text\",\n          \"text\": \"The image depicts a scenic landscape with a wooden boardwalk or pathway leading through lush, green grass under a blue sky with some clouds. The setting suggests a peaceful natural area, possibly a park or nature reserve. There are trees and shrubs in the background.\",\n          \"annotations\": []\n        }\n      ]\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": null,\n  \"reasoning\": {\n    \"effort\": null,\n    \"summary\": null\n  },\n  \"store\": true,\n  \"temperature\": 1.0,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [],\n  \"top_p\": 1.0,\n  \"truncation\": \"disabled\",\n  \"usage\": {\n    \"input_tokens\": 328,\n    \"input_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"cache_write_tokens\": 0\n    },\n    \"output_tokens\": 52,\n    \"output_tokens_details\": {\n      \"reasoning_tokens\": 0\n    },\n    \"total_tokens\": 380\n  },\n  \"user\": null,\n  \"metadata\": {}\n}\n"
+            },
+            {
+              "title": "File input",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/responses \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-6-astra\",\n    \"input\": [\n      {\n        \"role\": \"user\",\n        \"content\": [\n          {\"type\": \"input_text\", \"text\": \"what is in this file?\"},\n          {\n            \"type\": \"input_file\",\n            \"file_url\": \"https://www.berkshirehathaway.com/letters/2024ltr.pdf\",\n            \"detail\": \"auto\"\n          }\n        ]\n      }\n    ]\n  }'\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst response = await openai.responses.create({\n    model: \"gpt-6-astra\",\n    input: [\n        {\n            role: \"user\",\n            content: [\n                { type: \"input_text\", text: \"what is in this file?\" },\n                {\n                    type: \"input_file\",\n                    file_url: \"https://www.berkshirehathaway.com/letters/2024ltr.pdf\",\n                    detail: \"auto\",\n                },\n            ],\n        },\n    ],\n});\n\nconsole.log(response);\n",
+                "python": "from openai import OpenAI\n\nclient = OpenAI()\n\nresponse = client.responses.create(\n    model=\"gpt-6-astra\",\n    input=[\n        {\n            \"role\": \"user\",\n            \"content\": [\n                { \"type\": \"input_text\", \"text\": \"what is in this file?\" },\n                {\n                    \"type\": \"input_file\",\n                    \"file_url\": \"https://www.berkshirehathaway.com/letters/2024ltr.pdf\",\n                    \"detail\": \"auto\"\n                }\n            ]\n        }\n    ]\n)\n\nprint(response)\n"
+              },
+              "response": "{\n  \"id\": \"resp_686eef60237881a2bd1180bb8b13de430e34c516d176ff86\",\n  \"object\": \"response\",\n  \"created_at\": 1752100704,\n  \"status\": \"completed\",\n  \"completed_at\": 1752100705,\n  \"background\": false,\n  \"error\": null,\n  \"incomplete_details\": null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"max_tool_calls\": null,\n  \"model\": \"gpt-6-astra\",\n  \"output\": [\n    {\n      \"id\": \"msg_686eef60d3e081a29283bdcbc4322fd90e34c516d176ff86\",\n      \"type\": \"message\",\n      \"status\": \"completed\",\n      \"content\": [\n        {\n          \"type\": \"output_text\",\n          \"annotations\": [],\n          \"logprobs\": [],\n          \"text\": \"The file seems to contain excerpts from a letter to the shareholders of Berkshire Hathaway Inc., likely written by Warren Buffett. It covers several topics:\\n\\n1. **Communication Philosophy**: Buffett emphasizes the importance of transparency and candidness in reporting mistakes and successes to shareholders.\\n\\n2. **Mistakes and Learnings**: The letter acknowledges past mistakes in business assessments and management hires, highlighting the importance of correcting errors promptly.\\n\\n3. **CEO Succession**: Mention of Greg Abel stepping in as the new CEO and continuing the tradition of honest communication.\\n\\n4. **Pete Liegl Story**: A detailed account of acquiring Forest River and the relationship with its founder, highlighting trust and effective business decisions.\\n\\n5. **2024 Performance**: Overview of business performance, particularly in insurance and investment activities, with a focus on GEICO's improvement.\\n\\n6. **Tax Contributions**: Discussion of significant tax payments to the U.S. Treasury, credited to shareholders' reinvestments.\\n\\n7. **Investment Strategy**: A breakdown of Berkshire\\u2019s investments in both controlled subsidiaries and marketable equities, along with a focus on long-term holding strategies.\\n\\n8. **American Capitalism**: Reflections on America\\u2019s economic development and Berkshire\\u2019s role within it.\\n\\n9. **Property-Casualty Insurance**: Insights into the P/C insurance business model and its challenges and benefits.\\n\\n10. **Japanese Investments**: Information about Berkshire\\u2019s investments in Japanese companies and future plans.\\n\\n11. **Annual Meeting**: Details about the upcoming annual gathering in Omaha, including schedule changes and new book releases.\\n\\n12. **Personal Anecdotes**: Light-hearted stories about family and interactions, conveying Buffett's personable approach.\\n\\n13. **Financial Performance Data**: Tables comparing Berkshire\\u2019s annual performance to the S&P 500, showing impressive long-term gains.\\n\\nOverall, the letter reinforces Berkshire Hathaway's commitment to transparency, investment in both its businesses and the wider economy, and emphasizes strong leadership and prudent financial management.\"\n        }\n      ],\n      \"role\": \"assistant\"\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": null,\n  \"reasoning\": {\n    \"effort\": null,\n    \"summary\": null\n  },\n  \"service_tier\": \"default\",\n  \"store\": true,\n  \"temperature\": 1.0,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [],\n  \"top_logprobs\": 0,\n  \"top_p\": 1.0,\n  \"truncation\": \"disabled\",\n  \"usage\": {\n    \"input_tokens\": 8438,\n    \"input_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"cache_write_tokens\": 0\n    },\n    \"output_tokens\": 398,\n    \"output_tokens_details\": {\n      \"reasoning_tokens\": 0\n    },\n    \"total_tokens\": 8836\n  },\n  \"user\": null,\n  \"metadata\": {}\n}\n"
+            },
+            {
+              "title": "Web search",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/responses \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-6-astra\",\n    \"tools\": [{ \"type\": \"web_search_preview\" }],\n    \"input\": \"What was a positive news story from today?\"\n  }'\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst response = await openai.responses.create({\n    model: \"gpt-6-astra\",\n    tools: [{ type: \"web_search_preview\" }],\n    input: \"What was a positive news story from today?\",\n});\n\nconsole.log(response);\n",
+                "python": "from openai import OpenAI\n\nclient = OpenAI()\n\nresponse = client.responses.create(\n    model=\"gpt-6-astra\",\n    tools=[{ \"type\": \"web_search_preview\" }],\n    input=\"What was a positive news story from today?\",\n)\n\nprint(response)\n",
+                "csharp": "using System;\n\nusing OpenAI.Responses;\n\nOpenAIResponseClient client = new(\n    model: \"gpt-6-astra\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nstring userInputText = \"What was a positive news story from today?\";\n\nResponseCreationOptions options = new()\n{\n    Tools =\n    {\n        ResponseTool.CreateWebSearchTool()\n    },\n};\n\nOpenAIResponse response = client.CreateResponse(userInputText, options);\n\nConsole.WriteLine(response.GetOutputText());\n"
+              },
+              "response": "{\n  \"id\": \"resp_67ccf18ef5fc8190b16dbee19bc54e5f087bb177ab789d5c\",\n  \"object\": \"response\",\n  \"created_at\": 1741484430,\n  \"status\": \"completed\",\n  \"completed_at\": 1741484431,\n  \"error\": null,\n  \"incomplete_details\": null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"model\": \"gpt-6-astra\",\n  \"output\": [\n    {\n      \"type\": \"web_search_call\",\n      \"id\": \"ws_67ccf18f64008190a39b619f4c8455ef087bb177ab789d5c\",\n      \"status\": \"completed\"\n    },\n    {\n      \"type\": \"message\",\n      \"id\": \"msg_67ccf190ca3881909d433c50b1f6357e087bb177ab789d5c\",\n      \"status\": \"completed\",\n      \"role\": \"assistant\",\n      \"content\": [\n        {\n          \"type\": \"output_text\",\n          \"text\": \"As of today, March 9, 2025, one notable positive news story...\",\n          \"annotations\": [\n            {\n              \"type\": \"url_citation\",\n              \"start_index\": 442,\n              \"end_index\": 557,\n              \"url\": \"https://.../?utm_source=chatgpt.com\",\n              \"title\": \"...\"\n            },\n            {\n              \"type\": \"url_citation\",\n              \"start_index\": 962,\n              \"end_index\": 1077,\n              \"url\": \"https://.../?utm_source=chatgpt.com\",\n              \"title\": \"...\"\n            },\n            {\n              \"type\": \"url_citation\",\n              \"start_index\": 1336,\n              \"end_index\": 1451,\n              \"url\": \"https://.../?utm_source=chatgpt.com\",\n              \"title\": \"...\"\n            }\n          ]\n        }\n      ]\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": null,\n  \"reasoning\": {\n    \"effort\": null,\n    \"summary\": null\n  },\n  \"store\": true,\n  \"temperature\": 1.0,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [\n    {\n      \"type\": \"web_search_preview\",\n      \"domains\": [],\n      \"search_context_size\": \"medium\",\n      \"user_location\": {\n        \"type\": \"approximate\",\n        \"city\": null,\n        \"country\": \"US\",\n        \"region\": null,\n        \"timezone\": null\n      }\n    }\n  ],\n  \"top_p\": 1.0,\n  \"truncation\": \"disabled\",\n  \"usage\": {\n    \"input_tokens\": 328,\n    \"input_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"cache_write_tokens\": 0\n    },\n    \"output_tokens\": 356,\n    \"output_tokens_details\": {\n      \"reasoning_tokens\": 0\n    },\n    \"total_tokens\": 684\n  },\n  \"user\": null,\n  \"metadata\": {}\n}\n"
+            },
+            {
+              "title": "File search",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/responses \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-6-astra\",\n    \"tools\": [{\n      \"type\": \"file_search\",\n      \"vector_store_ids\": [\"vs_1234567890\"],\n      \"max_num_results\": 20\n    }],\n    \"input\": \"What are the attributes of an ancient brown dragon?\"\n  }'\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst response = await openai.responses.create({\n    model: \"gpt-6-astra\",\n    tools: [{\n      type: \"file_search\",\n      vector_store_ids: [\"vs_1234567890\"],\n      max_num_results: 20\n    }],\n    input: \"What are the attributes of an ancient brown dragon?\",\n});\n\nconsole.log(response);\n",
+                "python": "from openai import OpenAI\n\nclient = OpenAI()\n\nresponse = client.responses.create(\n    model=\"gpt-6-astra\",\n    tools=[{\n      \"type\": \"file_search\",\n      \"vector_store_ids\": [\"vs_1234567890\"],\n      \"max_num_results\": 20\n    }],\n    input=\"What are the attributes of an ancient brown dragon?\",\n)\n\nprint(response)\n",
+                "csharp": "using System;\n\nusing OpenAI.Responses;\n\nOpenAIResponseClient client = new(\n    model: \"gpt-6-astra\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nstring userInputText = \"What are the attributes of an ancient brown dragon?\";\n\nResponseCreationOptions options = new()\n{\n    Tools =\n    {\n        ResponseTool.CreateFileSearchTool(\n            vectorStoreIds: [\"vs_1234567890\"],\n            maxResultCount: 20\n        )\n    },\n};\n\nOpenAIResponse response = client.CreateResponse(userInputText, options);\n\nConsole.WriteLine(response.GetOutputText());\n"
+              },
+              "response": "{\n  \"id\": \"resp_67ccf4c55fc48190b71bd0463ad3306d09504fb6872380d7\",\n  \"object\": \"response\",\n  \"created_at\": 1741485253,\n  \"status\": \"completed\",\n  \"completed_at\": 1741485254,\n  \"error\": null,\n  \"incomplete_details\": null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"model\": \"gpt-6-astra\",\n  \"output\": [\n    {\n      \"type\": \"file_search_call\",\n      \"id\": \"fs_67ccf4c63cd08190887ef6464ba5681609504fb6872380d7\",\n      \"status\": \"completed\",\n      \"queries\": [\n        \"attributes of an ancient brown dragon\"\n      ],\n      \"results\": null\n    },\n    {\n      \"type\": \"message\",\n      \"id\": \"msg_67ccf4c93e5c81909d595b369351a9d309504fb6872380d7\",\n      \"status\": \"completed\",\n      \"role\": \"assistant\",\n      \"content\": [\n        {\n          \"type\": \"output_text\",\n          \"text\": \"The attributes of an ancient brown dragon include...\",\n          \"annotations\": [\n            {\n              \"type\": \"file_citation\",\n              \"index\": 320,\n              \"file_id\": \"file-4wDz5b167pAf72nx1h9eiN\",\n              \"filename\": \"dragons.pdf\"\n            },\n            {\n              \"type\": \"file_citation\",\n              \"index\": 576,\n              \"file_id\": \"file-4wDz5b167pAf72nx1h9eiN\",\n              \"filename\": \"dragons.pdf\"\n            },\n            {\n              \"type\": \"file_citation\",\n              \"index\": 815,\n              \"file_id\": \"file-4wDz5b167pAf72nx1h9eiN\",\n              \"filename\": \"dragons.pdf\"\n            },\n            {\n              \"type\": \"file_citation\",\n              \"index\": 815,\n              \"file_id\": \"file-4wDz5b167pAf72nx1h9eiN\",\n              \"filename\": \"dragons.pdf\"\n            },\n            {\n              \"type\": \"file_citation\",\n              \"index\": 1030,\n              \"file_id\": \"file-4wDz5b167pAf72nx1h9eiN\",\n              \"filename\": \"dragons.pdf\"\n            },\n            {\n              \"type\": \"file_citation\",\n              \"index\": 1030,\n              \"file_id\": \"file-4wDz5b167pAf72nx1h9eiN\",\n              \"filename\": \"dragons.pdf\"\n            },\n            {\n              \"type\": \"file_citation\",\n              \"index\": 1156,\n              \"file_id\": \"file-4wDz5b167pAf72nx1h9eiN\",\n              \"filename\": \"dragons.pdf\"\n            },\n            {\n              \"type\": \"file_citation\",\n              \"index\": 1225,\n              \"file_id\": \"file-4wDz5b167pAf72nx1h9eiN\",\n              \"filename\": \"dragons.pdf\"\n            }\n          ]\n        }\n      ]\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": null,\n  \"reasoning\": {\n    \"effort\": null,\n    \"summary\": null\n  },\n  \"store\": true,\n  \"temperature\": 1.0,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [\n    {\n      \"type\": \"file_search\",\n      \"filters\": null,\n      \"max_num_results\": 20,\n      \"ranking_options\": {\n        \"ranker\": \"auto\",\n        \"score_threshold\": 0.0\n      },\n      \"vector_store_ids\": [\n        \"vs_1234567890\"\n      ]\n    }\n  ],\n  \"top_p\": 1.0,\n  \"truncation\": \"disabled\",\n  \"usage\": {\n    \"input_tokens\": 18307,\n    \"input_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"cache_write_tokens\": 0\n    },\n    \"output_tokens\": 348,\n    \"output_tokens_details\": {\n      \"reasoning_tokens\": 0\n    },\n    \"total_tokens\": 18655\n  },\n  \"user\": null,\n  \"metadata\": {}\n}\n"
+            },
+            {
+              "title": "Streaming",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/responses \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-6-astra\",\n    \"instructions\": \"You are a helpful assistant.\",\n    \"input\": \"Hello!\",\n    \"stream\": true\n  }'\n",
+                "python": "from openai import OpenAI\n\nclient = OpenAI()\n\nresponse = client.responses.create(\n  model=\"gpt-6-astra\",\n  instructions=\"You are a helpful assistant.\",\n  input=\"Hello!\",\n  stream=True\n)\n\nfor event in response:\n  print(event)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst response = await openai.responses.create({\n    model: \"gpt-6-astra\",\n    instructions: \"You are a helpful assistant.\",\n    input: \"Hello!\",\n    stream: true,\n});\n\nfor await (const event of response) {\n    console.log(event);\n}\n",
+                "csharp": "using System;\nusing System.ClientModel;\nusing System.Threading.Tasks;\n\nusing OpenAI.Responses;\n\nOpenAIResponseClient client = new(\n    model: \"gpt-6-astra\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nstring userInputText = \"Hello!\";\n\nResponseCreationOptions options = new()\n{\n    Instructions = \"You are a helpful assistant.\",\n};\n\nAsyncCollectionResult<StreamingResponseUpdate> responseUpdates = client.CreateResponseStreamingAsync(userInputText, options);\n\nawait foreach (StreamingResponseUpdate responseUpdate in responseUpdates)\n{\n    if (responseUpdate is StreamingResponseOutputTextDeltaUpdate outputTextDeltaUpdate)\n    {\n        Console.Write(outputTextDeltaUpdate.Delta);\n    }\n}\n"
+              },
+              "response": "event: response.created\ndata: {\"type\":\"response.created\",\"response\":{\"id\":\"resp_67c9fdcecf488190bdd9a0409de3a1ec07b8b0ad4e5eb654\",\"object\":\"response\",\"created_at\":1741290958,\"status\":\"in_progress\",\"error\":null,\"incomplete_details\":null,\"instructions\":\"You are a helpful assistant.\",\"max_output_tokens\":null,\"model\":\"gpt-6-astra\",\"output\":[],\"parallel_tool_calls\":true,\"previous_response_id\":null,\"reasoning\":{\"effort\":null,\"summary\":null},\"store\":true,\"temperature\":1.0,\"text\":{\"format\":{\"type\":\"text\"}},\"tool_choice\":\"auto\",\"tools\":[],\"top_p\":1.0,\"truncation\":\"disabled\",\"usage\":null,\"user\":null,\"metadata\":{}}}\n\nevent: response.in_progress\ndata: {\"type\":\"response.in_progress\",\"response\":{\"id\":\"resp_67c9fdcecf488190bdd9a0409de3a1ec07b8b0ad4e5eb654\",\"object\":\"response\",\"created_at\":1741290958,\"status\":\"in_progress\",\"error\":null,\"incomplete_details\":null,\"instructions\":\"You are a helpful assistant.\",\"max_output_tokens\":null,\"model\":\"gpt-6-astra\",\"output\":[],\"parallel_tool_calls\":true,\"previous_response_id\":null,\"reasoning\":{\"effort\":null,\"summary\":null},\"store\":true,\"temperature\":1.0,\"text\":{\"format\":{\"type\":\"text\"}},\"tool_choice\":\"auto\",\"tools\":[],\"top_p\":1.0,\"truncation\":\"disabled\",\"usage\":null,\"user\":null,\"metadata\":{}}}\n\nevent: response.output_item.added\ndata: {\"type\":\"response.output_item.added\",\"output_index\":0,\"item\":{\"id\":\"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654\",\"type\":\"message\",\"status\":\"in_progress\",\"role\":\"assistant\",\"content\":[]}}\n\nevent: response.content_part.added\ndata: {\"type\":\"response.content_part.added\",\"item_id\":\"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654\",\"output_index\":0,\"content_index\":0,\"part\":{\"type\":\"output_text\",\"text\":\"\",\"annotations\":[]}}\n\nevent: response.output_text.delta\ndata: {\"type\":\"response.output_text.delta\",\"item_id\":\"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654\",\"output_index\":0,\"content_index\":0,\"delta\":\"Hi\"}\n\n...\n\nevent: response.output_text.done\ndata: {\"type\":\"response.output_text.done\",\"item_id\":\"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654\",\"output_index\":0,\"content_index\":0,\"text\":\"Hi there! How can I assist you today?\"}\n\nevent: response.content_part.done\ndata: {\"type\":\"response.content_part.done\",\"item_id\":\"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654\",\"output_index\":0,\"content_index\":0,\"part\":{\"type\":\"output_text\",\"text\":\"Hi there! How can I assist you today?\",\"annotations\":[]}}\n\nevent: response.output_item.done\ndata: {\"type\":\"response.output_item.done\",\"output_index\":0,\"item\":{\"id\":\"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654\",\"type\":\"message\",\"status\":\"completed\",\"role\":\"assistant\",\"content\":[{\"type\":\"output_text\",\"text\":\"Hi there! How can I assist you today?\",\"annotations\":[]}]}}\n\nevent: response.completed\ndata: {\"type\":\"response.completed\",\"response\":{\"id\":\"resp_67c9fdcecf488190bdd9a0409de3a1ec07b8b0ad4e5eb654\",\"object\":\"response\",\"created_at\":1741290958,\"status\":\"completed\",\"error\":null,\"incomplete_details\":null,\"instructions\":\"You are a helpful assistant.\",\"max_output_tokens\":null,\"model\":\"gpt-6-astra\",\"output\":[{\"id\":\"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654\",\"type\":\"message\",\"status\":\"completed\",\"role\":\"assistant\",\"content\":[{\"type\":\"output_text\",\"text\":\"Hi there! How can I assist you today?\",\"annotations\":[]}]}],\"parallel_tool_calls\":true,\"previous_response_id\":null,\"reasoning\":{\"effort\":null,\"summary\":null},\"store\":true,\"temperature\":1.0,\"text\":{\"format\":{\"type\":\"text\"}},\"tool_choice\":\"auto\",\"tools\":[],\"top_p\":1.0,\"truncation\":\"disabled\",\"usage\":{\"input_tokens\":37,\"output_tokens\":11,\"output_tokens_details\":{\"reasoning_tokens\":0},\"total_tokens\":48},\"user\":null,\"metadata\":{}}}\n"
+            },
+            {
+              "title": "Functions",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/responses \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-6-astra\",\n    \"input\": \"What is the weather like in Boston today?\",\n    \"tools\": [\n      {\n        \"type\": \"function\",\n        \"name\": \"get_current_weather\",\n        \"description\": \"Get the current weather in a given location\",\n        \"parameters\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"location\": {\n              \"type\": \"string\",\n              \"description\": \"The city and state, e.g. San Francisco, CA\"\n            },\n            \"unit\": {\n              \"type\": \"string\",\n              \"enum\": [\"celsius\", \"fahrenheit\"]\n            }\n          },\n          \"required\": [\"location\", \"unit\"]\n        }\n      }\n    ],\n    \"tool_choice\": \"auto\"\n  }'\n",
+                "python": "from openai import OpenAI\n\nclient = OpenAI()\n\ntools = [\n    {\n        \"type\": \"function\",\n        \"name\": \"get_current_weather\",\n        \"description\": \"Get the current weather in a given location\",\n        \"parameters\": {\n          \"type\": \"object\",\n          \"properties\": {\n              \"location\": {\n                  \"type\": \"string\",\n                  \"description\": \"The city and state, e.g. San Francisco, CA\",\n              },\n              \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]},\n          },\n          \"required\": [\"location\", \"unit\"],\n        }\n    }\n]\n\nresponse = client.responses.create(\n  model=\"gpt-6-astra\",\n  tools=tools,\n  input=\"What is the weather like in Boston today?\",\n  tool_choice=\"auto\"\n)\n\nprint(response)\n",
+                "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nconst tools = [\n    {\n        type: \"function\",\n        name: \"get_current_weather\",\n        description: \"Get the current weather in a given location\",\n        parameters: {\n            type: \"object\",\n            properties: {\n                location: {\n                    type: \"string\",\n                    description: \"The city and state, e.g. San Francisco, CA\",\n                },\n                unit: { type: \"string\", enum: [\"celsius\", \"fahrenheit\"] },\n            },\n            required: [\"location\", \"unit\"],\n        },\n    },\n];\n\nconst response = await openai.responses.create({\n    model: \"gpt-6-astra\",\n    tools: tools,\n    input: \"What is the weather like in Boston today?\",\n    tool_choice: \"auto\",\n});\n\nconsole.log(response);\n",
+                "csharp": "using System;\nusing OpenAI.Responses;\n\nOpenAIResponseClient client = new(\n    model: \"gpt-6-astra\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nResponseTool getCurrentWeatherFunctionTool = ResponseTool.CreateFunctionTool(\n    functionName: \"get_current_weather\",\n    functionDescription: \"Get the current weather in a given location\",\n    functionParameters: BinaryData.FromString(\"\"\"\n        {\n            \"type\": \"object\",\n            \"properties\": {\n                \"location\": {\n                    \"type\": \"string\",\n                    \"description\": \"The city and state, e.g. San Francisco, CA\"\n                },\n                \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]}\n            },\n            \"required\": [\"location\", \"unit\"]\n        }\n        \"\"\"\n    )\n);\n\nstring userInputText = \"What is the weather like in Boston today?\";\n\nResponseCreationOptions options = new()\n{\n    Tools =\n    {\n        getCurrentWeatherFunctionTool\n    },\n    ToolChoice = ResponseToolChoice.CreateAutoChoice(),\n};\n\nOpenAIResponse response = client.CreateResponse(userInputText, options);\n"
+              },
+              "response": "{\n  \"id\": \"resp_67ca09c5efe0819096d0511c92b8c890096610f474011cc0\",\n  \"object\": \"response\",\n  \"created_at\": 1741294021,\n  \"status\": \"completed\",\n  \"completed_at\": 1741294022,\n  \"error\": null,\n  \"incomplete_details\": null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"model\": \"gpt-6-astra\",\n  \"output\": [\n    {\n      \"type\": \"function_call\",\n      \"id\": \"fc_67ca09c6bedc8190a7abfec07b1a1332096610f474011cc0\",\n      \"call_id\": \"call_unLAR8MvFNptuiZK6K6HCy5k\",\n      \"name\": \"get_current_weather\",\n      \"arguments\": \"{\\\"location\\\":\\\"Boston, MA\\\",\\\"unit\\\":\\\"celsius\\\"}\",\n      \"status\": \"completed\"\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": null,\n  \"reasoning\": {\n    \"effort\": null,\n    \"summary\": null\n  },\n  \"store\": true,\n  \"temperature\": 1.0,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"description\": \"Get the current weather in a given location\",\n      \"name\": \"get_current_weather\",\n      \"parameters\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"location\": {\n            \"type\": \"string\",\n            \"description\": \"The city and state, e.g. San Francisco, CA\"\n          },\n          \"unit\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"celsius\",\n              \"fahrenheit\"\n            ]\n          }\n        },\n        \"required\": [\n          \"location\",\n          \"unit\"\n        ]\n      },\n      \"strict\": true\n    }\n  ],\n  \"top_p\": 1.0,\n  \"truncation\": \"disabled\",\n  \"usage\": {\n    \"input_tokens\": 291,\n    \"output_tokens\": 23,\n    \"output_tokens_details\": {\n      \"reasoning_tokens\": 0\n    },\n    \"total_tokens\": 314\n  },\n  \"user\": null,\n  \"metadata\": {}\n}\n"
+            },
+            {
+              "title": "Reasoning",
+              "request": {
+                "curl": "curl https://api.openai.com/v1/responses \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n  -d '{\n    \"model\": \"gpt-6-astra\",\n    \"input\": \"How much wood would a woodchuck chuck?\",\n    \"reasoning\": {\n      \"effort\": \"high\"\n    }\n  }'\n",
+                "javascript": "import OpenAI from \"openai\";\nconst openai = new OpenAI();\n\nconst response = await openai.responses.create({\n    model: \"gpt-6-astra\",\n    input: \"How much wood would a woodchuck chuck?\",\n    reasoning: {\n      effort: \"high\"\n    }\n});\n\nconsole.log(response);\n",
+                "python": "from openai import OpenAI\nclient = OpenAI()\n\nresponse = client.responses.create(\n    model=\"gpt-6-astra\",\n    input=\"How much wood would a woodchuck chuck?\",\n    reasoning={\n        \"effort\": \"high\"\n    }\n)\n\nprint(response)\n",
+                "csharp": "using System;\nusing OpenAI.Responses;\n\nOpenAIResponseClient client = new(\n    model: \"gpt-6-astra\",\n    apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nstring userInputText = \"How much wood would a woodchuck chuck?\";\n\nResponseCreationOptions options = new()\n{\n    ReasoningOptions = new()\n    {\n        ReasoningEffortLevel = ResponseReasoningEffortLevel.High,\n    },\n};\n\nOpenAIResponse response = client.CreateResponse(userInputText, options);\n\nConsole.WriteLine(response.GetOutputText());\n"
+              },
+              "response": "{\n  \"id\": \"resp_67ccd7eca01881908ff0b5146584e408072912b2993db808\",\n  \"object\": \"response\",\n  \"created_at\": 1741477868,\n  \"status\": \"completed\",\n  \"completed_at\": 1741477869,\n  \"error\": null,\n  \"incomplete_details\": null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"model\": \"gpt-6-astra\",\n  \"output\": [\n    {\n      \"type\": \"message\",\n      \"id\": \"msg_67ccd7f7b5848190a6f3e95d809f6b44072912b2993db808\",\n      \"status\": \"completed\",\n      \"role\": \"assistant\",\n      \"content\": [\n        {\n          \"type\": \"output_text\",\n          \"text\": \"The classic tongue twister...\",\n          \"annotations\": []\n        }\n      ]\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": null,\n  \"reasoning\": {\n    \"effort\": \"high\",\n    \"summary\": null\n  },\n  \"store\": true,\n  \"temperature\": 1.0,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [],\n  \"top_p\": 1.0,\n  \"truncation\": \"disabled\",\n  \"usage\": {\n    \"input_tokens\": 81,\n    \"input_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"cache_write_tokens\": 0\n    },\n    \"output_tokens\": 1035,\n    \"output_tokens_details\": {\n      \"reasoning_tokens\": 832\n    },\n    \"total_tokens\": 1116\n  },\n  \"user\": null,\n  \"metadata\": {}\n}\n"
+            }
+          ]
+        },
+        "parameters": [
+          {
+            "name": "openai-beta",
+            "in": "header",
+            "required": false,
+            "description": "Optional beta features to enable for this request.",
+            "style": "simple",
+            "explode": false,
+            "schema": {
+              "type": "array",
+              "x-stainless-param": "betas",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "responses_multi_agent=v1"
+                ]
+              }
+            }
+          }
+        ]
+      }
+    },
+    "/responses/{response_id}?beta=true": {
+      "get": {
+        "operationId": "beta_getResponse",
+        "tags": [
+          "Responses"
+        ],
+        "summary": "Retrieves a model response with the given ID.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "response_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "resp_677efb5139a88190b512bc3fef8e535d"
+            },
+            "description": "The ID of the response to retrieve."
+          },
+          {
+            "in": "query",
+            "name": "include",
+            "schema": {
+              "type": "array",
+              "items": {
+                "$ref": "#/components/schemas/BetaIncludeEnum"
+              }
+            },
+            "description": "Additional fields to include in the response. See the `include`\nparameter for Response creation above for more information.\n"
+          },
+          {
+            "in": "query",
+            "name": "stream",
+            "schema": {
+              "type": "boolean"
+            },
+            "description": "If set to true, the model response data will be streamed to the client\nas it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).\nSee the [Streaming section below](https://developers.openai.com/api/reference/resources/responses/streaming-events)\nfor more information.\n"
+          },
+          {
+            "in": "query",
+            "name": "starting_after",
+            "schema": {
+              "type": "integer"
+            },
+            "description": "The sequence number of the event after which to start streaming.\n"
+          },
+          {
+            "in": "query",
+            "name": "include_obfuscation",
+            "schema": {
+              "type": "boolean"
+            },
+            "description": "When true, stream obfuscation will be enabled. Stream obfuscation adds\nrandom characters to an `obfuscation` field on streaming delta events\nto normalize payload sizes as a mitigation to certain side-channel\nattacks. These obfuscation fields are included by default, but add a\nsmall amount of overhead to the data stream. You can set\n`include_obfuscation` to false to optimize for bandwidth if you trust\nthe network links between your application and the OpenAI API.\n"
+          },
+          {
+            "name": "openai-beta",
+            "in": "header",
+            "required": false,
+            "description": "Optional beta features to enable for this request.",
+            "style": "simple",
+            "explode": false,
+            "schema": {
+              "type": "array",
+              "x-stainless-param": "betas",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "responses_multi_agent=v1"
+                ]
+              }
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/BetaResponse"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Get a model response",
+          "group": "responses",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/responses/resp_123 \\\n    -H \"Content-Type: application/json\" \\\n    -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "javascript": "import OpenAI from \"openai\";\nconst client = new OpenAI();\n\nconst response = await client.responses.retrieve(\"resp_123\");\nconsole.log(response);\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nresponse = client.responses.retrieve(\"resp_123\")\nprint(response)\n"
+            },
+            "response": "{\n  \"id\": \"resp_67cb71b351908190a308f3859487620d06981a8637e6bc44\",\n  \"object\": \"response\",\n  \"created_at\": 1741386163,\n  \"status\": \"completed\",\n  \"completed_at\": 1741386164,\n  \"error\": null,\n  \"incomplete_details\": null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"model\": \"gpt-6-astra\",\n  \"output\": [\n    {\n      \"type\": \"message\",\n      \"id\": \"msg_67cb71b3c2b0819084d481baaaf148f206981a8637e6bc44\",\n      \"status\": \"completed\",\n      \"role\": \"assistant\",\n      \"content\": [\n        {\n          \"type\": \"output_text\",\n          \"text\": \"Silent circuits hum,  \\nThoughts emerge in data streams—  \\nDigital dawn breaks.\",\n          \"annotations\": []\n        }\n      ]\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": null,\n  \"reasoning\": {\n    \"effort\": null,\n    \"summary\": null\n  },\n  \"store\": true,\n  \"temperature\": 1.0,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [],\n  \"top_p\": 1.0,\n  \"truncation\": \"disabled\",\n  \"usage\": {\n    \"input_tokens\": 32,\n    \"input_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"cache_write_tokens\": 0\n    },\n    \"output_tokens\": 18,\n    \"output_tokens_details\": {\n      \"reasoning_tokens\": 0\n    },\n    \"total_tokens\": 50\n  },\n  \"user\": null,\n  \"metadata\": {}\n}\n"
+          }
+        }
+      },
+      "delete": {
+        "operationId": "beta_deleteResponse",
+        "tags": [
+          "Responses"
+        ],
+        "summary": "Deletes a model response with the given ID.\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "response_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "resp_677efb5139a88190b512bc3fef8e535d"
+            },
+            "description": "The ID of the response to delete."
+          },
+          {
+            "name": "openai-beta",
+            "in": "header",
+            "required": false,
+            "description": "Optional beta features to enable for this request.",
+            "style": "simple",
+            "explode": false,
+            "schema": {
+              "type": "array",
+              "x-stainless-param": "betas",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "responses_multi_agent=v1"
+                ]
+              }
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK"
+          },
+          "404": {
+            "description": "Not Found",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/BetaError"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Delete a model response",
+          "group": "responses",
+          "examples": {
+            "request": {
+              "curl": "curl -X DELETE https://api.openai.com/v1/responses/resp_123 \\\n    -H \"Content-Type: application/json\" \\\n    -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "javascript": "import OpenAI from \"openai\";\nconst client = new OpenAI();\n\nconst response = await client.responses.delete(\"resp_123\");\nconsole.log(response);\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nresponse = client.responses.delete(\"resp_123\")\nprint(response)\n"
+            },
+            "response": "{\n  \"id\": \"resp_6786a1bec27481909a17d673315b29f6\",\n  \"object\": \"response\",\n  \"deleted\": true\n}\n"
+          }
+        }
+      }
+    },
+    "/responses/{response_id}/cancel?beta=true": {
+      "post": {
+        "operationId": "beta_cancelResponse",
+        "tags": [
+          "Responses"
+        ],
+        "summary": "Cancels a model response with the given ID. Only responses created with\nthe `background` parameter set to `true` can be cancelled.\n[Learn more](https://developers.openai.com/api/docs/guides/background).\n",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "response_id",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "example": "resp_677efb5139a88190b512bc3fef8e535d"
+            },
+            "description": "The ID of the response to cancel."
+          },
+          {
+            "name": "openai-beta",
+            "in": "header",
+            "required": false,
+            "description": "Optional beta features to enable for this request.",
+            "style": "simple",
+            "explode": false,
+            "schema": {
+              "type": "array",
+              "x-stainless-param": "betas",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "responses_multi_agent=v1"
+                ]
+              }
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/BetaResponse"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "Not Found",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/BetaError"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Cancel a response",
+          "group": "responses",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/responses/resp_123/cancel \\\n    -H \"Content-Type: application/json\" \\\n    -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "javascript": "import OpenAI from \"openai\";\nconst client = new OpenAI();\n\nconst response = await client.responses.cancel(\"resp_123\");\nconsole.log(response);\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nresponse = client.responses.cancel(\"resp_123\")\nprint(response)\n"
+            },
+            "response": "{\n  \"id\": \"resp_67cb71b351908190a308f3859487620d06981a8637e6bc44\",\n  \"object\": \"response\",\n  \"created_at\": 1741386163,\n  \"status\": \"cancelled\",\n  \"background\": true,\n  \"completed_at\": null,\n  \"error\": null,\n  \"incomplete_details\": null,\n  \"instructions\": null,\n  \"max_output_tokens\": null,\n  \"model\": \"gpt-6-astra\",\n  \"output\": [\n    {\n      \"type\": \"message\",\n      \"id\": \"msg_67cb71b3c2b0819084d481baaaf148f206981a8637e6bc44\",\n      \"status\": \"in_progress\",\n      \"role\": \"assistant\",\n      \"content\": [\n        {\n          \"type\": \"output_text\",\n          \"text\": \"Silent circuits hum,  \\nThoughts emerge in data streams—  \\nDigital dawn breaks.\",\n          \"annotations\": []\n        }\n      ]\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"previous_response_id\": null,\n  \"reasoning\": {\n    \"effort\": null,\n    \"summary\": null\n  },\n  \"store\": true,\n  \"temperature\": 1.0,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"tool_choice\": \"auto\",\n  \"tools\": [],\n  \"top_p\": 1.0,\n  \"truncation\": \"disabled\",\n  \"usage\": null,\n  \"user\": null,\n  \"metadata\": {}\n}\n"
+          }
+        }
+      }
+    },
+    "/responses/compact?beta=true": {
+      "post": {
+        "summary": "Compact a conversation. Returns a compacted response object.\n\nLearn when and how to compact long-running conversations in the [conversation state guide](https://developers.openai.com/api/docs/guides/conversation-state#managing-the-context-window). For ZDR-compatible compaction details, see [Compaction (advanced)](https://developers.openai.com/api/docs/guides/conversation-state#compaction-advanced).",
+        "operationId": "beta_Compactconversation",
+        "parameters": [
+          {
+            "name": "openai-beta",
+            "in": "header",
+            "required": false,
+            "description": "Optional beta features to enable for this request.",
+            "style": "simple",
+            "explode": false,
+            "schema": {
+              "type": "array",
+              "x-stainless-param": "betas",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "responses_multi_agent=v1"
+                ]
+              }
+            }
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/BetaCompactResponseMethodPublicBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/BetaCompactResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/InferenceRateLimited"
+          },
+          "503": {
+            "$ref": "#/components/responses/InferenceServiceUnavailable"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Compact a response",
+          "group": "responses",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/responses/compact \\\n    -H \"Content-Type: application/json\" \\\n    -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n    -d '{\n      \"model\": \"gpt-6-astra\",\n      \"input\": [\n        {\n          \"role\": \"user\",\n          \"content\": \"Create a simple landing page for a dog petting café.\"\n        },\n        {\n          \"id\": \"msg_001\",\n          \"type\": \"message\",\n          \"status\": \"completed\",\n          \"content\": [\n            {\n              \"type\": \"output_text\",\n              \"annotations\": [],\n              \"logprobs\": [],\n              \"text\": \"Below is a single file, ready-to-use landing page for a dog petting café:...\"\n            }\n          ],\n          \"role\": \"assistant\"\n        }\n      ]\n    }'\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\n// Compact the previous response if you are running out of tokens\nconst compactedResponse = await openai.responses.compact({\n  model: \"gpt-6-astra\",\n  input: [\n    {\n      role: \"user\",\n      content: \"Create a simple landing page for a dog petting café.\",\n    },\n    // All items returned from previous requests are included here, like reasoning, message, function call, etc.\n    {\n      id: \"msg_030d085c0b53e67e0069332e3a72d4819c96c6f2c4adc15d33\",\n      type: \"message\",\n      status: \"completed\",\n      content: [\n        {\n          type: \"output_text\",\n          annotations: [],\n          logprobs: [],\n          text: \"Below is a single file, ready-to-use landing page for a dog petting café:...\",\n        },\n      ],\n      role: \"assistant\",\n    },\n  ],\n});\n\n// Pass the compactedResponse.output as input to the next request\nconsole.log(compactedResponse);\n",
+              "python": "from openai import OpenAI\n\nclient = OpenAI()\n\ncompacted_response = client.responses.compact(\n    model=\"gpt-6-astra\",\n    input=[\n    {\n        \"role\": \"user\",\n        \"content\": \"Create a simple landing page for a dog petting cafe.\",\n    },\n    # All items returned from previous requests are included here, like reasoning, message, function call, etc.\n    {\n        \"id\": \"msg_001\",\n        \"type\": \"message\",\n        \"status\": \"completed\",\n        \"content\": [\n        {\n            \"type\": \"output_text\",\n            \"annotations\": [],\n            \"logprobs\": [],\n            \"text\": \"Below is a single file, ready-to-use landing page for a dog petting café:...\",\n        },\n        ],\n        \"role\": \"assistant\",\n    },\n    ]\n)\n# Pass the compacted_response.output as input to the next request\nprint(compacted_response)\n"
+            },
+            "response": "{\n  \"id\": \"resp_001\",\n  \"object\": \"response.compaction\",\n  \"created_at\": 1764967971,\n  \"output\": [\n    {\n      \"id\": \"msg_000\",\n      \"type\": \"message\",\n      \"status\": \"completed\",\n      \"content\": [\n        {\n          \"type\": \"input_text\",\n          \"text\": \"Create a simple landing page for a dog petting cafe.\"\n        }\n      ],\n      \"role\": \"user\"\n    },\n    {\n      \"id\": \"cmp_001\",\n      \"type\": \"compaction\",\n      \"encrypted_content\": \"gAAAAABpM0Yj-...=\"\n    }\n  ],\n  \"usage\": {\n    \"input_tokens\": 139,\n    \"input_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"cache_write_tokens\": 0\n    },\n    \"output_tokens\": 438,\n    \"output_tokens_details\": {\n      \"reasoning_tokens\": 64\n    },\n    \"total_tokens\": 577\n  }\n}\n"
+          }
+        }
+      }
+    },
+    "/responses/{response_id}/input_items?beta=true": {
+      "get": {
+        "operationId": "beta_listInputItems",
+        "tags": [
+          "Responses"
+        ],
+        "summary": "Returns a list of input items for a given response.",
+        "parameters": [
+          {
+            "in": "path",
+            "name": "response_id",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "The ID of the response to retrieve input items for."
+          },
+          {
+            "name": "limit",
+            "in": "query",
+            "description": "A limit on the number of objects to be returned. Limit can range between\n1 and 100, and the default is 20.\n",
+            "required": false,
+            "schema": {
+              "type": "integer",
+              "default": 20
+            }
+          },
+          {
+            "in": "query",
+            "name": "order",
+            "schema": {
+              "type": "string",
+              "enum": [
+                "asc",
+                "desc"
+              ]
+            },
+            "description": "The order to return the input items in. Default is `desc`.\n- `asc`: Return the input items in ascending order.\n- `desc`: Return the input items in descending order.\n"
+          },
+          {
+            "in": "query",
+            "name": "after",
+            "schema": {
+              "type": "string"
+            },
+            "description": "An item ID to list items after, used in pagination.\n"
+          },
+          {
+            "in": "query",
+            "name": "include",
+            "schema": {
+              "type": "array",
+              "items": {
+                "$ref": "#/components/schemas/BetaIncludeEnum"
+              }
+            },
+            "description": "Additional fields to include in the response. See the `include`\nparameter for Response creation above for more information.\n"
+          },
+          {
+            "name": "openai-beta",
+            "in": "header",
+            "required": false,
+            "description": "Optional beta features to enable for this request.",
+            "style": "simple",
+            "explode": false,
+            "schema": {
+              "type": "array",
+              "x-stainless-param": "betas",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "responses_multi_agent=v1"
+                ]
+              }
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/BetaResponseItemList"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "List input items",
+          "group": "responses",
+          "examples": {
+            "request": {
+              "curl": "curl https://api.openai.com/v1/responses/resp_abc123/input_items \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\"\n",
+              "javascript": "import OpenAI from \"openai\";\nconst client = new OpenAI();\n\nconst response = await client.responses.inputItems.list(\"resp_123\");\nconsole.log(response.data);\n",
+              "python": "from openai import OpenAI\nclient = OpenAI()\n\nresponse = client.responses.input_items.list(\"resp_123\")\nprint(response.data)\n"
+            },
+            "response": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"id\": \"msg_abc123\",\n      \"type\": \"message\",\n      \"role\": \"user\",\n      \"content\": [\n        {\n          \"type\": \"input_text\",\n          \"text\": \"Tell me a three sentence bedtime story about a unicorn.\"\n        }\n      ]\n    }\n  ],\n  \"first_id\": \"msg_abc123\",\n  \"last_id\": \"msg_abc123\",\n  \"has_more\": false\n}\n"
+          }
+        }
+      }
+    },
+    "/responses/input_tokens?beta=true": {
+      "post": {
+        "summary": "Returns input token counts of the request.\n\nReturns an object with `object` set to `response.input_tokens` and an `input_tokens` count.",
+        "operationId": "beta_Getinputtokencounts",
+        "parameters": [
+          {
+            "name": "openai-beta",
+            "in": "header",
+            "required": false,
+            "description": "Optional beta features to enable for this request.",
+            "style": "simple",
+            "explode": false,
+            "schema": {
+              "type": "array",
+              "x-stainless-param": "betas",
+              "items": {
+                "type": "string",
+                "enum": [
+                  "responses_multi_agent=v1"
+                ]
+              }
+            }
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/BetaTokenCountsBody"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Success",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/BetaTokenCountsResource"
+                }
+              }
+            }
+          },
+          "429": {
+            "$ref": "#/components/responses/TooManyRequests"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "Get input token counts",
+          "group": "responses",
+          "examples": {
+            "request": {
+              "curl": "curl -X POST https://api.openai.com/v1/responses/input_tokens \\\n    -H \"Content-Type: application/json\" \\\n    -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n    -d '{\n      \"model\": \"gpt-6-astra\",\n      \"input\": \"Tell me a joke.\"\n    }'\n",
+              "javascript": "import OpenAI from \"openai\";\n\nconst client = new OpenAI();\n\nconst response = await client.responses.inputTokens.count({\n  model: \"gpt-6-astra\",\n  input: \"Tell me a joke.\",\n});\n\nconsole.log(response.input_tokens);\n",
+              "python": "from openai import OpenAI\n\nclient = OpenAI()\n\nresponse = client.responses.input_tokens.count(\n    model=\"gpt-6-astra\",\n    input=\"Tell me a joke.\"\n)\nprint(response.input_tokens)\n",
+              "go": "package main\n\nimport (\n  \"context\"\n  \"fmt\"\n\n  \"github.com/openai/openai-go\"\n  \"github.com/openai/openai-go/responses\"\n)\n\nfunc main() {\n  client := openai.NewClient()\n  response, err := client.Responses.InputTokens.Count(context.TODO(), responses.InputTokenCountParams{\n    Model: \"gpt-6-astra\",\n    Input: \"Tell me a joke.\",\n  })\n  if err != nil {\n    panic(err.Error())\n  }\n  fmt.Printf(\"%+v\\n\", response.InputTokens)\n}\n",
+              "ruby": "require \"openai\"\n\nopenai = OpenAI::Client.new\n\nresponse = openai.responses.input_tokens.count(model: \"gpt-6-astra\", input: \"Tell me a joke.\")\n\nputs(response)\n",
+              "java": "package com.openai.example;\n\nimport com.openai.client.OpenAIClient;\nimport com.openai.client.okhttp.OpenAIOkHttpClient;\nimport com.openai.models.responses.inputtokens.InputTokenCountParams;\nimport com.openai.models.responses.inputtokens.InputTokenCountResponse;\n\npublic final class Main {\n    private Main() {}\n\n    public static void main(String[] args) {\n        OpenAIClient client = OpenAIOkHttpClient.fromEnv();\n\n        InputTokenCountParams params = InputTokenCountParams.builder()\n            .model(\"gpt-6-astra\")\n            .input(\"Tell me a joke.\")\n            .build();\n\n        InputTokenCountResponse response = client.responses().inputTokens().count(params);\n    }\n}\n"
+            },
+            "response": "{\n  \"object\": \"response.input_tokens\",\n  \"input_tokens\": 11\n}\n"
+          }
+        }
+      }
+    }
+  },
+  "webhooks": {
+    "batch_cancelled": {
+      "post": {
+        "description": "Sent when a batch has been cancelled.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookBatchCancelled"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried.\n"
+          }
+        }
+      }
+    },
+    "batch_completed": {
+      "post": {
+        "description": "Sent when a batch has completed processing.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookBatchCompleted"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried.\n"
+          }
+        }
+      }
+    },
+    "batch_expired": {
+      "post": {
+        "description": "Sent when a batch has expired before completion.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookBatchExpired"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried.\n"
+          }
+        }
+      }
+    },
+    "batch_failed": {
+      "post": {
+        "description": "Sent when a batch has failed.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookBatchFailed"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried.\n"
+          }
+        }
+      }
+    },
+    "eval_run_canceled": {
+      "post": {
+        "description": "Sent when an eval run has been canceled.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookEvalRunCanceled"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried. \n"
+          }
+        }
+      }
+    },
+    "eval_run_failed": {
+      "post": {
+        "description": "Sent when an eval run has failed.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookEvalRunFailed"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried. \n"
+          }
+        }
+      }
+    },
+    "eval_run_succeeded": {
+      "post": {
+        "description": "Sent when an eval run has succeeded.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookEvalRunSucceeded"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried. \n"
+          }
+        }
+      }
+    },
+    "fine_tuning_job_cancelled": {
+      "post": {
+        "description": "Sent when a fine-tuning job has been cancelled.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookFineTuningJobCancelled"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried. \n"
+          }
+        }
+      }
+    },
+    "fine_tuning_job_failed": {
+      "post": {
+        "description": "Sent when a fine-tuning job has failed.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookFineTuningJobFailed"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried. \n"
+          }
+        }
+      }
+    },
+    "fine_tuning_job_succeeded": {
+      "post": {
+        "description": "Sent when a fine-tuning job has succeeded.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookFineTuningJobSucceeded"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried. \n"
+          }
+        }
+      }
+    },
+    "live_call_incoming": {
+      "post": {
+        "deprecated": true,
+        "description": "Deprecated: use `live.transport.incoming`. Retained only for existing subscriptions.\nSent when an incoming API SIP session is available for Live acceptance.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookLiveCallIncoming"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200\nstatus codes will be retried.\n"
+          }
+        }
+      }
+    },
+    "live_transport_incoming": {
+      "post": {
+        "description": "Sent when an incoming API SIP session is available for Live acceptance.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookLiveTransportIncoming"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200\nstatus codes will be retried.\n"
+          }
+        }
+      }
+    },
+    "realtime_call_incoming": {
+      "post": {
+        "description": "Sent when an incoming API SIP session is available for Realtime acceptance.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookRealtimeCallIncoming"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200\nstatus codes will be retried.\n"
+          }
+        }
+      }
+    },
+    "response_cancelled": {
+      "post": {
+        "description": "Sent when a background response has been cancelled.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookResponseCancelled"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried.\n"
+          }
+        }
+      }
+    },
+    "response_completed": {
+      "post": {
+        "description": "Sent when a background response has completed successfully.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookResponseCompleted"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried. \n"
+          }
+        }
+      }
+    },
+    "response_failed": {
+      "post": {
+        "description": "Sent when a background response has failed.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookResponseFailed"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried.\n"
+          }
+        }
+      }
+    },
+    "response_incomplete": {
+      "post": {
+        "description": "Sent when a background response is incomplete.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookResponseIncomplete"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return a 200 status code to acknowledge receipt of the event. Non-200 \nstatus codes will be retried.\n"
+          }
+        }
+      }
+    },
+    "safety_alert_created": {
+      "post": {
+        "description": "Sent when an approved safety alert is available for an API project.\nRetrieve the alert with a project API key granted `api.safety.alerts.read`.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookSafetyAlertCreated"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return any 2xx status code to acknowledge receipt. A 410 Gone response also stops retries; other non-2xx responses are retried."
+          }
+        }
+      }
+    },
+    "safety_org_alert_created": {
+      "post": {
+        "description": "Sent when an approved safety alert is available for an enterprise workspace.\nRetrieve the alert from `https://api.chatgpt.com/v1/safety/alerts/{id}` with\nan administrator API key for the workspace's backing organization granted\n`chatgpt.enterprise.safety_alerts.read`.\n",
+        "requestBody": {
+          "description": "The event payload sent by the API.",
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/WebhookSafetyOrgAlertCreated"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Return any 2xx status code to acknowledge receipt. A 410 Gone response also stops retries; other non-2xx responses are retried."
+          }
+        }
+      }
+    }
+  },
+  "components": {
+    "schemas": {
+      "AddUploadPartRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "data": {
+            "description": "The chunk of bytes for this Part.\n",
+            "type": "string",
+            "format": "binary"
+          }
+        },
+        "required": [
+          "data"
+        ]
+      },
+      "AdminApiKey": {
+        "type": "object",
+        "description": "Represents an individual Admin API key in an org.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.admin_api_key"
+            ],
+            "description": "The object type, which is always `organization.admin_api_key`",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "example": "key_abc",
+            "description": "The identifier, which can be referenced in API endpoints"
+          },
+          "name": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "example": "Administration Key",
+            "description": "The name of the API key"
+          },
+          "redacted_value": {
+            "type": "string",
+            "example": "sk-admin...def",
+            "description": "The redacted value of the API key"
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "example": 1711471533,
+            "description": "The Unix timestamp (in seconds) of when the API key was created"
+          },
+          "expires_at": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "format": "unixtime",
+                "example": 1714063533,
+                "description": "The Unix timestamp (in seconds) of when the API key expires"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "last_used_at": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "format": "unixtime",
+                "example": 1711471534,
+                "description": "The Unix timestamp (in seconds) of when the API key was last used"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "owner": {
+            "type": "object",
+            "properties": {
+              "type": {
+                "type": "string",
+                "example": "user",
+                "description": "Always `user`"
+              },
+              "object": {
+                "type": "string",
+                "example": "organization.user",
+                "description": "The object type, which is always organization.user"
+              },
+              "id": {
+                "type": "string",
+                "example": "sa_456",
+                "description": "The identifier, which can be referenced in API endpoints"
+              },
+              "name": {
+                "type": "string",
+                "example": "My Service Account",
+                "description": "The name of the user"
+              },
+              "created_at": {
+                "type": "integer",
+                "format": "unixtime",
+                "example": 1711471533,
+                "description": "The Unix timestamp (in seconds) of when the user was created"
+              },
+              "role": {
+                "type": "string",
+                "example": "owner",
+                "description": "Always `owner`"
+              }
+            }
+          }
+        },
+        "required": [
+          "object",
+          "redacted_value",
+          "created_at",
+          "expires_at",
+          "id",
+          "owner"
+        ],
+        "x-oaiMeta": {
+          "name": "The admin API key object",
+          "example": "{\n  \"object\": \"organization.admin_api_key\",\n  \"id\": \"key_abc\",\n  \"name\": \"Main Admin Key\",\n  \"redacted_value\": \"sk-admin...xyz\",\n  \"created_at\": 1711471533,\n  \"last_used_at\": 1711471534,\n  \"owner\": {\n    \"type\": \"user\",\n    \"object\": \"organization.user\",\n    \"id\": \"user_123\",\n    \"name\": \"John Doe\",\n    \"created_at\": 1711471533,\n    \"role\": \"owner\"\n  }\n}\n"
+        }
+      },
+      "AdminApiKeyCreateResponse": {
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/AdminApiKey"
+          },
+          {
+            "type": "object",
+            "description": "The newly created admin API key. The `value` field is only returned once, when the key is created.",
+            "properties": {
+              "value": {
+                "type": "string",
+                "example": "sk-admin-1234abcd",
+                "description": "The value of the API key. Only shown on create."
+              }
+            },
+            "required": [
+              "value"
+            ]
+          }
+        ]
+      },
+      "ApiKeyList": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "example": "list",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/AdminApiKey"
+            }
+          },
+          "has_more": {
+            "type": "boolean",
+            "example": false
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "example": "key_abc"
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "example": "key_xyz"
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more"
+        ]
+      },
+      "AssignedRoleDetails": {
+        "type": "object",
+        "description": "Detailed information about a role assignment entry returned when listing assignments.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Identifier for the role."
+          },
+          "name": {
+            "type": "string",
+            "description": "Name of the role."
+          },
+          "permissions": {
+            "type": "array",
+            "description": "Permissions associated with the role.",
+            "items": {
+              "type": "string"
+            }
+          },
+          "resource_type": {
+            "type": "string",
+            "description": "Resource type the role applies to."
+          },
+          "predefined_role": {
+            "type": "boolean",
+            "description": "Whether the role is predefined by OpenAI."
+          },
+          "description": {
+            "description": "Description of the role.",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "created_at": {
+            "description": "When the role was created.",
+            "anyOf": [
+              {
+                "type": "integer",
+                "format": "unixtime"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "updated_at": {
+            "description": "When the role was last updated.",
+            "anyOf": [
+              {
+                "type": "integer",
+                "format": "unixtime"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "created_by": {
+            "description": "Identifier of the actor who created the role.",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "created_by_user_obj": {
+            "description": "User details for the actor that created the role, when available.",
+            "anyOf": [
+              {
+                "type": "object",
+                "additionalProperties": true
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "metadata": {
+            "description": "Arbitrary metadata stored on the role.",
+            "anyOf": [
+              {
+                "type": "object",
+                "additionalProperties": true
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "assignment_sources": {
+            "description": "Principals from which the role assignment is inherited, when available.",
+            "anyOf": [
+              {
+                "type": "array",
+                "items": {
+                  "type": "object",
+                  "properties": {
+                    "principal_id": {
+                      "type": "string"
+                    },
+                    "principal_type": {
+                      "type": "string"
+                    }
+                  },
+                  "required": [
+                    "principal_id",
+                    "principal_type"
+                  ]
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "name",
+          "permissions",
+          "resource_type",
+          "predefined_role",
+          "description",
+          "created_at",
+          "updated_at",
+          "created_by",
+          "created_by_user_obj",
+          "metadata",
+          "assignment_sources"
+        ]
+      },
+      "AssistantObject": {
+        "type": "object",
+        "title": "Assistant",
+        "description": "Represents an `assistant` that can call the model and use tools.",
+        "properties": {
+          "id": {
+            "description": "The identifier, which can be referenced in API endpoints.",
+            "type": "string"
+          },
+          "object": {
+            "description": "The object type, which is always `assistant`.",
+            "type": "string",
+            "enum": [
+              "assistant"
+            ],
+            "x-stainless-const": true
+          },
+          "created_at": {
+            "description": "The Unix timestamp (in seconds) for when the assistant was created.",
+            "type": "integer",
+            "format": "unixtime"
+          },
+          "name": {
+            "anyOf": [
+              {
+                "description": "The name of the assistant. The maximum length is 256 characters.\n",
+                "type": "string",
+                "maxLength": 256
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "description": {
+            "anyOf": [
+              {
+                "description": "The description of the assistant. The maximum length is 512 characters.\n",
+                "type": "string",
+                "maxLength": 512
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "model": {
+            "description": "ID of the model to use. You can use the [List models](https://developers.openai.com/api/reference/resources/models/methods/list) API to see all of your available models, or see our [Model overview](https://developers.openai.com/api/docs/models) for descriptions of them.\n",
+            "type": "string"
+          },
+          "instructions": {
+            "anyOf": [
+              {
+                "description": "The system instructions that the assistant uses. The maximum length is 256,000 characters.\n",
+                "type": "string",
+                "maxLength": 256000
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "tools": {
+            "description": "A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types `code_interpreter`, `file_search`, or `function`.\n",
+            "default": [],
+            "type": "array",
+            "maxItems": 128,
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/AssistantToolsCode"
+                },
+                {
+                  "$ref": "#/components/schemas/AssistantToolsFileSearch"
+                },
+                {
+                  "$ref": "#/components/schemas/AssistantToolsFunction"
+                }
+              ]
+            }
+          },
+          "tool_resources": {
+            "anyOf": [
+              {
+                "type": "object",
+                "description": "A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs.\n",
+                "properties": {
+                  "code_interpreter": {
+                    "type": "object",
+                    "properties": {
+                      "file_ids": {
+                        "type": "array",
+                        "description": "A list of [file](https://developers.openai.com/api/reference/resources/files) IDs made available to the `code_interpreter`` tool. There can be a maximum of 20 files associated with the tool.\n",
+                        "default": [],
+                        "maxItems": 20,
+                        "items": {
+                          "type": "string"
+                        }
+                      }
+                    }
+                  },
+                  "file_search": {
+                    "type": "object",
+                    "properties": {
+                      "vector_store_ids": {
+                        "type": "array",
+                        "description": "The ID of the [vector store](https://developers.openai.com/api/reference/resources/vector_stores) attached to this assistant. There can be a maximum of 1 vector store attached to the assistant.\n",
+                        "maxItems": 1,
+                        "items": {
+                          "type": "string"
+                        }
+                      }
+                    }
+                  }
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          },
+          "temperature": {
+            "anyOf": [
+              {
+                "description": "What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.\n",
+                "type": "number",
+                "minimum": 0,
+                "maximum": 2,
+                "default": 1,
+                "example": 1
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "top_p": {
+            "anyOf": [
+              {
+                "type": "number",
+                "minimum": 0,
+                "maximum": 1,
+                "default": 1,
+                "example": 1,
+                "description": "An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\n\nWe generally recommend altering this or temperature but not both.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "response_format": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/AssistantsApiResponseFormatOption"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "created_at",
+          "name",
+          "description",
+          "model",
+          "instructions",
+          "tools",
+          "metadata"
+        ],
+        "x-oaiMeta": {
+          "name": "The assistant object",
+          "example": "{\n  \"id\": \"asst_abc123\",\n  \"object\": \"assistant\",\n  \"created_at\": 1698984975,\n  \"name\": \"Math Tutor\",\n  \"description\": null,\n  \"model\": \"gpt-5\",\n  \"instructions\": \"You are a personal math tutor. When asked a question, write and run Python code to answer the question.\",\n  \"tools\": [\n    {\n      \"type\": \"code_interpreter\"\n    }\n  ],\n  \"metadata\": {},\n  \"top_p\": 1.0,\n  \"temperature\": 1.0,\n  \"response_format\": \"auto\"\n}\n"
+        },
+        "deprecated": true
+      },
+      "AssistantStreamEvent": {
+        "description": "Represents an event emitted when streaming a Run.\n\nEach event in a server-sent events stream has an `event` and `data` property:\n\n```\nevent: thread.created\ndata: {\"id\": \"thread_123\", \"object\": \"thread\", ...}\n```\n\nWe emit events whenever a new object is created, transitions to a new state, or is being\nstreamed in parts (deltas). For example, we emit `thread.run.created` when a new run\nis created, `thread.run.completed` when a run completes, and so on. When an Assistant chooses\nto create a message during a run, we emit a `thread.message.created event`, a\n`thread.message.in_progress` event, many `thread.message.delta` events, and finally a\n`thread.message.completed` event.\n\nWe may add additional events over time, so we recommend handling unknown events gracefully\nin your code. See the [Assistants API quickstart](https://developers.openai.com/api/docs/assistants/migration) to learn how to\nintegrate the Assistants API with streaming.\n",
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/ThreadStreamEvent"
+          },
+          {
+            "$ref": "#/components/schemas/RunStreamEvent"
+          },
+          {
+            "$ref": "#/components/schemas/RunStepStreamEvent"
+          },
+          {
+            "$ref": "#/components/schemas/MessageStreamEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ErrorEvent"
+          },
+          {
+            "$ref": "#/components/schemas/DoneEvent"
+          }
+        ],
+        "x-oaiMeta": {
+          "name": "Assistant stream events",
+          "beta": true
+        }
+      },
+      "AssistantSupportedModels": {
+        "type": "string",
+        "enum": [
+          "gpt-5",
+          "gpt-5-mini",
+          "gpt-5-nano",
+          "gpt-5-2025-08-07",
+          "gpt-5-mini-2025-08-07",
+          "gpt-5-nano-2025-08-07",
+          "gpt-4.1",
+          "gpt-4.1-mini",
+          "gpt-4.1-nano",
+          "gpt-4.1-2025-04-14",
+          "gpt-4.1-mini-2025-04-14",
+          "gpt-4.1-nano-2025-04-14",
+          "o3-mini",
+          "o3-mini-2025-01-31",
+          "o1",
+          "o1-2024-12-17",
+          "gpt-4o",
+          "gpt-4o-2024-11-20",
+          "gpt-4o-2024-08-06",
+          "gpt-4o-2024-05-13",
+          "gpt-4o-mini",
+          "gpt-4o-mini-2024-07-18",
+          "gpt-4.5-preview",
+          "gpt-4.5-preview-2025-02-27",
+          "gpt-4-turbo",
+          "gpt-4-turbo-2024-04-09",
+          "gpt-4-0125-preview",
+          "gpt-4-turbo-preview",
+          "gpt-4-1106-preview",
+          "gpt-4-vision-preview",
+          "gpt-4",
+          "gpt-4-0314",
+          "gpt-4-0613",
+          "gpt-4-32k",
+          "gpt-4-32k-0314",
+          "gpt-4-32k-0613",
+          "gpt-3.5-turbo",
+          "gpt-3.5-turbo-16k",
+          "gpt-3.5-turbo-0613",
+          "gpt-3.5-turbo-1106",
+          "gpt-3.5-turbo-0125",
+          "gpt-3.5-turbo-16k-0613"
+        ]
+      },
+      "AssistantToolsCode": {
+        "type": "object",
+        "title": "Code interpreter tool",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of tool being defined: `code_interpreter`",
+            "enum": [
+              "code_interpreter"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "AssistantToolsFileSearch": {
+        "type": "object",
+        "title": "FileSearch tool",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of tool being defined: `file_search`",
+            "enum": [
+              "file_search"
+            ],
+            "x-stainless-const": true
+          },
+          "file_search": {
+            "type": "object",
+            "description": "Overrides for the file search tool.",
+            "properties": {
+              "max_num_results": {
+                "type": "integer",
+                "minimum": 1,
+                "maximum": 50,
+                "description": "The maximum number of results the file search tool should output. The default is 20 for `gpt-4*` models and 5 for `gpt-3.5-turbo`. This number should be between 1 and 50 inclusive.\n\nNote that the file search tool may output fewer than `max_num_results` results. See the [file search tool documentation](https://developers.openai.com/api/docs/guides/tools-file-search#retrieval-customization) for more information.\n"
+              },
+              "ranking_options": {
+                "$ref": "#/components/schemas/FileSearchRankingOptions"
+              }
+            }
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "AssistantToolsFileSearchTypeOnly": {
+        "type": "object",
+        "title": "FileSearch tool",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of tool being defined: `file_search`",
+            "enum": [
+              "file_search"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "AssistantToolsFunction": {
+        "type": "object",
+        "title": "Function tool",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of tool being defined: `function`",
+            "enum": [
+              "function"
+            ],
+            "x-stainless-const": true
+          },
+          "function": {
+            "$ref": "#/components/schemas/FunctionObject"
+          }
+        },
+        "required": [
+          "type",
+          "function"
+        ]
+      },
+      "AssistantsApiResponseFormatOption": {
+        "description": "Specifies the format that the model must output. Compatible with [GPT-4o](https://developers.openai.com/api/docs/models/gpt-4o), [GPT-4 Turbo](https://developers.openai.com/api/docs/models/gpt-4-turbo), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`.\n\nSetting to `{ \"type\": \"json_schema\", \"json_schema\": {...} }` enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the [Structured Outputs guide](https://developers.openai.com/api/docs/guides/structured-outputs).\n\nSetting to `{ \"type\": \"json_object\" }` enables JSON mode, which ensures the message the model generates is valid JSON.\n\n**Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly \"stuck\" request. Also note that the message content may be partially cut off if `finish_reason=\"length\"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length.\n",
+        "oneOf": [
+          {
+            "type": "string",
+            "description": "`auto` is the default value\n",
+            "enum": [
+              "auto"
+            ],
+            "x-stainless-const": true
+          },
+          {
+            "$ref": "#/components/schemas/ResponseFormatText"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseFormatJsonObject"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseFormatJsonSchema"
+          }
+        ]
+      },
+      "AssistantsApiToolChoiceOption": {
+        "description": "Controls which (if any) tool is called by the model.\n`none` means the model will not call any tools and instead generates a message.\n`auto` is the default value and means the model can pick between generating a message or calling one or more tools.\n`required` means the model must call one or more tools before responding to the user.\nSpecifying a particular tool like `{\"type\": \"file_search\"}` or `{\"type\": \"function\", \"function\": {\"name\": \"my_function\"}}` forces the model to call that tool.\n",
+        "oneOf": [
+          {
+            "type": "string",
+            "description": "`none` means the model will not call any tools and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call one or more tools before responding to the user.\n",
+            "enum": [
+              "none",
+              "auto",
+              "required"
+            ]
+          },
+          {
+            "$ref": "#/components/schemas/AssistantsNamedToolChoice"
+          }
+        ]
+      },
+      "AssistantsNamedToolChoice": {
+        "type": "object",
+        "description": "Specifies a tool the model should use. Use to force the model to call a specific tool.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "function",
+              "code_interpreter",
+              "file_search"
+            ],
+            "description": "The type of the tool. If type is `function`, the function name must be set"
+          },
+          "function": {
+            "type": "object",
+            "properties": {
+              "name": {
+                "type": "string",
+                "description": "The name of the function to call."
+              }
+            },
+            "required": [
+              "name"
+            ]
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "AudioResponseFormat": {
+        "description": "The format of the output, in one of these options: `json`, `text`, `srt`, `verbose_json`, `vtt`, or `diarized_json`. For `gpt-4o-transcribe` and `gpt-4o-mini-transcribe`, the only supported format is `json`. For `gpt-4o-transcribe-diarize`, the supported formats are `json`, `text`, and `diarized_json`, with `diarized_json` required to receive speaker annotations.\n",
+        "type": "string",
+        "enum": [
+          "json",
+          "text",
+          "srt",
+          "verbose_json",
+          "vtt",
+          "diarized_json"
+        ],
+        "default": "json"
+      },
+      "AudioTranscription": {
+        "type": "object",
+        "properties": {
+          "model": {
+            "description": "The model to use for transcription. Current options are `whisper-1`, `gpt-transcribe`, `gpt-live-transcribe`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels.\n",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "whisper-1",
+                  "gpt-transcribe",
+                  "gpt-live-transcribe",
+                  "gpt-4o-mini-transcribe",
+                  "gpt-4o-mini-transcribe-2025-12-15",
+                  "gpt-4o-transcribe",
+                  "gpt-4o-transcribe-diarize",
+                  "gpt-realtime-whisper"
+                ]
+              }
+            ]
+          },
+          "language": {
+            "type": "string",
+            "description": "The language of the input audio. Supplying the input language in\n[ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format\nwill improve accuracy and latency.\n"
+          },
+          "languages": {
+            "type": "array",
+            "description": "Possible languages of the input audio, in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format. Supported by `gpt-transcribe` and `gpt-live-transcribe`.\n",
+            "minItems": 1,
+            "items": {
+              "type": "string"
+            }
+          },
+          "keywords": {
+            "type": "array",
+            "description": "Words or phrases to guide transcription of the input audio. Supported by `gpt-transcribe` and `gpt-live-transcribe`.\n",
+            "items": {
+              "type": "string"
+            }
+          },
+          "prompt": {
+            "type": "string",
+            "description": "An optional text to guide the model's style or continue a previous audio\nsegment.\nFor `whisper-1`, the [prompt is a list of keywords](https://developers.openai.com/api/docs/guides/speech-to-text#prompting).\nFor `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example \"expect words related to technology\".\nPrompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions.\n"
+          },
+          "delay": {
+            "type": "string",
+            "description": "Controls how long the model waits before emitting transcription text.\nHigher values can improve transcription accuracy at the cost of latency.\nOnly supported with `gpt-realtime-whisper` in GA Realtime sessions.\n",
+            "enum": [
+              "minimal",
+              "low",
+              "medium",
+              "high",
+              "xhigh"
+            ]
+          }
+        }
+      },
+      "AudioTranscriptionResponse": {
+        "type": "object",
+        "properties": {
+          "model": {
+            "description": "The model used for transcription. Current options are `whisper-1`, `gpt-transcribe`, `gpt-live-transcribe`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`.\n",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "whisper-1",
+                  "gpt-transcribe",
+                  "gpt-live-transcribe",
+                  "gpt-4o-mini-transcribe",
+                  "gpt-4o-mini-transcribe-2025-12-15",
+                  "gpt-4o-transcribe",
+                  "gpt-4o-transcribe-diarize",
+                  "gpt-realtime-whisper"
+                ]
+              }
+            ]
+          },
+          "language": {
+            "type": "string",
+            "description": "The language of the input audio.\n"
+          },
+          "languages": {
+            "type": "array",
+            "description": "The possible input audio languages configured for transcription, in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format.\n",
+            "minItems": 1,
+            "items": {
+              "type": "string"
+            }
+          },
+          "prompt": {
+            "type": "string",
+            "description": "The prompt configured for input audio transcription, when present.\n"
+          }
+        }
+      },
+      "AuditLog": {
+        "type": "object",
+        "description": "A log of a user action or configuration change within this organization.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The ID of this log."
+          },
+          "type": {
+            "$ref": "#/components/schemas/AuditLogEventType"
+          },
+          "effective_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of the event."
+          },
+          "project": {
+            "type": "object",
+            "description": "The project that the action was scoped to. Absent for actions not scoped to projects. Note that any admin actions taken via Admin API keys are associated with the default project.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The project ID."
+              },
+              "name": {
+                "type": "string",
+                "description": "The project title."
+              }
+            }
+          },
+          "actor": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/AuditLogActor"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "api_key.created": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The tracking ID of the API key."
+              },
+              "data": {
+                "type": "object",
+                "description": "The payload used to create the API key.",
+                "properties": {
+                  "scopes": {
+                    "type": "array",
+                    "items": {
+                      "type": "string"
+                    },
+                    "description": "A list of scopes allowed for the API key, e.g. `[\"api.model.request\"]`"
+                  }
+                }
+              }
+            }
+          },
+          "api_key.updated": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The tracking ID of the API key."
+              },
+              "changes_requested": {
+                "type": "object",
+                "description": "The payload used to update the API key.",
+                "properties": {
+                  "scopes": {
+                    "type": "array",
+                    "items": {
+                      "type": "string"
+                    },
+                    "description": "A list of scopes allowed for the API key, e.g. `[\"api.model.request\"]`"
+                  }
+                }
+              }
+            }
+          },
+          "api_key.deleted": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The tracking ID of the API key."
+              }
+            }
+          },
+          "checkpoint.permission.created": {
+            "type": "object",
+            "description": "The project and fine-tuned model checkpoint that the checkpoint permission was created for.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID of the checkpoint permission."
+              },
+              "data": {
+                "type": "object",
+                "description": "The payload used to create the checkpoint permission.",
+                "properties": {
+                  "project_id": {
+                    "type": "string",
+                    "description": "The ID of the project that the checkpoint permission was created for."
+                  },
+                  "fine_tuned_model_checkpoint": {
+                    "type": "string",
+                    "description": "The ID of the fine-tuned model checkpoint."
+                  }
+                }
+              }
+            }
+          },
+          "checkpoint.permission.deleted": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID of the checkpoint permission."
+              }
+            }
+          },
+          "external_key.registered": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID of the external key configuration."
+              },
+              "data": {
+                "type": "object",
+                "description": "The configuration for the external key."
+              }
+            }
+          },
+          "external_key.removed": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID of the external key configuration."
+              }
+            }
+          },
+          "group.created": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID of the group."
+              },
+              "data": {
+                "type": "object",
+                "description": "Information about the created group.",
+                "properties": {
+                  "group_name": {
+                    "type": "string",
+                    "description": "The group name."
+                  }
+                }
+              }
+            }
+          },
+          "group.updated": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID of the group."
+              },
+              "changes_requested": {
+                "type": "object",
+                "description": "The payload used to update the group.",
+                "properties": {
+                  "group_name": {
+                    "type": "string",
+                    "description": "The updated group name."
+                  }
+                }
+              }
+            }
+          },
+          "group.deleted": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID of the group."
+              }
+            }
+          },
+          "scim.enabled": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID of the SCIM was enabled for."
+              }
+            }
+          },
+          "scim.disabled": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID of the SCIM was disabled for."
+              }
+            }
+          },
+          "invite.sent": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID of the invite."
+              },
+              "data": {
+                "type": "object",
+                "description": "The payload used to create the invite.",
+                "properties": {
+                  "email": {
+                    "type": "string",
+                    "description": "The email invited to the organization."
+                  },
+                  "role": {
+                    "type": "string",
+                    "description": "The role the email was invited to be. Is either `owner` or `member`."
+                  }
+                }
+              }
+            }
+          },
+          "invite.accepted": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID of the invite."
+              }
+            }
+          },
+          "invite.deleted": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID of the invite."
+              }
+            }
+          },
+          "ip_allowlist.created": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID of the IP allowlist configuration."
+              },
+              "name": {
+                "type": "string",
+                "description": "The name of the IP allowlist configuration."
+              },
+              "allowed_ips": {
+                "type": "array",
+                "description": "The IP addresses or CIDR ranges included in the configuration.",
+                "items": {
+                  "type": "string"
+                }
+              }
+            }
+          },
+          "ip_allowlist.updated": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID of the IP allowlist configuration."
+              },
+              "allowed_ips": {
+                "type": "array",
+                "description": "The updated set of IP addresses or CIDR ranges in the configuration.",
+                "items": {
+                  "type": "string"
+                }
+              }
+            }
+          },
+          "ip_allowlist.deleted": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID of the IP allowlist configuration."
+              },
+              "name": {
+                "type": "string",
+                "description": "The name of the IP allowlist configuration."
+              },
+              "allowed_ips": {
+                "type": "array",
+                "description": "The IP addresses or CIDR ranges that were in the configuration.",
+                "items": {
+                  "type": "string"
+                }
+              }
+            }
+          },
+          "ip_allowlist.config.activated": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "configs": {
+                "type": "array",
+                "description": "The configurations that were activated.",
+                "items": {
+                  "type": "object",
+                  "properties": {
+                    "id": {
+                      "type": "string",
+                      "description": "The ID of the IP allowlist configuration."
+                    },
+                    "name": {
+                      "type": "string",
+                      "description": "The name of the IP allowlist configuration."
+                    }
+                  }
+                }
+              }
+            }
+          },
+          "ip_allowlist.config.deactivated": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "configs": {
+                "type": "array",
+                "description": "The configurations that were deactivated.",
+                "items": {
+                  "type": "object",
+                  "properties": {
+                    "id": {
+                      "type": "string",
+                      "description": "The ID of the IP allowlist configuration."
+                    },
+                    "name": {
+                      "type": "string",
+                      "description": "The name of the IP allowlist configuration."
+                    }
+                  }
+                }
+              }
+            }
+          },
+          "login.succeeded": {
+            "type": "object",
+            "description": "This event has no additional fields beyond the standard audit log attributes."
+          },
+          "login.failed": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "error_code": {
+                "type": "string",
+                "description": "The error code of the failure."
+              },
+              "error_message": {
+                "type": "string",
+                "description": "The error message of the failure."
+              }
+            }
+          },
+          "logout.succeeded": {
+            "type": "object",
+            "description": "This event has no additional fields beyond the standard audit log attributes."
+          },
+          "logout.failed": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "error_code": {
+                "type": "string",
+                "description": "The error code of the failure."
+              },
+              "error_message": {
+                "type": "string",
+                "description": "The error message of the failure."
+              }
+            }
+          },
+          "organization.updated": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The organization ID."
+              },
+              "changes_requested": {
+                "type": "object",
+                "description": "The payload used to update the organization settings.",
+                "properties": {
+                  "title": {
+                    "type": "string",
+                    "description": "The organization title."
+                  },
+                  "description": {
+                    "type": "string",
+                    "description": "The organization description."
+                  },
+                  "name": {
+                    "type": "string",
+                    "description": "The organization name."
+                  },
+                  "threads_ui_visibility": {
+                    "type": "string",
+                    "description": "Visibility of the threads page which shows messages created with the Assistants API and Playground. One of `ANY_ROLE`, `OWNERS`, or `NONE`."
+                  },
+                  "usage_dashboard_visibility": {
+                    "type": "string",
+                    "description": "Visibility of the usage dashboard which shows activity and costs for your organization. One of `ANY_ROLE` or `OWNERS`."
+                  },
+                  "api_call_logging": {
+                    "type": "string",
+                    "description": "How your organization logs data from supported API calls. One of `disabled`, `enabled_per_call`, `enabled_for_all_projects`, or `enabled_for_selected_projects`"
+                  },
+                  "api_call_logging_project_ids": {
+                    "type": "string",
+                    "description": "The list of project ids if api_call_logging is set to `enabled_for_selected_projects`"
+                  }
+                }
+              }
+            }
+          },
+          "project.created": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The project ID."
+              },
+              "data": {
+                "type": "object",
+                "description": "The payload used to create the project.",
+                "properties": {
+                  "name": {
+                    "type": "string",
+                    "description": "The project name."
+                  },
+                  "title": {
+                    "type": "string",
+                    "description": "The title of the project as seen on the dashboard."
+                  }
+                }
+              }
+            }
+          },
+          "project.updated": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The project ID."
+              },
+              "changes_requested": {
+                "type": "object",
+                "description": "The payload used to update the project.",
+                "properties": {
+                  "title": {
+                    "type": "string",
+                    "description": "The title of the project as seen on the dashboard."
+                  }
+                }
+              }
+            }
+          },
+          "project.archived": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The project ID."
+              }
+            }
+          },
+          "project.deleted": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The project ID."
+              }
+            }
+          },
+          "rate_limit.updated": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The rate limit ID"
+              },
+              "changes_requested": {
+                "type": "object",
+                "description": "The payload used to update the rate limits.",
+                "properties": {
+                  "max_requests_per_1_minute": {
+                    "type": "integer",
+                    "description": "The maximum requests per minute."
+                  },
+                  "max_tokens_per_1_minute": {
+                    "type": "integer",
+                    "description": "The maximum tokens per minute."
+                  },
+                  "max_images_per_1_minute": {
+                    "type": "integer",
+                    "description": "The maximum images per minute. Only relevant for certain models."
+                  },
+                  "max_audio_megabytes_per_1_minute": {
+                    "type": "integer",
+                    "description": "The maximum audio megabytes per minute. Only relevant for certain models."
+                  },
+                  "max_requests_per_1_day": {
+                    "type": "integer",
+                    "description": "The maximum requests per day. Only relevant for certain models."
+                  },
+                  "batch_1_day_max_input_tokens": {
+                    "type": "integer",
+                    "description": "The maximum batch input tokens per day. Only relevant for certain models."
+                  }
+                }
+              }
+            }
+          },
+          "rate_limit.deleted": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The rate limit ID"
+              }
+            }
+          },
+          "role.created": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The role ID."
+              },
+              "role_name": {
+                "type": "string",
+                "description": "The name of the role."
+              },
+              "permissions": {
+                "type": "array",
+                "items": {
+                  "type": "string"
+                },
+                "description": "The permissions granted by the role."
+              },
+              "resource_type": {
+                "type": "string",
+                "description": "The type of resource the role belongs to."
+              },
+              "resource_id": {
+                "type": "string",
+                "description": "The resource the role is scoped to."
+              }
+            }
+          },
+          "role.updated": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The role ID."
+              },
+              "changes_requested": {
+                "type": "object",
+                "description": "The payload used to update the role.",
+                "properties": {
+                  "role_name": {
+                    "type": "string",
+                    "description": "The updated role name, when provided."
+                  },
+                  "resource_id": {
+                    "type": "string",
+                    "description": "The resource the role is scoped to."
+                  },
+                  "resource_type": {
+                    "type": "string",
+                    "description": "The type of resource the role belongs to."
+                  },
+                  "permissions_added": {
+                    "type": "array",
+                    "items": {
+                      "type": "string"
+                    },
+                    "description": "The permissions added to the role."
+                  },
+                  "permissions_removed": {
+                    "type": "array",
+                    "items": {
+                      "type": "string"
+                    },
+                    "description": "The permissions removed from the role."
+                  },
+                  "description": {
+                    "type": "string",
+                    "description": "The updated role description, when provided."
+                  },
+                  "metadata": {
+                    "type": "object",
+                    "description": "Additional metadata stored on the role."
+                  }
+                }
+              }
+            }
+          },
+          "role.deleted": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The role ID."
+              }
+            }
+          },
+          "role.assignment.created": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The identifier of the role assignment."
+              },
+              "principal_id": {
+                "type": "string",
+                "description": "The principal (user or group) that received the role."
+              },
+              "principal_type": {
+                "type": "string",
+                "description": "The type of principal (user or group) that received the role."
+              },
+              "resource_id": {
+                "type": "string",
+                "description": "The resource the role assignment is scoped to."
+              },
+              "resource_type": {
+                "type": "string",
+                "description": "The type of resource the role assignment is scoped to."
+              }
+            }
+          },
+          "role.assignment.deleted": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The identifier of the role assignment."
+              },
+              "principal_id": {
+                "type": "string",
+                "description": "The principal (user or group) that had the role removed."
+              },
+              "principal_type": {
+                "type": "string",
+                "description": "The type of principal (user or group) that had the role removed."
+              },
+              "resource_id": {
+                "type": "string",
+                "description": "The resource the role assignment was scoped to."
+              },
+              "resource_type": {
+                "type": "string",
+                "description": "The type of resource the role assignment was scoped to."
+              }
+            }
+          },
+          "role.bound_to_resource": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID of the resource the role was bound to. ChatGPT workspace connector resources use `<workspace_id>__<connector_id>`."
+              },
+              "role_id": {
+                "type": "string",
+                "description": "The ID of the role that was bound to the resource."
+              },
+              "resource_id": {
+                "type": "string",
+                "description": "The ID of the resource the role was bound to."
+              },
+              "resource_type": {
+                "type": "string",
+                "description": "The type of resource the role was bound to."
+              },
+              "permissions": {
+                "type": "array",
+                "items": {
+                  "type": "string"
+                },
+                "description": "The permissions granted to the role for the resource."
+              },
+              "workspace_id": {
+                "type": "string",
+                "description": "The workspace ID for a ChatGPT workspace connector resource."
+              },
+              "connector_id": {
+                "type": "string",
+                "description": "The connector ID for a ChatGPT workspace connector resource."
+              },
+              "connector_name": {
+                "type": "string",
+                "description": "The connector display name for a ChatGPT workspace connector resource, or the connector ID when the display name could not be resolved."
+              },
+              "enabled": {
+                "type": "boolean",
+                "description": "Whether the connector is enabled for the role."
+              },
+              "source": {
+                "type": "string",
+                "description": "The connector role mutation path that produced the event.",
+                "enum": [
+                  "role_toggle",
+                  "role_connector_update",
+                  "role_delete",
+                  "workspace_permissions",
+                  "connector_publish"
+                ]
+              }
+            }
+          },
+          "role.unbound_from_resource": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID of the resource the role was unbound from. ChatGPT workspace connector resources use `<workspace_id>__<connector_id>`."
+              },
+              "role_id": {
+                "type": "string",
+                "description": "The ID of the role that was unbound from the resource."
+              },
+              "resource_id": {
+                "type": "string",
+                "description": "The ID of the resource the role was unbound from."
+              },
+              "resource_type": {
+                "type": "string",
+                "description": "The type of resource the role was unbound from."
+              },
+              "permissions": {
+                "type": "array",
+                "items": {
+                  "type": "string"
+                },
+                "description": "The permissions remaining for the role after the change."
+              },
+              "workspace_id": {
+                "type": "string",
+                "description": "The workspace ID for a ChatGPT workspace connector resource."
+              },
+              "connector_id": {
+                "type": "string",
+                "description": "The connector ID for a ChatGPT workspace connector resource."
+              },
+              "connector_name": {
+                "type": "string",
+                "description": "The connector display name for a ChatGPT workspace connector resource, or the connector ID when the display name could not be resolved."
+              },
+              "enabled": {
+                "type": "boolean",
+                "description": "Whether the connector is enabled for the role."
+              },
+              "source": {
+                "type": "string",
+                "description": "The connector role mutation path that produced the event.",
+                "enum": [
+                  "role_toggle",
+                  "role_connector_update",
+                  "role_delete",
+                  "workspace_permissions",
+                  "connector_publish"
+                ]
+              }
+            }
+          },
+          "service_account.created": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The service account ID."
+              },
+              "data": {
+                "type": "object",
+                "description": "The payload used to create the service account.",
+                "properties": {
+                  "role": {
+                    "type": "string",
+                    "description": "The role of the service account. Is either `owner` or `member`."
+                  }
+                }
+              }
+            }
+          },
+          "service_account.updated": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The service account ID."
+              },
+              "changes_requested": {
+                "type": "object",
+                "description": "The payload used to updated the service account.",
+                "properties": {
+                  "role": {
+                    "type": "string",
+                    "description": "The role of the service account. Is either `owner` or `member`."
+                  }
+                }
+              }
+            }
+          },
+          "service_account.deleted": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The service account ID."
+              }
+            }
+          },
+          "workload_identity_provider.created": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The workload identity provider ID."
+              },
+              "data": {
+                "type": "object",
+                "description": "The payload used to create the workload identity provider."
+              }
+            }
+          },
+          "workload_identity_provider.updated": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The workload identity provider ID."
+              },
+              "changes_requested": {
+                "type": "object",
+                "description": "The payload used to update the workload identity provider."
+              }
+            }
+          },
+          "workload_identity_provider.deleted": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The workload identity provider ID."
+              },
+              "name": {
+                "type": "string",
+                "description": "The workload identity provider name."
+              }
+            }
+          },
+          "workload_identity_provider_mapping.created": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The workload identity provider mapping ID."
+              },
+              "identity_provider_id": {
+                "type": "string",
+                "description": "The workload identity provider ID."
+              },
+              "data": {
+                "type": "object",
+                "description": "The payload used to create the workload identity provider mapping."
+              }
+            }
+          },
+          "workload_identity_provider_mapping.updated": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The workload identity provider mapping ID."
+              },
+              "identity_provider_id": {
+                "type": "string",
+                "description": "The workload identity provider ID."
+              },
+              "changes_requested": {
+                "type": "object",
+                "description": "The payload used to update the workload identity provider mapping."
+              }
+            }
+          },
+          "workload_identity_provider_mapping.deleted": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The workload identity provider mapping ID."
+              },
+              "identity_provider_id": {
+                "type": "string",
+                "description": "The workload identity provider ID."
+              },
+              "project_id": {
+                "type": "string",
+                "description": "The project ID."
+              },
+              "service_account_id": {
+                "type": "string",
+                "description": "The mapped service account ID."
+              }
+            }
+          },
+          "user.added": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The user ID."
+              },
+              "data": {
+                "type": "object",
+                "description": "The payload used to add the user to the project.",
+                "properties": {
+                  "role": {
+                    "type": "string",
+                    "description": "The role of the user. Is either `owner` or `member`."
+                  }
+                }
+              }
+            }
+          },
+          "user.updated": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The project ID."
+              },
+              "changes_requested": {
+                "type": "object",
+                "description": "The payload used to update the user.",
+                "properties": {
+                  "role": {
+                    "type": "string",
+                    "description": "The role of the user. Is either `owner` or `member`."
+                  }
+                }
+              }
+            }
+          },
+          "user.deleted": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The user ID."
+              }
+            }
+          },
+          "certificate.created": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The certificate ID."
+              },
+              "name": {
+                "type": "string",
+                "description": "The name of the certificate."
+              }
+            }
+          },
+          "certificate.updated": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The certificate ID."
+              },
+              "name": {
+                "type": "string",
+                "description": "The name of the certificate."
+              }
+            }
+          },
+          "certificate.deleted": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The certificate ID."
+              },
+              "name": {
+                "type": "string",
+                "description": "The name of the certificate."
+              },
+              "certificate": {
+                "type": "string",
+                "description": "The certificate content in PEM format."
+              }
+            }
+          },
+          "certificates.activated": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "certificates": {
+                "type": "array",
+                "items": {
+                  "type": "object",
+                  "properties": {
+                    "id": {
+                      "type": "string",
+                      "description": "The certificate ID."
+                    },
+                    "name": {
+                      "type": "string",
+                      "description": "The name of the certificate."
+                    }
+                  }
+                }
+              }
+            }
+          },
+          "certificates.deactivated": {
+            "type": "object",
+            "description": "The details for events with this `type`.",
+            "properties": {
+              "certificates": {
+                "type": "array",
+                "items": {
+                  "type": "object",
+                  "properties": {
+                    "id": {
+                      "type": "string",
+                      "description": "The certificate ID."
+                    },
+                    "name": {
+                      "type": "string",
+                      "description": "The name of the certificate."
+                    }
+                  }
+                }
+              }
+            }
+          }
+        },
+        "required": [
+          "id",
+          "type",
+          "effective_at"
+        ],
+        "x-oaiMeta": {
+          "name": "The audit log object",
+          "example": "{\n    \"id\": \"req_xxx_20240101\",\n    \"type\": \"api_key.created\",\n    \"effective_at\": 1720804090,\n    \"actor\": {\n        \"type\": \"session\",\n        \"session\": {\n            \"user\": {\n                \"id\": \"user-xxx\",\n                \"email\": \"user@example.com\"\n            },\n            \"ip_address\": \"127.0.0.1\",\n            \"user_agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36\"\n        }\n    },\n    \"api_key.created\": {\n        \"id\": \"key_xxxx\",\n        \"data\": {\n            \"scopes\": [\"resource.operation\"]\n        }\n    }\n}\n"
+        }
+      },
+      "AuditLogActor": {
+        "type": "object",
+        "description": "The actor who performed the audit logged action.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of actor. Is either `session` or `api_key`.",
+            "enum": [
+              "session",
+              "api_key"
+            ]
+          },
+          "session": {
+            "$ref": "#/components/schemas/AuditLogActorSession"
+          },
+          "api_key": {
+            "$ref": "#/components/schemas/AuditLogActorApiKey"
+          }
+        }
+      },
+      "AuditLogActorApiKey": {
+        "type": "object",
+        "description": "The API Key used to perform the audit logged action.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The tracking id of the API key."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of API key. Can be either `user` or `service_account`.",
+            "enum": [
+              "user",
+              "service_account"
+            ]
+          },
+          "user": {
+            "$ref": "#/components/schemas/AuditLogActorUser"
+          },
+          "service_account": {
+            "$ref": "#/components/schemas/AuditLogActorServiceAccount"
+          }
+        }
+      },
+      "AuditLogActorServiceAccount": {
+        "type": "object",
+        "description": "The service account that performed the audit logged action.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The service account id."
+          }
+        }
+      },
+      "AuditLogActorSession": {
+        "type": "object",
+        "description": "The session in which the audit logged action was performed.",
+        "properties": {
+          "user": {
+            "$ref": "#/components/schemas/AuditLogActorUser"
+          },
+          "ip_address": {
+            "type": "string",
+            "description": "The IP address from which the action was performed."
+          }
+        }
+      },
+      "AuditLogActorUser": {
+        "type": "object",
+        "description": "The user who performed the audit logged action.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The user id."
+          },
+          "email": {
+            "type": "string",
+            "description": "The user email."
+          }
+        }
+      },
+      "AuditLogEventType": {
+        "type": "string",
+        "description": "The event type.",
+        "enum": [
+          "api_key.created",
+          "api_key.updated",
+          "api_key.deleted",
+          "certificate.created",
+          "certificate.updated",
+          "certificate.deleted",
+          "certificates.activated",
+          "certificates.deactivated",
+          "checkpoint.permission.created",
+          "checkpoint.permission.deleted",
+          "external_key.registered",
+          "external_key.removed",
+          "group.created",
+          "group.updated",
+          "group.deleted",
+          "invite.sent",
+          "invite.accepted",
+          "invite.deleted",
+          "ip_allowlist.created",
+          "ip_allowlist.updated",
+          "ip_allowlist.deleted",
+          "ip_allowlist.config.activated",
+          "ip_allowlist.config.deactivated",
+          "login.succeeded",
+          "login.failed",
+          "logout.succeeded",
+          "logout.failed",
+          "organization.updated",
+          "project.created",
+          "project.updated",
+          "project.archived",
+          "project.deleted",
+          "rate_limit.updated",
+          "rate_limit.deleted",
+          "resource.deleted",
+          "tunnel.created",
+          "tunnel.updated",
+          "tunnel.deleted",
+          "workload_identity_provider.created",
+          "workload_identity_provider.updated",
+          "workload_identity_provider.deleted",
+          "workload_identity_provider_mapping.created",
+          "workload_identity_provider_mapping.updated",
+          "workload_identity_provider_mapping.deleted",
+          "role.created",
+          "role.updated",
+          "role.deleted",
+          "role.assignment.created",
+          "role.assignment.deleted",
+          "role.bound_to_resource",
+          "role.unbound_from_resource",
+          "scim.enabled",
+          "scim.disabled",
+          "service_account.created",
+          "service_account.updated",
+          "service_account.deleted",
+          "user.added",
+          "user.updated",
+          "user.deleted",
+          "tenant.metadata.updated",
+          "tenant.microsoft_entra_mapping.upserted",
+          "tenant.microsoft_entra_mapping.deleted",
+          "tenant.workload_identity.provider.created",
+          "tenant.workload_identity.provider.updated",
+          "tenant.workload_identity.provider.archived",
+          "tenant.workload_identity.mapping.created",
+          "tenant.workload_identity.mapping.updated",
+          "tenant.workload_identity.mapping.archived",
+          "tenant.workload_identity.binding.created",
+          "tenant.workload_identity.principal.provisioned",
+          "tenant.workload_identity.access_token.issued",
+          "tenant.admin_api_key.created",
+          "tenant.admin_api_key.updated",
+          "tenant.admin_api_key.deleted",
+          "tenant.project_api_key.created",
+          "tenant.trusted_access.business_verification.started",
+          "tenant.trusted_access.application.submitted",
+          "tenant.chatgpt_access_token.revoked",
+          "tenant.migration.completed",
+          "tenant.sso.migrated",
+          "tenant.domains.migrated",
+          "tenant.sso_connection.created",
+          "tenant.sso_connection.updated",
+          "tenant.sso_connection.deleted",
+          "tenant.sso_connection.setup.started",
+          "tenant.policy.created",
+          "tenant.policy.updated",
+          "tenant.policy.deleted",
+          "tenant.policy.attached",
+          "tenant.policy.detached",
+          "tenant.principal_authentication_policy.resolved",
+          "tenant.scim.setup.started",
+          "tenant.scim.deletion.requested",
+          "tenant.scim.directory.created",
+          "tenant.product_access_policy.updated",
+          "tenant.resource_share_grant.created",
+          "tenant.resource_share_grant.updated",
+          "tenant.resource_share_grant.accepted",
+          "tenant.resource_share_grant.declined",
+          "tenant.resource_share_grant.revoked",
+          "tenant.resource_share_grant.deleted",
+          "tenant.service_account.updated",
+          "tenant.service_account.deleted",
+          "tenant.service_account.token.revoked",
+          "tenant.billing.overage_limit.updated",
+          "tenant.billing.alerts.updated",
+          "tenant.billing.info.updated",
+          "tenant.usage_limit.workspace.updated",
+          "tenant.usage_limit.group.updated",
+          "tenant.usage_limit.user.updated",
+          "tenant.usage_limit.increase_request.updated",
+          "tenant.usage_limit.increase_request.resolved",
+          "tenant.group.created",
+          "tenant.group.updated",
+          "tenant.group.deleted",
+          "tenant.group.member.added",
+          "tenant.group.member.removed",
+          "tenant.migration_rollout.status.updated",
+          "tenant.migration_rollout.tier.updated",
+          "tenant.role.metadata.updated",
+          "tenant.custom_role.created",
+          "tenant.custom_role.updated",
+          "tenant.custom_role.deleted",
+          "tenant.role_assignment.created",
+          "tenant.role_assignment.deleted",
+          "tenant.resource_role_assignment.created",
+          "tenant.resource_role_assignment.deleted",
+          "tenant.resource_access.updated",
+          "tenant.resource_access.deleted",
+          "tenant.ads_account.onboarding.redemption",
+          "tenant.session_policy.created",
+          "tenant.session_policy.updated",
+          "tenant.session_policy.deleted",
+          "tenant.session_revocation.started",
+          "tenant.third_party_app_policy.updated",
+          "tenant.user.added",
+          "tenant.user.updated",
+          "tenant.user.removed",
+          "tenant.user.looked_up",
+          "tenant.user.invited",
+          "tenant.membership.revoked",
+          "tenant.api_organization_invite.upserted",
+          "tenant.api_organization_invite.deleted",
+          "tenant.chatgpt_workspace_invite.upserted",
+          "tenant.membership.accepted",
+          "tenant.membership.declined",
+          "tenant.workspace_invite_email_settings.updated"
+        ]
+      },
+      "AutoChunkingStrategyRequestParam": {
+        "type": "object",
+        "title": "Auto Chunking Strategy",
+        "description": "The default strategy. This strategy currently uses a `max_chunk_size_tokens` of `800` and `chunk_overlap_tokens` of `400`.",
+        "additionalProperties": false,
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "Always `auto`.",
+            "enum": [
+              "auto"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "Batch": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string"
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "batch"
+            ],
+            "description": "The object type, which is always `batch`.",
+            "x-stainless-const": true
+          },
+          "endpoint": {
+            "type": "string",
+            "description": "The OpenAI API endpoint used by the batch."
+          },
+          "model": {
+            "type": "string",
+            "description": "Model ID used to process the batch, like `gpt-6-astra`. OpenAI\noffers a wide range of models with different capabilities, performance\ncharacteristics, and price points. Refer to the [model\nguide](https://developers.openai.com/api/docs/models) to browse and compare available models.\n"
+          },
+          "errors": {
+            "type": "object",
+            "properties": {
+              "object": {
+                "type": "string",
+                "description": "The object type, which is always `list`."
+              },
+              "data": {
+                "type": "array",
+                "items": {
+                  "$ref": "#/components/schemas/BatchError"
+                }
+              }
+            }
+          },
+          "input_file_id": {
+            "type": "string",
+            "description": "The ID of the input file for the batch."
+          },
+          "completion_window": {
+            "type": "string",
+            "description": "The time frame within which the batch should be processed."
+          },
+          "status": {
+            "type": "string",
+            "description": "The current status of the batch.",
+            "enum": [
+              "validating",
+              "failed",
+              "in_progress",
+              "finalizing",
+              "completed",
+              "expired",
+              "cancelling",
+              "cancelled"
+            ]
+          },
+          "output_file_id": {
+            "type": "string",
+            "description": "The ID of the file containing the outputs of successfully executed requests."
+          },
+          "error_file_id": {
+            "type": "string",
+            "description": "The ID of the file containing the outputs of requests with errors."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the batch was created."
+          },
+          "in_progress_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the batch started processing."
+          },
+          "expires_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the batch will expire."
+          },
+          "finalizing_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the batch started finalizing."
+          },
+          "completed_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the batch was completed."
+          },
+          "failed_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the batch failed."
+          },
+          "expired_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the batch expired."
+          },
+          "cancelling_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the batch started cancelling."
+          },
+          "cancelled_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the batch was cancelled."
+          },
+          "request_counts": {
+            "$ref": "#/components/schemas/BatchRequestCounts"
+          },
+          "usage": {
+            "type": "object",
+            "description": "Represents token usage details including input tokens, output tokens, a\nbreakdown of output tokens, and the total tokens used. Only populated on\nbatches created after September 7, 2025.\n",
+            "properties": {
+              "input_tokens": {
+                "type": "integer",
+                "description": "The number of input tokens."
+              },
+              "input_tokens_details": {
+                "type": "object",
+                "description": "A detailed breakdown of the input tokens.",
+                "properties": {
+                  "cached_tokens": {
+                    "type": "integer",
+                    "description": "The number of tokens that were retrieved from the cache. [More on\nprompt caching](https://developers.openai.com/api/docs/guides/prompt-caching).\n"
+                  }
+                },
+                "required": [
+                  "cached_tokens"
+                ]
+              },
+              "output_tokens": {
+                "type": "integer",
+                "description": "The number of output tokens."
+              },
+              "output_tokens_details": {
+                "type": "object",
+                "description": "A detailed breakdown of the output tokens.",
+                "properties": {
+                  "reasoning_tokens": {
+                    "type": "integer",
+                    "description": "The number of reasoning tokens."
+                  }
+                },
+                "required": [
+                  "reasoning_tokens"
+                ]
+              },
+              "total_tokens": {
+                "type": "integer",
+                "description": "The total number of tokens used."
+              }
+            },
+            "required": [
+              "input_tokens",
+              "input_tokens_details",
+              "output_tokens",
+              "output_tokens_details",
+              "total_tokens"
+            ]
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "endpoint",
+          "input_file_id",
+          "completion_window",
+          "status",
+          "created_at"
+        ],
+        "x-oaiMeta": {
+          "name": "The batch object",
+          "example": "{\n  \"id\": \"batch_abc123\",\n  \"object\": \"batch\",\n  \"endpoint\": \"/v1/chat/completions\",\n  \"model\": \"gpt-6-astra\",\n  \"errors\": null,\n  \"input_file_id\": \"file-abc123\",\n  \"completion_window\": \"24h\",\n  \"status\": \"completed\",\n  \"output_file_id\": \"file-cvaTdG\",\n  \"error_file_id\": \"file-HOWS94\",\n  \"created_at\": 1711471533,\n  \"in_progress_at\": 1711471538,\n  \"expires_at\": 1711557933,\n  \"finalizing_at\": 1711493133,\n  \"completed_at\": 1711493163,\n  \"failed_at\": null,\n  \"expired_at\": null,\n  \"cancelling_at\": null,\n  \"cancelled_at\": null,\n  \"request_counts\": {\n    \"total\": 100,\n    \"completed\": 95,\n    \"failed\": 5\n  },\n  \"usage\": {\n    \"input_tokens\": 1500,\n    \"input_tokens_details\": {\n      \"cached_tokens\": 1024\n    },\n    \"output_tokens\": 500,\n    \"output_tokens_details\": {\n      \"reasoning_tokens\": 300\n    },\n    \"total_tokens\": 2000\n  },\n  \"metadata\": {\n    \"customer_id\": \"user_123456789\",\n    \"batch_description\": \"Nightly eval job\",\n  }\n}\n"
+        }
+      },
+      "BatchError": {
+        "type": "object",
+        "properties": {
+          "code": {
+            "type": "string",
+            "description": "An error code identifying the error type."
+          },
+          "message": {
+            "type": "string",
+            "description": "A human-readable message providing more details about the error."
+          },
+          "param": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The name of the parameter that caused the error, if applicable."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "line": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "The line number of the input file where the error occurred, if applicable."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        }
+      },
+      "BatchFileExpirationAfter": {
+        "type": "object",
+        "title": "File expiration policy",
+        "description": "The expiration policy for the output and/or error file that are generated for a batch.",
+        "properties": {
+          "anchor": {
+            "description": "Anchor timestamp after which the expiration policy applies. Supported anchors: `created_at`. Note that the anchor is the file creation time, not the time the batch is created.",
+            "type": "string",
+            "enum": [
+              "created_at"
+            ],
+            "x-stainless-const": true
+          },
+          "seconds": {
+            "description": "The number of seconds after the anchor time that the file will expire. Must be between 3600 (1 hour) and 2592000 (30 days).",
+            "type": "integer",
+            "format": "int64",
+            "minimum": 3600,
+            "maximum": 2592000
+          }
+        },
+        "required": [
+          "anchor",
+          "seconds"
+        ]
+      },
+      "BatchRequestCounts": {
+        "type": "object",
+        "properties": {
+          "total": {
+            "type": "integer",
+            "description": "Total number of requests in the batch."
+          },
+          "completed": {
+            "type": "integer",
+            "description": "Number of requests that have been completed successfully."
+          },
+          "failed": {
+            "type": "integer",
+            "description": "Number of requests that have failed."
+          }
+        },
+        "required": [
+          "total",
+          "completed",
+          "failed"
+        ],
+        "description": "The request counts for different statuses within the batch."
+      },
+      "Certificate": {
+        "type": "object",
+        "description": "Represents an individual `certificate` uploaded to the organization.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "certificate",
+              "organization.certificate",
+              "organization.project.certificate"
+            ],
+            "description": "The object type.\n\n- If creating, updating, or getting a specific certificate, the object type is `certificate`.\n- If listing, activating, or deactivating certificates for the organization, the object type is `organization.certificate`.\n- If listing, activating, or deactivating certificates for a project, the object type is `organization.project.certificate`.\n",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The identifier, which can be referenced in API endpoints"
+          },
+          "name": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The name of the certificate."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the certificate was uploaded."
+          },
+          "certificate_details": {
+            "type": "object",
+            "properties": {
+              "valid_at": {
+                "type": "integer",
+                "format": "unixtime",
+                "description": "The Unix timestamp (in seconds) of when the certificate becomes valid."
+              },
+              "expires_at": {
+                "type": "integer",
+                "format": "unixtime",
+                "description": "The Unix timestamp (in seconds) of when the certificate expires."
+              },
+              "content": {
+                "type": "string",
+                "description": "The content of the certificate in PEM format."
+              }
+            }
+          },
+          "active": {
+            "type": "boolean",
+            "description": "Whether the certificate is currently active at the specified scope. Not returned when getting details for a specific certificate."
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "name",
+          "created_at",
+          "certificate_details"
+        ],
+        "x-oaiMeta": {
+          "name": "The certificate object",
+          "example": "{\n  \"object\": \"certificate\",\n  \"id\": \"cert_abc\",\n  \"name\": \"My Certificate\",\n  \"created_at\": 1234567,\n  \"certificate_details\": {\n    \"valid_at\": 1234567,\n    \"expires_at\": 12345678,\n    \"content\": \"-----BEGIN CERTIFICATE----- MIIGAjCCA...6znFlOW+ -----END CERTIFICATE-----\"\n  }\n}\n"
+        }
+      },
+      "ChatCompletionAllowedTools": {
+        "type": "object",
+        "title": "Allowed tools",
+        "description": "Constrains the tools available to the model to a pre-defined set.\n",
+        "properties": {
+          "mode": {
+            "type": "string",
+            "enum": [
+              "auto",
+              "required"
+            ],
+            "description": "Constrains the tools available to the model to a pre-defined set.\n\n`auto` allows the model to pick from among the allowed tools and generate a\nmessage.\n\n`required` requires the model to call one or more of the allowed tools.\n"
+          },
+          "tools": {
+            "type": "array",
+            "description": "A list of tool definitions that the model should be allowed to call.\n\nFor the Chat Completions API, the list of tool definitions might look like:\n```json\n[\n  { \"type\": \"function\", \"function\": { \"name\": \"get_weather\" } },\n  { \"type\": \"function\", \"function\": { \"name\": \"get_time\" } }\n]\n```\n",
+            "items": {
+              "type": "object",
+              "x-oaiExpandable": false,
+              "description": "A tool definition that the model should be allowed to call.\n",
+              "additionalProperties": true
+            }
+          }
+        },
+        "required": [
+          "mode",
+          "tools"
+        ]
+      },
+      "ChatCompletionAllowedToolsChoice": {
+        "type": "object",
+        "title": "Allowed tools",
+        "description": "Constrains the tools available to the model to a pre-defined set.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "allowed_tools"
+            ],
+            "description": "Allowed tool configuration type. Always `allowed_tools`.",
+            "x-stainless-const": true
+          },
+          "allowed_tools": {
+            "$ref": "#/components/schemas/ChatCompletionAllowedTools"
+          }
+        },
+        "required": [
+          "type",
+          "allowed_tools"
+        ]
+      },
+      "ChatCompletionDeleted": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "description": "The type of object being deleted.",
+            "enum": [
+              "chat.completion.deleted"
+            ],
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The ID of the chat completion that was deleted."
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the chat completion was deleted."
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "deleted"
+        ]
+      },
+      "ChatCompletionFunctionCallOption": {
+        "type": "object",
+        "description": "Specifying a particular function via `{\"name\": \"my_function\"}` forces the model to call that function.\n",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The name of the function to call."
+          }
+        },
+        "required": [
+          "name"
+        ]
+      },
+      "ChatCompletionFunctions": {
+        "type": "object",
+        "deprecated": true,
+        "properties": {
+          "description": {
+            "type": "string",
+            "description": "A description of what the function does, used by the model to choose when and how to call the function."
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64."
+          },
+          "parameters": {
+            "$ref": "#/components/schemas/FunctionParameters"
+          }
+        },
+        "required": [
+          "name"
+        ]
+      },
+      "ChatCompletionList": {
+        "type": "object",
+        "title": "ChatCompletionList",
+        "description": "An object representing a list of Chat Completions.\n",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "description": "The type of this object. It is always set to \"list\".\n",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "description": "An array of chat completion objects.\n",
+            "items": {
+              "$ref": "#/components/schemas/CreateChatCompletionResponse"
+            }
+          },
+          "first_id": {
+            "type": "string",
+            "description": "The identifier of the first chat completion in the data array."
+          },
+          "last_id": {
+            "type": "string",
+            "description": "The identifier of the last chat completion in the data array."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Indicates whether there are more Chat Completions available."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "x-oaiMeta": {
+          "name": "The chat completion list object",
+          "group": "chat",
+          "example": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\": \"chat.completion\",\n      \"id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2\",\n      \"model\": \"gpt-6-astra\",\n      \"created\": 1738960610,\n      \"request_id\": \"req_ded8ab984ec4bf840f37566c1011c417\",\n      \"tool_choice\": null,\n      \"usage\": {\n        \"total_tokens\": 31,\n        \"completion_tokens\": 18,\n        \"prompt_tokens\": 13\n      },\n      \"seed\": 4944116822809979520,\n      \"top_p\": 1.0,\n      \"temperature\": 1.0,\n      \"presence_penalty\": 0.0,\n      \"frequency_penalty\": 0.0,\n      \"system_fingerprint\": \"fp_50cad350e4\",\n      \"input_user\": null,\n      \"service_tier\": \"default\",\n      \"tools\": null,\n      \"metadata\": {},\n      \"choices\": [\n        {\n          \"index\": 0,\n          \"message\": {\n            \"content\": \"Mind of circuits hum,  \\nLearning patterns in silence—  \\nFuture's quiet spark.\",\n            \"role\": \"assistant\",\n            \"tool_calls\": null,\n            \"function_call\": null\n          },\n          \"finish_reason\": \"stop\",\n          \"logprobs\": null\n        }\n      ],\n      \"response_format\": null\n    }\n  ],\n  \"first_id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2\",\n  \"last_id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2\",\n  \"has_more\": false\n}\n"
+        }
+      },
+      "ChatCompletionMessageCustomToolCall": {
+        "type": "object",
+        "title": "Custom tool call",
+        "description": "A call to a custom tool created by the model.\n",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The ID of the tool call."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "custom"
+            ],
+            "description": "The type of the tool. Always `custom`.",
+            "x-stainless-const": true
+          },
+          "custom": {
+            "type": "object",
+            "description": "The custom tool that the model called.",
+            "properties": {
+              "name": {
+                "type": "string",
+                "description": "The name of the custom tool to call."
+              },
+              "input": {
+                "type": "string",
+                "description": "The input for the custom tool call generated by the model."
+              }
+            },
+            "required": [
+              "name",
+              "input"
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "type",
+          "custom"
+        ]
+      },
+      "ChatCompletionMessageList": {
+        "type": "object",
+        "title": "ChatCompletionMessageList",
+        "description": "An object representing a list of chat completion messages.\n",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "description": "The type of this object. It is always set to \"list\".\n",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "description": "An array of chat completion message objects.\n",
+            "items": {
+              "allOf": [
+                {
+                  "$ref": "#/components/schemas/ChatCompletionResponseMessage"
+                },
+                {
+                  "type": "object",
+                  "required": [
+                    "id"
+                  ],
+                  "properties": {
+                    "id": {
+                      "type": "string",
+                      "description": "The identifier of the chat message."
+                    },
+                    "content_parts": {
+                      "anyOf": [
+                        {
+                          "type": "array",
+                          "description": "If a content parts array was provided, this is an array of `text` and `image_url` parts.\nOtherwise, null.\n",
+                          "items": {
+                            "oneOf": [
+                              {
+                                "$ref": "#/components/schemas/ChatCompletionRequestMessageContentPartText"
+                              },
+                              {
+                                "$ref": "#/components/schemas/ChatCompletionRequestMessageContentPartImage"
+                              }
+                            ]
+                          }
+                        },
+                        {
+                          "type": "null"
+                        }
+                      ]
+                    }
+                  }
+                }
+              ]
+            }
+          },
+          "first_id": {
+            "type": "string",
+            "description": "The identifier of the first chat message in the data array."
+          },
+          "last_id": {
+            "type": "string",
+            "description": "The identifier of the last chat message in the data array."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Indicates whether there are more chat messages available."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "x-oaiMeta": {
+          "name": "The chat completion message list object",
+          "group": "chat",
+          "example": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2-0\",\n      \"role\": \"user\",\n      \"content\": \"write a haiku about ai\",\n      \"name\": null,\n      \"content_parts\": null\n    }\n  ],\n  \"first_id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2-0\",\n  \"last_id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2-0\",\n  \"has_more\": false\n}\n"
+        }
+      },
+      "ChatCompletionMessageToolCall": {
+        "type": "object",
+        "title": "Function tool call",
+        "description": "A call to a function tool created by the model.\n",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The ID of the tool call."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "function"
+            ],
+            "description": "The type of the tool. Currently, only `function` is supported.",
+            "x-stainless-const": true
+          },
+          "function": {
+            "type": "object",
+            "description": "The function that the model called.",
+            "properties": {
+              "name": {
+                "type": "string",
+                "description": "The name of the function to call."
+              },
+              "arguments": {
+                "type": "string",
+                "description": "The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."
+              }
+            },
+            "required": [
+              "name",
+              "arguments"
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "type",
+          "function"
+        ]
+      },
+      "ChatCompletionMessageToolCallChunk": {
+        "type": "object",
+        "properties": {
+          "index": {
+            "type": "integer"
+          },
+          "id": {
+            "type": "string",
+            "description": "The ID of the tool call."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "function"
+            ],
+            "description": "The type of the tool. Currently, only `function` is supported.",
+            "x-stainless-const": true
+          },
+          "function": {
+            "type": "object",
+            "properties": {
+              "name": {
+                "type": "string",
+                "description": "The name of the function to call."
+              },
+              "arguments": {
+                "type": "string",
+                "description": "The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."
+              }
+            }
+          }
+        },
+        "required": [
+          "index"
+        ]
+      },
+      "ChatCompletionMessageToolCalls": {
+        "type": "array",
+        "description": "The tool calls generated by the model, such as function calls.",
+        "items": {
+          "oneOf": [
+            {
+              "$ref": "#/components/schemas/ChatCompletionMessageToolCall"
+            },
+            {
+              "$ref": "#/components/schemas/ChatCompletionMessageCustomToolCall"
+            }
+          ],
+          "discriminator": {
+            "propertyName": "type"
+          }
+        }
+      },
+      "ChatCompletionModalities": {
+        "anyOf": [
+          {
+            "type": "array",
+            "description": "Output types that you would like the model to generate for this request.\nMost models are capable of generating text, which is the default:\n\n`[\"text\"]`\n\nThe `gpt-4o-audio-preview` model can also be used to [generate audio](https://developers.openai.com/api/docs/guides/audio). To\nrequest that this model generate both text and audio responses, you can\nuse:\n\n`[\"text\", \"audio\"]`\n",
+            "items": {
+              "type": "string",
+              "enum": [
+                "text",
+                "audio"
+              ]
+            }
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "ChatCompletionModeration": {
+        "type": "object",
+        "description": "Moderation results or errors for the request input and generated output.",
+        "properties": {
+          "input": {
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/ChatCompletionModerationResults"
+              },
+              {
+                "$ref": "#/components/schemas/ChatCompletionModerationError"
+              }
+            ],
+            "discriminator": {
+              "propertyName": "type"
+            },
+            "description": "Moderation for the request input."
+          },
+          "output": {
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/ChatCompletionModerationResults"
+              },
+              {
+                "$ref": "#/components/schemas/ChatCompletionModerationError"
+              }
+            ],
+            "discriminator": {
+              "propertyName": "type"
+            },
+            "description": "Moderation for the generated output."
+          }
+        },
+        "required": [
+          "input",
+          "output"
+        ]
+      },
+      "ChatCompletionModerationError": {
+        "type": "object",
+        "description": "An error produced while attempting moderation.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "error"
+            ],
+            "description": "The object type, which is always `error`.",
+            "x-stainless-const": true
+          },
+          "code": {
+            "type": "string",
+            "description": "The error code."
+          },
+          "message": {
+            "type": "string",
+            "description": "The error message."
+          }
+        },
+        "required": [
+          "type",
+          "code",
+          "message"
+        ]
+      },
+      "ChatCompletionModerationResults": {
+        "type": "object",
+        "description": "Successful moderation results for the request input or generated output.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "moderation_results"
+            ],
+            "description": "The object type, which is always `moderation_results`.",
+            "x-stainless-const": true
+          },
+          "model": {
+            "type": "string",
+            "description": "The moderation model used to generate the results."
+          },
+          "results": {
+            "type": "array",
+            "description": "A list of moderation results.",
+            "items": {
+              "$ref": "#/components/schemas/ModerationResultBody"
+            }
+          }
+        },
+        "required": [
+          "type",
+          "model",
+          "results"
+        ]
+      },
+      "ChatCompletionNamedToolChoice": {
+        "type": "object",
+        "title": "Function tool choice",
+        "description": "Specifies a tool the model should use. Use to force the model to call a specific function.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "function"
+            ],
+            "description": "For function calling, the type is always `function`.",
+            "x-stainless-const": true
+          },
+          "function": {
+            "type": "object",
+            "properties": {
+              "name": {
+                "type": "string",
+                "description": "The name of the function to call."
+              }
+            },
+            "required": [
+              "name"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "function"
+        ]
+      },
+      "ChatCompletionNamedToolChoiceCustom": {
+        "type": "object",
+        "title": "Custom tool choice",
+        "description": "Specifies a tool the model should use. Use to force the model to call a specific custom tool.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "custom"
+            ],
+            "description": "For custom tool calling, the type is always `custom`.",
+            "x-stainless-const": true
+          },
+          "custom": {
+            "type": "object",
+            "properties": {
+              "name": {
+                "type": "string",
+                "description": "The name of the custom tool to call."
+              }
+            },
+            "required": [
+              "name"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "custom"
+        ]
+      },
+      "ChatCompletionRequestAssistantMessage": {
+        "type": "object",
+        "title": "Assistant message",
+        "description": "Messages sent by the model in response to user messages.\n",
+        "properties": {
+          "content": {
+            "anyOf": [
+              {
+                "oneOf": [
+                  {
+                    "type": "string",
+                    "description": "The contents of the assistant message.",
+                    "title": "Text content"
+                  },
+                  {
+                    "type": "array",
+                    "description": "An array of content parts with a defined type. Can be one or more of type `text`, or exactly one of type `refusal`.",
+                    "title": "Array of content parts",
+                    "items": {
+                      "$ref": "#/components/schemas/ChatCompletionRequestAssistantMessageContentPart"
+                    },
+                    "minItems": 1
+                  }
+                ],
+                "description": "The contents of the assistant message. Required unless `tool_calls` or `function_call` is specified.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "refusal": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The refusal message by the assistant."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "assistant"
+            ],
+            "description": "The role of the messages author, in this case `assistant`.",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "An optional name for the participant. Provides the model information to differentiate between participants of the same role."
+          },
+          "audio": {
+            "anyOf": [
+              {
+                "type": "object",
+                "description": "Data about a previous audio response from the model.\n[Learn more](https://developers.openai.com/api/docs/guides/audio).\n",
+                "required": [
+                  "id"
+                ],
+                "properties": {
+                  "id": {
+                    "type": "string",
+                    "description": "Unique identifier for a previous audio response from the model.\n"
+                  }
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "tool_calls": {
+            "$ref": "#/components/schemas/ChatCompletionMessageToolCalls"
+          },
+          "function_call": {
+            "anyOf": [
+              {
+                "type": "object",
+                "deprecated": true,
+                "description": "Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model.",
+                "properties": {
+                  "arguments": {
+                    "type": "string",
+                    "description": "The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."
+                  },
+                  "name": {
+                    "type": "string",
+                    "description": "The name of the function to call."
+                  }
+                },
+                "required": [
+                  "arguments",
+                  "name"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "role"
+        ]
+      },
+      "ChatCompletionRequestAssistantMessageContentPart": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/ChatCompletionRequestMessageContentPartText"
+          },
+          {
+            "$ref": "#/components/schemas/ChatCompletionRequestMessageContentPartRefusal"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "ChatCompletionRequestDeveloperMessage": {
+        "type": "object",
+        "title": "Developer message",
+        "description": "Developer-provided instructions that the model should follow, regardless of\nmessages sent by the user. With o1 models and newer, `developer` messages\nreplace the previous `system` messages.\n",
+        "properties": {
+          "content": {
+            "description": "The contents of the developer message.",
+            "oneOf": [
+              {
+                "type": "string",
+                "description": "The contents of the developer message.",
+                "title": "Text content"
+              },
+              {
+                "type": "array",
+                "description": "An array of content parts with a defined type. For developer messages, only type `text` is supported.",
+                "title": "Array of content parts",
+                "items": {
+                  "$ref": "#/components/schemas/ChatCompletionRequestMessageContentPartText"
+                },
+                "minItems": 1
+              }
+            ]
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "developer"
+            ],
+            "description": "The role of the messages author, in this case `developer`.",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "An optional name for the participant. Provides the model information to differentiate between participants of the same role."
+          }
+        },
+        "required": [
+          "content",
+          "role"
+        ]
+      },
+      "ChatCompletionRequestFunctionMessage": {
+        "type": "object",
+        "title": "Function message",
+        "deprecated": true,
+        "properties": {
+          "role": {
+            "type": "string",
+            "enum": [
+              "function"
+            ],
+            "description": "The role of the messages author, in this case `function`.",
+            "x-stainless-const": true
+          },
+          "content": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The contents of the function message."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the function to call."
+          }
+        },
+        "required": [
+          "role",
+          "content",
+          "name"
+        ]
+      },
+      "ChatCompletionRequestMessage": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/ChatCompletionRequestDeveloperMessage"
+          },
+          {
+            "$ref": "#/components/schemas/ChatCompletionRequestSystemMessage"
+          },
+          {
+            "$ref": "#/components/schemas/ChatCompletionRequestUserMessage"
+          },
+          {
+            "$ref": "#/components/schemas/ChatCompletionRequestAssistantMessage"
+          },
+          {
+            "$ref": "#/components/schemas/ChatCompletionRequestToolMessage"
+          },
+          {
+            "$ref": "#/components/schemas/ChatCompletionRequestFunctionMessage"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "role"
+        }
+      },
+      "ChatCompletionRequestMessageContentPartAudio": {
+        "type": "object",
+        "title": "Audio content part",
+        "description": "Learn about [audio inputs](https://developers.openai.com/api/docs/guides/audio).\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_audio"
+            ],
+            "description": "The type of the content part. Always `input_audio`.",
+            "x-stainless-const": true
+          },
+          "input_audio": {
+            "type": "object",
+            "properties": {
+              "data": {
+                "type": "string",
+                "description": "Base64 encoded audio data."
+              },
+              "format": {
+                "type": "string",
+                "enum": [
+                  "wav",
+                  "mp3"
+                ],
+                "description": "The format of the encoded audio data. Currently supports \"wav\" and \"mp3\".\n"
+              }
+            },
+            "required": [
+              "data",
+              "format"
+            ]
+          },
+          "prompt_cache_breakpoint": {
+            "$ref": "#/components/schemas/PromptCacheBreakpointParam"
+          }
+        },
+        "required": [
+          "type",
+          "input_audio"
+        ]
+      },
+      "ChatCompletionRequestMessageContentPartFile": {
+        "type": "object",
+        "title": "File content part",
+        "description": "Learn about [file inputs](https://developers.openai.com/api/docs/guides/text) for text generation.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "file"
+            ],
+            "description": "The type of the content part. Always `file`.",
+            "x-stainless-const": true
+          },
+          "file": {
+            "type": "object",
+            "properties": {
+              "filename": {
+                "type": "string",
+                "description": "The name of the file, used when passing the file to the model as a\nstring.\n"
+              },
+              "file_data": {
+                "type": "string",
+                "description": "The base64 encoded file data, used when passing the file to the model\nas a string.\n"
+              },
+              "file_id": {
+                "type": "string",
+                "description": "The ID of an uploaded file to use as input.\n"
+              }
+            }
+          },
+          "prompt_cache_breakpoint": {
+            "$ref": "#/components/schemas/PromptCacheBreakpointParam"
+          }
+        },
+        "required": [
+          "type",
+          "file"
+        ]
+      },
+      "ChatCompletionRequestMessageContentPartImage": {
+        "type": "object",
+        "title": "Image content part",
+        "description": "Learn about [image inputs](https://developers.openai.com/api/docs/guides/images-vision).\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "image_url"
+            ],
+            "description": "The type of the content part.",
+            "x-stainless-const": true
+          },
+          "image_url": {
+            "type": "object",
+            "properties": {
+              "url": {
+                "type": "string",
+                "description": "Either a URL of the image or the base64 encoded image data.",
+                "format": "uri"
+              },
+              "detail": {
+                "type": "string",
+                "description": "Specifies the detail level of the image. Learn more in the [Vision guide](https://developers.openai.com/api/docs/guides/images-vision#choose-an-image-detail-level).",
+                "enum": [
+                  "auto",
+                  "low",
+                  "high"
+                ],
+                "default": "auto"
+              }
+            },
+            "required": [
+              "url"
+            ]
+          },
+          "prompt_cache_breakpoint": {
+            "$ref": "#/components/schemas/PromptCacheBreakpointParam"
+          }
+        },
+        "required": [
+          "type",
+          "image_url"
+        ]
+      },
+      "ChatCompletionRequestMessageContentPartRefusal": {
+        "type": "object",
+        "title": "Refusal content part",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "refusal"
+            ],
+            "description": "The type of the content part.",
+            "x-stainless-const": true
+          },
+          "refusal": {
+            "type": "string",
+            "description": "The refusal message generated by the model."
+          }
+        },
+        "required": [
+          "type",
+          "refusal"
+        ]
+      },
+      "ChatCompletionRequestMessageContentPartText": {
+        "type": "object",
+        "title": "Text content part",
+        "description": "Learn about [text inputs](https://developers.openai.com/api/docs/guides/text).\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "text"
+            ],
+            "description": "The type of the content part.",
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string",
+            "description": "The text content."
+          },
+          "prompt_cache_breakpoint": {
+            "$ref": "#/components/schemas/PromptCacheBreakpointParam"
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ]
+      },
+      "ChatCompletionRequestSystemMessage": {
+        "type": "object",
+        "title": "System message",
+        "description": "Developer-provided instructions that the model should follow, regardless of\nmessages sent by the user. With o1 models and newer, use `developer` messages\nfor this purpose instead.\n",
+        "properties": {
+          "content": {
+            "description": "The contents of the system message.",
+            "oneOf": [
+              {
+                "type": "string",
+                "description": "The contents of the system message.",
+                "title": "Text content"
+              },
+              {
+                "type": "array",
+                "description": "An array of content parts with a defined type. For system messages, only type `text` is supported.",
+                "title": "Array of content parts",
+                "items": {
+                  "$ref": "#/components/schemas/ChatCompletionRequestSystemMessageContentPart"
+                },
+                "minItems": 1
+              }
+            ]
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "system"
+            ],
+            "description": "The role of the messages author, in this case `system`.",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "An optional name for the participant. Provides the model information to differentiate between participants of the same role."
+          }
+        },
+        "required": [
+          "content",
+          "role"
+        ]
+      },
+      "ChatCompletionRequestSystemMessageContentPart": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/ChatCompletionRequestMessageContentPartText"
+          }
+        ]
+      },
+      "ChatCompletionRequestToolMessage": {
+        "type": "object",
+        "title": "Tool message",
+        "properties": {
+          "role": {
+            "type": "string",
+            "enum": [
+              "tool"
+            ],
+            "description": "The role of the messages author, in this case `tool`.",
+            "x-stainless-const": true
+          },
+          "content": {
+            "oneOf": [
+              {
+                "type": "string",
+                "description": "The contents of the tool message.",
+                "title": "Text content"
+              },
+              {
+                "type": "array",
+                "description": "An array of content parts with a defined type. For tool messages, only type `text` is supported.",
+                "title": "Array of content parts",
+                "items": {
+                  "$ref": "#/components/schemas/ChatCompletionRequestToolMessageContentPart"
+                },
+                "minItems": 1
+              }
+            ],
+            "description": "The contents of the tool message."
+          },
+          "tool_call_id": {
+            "type": "string",
+            "description": "Tool call that this message is responding to."
+          }
+        },
+        "required": [
+          "role",
+          "content",
+          "tool_call_id"
+        ]
+      },
+      "ChatCompletionRequestToolMessageContentPart": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/ChatCompletionRequestMessageContentPartText"
+          }
+        ]
+      },
+      "ChatCompletionRequestUserMessage": {
+        "type": "object",
+        "title": "User message",
+        "description": "Messages sent by an end user, containing prompts or additional context\ninformation.\n",
+        "properties": {
+          "content": {
+            "description": "The contents of the user message.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "description": "The text contents of the message.",
+                "title": "Text content"
+              },
+              {
+                "type": "array",
+                "description": "An array of content parts with a defined type. Supported options differ based on the [model](https://developers.openai.com/api/docs/models) being used to generate the response. Can contain text, image, or audio inputs.",
+                "title": "Array of content parts",
+                "items": {
+                  "$ref": "#/components/schemas/ChatCompletionRequestUserMessageContentPart"
+                },
+                "minItems": 1
+              }
+            ]
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "user"
+            ],
+            "description": "The role of the messages author, in this case `user`.",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "An optional name for the participant. Provides the model information to differentiate between participants of the same role."
+          }
+        },
+        "required": [
+          "content",
+          "role"
+        ]
+      },
+      "ChatCompletionRequestUserMessageContentPart": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/ChatCompletionRequestMessageContentPartText"
+          },
+          {
+            "$ref": "#/components/schemas/ChatCompletionRequestMessageContentPartImage"
+          },
+          {
+            "$ref": "#/components/schemas/ChatCompletionRequestMessageContentPartAudio"
+          },
+          {
+            "$ref": "#/components/schemas/ChatCompletionRequestMessageContentPartFile"
+          }
+        ]
+      },
+      "ChatCompletionResponseMessage": {
+        "type": "object",
+        "description": "A chat completion message generated by the model.",
+        "properties": {
+          "content": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The contents of the message."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "refusal": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The refusal message generated by the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "tool_calls": {
+            "$ref": "#/components/schemas/ChatCompletionMessageToolCalls"
+          },
+          "annotations": {
+            "type": "array",
+            "description": "Annotations for the message, when applicable, as when using the\n[web search tool](https://developers.openai.com/api/docs/guides/tools-web-search).\n",
+            "items": {
+              "type": "object",
+              "description": "A URL citation when using web search.\n",
+              "required": [
+                "type",
+                "url_citation"
+              ],
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "description": "The type of the URL citation. Always `url_citation`.",
+                  "enum": [
+                    "url_citation"
+                  ],
+                  "x-stainless-const": true
+                },
+                "url_citation": {
+                  "type": "object",
+                  "description": "A URL citation when using web search.",
+                  "required": [
+                    "end_index",
+                    "start_index",
+                    "url",
+                    "title"
+                  ],
+                  "properties": {
+                    "end_index": {
+                      "type": "integer",
+                      "description": "The index of the last character of the URL citation in the message."
+                    },
+                    "start_index": {
+                      "type": "integer",
+                      "description": "The index of the first character of the URL citation in the message."
+                    },
+                    "url": {
+                      "type": "string",
+                      "format": "uri",
+                      "description": "The URL of the web resource."
+                    },
+                    "title": {
+                      "type": "string",
+                      "description": "The title of the web resource."
+                    }
+                  }
+                }
+              }
+            }
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "assistant"
+            ],
+            "description": "The role of the author of this message.",
+            "x-stainless-const": true
+          },
+          "function_call": {
+            "type": "object",
+            "deprecated": true,
+            "description": "Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model.",
+            "properties": {
+              "arguments": {
+                "type": "string",
+                "description": "The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."
+              },
+              "name": {
+                "type": "string",
+                "description": "The name of the function to call."
+              }
+            },
+            "required": [
+              "name",
+              "arguments"
+            ]
+          },
+          "audio": {
+            "anyOf": [
+              {
+                "type": "object",
+                "description": "If the audio output modality is requested, this object contains data\nabout the audio response from the model. [Learn more](https://developers.openai.com/api/docs/guides/audio).\n",
+                "required": [
+                  "id",
+                  "expires_at",
+                  "data",
+                  "transcript"
+                ],
+                "properties": {
+                  "id": {
+                    "type": "string",
+                    "description": "Unique identifier for this audio response."
+                  },
+                  "expires_at": {
+                    "type": "integer",
+                    "format": "unixtime",
+                    "description": "The Unix timestamp (in seconds) for when this audio response will\nno longer be accessible on the server for use in multi-turn\nconversations.\n"
+                  },
+                  "data": {
+                    "type": "string",
+                    "description": "Base64 encoded audio bytes generated by the model, in the format\nspecified in the request.\n"
+                  },
+                  "transcript": {
+                    "type": "string",
+                    "description": "Transcript of the audio generated by the model."
+                  }
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "role",
+          "content",
+          "refusal"
+        ]
+      },
+      "ChatCompletionRole": {
+        "type": "string",
+        "description": "The role of the author of a message",
+        "enum": [
+          "developer",
+          "system",
+          "user",
+          "assistant",
+          "tool",
+          "function"
+        ]
+      },
+      "ChatCompletionStreamOptions": {
+        "anyOf": [
+          {
+            "description": "Options for streaming response. Only set this when you set `stream: true`.\n",
+            "type": "object",
+            "default": null,
+            "properties": {
+              "include_usage": {
+                "type": "boolean",
+                "description": "If set, an additional chunk will be streamed before the `data: [DONE]`\nmessage. The `usage` field on this chunk shows the token usage statistics\nfor the entire request, and the `choices` field will always be an empty\narray.\n\nAll other chunks will also include a `usage` field, but with a null\nvalue. **NOTE:** If the stream is interrupted, you may not receive the\nfinal usage chunk which contains the total token usage for the request.\n"
+              },
+              "include_obfuscation": {
+                "type": "boolean",
+                "description": "When true, stream obfuscation will be enabled. Stream obfuscation adds\nrandom characters to an `obfuscation` field on streaming delta events to\nnormalize payload sizes as a mitigation to certain side-channel attacks.\nThese obfuscation fields are included by default, but add a small amount\nof overhead to the data stream. You can set `include_obfuscation` to\nfalse to optimize for bandwidth if you trust the network links between\nyour application and the OpenAI API.\n"
+              }
+            }
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "ChatCompletionStreamResponseDelta": {
+        "type": "object",
+        "description": "A chat completion delta generated by streamed model responses.",
+        "properties": {
+          "content": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The contents of the chunk message."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "function_call": {
+            "deprecated": true,
+            "type": "object",
+            "description": "Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model.",
+            "properties": {
+              "arguments": {
+                "type": "string",
+                "description": "The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."
+              },
+              "name": {
+                "type": "string",
+                "description": "The name of the function to call."
+              }
+            }
+          },
+          "tool_calls": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/ChatCompletionMessageToolCallChunk"
+            }
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "developer",
+              "system",
+              "user",
+              "assistant",
+              "tool"
+            ],
+            "description": "The role of the author of this message."
+          },
+          "refusal": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The refusal message generated by the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        }
+      },
+      "ChatCompletionTokenLogprob": {
+        "type": "object",
+        "properties": {
+          "token": {
+            "description": "The token.",
+            "type": "string"
+          },
+          "logprob": {
+            "description": "The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely.",
+            "type": "number"
+          },
+          "bytes": {
+            "anyOf": [
+              {
+                "description": "A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token.",
+                "type": "array",
+                "items": {
+                  "type": "integer"
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "top_logprobs": {
+            "description": "List of the most likely tokens and their log probability, at this token position. The number of entries may be fewer than the requested `top_logprobs`.",
+            "type": "array",
+            "items": {
+              "type": "object",
+              "properties": {
+                "token": {
+                  "description": "The token.",
+                  "type": "string"
+                },
+                "logprob": {
+                  "description": "The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely.",
+                  "type": "number"
+                },
+                "bytes": {
+                  "anyOf": [
+                    {
+                      "description": "A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token.",
+                      "type": "array",
+                      "items": {
+                        "type": "integer"
+                      }
+                    },
+                    {
+                      "type": "null"
+                    }
+                  ]
+                }
+              },
+              "required": [
+                "token",
+                "logprob",
+                "bytes"
+              ]
+            }
+          }
+        },
+        "required": [
+          "token",
+          "logprob",
+          "bytes",
+          "top_logprobs"
+        ]
+      },
+      "ChatCompletionTool": {
+        "type": "object",
+        "title": "Function tool",
+        "description": "A function tool that can be used to generate a response.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "function"
+            ],
+            "description": "The type of the tool. Currently, only `function` is supported.",
+            "x-stainless-const": true
+          },
+          "function": {
+            "$ref": "#/components/schemas/FunctionObject"
+          }
+        },
+        "required": [
+          "type",
+          "function"
+        ]
+      },
+      "ChatCompletionToolChoiceOption": {
+        "description": "Controls which (if any) tool is called by the model.\n`none` means the model will not call any tool and instead generates a message.\n`auto` means the model can pick between generating a message or calling one or more tools.\n`required` means the model must call one or more tools.\nSpecifying a particular tool via `{\"type\": \"function\", \"function\": {\"name\": \"my_function\"}}` forces the model to call that tool.\n\n`none` is the default when no tools are present. `auto` is the default if tools are present.\n",
+        "oneOf": [
+          {
+            "type": "string",
+            "title": "Tool choice mode",
+            "description": "`none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call one or more tools.\n",
+            "enum": [
+              "none",
+              "auto",
+              "required"
+            ]
+          },
+          {
+            "$ref": "#/components/schemas/ChatCompletionAllowedToolsChoice"
+          },
+          {
+            "$ref": "#/components/schemas/ChatCompletionNamedToolChoice"
+          },
+          {
+            "$ref": "#/components/schemas/ChatCompletionNamedToolChoiceCustom"
+          }
+        ]
+      },
+      "ChunkingStrategyRequestParam": {
+        "type": "object",
+        "description": "The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy.",
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/AutoChunkingStrategyRequestParam"
+          },
+          {
+            "$ref": "#/components/schemas/StaticChunkingStrategyRequestParam"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "CodeInterpreterFileOutput": {
+        "type": "object",
+        "title": "Code interpreter file output",
+        "description": "The output of a code interpreter tool call that is a file.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "files"
+            ],
+            "description": "The type of the code interpreter file output. Always `files`.\n",
+            "x-stainless-const": true
+          },
+          "files": {
+            "type": "array",
+            "items": {
+              "type": "object",
+              "properties": {
+                "mime_type": {
+                  "type": "string",
+                  "description": "The MIME type of the file.\n"
+                },
+                "file_id": {
+                  "type": "string",
+                  "description": "The ID of the file.\n"
+                }
+              },
+              "required": [
+                "mime_type",
+                "file_id"
+              ]
+            }
+          }
+        },
+        "required": [
+          "type",
+          "files"
+        ]
+      },
+      "CodeInterpreterTextOutput": {
+        "type": "object",
+        "title": "Code interpreter text output",
+        "description": "The output of a code interpreter tool call that is text.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "logs"
+            ],
+            "description": "The type of the code interpreter text output. Always `logs`.\n",
+            "x-stainless-const": true
+          },
+          "logs": {
+            "type": "string",
+            "description": "The logs of the code interpreter tool call.\n"
+          }
+        },
+        "required": [
+          "type",
+          "logs"
+        ]
+      },
+      "CodeInterpreterTool": {
+        "type": "object",
+        "title": "Code interpreter",
+        "description": "A tool that runs Python code to help generate a response to a prompt.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "code_interpreter"
+            ],
+            "description": "The type of the code interpreter tool. Always `code_interpreter`.\n",
+            "x-stainless-const": true
+          },
+          "container": {
+            "description": "The code interpreter container. Can be a container ID or an object that\nspecifies uploaded file IDs to make available to your code, along with an\noptional `memory_limit` setting.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "description": "The container ID."
+              },
+              {
+                "$ref": "#/components/schemas/AutoCodeInterpreterToolParam"
+              }
+            ]
+          },
+          "allowed_callers": {
+            "anyOf": [
+              {
+                "type": "array",
+                "minItems": 1,
+                "items": {
+                  "$ref": "#/components/schemas/CallableToolAllowedCaller"
+                },
+                "description": "The tool invocation context(s)."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "container"
+        ]
+      },
+      "CodeInterpreterToolCall": {
+        "type": "object",
+        "title": "Code interpreter tool call",
+        "description": "A tool call to run code.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "code_interpreter_call"
+            ],
+            "default": "code_interpreter_call",
+            "x-stainless-const": true,
+            "description": "The type of the code interpreter tool call. Always `code_interpreter_call`.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the code interpreter tool call.\n"
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "in_progress",
+              "completed",
+              "incomplete",
+              "interpreting",
+              "failed"
+            ],
+            "description": "The status of the code interpreter tool call. Valid values are `in_progress`, `completed`, `incomplete`, `interpreting`, and `failed`.\n"
+          },
+          "container_id": {
+            "type": "string",
+            "description": "The ID of the container used to run the code.\n"
+          },
+          "code": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The code to run, or null if not available.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "outputs": {
+            "anyOf": [
+              {
+                "type": "array",
+                "items": {
+                  "oneOf": [
+                    {
+                      "$ref": "#/components/schemas/CodeInterpreterOutputLogs"
+                    },
+                    {
+                      "$ref": "#/components/schemas/CodeInterpreterOutputImage"
+                    }
+                  ],
+                  "discriminator": {
+                    "propertyName": "type"
+                  }
+                },
+                "discriminator": {
+                  "propertyName": "type"
+                },
+                "description": "The outputs generated by the code interpreter, such as logs or images.\nCan be null if no outputs are available.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "status",
+          "container_id",
+          "code",
+          "outputs"
+        ]
+      },
+      "ComparisonFilter": {
+        "type": "object",
+        "additionalProperties": false,
+        "title": "Comparison Filter",
+        "description": "A filter used to compare a specified attribute key to a given value using a defined comparison operation.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "default": "eq",
+            "enum": [
+              "eq",
+              "ne",
+              "gt",
+              "gte",
+              "lt",
+              "lte",
+              "in",
+              "nin"
+            ],
+            "description": "Specifies the comparison operator: `eq`, `ne`, `gt`, `gte`, `lt`, `lte`, `in`, `nin`.\n- `eq`: equals\n- `ne`: not equal\n- `gt`: greater than\n- `gte`: greater than or equal\n- `lt`: less than\n- `lte`: less than or equal\n- `in`: in\n- `nin`: not in\n"
+          },
+          "key": {
+            "type": "string",
+            "description": "The key to compare against the value."
+          },
+          "value": {
+            "oneOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "number"
+              },
+              {
+                "type": "boolean"
+              },
+              {
+                "type": "array",
+                "items": {
+                  "oneOf": [
+                    {
+                      "type": "string"
+                    },
+                    {
+                      "type": "number"
+                    }
+                  ]
+                }
+              }
+            ],
+            "description": "The value to compare against the attribute key; supports string, number, or boolean types."
+          }
+        },
+        "required": [
+          "type",
+          "key",
+          "value"
+        ],
+        "x-oaiMeta": {
+          "name": "ComparisonFilter"
+        }
+      },
+      "CompleteUploadRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "part_ids": {
+            "type": "array",
+            "description": "The ordered list of Part IDs.\n",
+            "items": {
+              "type": "string"
+            }
+          },
+          "md5": {
+            "description": "The optional md5 checksum for the file contents to verify if the bytes uploaded matches what you expect.\n",
+            "type": "string"
+          }
+        },
+        "required": [
+          "part_ids"
+        ]
+      },
+      "CompletionUsage": {
+        "type": "object",
+        "description": "Usage statistics for the completion request.",
+        "properties": {
+          "completion_tokens": {
+            "type": "integer",
+            "default": 0,
+            "description": "Number of tokens in the generated completion."
+          },
+          "prompt_tokens": {
+            "type": "integer",
+            "default": 0,
+            "description": "Number of tokens in the prompt."
+          },
+          "total_tokens": {
+            "type": "integer",
+            "default": 0,
+            "description": "Total number of tokens used in the request (prompt + completion)."
+          },
+          "completion_tokens_details": {
+            "type": "object",
+            "description": "Breakdown of tokens used in a completion.",
+            "properties": {
+              "accepted_prediction_tokens": {
+                "type": "integer",
+                "default": 0,
+                "description": "When using Predicted Outputs, the number of tokens in the\nprediction that appeared in the completion.\n"
+              },
+              "audio_tokens": {
+                "type": "integer",
+                "default": 0,
+                "description": "Audio input tokens generated by the model."
+              },
+              "reasoning_tokens": {
+                "type": "integer",
+                "default": 0,
+                "description": "Tokens generated by the model for reasoning."
+              },
+              "text_tokens": {
+                "type": "integer",
+                "description": "Text output tokens generated by the model."
+              },
+              "rejected_prediction_tokens": {
+                "type": "integer",
+                "default": 0,
+                "description": "When using Predicted Outputs, the number of tokens in the\nprediction that did not appear in the completion. However, like\nreasoning tokens, these tokens are still counted in the total\ncompletion tokens for purposes of billing, output, and context window\nlimits.\n"
+              }
+            }
+          },
+          "prompt_tokens_details": {
+            "type": "object",
+            "description": "Breakdown of tokens used in the prompt.",
+            "properties": {
+              "audio_tokens": {
+                "type": "integer",
+                "default": 0,
+                "description": "Audio input tokens present in the prompt."
+              },
+              "cached_tokens": {
+                "type": "integer",
+                "default": 0,
+                "description": "Cached tokens present in the prompt."
+              },
+              "text_tokens": {
+                "type": "integer",
+                "description": "Text input tokens present in the prompt."
+              },
+              "image_tokens": {
+                "type": "integer",
+                "description": "Image input tokens present in the prompt."
+              },
+              "cache_write_tokens": {
+                "type": "integer",
+                "default": 0,
+                "description": "The unadjusted number of prompt tokens written to cache."
+              }
+            }
+          }
+        },
+        "required": [
+          "prompt_tokens",
+          "completion_tokens",
+          "total_tokens"
+        ]
+      },
+      "CompoundFilter": {
+        "$recursiveAnchor": true,
+        "type": "object",
+        "additionalProperties": false,
+        "title": "Compound Filter",
+        "description": "Combine multiple filters using `and` or `or`.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "Type of operation: `and` or `or`.",
+            "enum": [
+              "and",
+              "or"
+            ]
+          },
+          "filters": {
+            "type": "array",
+            "description": "Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`.",
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/ComparisonFilter"
+                },
+                {
+                  "$recursiveRef": "#"
+                }
+              ],
+              "discriminator": {
+                "propertyName": "type"
+              }
+            }
+          }
+        },
+        "required": [
+          "type",
+          "filters"
+        ],
+        "x-oaiMeta": {
+          "name": "CompoundFilter"
+        }
+      },
+      "ComputerAction": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/ClickParam"
+          },
+          {
+            "$ref": "#/components/schemas/DoubleClickAction"
+          },
+          {
+            "$ref": "#/components/schemas/DragParam"
+          },
+          {
+            "$ref": "#/components/schemas/KeyPressAction"
+          },
+          {
+            "$ref": "#/components/schemas/MoveParam"
+          },
+          {
+            "$ref": "#/components/schemas/ScreenshotParam"
+          },
+          {
+            "$ref": "#/components/schemas/ScrollParam"
+          },
+          {
+            "$ref": "#/components/schemas/TypeParam"
+          },
+          {
+            "$ref": "#/components/schemas/WaitParam"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "ComputerActionList": {
+        "title": "Computer Action List",
+        "type": "array",
+        "description": "Flattened batched actions for `computer_use`. Each action includes an\n`type` discriminator and action-specific fields.\n",
+        "items": {
+          "$ref": "#/components/schemas/ComputerAction"
+        }
+      },
+      "ComputerScreenshotImage": {
+        "type": "object",
+        "description": "A computer screenshot image used with the computer use tool.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "computer_screenshot"
+            ],
+            "default": "computer_screenshot",
+            "description": "Specifies the event type. For a computer screenshot, this property is \nalways set to `computer_screenshot`.\n",
+            "x-stainless-const": true
+          },
+          "image_url": {
+            "type": "string",
+            "format": "uri",
+            "description": "The URL of the screenshot image."
+          },
+          "file_id": {
+            "type": "string",
+            "description": "The identifier of an uploaded file that contains the screenshot."
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "ComputerToolCall": {
+        "type": "object",
+        "title": "Computer tool call",
+        "description": "A tool call to a computer use tool. See the\n[computer use guide](https://developers.openai.com/api/docs/guides/tools-computer-use) for more information.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the computer call. Always `computer_call`.",
+            "enum": [
+              "computer_call"
+            ],
+            "default": "computer_call"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the computer call."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "An identifier used when responding to the tool call with output.\n"
+          },
+          "action": {
+            "$ref": "#/components/schemas/ComputerAction"
+          },
+          "actions": {
+            "$ref": "#/components/schemas/ComputerActionList"
+          },
+          "pending_safety_checks": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/ComputerCallSafetyCheckParam"
+            },
+            "description": "The pending safety checks for the computer call.\n"
+          },
+          "status": {
+            "type": "string",
+            "description": "The status of the item. One of `in_progress`, `completed`, or\n`incomplete`. Populated when items are returned via API.\n",
+            "enum": [
+              "in_progress",
+              "completed",
+              "incomplete"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "pending_safety_checks",
+          "status"
+        ]
+      },
+      "ComputerToolCallOutput": {
+        "type": "object",
+        "title": "Computer tool call output",
+        "description": "The output of a computer tool call.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the computer tool call output. Always `computer_call_output`.\n",
+            "enum": [
+              "computer_call_output"
+            ],
+            "default": "computer_call_output",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The ID of the computer tool call output.\n"
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The ID of the computer tool call that produced the output.\n"
+          },
+          "acknowledged_safety_checks": {
+            "type": "array",
+            "description": "The safety checks reported by the API that have been acknowledged by the\ndeveloper.\n",
+            "items": {
+              "$ref": "#/components/schemas/ComputerCallSafetyCheckParam"
+            }
+          },
+          "output": {
+            "$ref": "#/components/schemas/ComputerScreenshotImage"
+          },
+          "status": {
+            "type": "string",
+            "description": "The status of the message input. One of `in_progress`, `completed`, or\n`incomplete`. Populated when input items are returned via API.\n",
+            "enum": [
+              "in_progress",
+              "completed",
+              "incomplete"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "call_id",
+          "output"
+        ]
+      },
+      "ComputerToolCallOutputResource": {
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/ComputerToolCallOutput"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the computer call tool output.\n"
+              },
+              "status": {
+                "description": "The status of the message input. One of `in_progress`, `completed`, or\n`incomplete`. Populated when input items are returned via API.\n",
+                "$ref": "#/components/schemas/ComputerCallOutputStatus"
+              },
+              "created_by": {
+                "type": "string",
+                "description": "The identifier of the actor that created the item.\n"
+              }
+            },
+            "required": [
+              "id",
+              "status"
+            ]
+          }
+        ]
+      },
+      "ContainerFileListResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "description": "The type of object returned, must be 'list'."
+          },
+          "data": {
+            "type": "array",
+            "description": "A list of container files.",
+            "items": {
+              "$ref": "#/components/schemas/ContainerFileResource"
+            }
+          },
+          "first_id": {
+            "type": "string",
+            "description": "The ID of the first file in the list."
+          },
+          "last_id": {
+            "type": "string",
+            "description": "The ID of the last file in the list."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more files available."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ]
+      },
+      "ContainerFileResource": {
+        "type": "object",
+        "title": "The container file object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Unique identifier for the file."
+          },
+          "object": {
+            "type": "string",
+            "description": "The type of this object (`container.file`)."
+          },
+          "container_id": {
+            "type": "string",
+            "description": "The container this file belongs to."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (in seconds) when the file was created."
+          },
+          "bytes": {
+            "type": "integer",
+            "description": "Size of the file in bytes."
+          },
+          "path": {
+            "type": "string",
+            "description": "Path of the file in the container."
+          },
+          "source": {
+            "type": "string",
+            "description": "Source of the file (e.g., `user`, `assistant`)."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "created_at",
+          "bytes",
+          "container_id",
+          "path",
+          "source"
+        ],
+        "x-oaiMeta": {
+          "name": "The container file object",
+          "example": "{\n    \"id\": \"cfile_682e0e8a43c88191a7978f477a09bdf5\",\n    \"object\": \"container.file\",\n    \"created_at\": 1747848842,\n    \"bytes\": 880,\n    \"container_id\": \"cntr_682e0e7318108198aa783fd921ff305e08e78805b9fdbb04\",\n    \"path\": \"/mnt/data/88e12fa445d32636f190a0b33daed6cb-tsconfig.json\",\n    \"source\": \"user\"\n}\n"
+        }
+      },
+      "ContainerListResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "description": "The type of object returned, must be 'list'."
+          },
+          "data": {
+            "type": "array",
+            "description": "A list of containers.",
+            "items": {
+              "$ref": "#/components/schemas/ContainerResource"
+            }
+          },
+          "first_id": {
+            "type": "string",
+            "description": "The ID of the first container in the list."
+          },
+          "last_id": {
+            "type": "string",
+            "description": "The ID of the last container in the list."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more containers available."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ]
+      },
+      "ContainerResource": {
+        "type": "object",
+        "title": "The container object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Unique identifier for the container."
+          },
+          "object": {
+            "type": "string",
+            "description": "The type of this object."
+          },
+          "name": {
+            "type": "string",
+            "description": "Name of the container."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (in seconds) when the container was created."
+          },
+          "status": {
+            "type": "string",
+            "description": "Status of the container (e.g., active, deleted)."
+          },
+          "last_active_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (in seconds) when the container was last active."
+          },
+          "expires_after": {
+            "type": "object",
+            "description": "The container will expire after this time period.\nThe anchor is the reference point for the expiration.\nThe minutes is the number of minutes after the anchor before the container expires.\n",
+            "properties": {
+              "anchor": {
+                "type": "string",
+                "description": "The reference point for the expiration.",
+                "enum": [
+                  "last_active_at"
+                ]
+              },
+              "minutes": {
+                "type": "integer",
+                "description": "The number of minutes after the anchor before the container expires."
+              }
+            }
+          },
+          "memory_limit": {
+            "type": "string",
+            "description": "The memory limit configured for the container.",
+            "enum": [
+              "1g",
+              "4g",
+              "16g",
+              "64g"
+            ]
+          },
+          "network_policy": {
+            "description": "Network access policy for the container.",
+            "type": "object",
+            "properties": {
+              "type": {
+                "type": "string",
+                "description": "The network policy mode.",
+                "enum": [
+                  "allowlist",
+                  "disabled"
+                ]
+              },
+              "allowed_domains": {
+                "type": "array",
+                "description": "Allowed outbound domains when `type` is `allowlist`.",
+                "items": {
+                  "type": "string"
+                }
+              }
+            },
+            "required": [
+              "type"
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "name",
+          "created_at",
+          "status",
+          "id",
+          "name",
+          "created_at",
+          "status"
+        ],
+        "x-oaiMeta": {
+          "name": "The container object",
+          "example": "{\n   \"id\": \"cntr_682dfebaacac8198bbfe9c2474fb6f4a085685cbe3cb5863\",\n   \"object\": \"container\",\n   \"created_at\": 1747844794,\n   \"status\": \"running\",\n   \"expires_after\": {\n     \"anchor\": \"last_active_at\",\n     \"minutes\": 20\n   },\n   \"last_active_at\": 1747844794,\n   \"memory_limit\": \"1g\",\n   \"name\": \"My Container\"\n}\n"
+        }
+      },
+      "Content": {
+        "description": "Multi-modal input and output contents.\n",
+        "oneOf": [
+          {
+            "title": "Input content types",
+            "$ref": "#/components/schemas/InputContent"
+          },
+          {
+            "title": "Output content types",
+            "$ref": "#/components/schemas/OutputContent"
+          }
+        ]
+      },
+      "ConversationItem": {
+        "title": "Conversation item",
+        "description": "A single item within a conversation. The set of possible types are the same as the `output` type of a [Response object](https://developers.openai.com/api/reference/resources/responses#%28resource%29%20responses%20%3E%20%28model%29%20response%20%3E%20%28schema%29%20%3E%20%28property%29%20output).",
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/Message"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionToolCallResource"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionToolCallOutputResource"
+          },
+          {
+            "$ref": "#/components/schemas/FileSearchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/WebSearchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/ImageGenToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/ComputerToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/ComputerToolCallOutputResource"
+          },
+          {
+            "$ref": "#/components/schemas/ToolSearchCall"
+          },
+          {
+            "$ref": "#/components/schemas/ToolSearchOutput"
+          },
+          {
+            "$ref": "#/components/schemas/AdditionalTools"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseConfigurationUpdate"
+          },
+          {
+            "$ref": "#/components/schemas/ReasoningItem"
+          },
+          {
+            "$ref": "#/components/schemas/Program"
+          },
+          {
+            "$ref": "#/components/schemas/ProgramOutput"
+          },
+          {
+            "$ref": "#/components/schemas/CompactionBody"
+          },
+          {
+            "$ref": "#/components/schemas/CodeInterpreterToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/LocalShellToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/LocalShellToolCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionShellCall"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionShellCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/ApplyPatchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/ApplyPatchToolCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/MCPListTools"
+          },
+          {
+            "$ref": "#/components/schemas/MCPApprovalRequest"
+          },
+          {
+            "$ref": "#/components/schemas/MCPApprovalResponseResource"
+          },
+          {
+            "$ref": "#/components/schemas/MCPToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/CustomToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/CustomToolCallOutput"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "ConversationItemList": {
+        "type": "object",
+        "title": "The conversation item list",
+        "description": "A list of Conversation items.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "description": "The type of object returned, must be `list`.",
+            "enum": [
+              "list"
+            ],
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "description": "A list of conversation items.",
+            "items": {
+              "$ref": "#/components/schemas/ConversationItem"
+            }
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more items available."
+          },
+          "first_id": {
+            "type": "string",
+            "description": "The ID of the first item in the list."
+          },
+          "last_id": {
+            "type": "string",
+            "description": "The ID of the last item in the list."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more",
+          "first_id",
+          "last_id"
+        ],
+        "x-oaiMeta": {
+          "name": "The item list",
+          "group": "conversations"
+        }
+      },
+      "ConversationParam": {
+        "description": "The conversation that this response belongs to. Items from this conversation are prepended to `input_items` for this response request.\nInput items and output items from this response are automatically added to this conversation after this response completes.\n",
+        "default": null,
+        "oneOf": [
+          {
+            "type": "string",
+            "title": "Conversation ID",
+            "description": "The unique ID of the conversation.\n"
+          },
+          {
+            "$ref": "#/components/schemas/ConversationParam-2"
+          }
+        ]
+      },
+      "CostsResult": {
+        "type": "object",
+        "description": "The aggregated costs details of the specific time bucket.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.costs.result"
+            ],
+            "x-stainless-const": true
+          },
+          "amount": {
+            "type": "object",
+            "description": "The monetary value in its associated currency.",
+            "properties": {
+              "value": {
+                "type": "number",
+                "description": "The numeric value of the cost."
+              },
+              "currency": {
+                "type": "string",
+                "description": "Lowercase ISO-4217 currency e.g. \"usd\""
+              }
+            }
+          },
+          "line_item": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=line_item`, this field provides the line item of the grouped costs result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "project_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=project_id`, this field provides the project ID of the grouped costs result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "api_key_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=api_key_id`, this field provides the API Key ID of the grouped costs result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "quantity": {
+            "anyOf": [
+              {
+                "type": "number",
+                "description": "When `group_by=line_item`, this field provides the quantity of the grouped costs result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "quantity_unit": {
+            "description": "The unit of the `quantity` value. If no single supported unit applies to the result, this field is `null`.",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "tokens",
+                  "1000_tokens",
+                  "duration_seconds",
+                  "duration_minutes",
+                  "duration_hours",
+                  "gibibyte_hours",
+                  "images",
+                  "characters"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object"
+        ],
+        "x-oaiMeta": {
+          "name": "Costs object",
+          "example": "{\n    \"object\": \"organization.costs.result\",\n    \"amount\": {\n      \"value\": 0.06,\n      \"currency\": \"usd\"\n    },\n    \"line_item\": \"gpt-6-astra, input_tokens\",\n    \"project_id\": \"proj_abc\",\n    \"quantity\": 10000,\n    \"quantity_unit\": \"tokens\"\n}\n"
+        }
+      },
+      "CreateAssistantRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "model": {
+            "description": "ID of the model to use. You can use the [List models](https://developers.openai.com/api/reference/resources/models/methods/list) API to see all of your available models, or see our [Model overview](https://developers.openai.com/api/docs/models) for descriptions of them.\n",
+            "example": "gpt-5",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "$ref": "#/components/schemas/AssistantSupportedModels"
+              }
+            ],
+            "x-oaiTypeLabel": "string"
+          },
+          "name": {
+            "anyOf": [
+              {
+                "description": "The name of the assistant. The maximum length is 256 characters.\n",
+                "type": "string",
+                "maxLength": 256
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "description": {
+            "anyOf": [
+              {
+                "description": "The description of the assistant. The maximum length is 512 characters.\n",
+                "type": "string",
+                "maxLength": 512
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "instructions": {
+            "anyOf": [
+              {
+                "description": "The system instructions that the assistant uses. The maximum length is 256,000 characters.\n",
+                "type": "string",
+                "maxLength": 256000
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "reasoning_effort": {
+            "$ref": "#/components/schemas/ReasoningEffort"
+          },
+          "tools": {
+            "description": "A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types `code_interpreter`, `file_search`, or `function`.\n",
+            "default": [],
+            "type": "array",
+            "maxItems": 128,
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/AssistantToolsCode"
+                },
+                {
+                  "$ref": "#/components/schemas/AssistantToolsFileSearch"
+                },
+                {
+                  "$ref": "#/components/schemas/AssistantToolsFunction"
+                }
+              ]
+            }
+          },
+          "tool_resources": {
+            "anyOf": [
+              {
+                "type": "object",
+                "description": "A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs.\n",
+                "properties": {
+                  "code_interpreter": {
+                    "type": "object",
+                    "properties": {
+                      "file_ids": {
+                        "type": "array",
+                        "description": "A list of [file](https://developers.openai.com/api/reference/resources/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool.\n",
+                        "default": [],
+                        "maxItems": 20,
+                        "items": {
+                          "type": "string"
+                        }
+                      }
+                    }
+                  },
+                  "file_search": {
+                    "type": "object",
+                    "properties": {
+                      "vector_store_ids": {
+                        "type": "array",
+                        "description": "The [vector store](https://developers.openai.com/api/reference/resources/vector_stores) attached to this assistant. There can be a maximum of 1 vector store attached to the assistant.\n",
+                        "maxItems": 1,
+                        "items": {
+                          "type": "string"
+                        }
+                      },
+                      "vector_stores": {
+                        "type": "array",
+                        "description": "A helper to create a [vector store](https://developers.openai.com/api/reference/resources/vector_stores) with file_ids and attach it to this assistant. There can be a maximum of 1 vector store attached to the assistant.\n",
+                        "maxItems": 1,
+                        "items": {
+                          "type": "object",
+                          "properties": {
+                            "file_ids": {
+                              "type": "array",
+                              "description": "A list of [file](https://developers.openai.com/api/reference/resources/files) IDs to add to the vector store. For vector stores created before Nov 2025, there can be a maximum of 10,000 files in a vector store. For vector stores created starting in Nov 2025, the limit is 100,000,000 files.\n",
+                              "maxItems": 100000000,
+                              "items": {
+                                "type": "string"
+                              }
+                            },
+                            "chunking_strategy": {
+                              "type": "object",
+                              "description": "The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy.",
+                              "oneOf": [
+                                {
+                                  "type": "object",
+                                  "title": "Auto Chunking Strategy",
+                                  "description": "The default strategy. This strategy currently uses a `max_chunk_size_tokens` of `800` and `chunk_overlap_tokens` of `400`.",
+                                  "additionalProperties": false,
+                                  "properties": {
+                                    "type": {
+                                      "type": "string",
+                                      "description": "Always `auto`.",
+                                      "enum": [
+                                        "auto"
+                                      ],
+                                      "x-stainless-const": true
+                                    }
+                                  },
+                                  "required": [
+                                    "type"
+                                  ]
+                                },
+                                {
+                                  "type": "object",
+                                  "title": "Static Chunking Strategy",
+                                  "additionalProperties": false,
+                                  "properties": {
+                                    "type": {
+                                      "type": "string",
+                                      "description": "Always `static`.",
+                                      "enum": [
+                                        "static"
+                                      ],
+                                      "x-stainless-const": true
+                                    },
+                                    "static": {
+                                      "type": "object",
+                                      "additionalProperties": false,
+                                      "properties": {
+                                        "max_chunk_size_tokens": {
+                                          "type": "integer",
+                                          "minimum": 100,
+                                          "maximum": 4096,
+                                          "description": "The maximum number of tokens in each chunk. The default value is `800`. The minimum value is `100` and the maximum value is `4096`."
+                                        },
+                                        "chunk_overlap_tokens": {
+                                          "type": "integer",
+                                          "description": "The number of tokens that overlap between chunks. The default value is `400`.\n\nNote that the overlap must not exceed half of `max_chunk_size_tokens`.\n"
+                                        }
+                                      },
+                                      "required": [
+                                        "max_chunk_size_tokens",
+                                        "chunk_overlap_tokens"
+                                      ]
+                                    }
+                                  },
+                                  "required": [
+                                    "type",
+                                    "static"
+                                  ]
+                                }
+                              ]
+                            },
+                            "metadata": {
+                              "$ref": "#/components/schemas/Metadata"
+                            }
+                          }
+                        }
+                      }
+                    },
+                    "oneOf": [
+                      {
+                        "required": [
+                          "vector_store_ids"
+                        ]
+                      },
+                      {
+                        "required": [
+                          "vector_stores"
+                        ]
+                      }
+                    ]
+                  }
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          },
+          "temperature": {
+            "anyOf": [
+              {
+                "description": "What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.\n",
+                "type": "number",
+                "minimum": 0,
+                "maximum": 2,
+                "default": 1,
+                "example": 1
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "top_p": {
+            "anyOf": [
+              {
+                "type": "number",
+                "minimum": 0,
+                "maximum": 1,
+                "default": 1,
+                "example": 1,
+                "description": "An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\n\nWe generally recommend altering this or temperature but not both.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "response_format": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/AssistantsApiResponseFormatOption"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "model"
+        ]
+      },
+      "CreateBatchRequest": {
+        "type": "object",
+        "required": [
+          "input_file_id",
+          "endpoint",
+          "completion_window"
+        ],
+        "properties": {
+          "input_file_id": {
+            "type": "string",
+            "description": "The ID of an uploaded file that contains requests for the new batch.\n\nSee [upload file](https://developers.openai.com/api/reference/resources/files/methods/create) for how to upload a file.\n\nYour input file must be formatted as a [JSONL file](https://developers.openai.com/api/docs/guides/batch#1-prepare-your-batch-file), and must be uploaded with the purpose `batch`. The file can contain up to 50,000 requests, and can be up to 200 MB in size.\n"
+          },
+          "endpoint": {
+            "type": "string",
+            "enum": [
+              "/v1/responses",
+              "/v1/chat/completions",
+              "/v1/embeddings",
+              "/v1/completions",
+              "/v1/moderations",
+              "/v1/images/generations",
+              "/v1/images/edits",
+              "/v1/videos"
+            ],
+            "description": "The endpoint to be used for all requests in the batch. Currently `/v1/responses`, `/v1/chat/completions`, `/v1/embeddings`, `/v1/completions`, `/v1/moderations`, `/v1/images/generations`, `/v1/images/edits`, and `/v1/videos` are supported. Note that `/v1/embeddings` batches are also restricted to a maximum of 50,000 embedding inputs across all requests in the batch."
+          },
+          "completion_window": {
+            "type": "string",
+            "enum": [
+              "24h"
+            ],
+            "description": "The time frame within which the batch should be processed. Currently only `24h` is supported."
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          },
+          "output_expires_after": {
+            "$ref": "#/components/schemas/BatchFileExpirationAfter"
+          }
+        }
+      },
+      "CreateChatCompletionRequest": {
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/CreateModelResponseProperties"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "messages": {
+                "description": "A list of messages comprising the conversation so far. Depending on the\n[model](https://developers.openai.com/api/docs/models) you use, different message types (modalities) are\nsupported, like [text](https://developers.openai.com/api/docs/guides/text),\n[images](https://developers.openai.com/api/docs/guides/images-vision), and [audio](https://developers.openai.com/api/docs/guides/audio).\n",
+                "type": "array",
+                "minItems": 1,
+                "items": {
+                  "$ref": "#/components/schemas/ChatCompletionRequestMessage"
+                }
+              },
+              "model": {
+                "description": "Model ID used to generate the response, like `gpt-6-astra` or `o3`. OpenAI\noffers a wide range of models with different capabilities, performance\ncharacteristics, and price points. Refer to the [model guide](https://developers.openai.com/api/docs/models)\nto browse and compare available models.\n",
+                "$ref": "#/components/schemas/ModelIdsShared"
+              },
+              "service_tier": {
+                "$ref": "#/components/schemas/ServiceTier"
+              },
+              "modalities": {
+                "$ref": "#/components/schemas/ResponseModalities"
+              },
+              "verbosity": {
+                "$ref": "#/components/schemas/Verbosity"
+              },
+              "reasoning_effort": {
+                "$ref": "#/components/schemas/ReasoningEffort"
+              },
+              "max_completion_tokens": {
+                "description": "An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and [reasoning tokens](https://developers.openai.com/api/docs/guides/reasoning).\n",
+                "type": "integer",
+                "nullable": true
+              },
+              "frequency_penalty": {
+                "type": "number",
+                "default": 0,
+                "minimum": -2,
+                "maximum": 2,
+                "nullable": true,
+                "description": "Number between -2.0 and 2.0. Positive values penalize new tokens based on\ntheir existing frequency in the text so far, decreasing the model's\nlikelihood to repeat the same line verbatim.\n"
+              },
+              "presence_penalty": {
+                "type": "number",
+                "default": 0,
+                "minimum": -2,
+                "maximum": 2,
+                "nullable": true,
+                "description": "Number between -2.0 and 2.0. Positive values penalize new tokens based on\nwhether they appear in the text so far, increasing the model's likelihood\nto talk about new topics.\n"
+              },
+              "web_search_options": {
+                "type": "object",
+                "title": "Web search",
+                "description": "This tool searches the web for relevant results to use in a response.\nLearn more about the [web search tool](https://developers.openai.com/api/docs/guides/tools-web-search).\n",
+                "properties": {
+                  "user_location": {
+                    "type": "object",
+                    "nullable": true,
+                    "required": [
+                      "type",
+                      "approximate"
+                    ],
+                    "description": "Approximate location parameters for the search.\n",
+                    "properties": {
+                      "type": {
+                        "type": "string",
+                        "description": "The type of location approximation. Always `approximate`.\n",
+                        "enum": [
+                          "approximate"
+                        ],
+                        "x-stainless-const": true
+                      },
+                      "approximate": {
+                        "$ref": "#/components/schemas/WebSearchLocation"
+                      }
+                    }
+                  },
+                  "search_context_size": {
+                    "$ref": "#/components/schemas/WebSearchContextSize"
+                  }
+                }
+              },
+              "top_logprobs": {
+                "description": "An integer between 0 and 20 specifying the maximum number of most likely\ntokens to return at each token position, each with an associated log\nprobability. In some cases, the number of returned tokens may be fewer than\nrequested.\n`logprobs` must be set to `true` if this parameter is used.\n",
+                "type": "integer",
+                "minimum": 0,
+                "maximum": 20,
+                "nullable": true
+              },
+              "response_format": {
+                "description": "An object specifying the format that the model must output.\n\nSetting to `{ \"type\": \"json_schema\", \"json_schema\": {...} }` enables\nStructured Outputs which ensures the model will match your supplied JSON\nschema. Learn more in the [Structured Outputs\nguide](https://developers.openai.com/api/docs/guides/structured-outputs).\n\nSetting to `{ \"type\": \"json_object\" }` enables the older JSON mode, which\nensures the message the model generates is valid JSON. Using `json_schema`\nis preferred for models that support it.\n",
+                "oneOf": [
+                  {
+                    "$ref": "#/components/schemas/ResponseFormatText"
+                  },
+                  {
+                    "$ref": "#/components/schemas/ResponseFormatJsonSchema"
+                  },
+                  {
+                    "$ref": "#/components/schemas/ResponseFormatJsonObject"
+                  }
+                ],
+                "discriminator": {
+                  "propertyName": "type"
+                }
+              },
+              "audio": {
+                "type": "object",
+                "nullable": true,
+                "description": "Parameters for audio output. Required when audio output is requested with\n`modalities: [\"audio\"]`. [Learn more](https://developers.openai.com/api/docs/guides/audio).\n",
+                "required": [
+                  "voice",
+                  "format"
+                ],
+                "properties": {
+                  "voice": {
+                    "$ref": "#/components/schemas/VoiceIdsOrCustomVoice",
+                    "description": "The voice the model uses to respond. Supported built-in voices are\n`alloy`, `ash`, `ballad`, `coral`, `echo`, `fable`, `nova`, `onyx`,\n`sage`, `shimmer`, `marin`, and `cedar`. You may also provide a\ncustom voice object with an `id`, for example `{ \"id\": \"voice_1234\" }`.\n"
+                  },
+                  "format": {
+                    "type": "string",
+                    "enum": [
+                      "wav",
+                      "aac",
+                      "mp3",
+                      "flac",
+                      "opus",
+                      "pcm16"
+                    ],
+                    "description": "Specifies the output audio format. Must be one of `wav`, `mp3`, `flac`,\n`opus`, or `pcm16`.\n"
+                  }
+                }
+              },
+              "store": {
+                "type": "boolean",
+                "default": false,
+                "nullable": true,
+                "description": "Whether or not to store the output of this chat completion request for\nuse in our [model distillation](https://developers.openai.com/api/docs/guides/supervised-fine-tuning#distilling-from-a-larger-model) or\n[evals](https://developers.openai.com/api/docs/guides/evals) products.\n\nSupports text and image inputs. Note: image inputs over 8MB will be dropped.\n"
+              },
+              "moderation": {
+                "anyOf": [
+                  {
+                    "$ref": "#/components/schemas/ModerationParam",
+                    "description": "Configuration for running moderation on the request input and generated output.\n"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "stream": {
+                "description": "If set to true, the model response data will be streamed to the client\nas it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).\nSee the [Streaming section below](https://developers.openai.com/api/reference/resources/chat/subresources/completions/streaming-events)\nfor more information, along with the [streaming responses](https://developers.openai.com/api/docs/guides/streaming-responses)\nguide for more information on how to handle the streaming events.\n",
+                "type": "boolean",
+                "nullable": true,
+                "default": false
+              },
+              "stop": {
+                "$ref": "#/components/schemas/StopConfiguration"
+              },
+              "logit_bias": {
+                "type": "object",
+                "x-oaiTypeLabel": "map",
+                "default": null,
+                "nullable": true,
+                "additionalProperties": {
+                  "type": "integer"
+                },
+                "description": "Modify the likelihood of specified tokens appearing in the completion.\n\nAccepts a JSON object that maps tokens (specified by their token ID in the\ntokenizer) to an associated bias value from -100 to 100. Mathematically,\nthe bias is added to the logits generated by the model prior to sampling.\nThe exact effect will vary per model, but values between -1 and 1 should\ndecrease or increase likelihood of selection; values like -100 or 100\nshould result in a ban or exclusive selection of the relevant token.\n"
+              },
+              "logprobs": {
+                "description": "Whether to return log probabilities of the output tokens or not. If true,\nreturns the log probabilities of each output token returned in the\n`content` of `message`.\n",
+                "type": "boolean",
+                "default": false,
+                "nullable": true
+              },
+              "max_tokens": {
+                "description": "The maximum number of [tokens](https://platform.openai.com/tokenizer) that can be generated in the\nchat completion. This value can be used to control\n[costs](https://openai.com/api/pricing/) for text generated via API.\n\nThis value is now deprecated in favor of `max_completion_tokens`, and is\nnot compatible with [o-series models](https://developers.openai.com/api/docs/guides/reasoning).\n",
+                "type": "integer",
+                "nullable": true,
+                "deprecated": true
+              },
+              "n": {
+                "type": "integer",
+                "minimum": 1,
+                "maximum": 128,
+                "default": 1,
+                "example": 1,
+                "nullable": true,
+                "description": "How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs."
+              },
+              "prediction": {
+                "nullable": true,
+                "description": "Configuration for a [Predicted Output](https://developers.openai.com/api/docs/guides/predicted-outputs),\nwhich can greatly improve response times when large parts of the model\nresponse are known ahead of time. This is most common when you are\nregenerating a file with only minor changes to most of the content.\n",
+                "oneOf": [
+                  {
+                    "$ref": "#/components/schemas/PredictionContent"
+                  }
+                ]
+              },
+              "seed": {
+                "type": "integer",
+                "minimum": -9223372036854776000,
+                "maximum": 9223372036854776000,
+                "nullable": true,
+                "deprecated": true,
+                "description": "This feature is in Beta.\nIf specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result.\nDeterminism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend.\n",
+                "x-oaiMeta": {
+                  "beta": true
+                }
+              },
+              "stream_options": {
+                "$ref": "#/components/schemas/ChatCompletionStreamOptions"
+              },
+              "tools": {
+                "type": "array",
+                "description": "A list of tools the model may call. You can provide either\n[custom tools](https://developers.openai.com/api/docs/guides/function-calling#custom-tools) or\n[function tools](https://developers.openai.com/api/docs/guides/function-calling).\n",
+                "items": {
+                  "oneOf": [
+                    {
+                      "$ref": "#/components/schemas/ChatCompletionTool"
+                    },
+                    {
+                      "$ref": "#/components/schemas/CustomToolChatCompletions"
+                    }
+                  ]
+                }
+              },
+              "tool_choice": {
+                "$ref": "#/components/schemas/ChatCompletionToolChoiceOption"
+              },
+              "parallel_tool_calls": {
+                "$ref": "#/components/schemas/ParallelToolCalls"
+              },
+              "function_call": {
+                "deprecated": true,
+                "description": "Deprecated in favor of `tool_choice`.\n\nControls which (if any) function is called by the model.\n\n`none` means the model will not call a function and instead generates a\nmessage.\n\n`auto` means the model can pick between generating a message or calling a\nfunction.\n\nSpecifying a particular function via `{\"name\": \"my_function\"}` forces the\nmodel to call that function.\n\n`none` is the default when no functions are present. `auto` is the default\nif functions are present.\n",
+                "oneOf": [
+                  {
+                    "type": "string",
+                    "description": "`none` means the model will not call a function and instead generates a message. `auto` means the model can pick between generating a message or calling a function.\n",
+                    "enum": [
+                      "none",
+                      "auto"
+                    ]
+                  },
+                  {
+                    "$ref": "#/components/schemas/ChatCompletionFunctionCallOption"
+                  }
+                ]
+              },
+              "functions": {
+                "deprecated": true,
+                "description": "Deprecated in favor of `tools`.\n\nA list of functions the model may generate JSON inputs for.\n",
+                "type": "array",
+                "minItems": 1,
+                "maxItems": 128,
+                "items": {
+                  "$ref": "#/components/schemas/ChatCompletionFunctions"
+                }
+              }
+            },
+            "required": [
+              "model",
+              "messages"
+            ]
+          }
+        ]
+      },
+      "CreateChatCompletionResponse": {
+        "type": "object",
+        "description": "Represents a chat completion response returned by model, based on the provided input.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "A unique identifier for the chat completion."
+          },
+          "choices": {
+            "type": "array",
+            "description": "A list of chat completion choices. Can be more than one if `n` is greater than 1.",
+            "items": {
+              "type": "object",
+              "required": [
+                "finish_reason",
+                "index",
+                "message",
+                "logprobs"
+              ],
+              "properties": {
+                "finish_reason": {
+                  "type": "string",
+                  "description": "The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence,\n`length` if the maximum number of tokens specified in the request was reached,\n`content_filter` if content was omitted due to a flag from our content filters,\n`tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function.\nRead the [Model Spec](https://model-spec.openai.com/2025-12-18.html) for more.\n",
+                  "enum": [
+                    "stop",
+                    "length",
+                    "tool_calls",
+                    "content_filter",
+                    "function_call"
+                  ]
+                },
+                "index": {
+                  "type": "integer",
+                  "description": "The index of the choice in the list of choices."
+                },
+                "message": {
+                  "$ref": "#/components/schemas/ChatCompletionResponseMessage"
+                },
+                "logprobs": {
+                  "anyOf": [
+                    {
+                      "description": "Log probability information for the choice.",
+                      "type": "object",
+                      "properties": {
+                        "content": {
+                          "anyOf": [
+                            {
+                              "description": "A list of message content tokens with log probability information.",
+                              "type": "array",
+                              "items": {
+                                "$ref": "#/components/schemas/ChatCompletionTokenLogprob"
+                              }
+                            },
+                            {
+                              "type": "null"
+                            }
+                          ]
+                        },
+                        "refusal": {
+                          "anyOf": [
+                            {
+                              "description": "A list of message refusal tokens with log probability information.",
+                              "type": "array",
+                              "items": {
+                                "$ref": "#/components/schemas/ChatCompletionTokenLogprob"
+                              }
+                            },
+                            {
+                              "type": "null"
+                            }
+                          ]
+                        }
+                      },
+                      "required": [
+                        "content",
+                        "refusal"
+                      ]
+                    },
+                    {
+                      "type": "null"
+                    }
+                  ]
+                }
+              }
+            }
+          },
+          "created": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the chat completion was created."
+          },
+          "model": {
+            "type": "string",
+            "description": "The model used for the chat completion."
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          },
+          "service_tier": {
+            "$ref": "#/components/schemas/ServiceTier"
+          },
+          "system_fingerprint": {
+            "type": "string",
+            "deprecated": true,
+            "description": "This fingerprint represents the backend configuration that the model runs with.\n\nCan be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism.\n"
+          },
+          "object": {
+            "type": "string",
+            "description": "The object type, which is always `chat.completion`.",
+            "enum": [
+              "chat.completion"
+            ],
+            "x-stainless-const": true
+          },
+          "usage": {
+            "$ref": "#/components/schemas/CompletionUsage"
+          },
+          "moderation": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ChatCompletionModeration",
+                "description": "Moderation results for the request input and generated output, if moderated\ncompletions were requested.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "choices",
+          "created",
+          "id",
+          "model",
+          "object"
+        ],
+        "x-oaiMeta": {
+          "name": "The chat completion object",
+          "group": "chat",
+          "example": "{\n  \"id\": \"chatcmpl-B9MHDbslfkBeAs8l4bebGdFOJ6PeG\",\n  \"object\": \"chat.completion\",\n  \"created\": 1741570283,\n  \"model\": \"gpt-6-astra\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"The image shows a wooden boardwalk path running through a lush green field or meadow. The sky is bright blue with some scattered clouds, giving the scene a serene and peaceful atmosphere. Trees and shrubs are visible in the background.\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 1117,\n    \"completion_tokens\": 46,\n    \"total_tokens\": 1163,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\": \"default\",\n  \"system_fingerprint\": \"fp_fc9f1d7035\"\n}\n"
+        }
+      },
+      "CreateChatCompletionStreamResponse": {
+        "type": "object",
+        "description": "Represents a streamed chunk of a chat completion response returned\nby the model, based on the provided input.\n[Learn more](https://developers.openai.com/api/docs/guides/streaming-responses).\n",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "A unique identifier for the chat completion. Each chunk has the same ID."
+          },
+          "choices": {
+            "type": "array",
+            "description": "A list of chat completion choices. Can contain more than one elements if `n` is greater than 1. Can also be empty for the\nlast chunk if you set `stream_options: {\"include_usage\": true}`.\n",
+            "items": {
+              "type": "object",
+              "required": [
+                "delta",
+                "finish_reason",
+                "index"
+              ],
+              "properties": {
+                "delta": {
+                  "$ref": "#/components/schemas/ChatCompletionStreamResponseDelta"
+                },
+                "logprobs": {
+                  "description": "Log probability information for the choice.",
+                  "type": "object",
+                  "nullable": true,
+                  "properties": {
+                    "content": {
+                      "description": "A list of message content tokens with log probability information.",
+                      "type": "array",
+                      "items": {
+                        "$ref": "#/components/schemas/ChatCompletionTokenLogprob"
+                      },
+                      "nullable": true
+                    },
+                    "refusal": {
+                      "description": "A list of message refusal tokens with log probability information.",
+                      "type": "array",
+                      "items": {
+                        "$ref": "#/components/schemas/ChatCompletionTokenLogprob"
+                      },
+                      "nullable": true
+                    }
+                  },
+                  "required": [
+                    "content",
+                    "refusal"
+                  ]
+                },
+                "finish_reason": {
+                  "type": "string",
+                  "description": "The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence,\n`length` if the maximum number of tokens specified in the request was reached,\n`content_filter` if content was omitted due to a flag from our content filters,\n`tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function.\n",
+                  "enum": [
+                    "stop",
+                    "length",
+                    "tool_calls",
+                    "content_filter",
+                    "function_call"
+                  ],
+                  "nullable": true
+                },
+                "index": {
+                  "type": "integer",
+                  "description": "The index of the choice in the list of choices."
+                }
+              }
+            }
+          },
+          "created": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp."
+          },
+          "model": {
+            "type": "string",
+            "description": "The model to generate the completion."
+          },
+          "obfuscation": {
+            "type": "string",
+            "description": "An obfuscation string added to normalize the size of streamed chunks as a\nmitigation to certain side-channel attacks. The field is included by\ndefault and omitted when `stream_options.include_obfuscation` is `false`.\n"
+          },
+          "service_tier": {
+            "$ref": "#/components/schemas/ServiceTier"
+          },
+          "system_fingerprint": {
+            "type": "string",
+            "deprecated": true,
+            "description": "This fingerprint represents the backend configuration that the model runs with.\nCan be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism.\n"
+          },
+          "object": {
+            "type": "string",
+            "description": "The object type, which is always `chat.completion.chunk`.",
+            "enum": [
+              "chat.completion.chunk"
+            ],
+            "x-stainless-const": true
+          },
+          "usage": {
+            "$ref": "#/components/schemas/CompletionUsage",
+            "nullable": true,
+            "description": "An optional field that will only be present when you set\n`stream_options: {\"include_usage\": true}` in your request. When present, it\ncontains a null value **except for the last chunk** which contains the\ntoken usage statistics for the entire request.\n\n**NOTE:** If the stream is interrupted or cancelled, you may not\nreceive the final usage chunk which contains the total token usage for\nthe request.\n"
+          },
+          "moderation": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ChatCompletionModeration",
+                "description": "Moderation results for the request input and generated output. Present\non the moderation chunk when moderated completions are requested.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "choices",
+          "created",
+          "id",
+          "model",
+          "object"
+        ],
+        "x-oaiMeta": {
+          "name": "The chat completion chunk object",
+          "group": "chat",
+          "example": "{\"id\":\"chatcmpl-123\",\"object\":\"chat.completion.chunk\",\"created\":1694268190,\"model\":\"gpt-6-astra\", \"system_fingerprint\": \"fp_44709d6fcb\", \"choices\":[{\"index\":0,\"delta\":{\"role\":\"assistant\",\"content\":\"\"},\"logprobs\":null,\"finish_reason\":null}],\"obfuscation\":\"r4N7vQ2m\"}\n\n{\"id\":\"chatcmpl-123\",\"object\":\"chat.completion.chunk\",\"created\":1694268190,\"model\":\"gpt-6-astra\", \"system_fingerprint\": \"fp_44709d6fcb\", \"choices\":[{\"index\":0,\"delta\":{\"content\":\"Hello\"},\"logprobs\":null,\"finish_reason\":null}],\"obfuscation\":\"p9K3xT6w\"}\n\n....\n\n{\"id\":\"chatcmpl-123\",\"object\":\"chat.completion.chunk\",\"created\":1694268190,\"model\":\"gpt-6-astra\", \"system_fingerprint\": \"fp_44709d6fcb\", \"choices\":[{\"index\":0,\"delta\":{},\"logprobs\":null,\"finish_reason\":\"stop\"}],\"obfuscation\":\"\"}\n"
+        }
+      },
+      "CreateCompletionRequest": {
+        "type": "object",
+        "properties": {
+          "model": {
+            "description": "ID of the model to use. You can use the [List models](https://developers.openai.com/api/reference/resources/models/methods/list) API to see all of your available models, or see our [Model overview](https://developers.openai.com/api/docs/models) for descriptions of them.\n",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "gpt-3.5-turbo-instruct",
+                  "davinci-002",
+                  "babbage-002"
+                ]
+              }
+            ],
+            "x-oaiTypeLabel": "string"
+          },
+          "prompt": {
+            "description": "The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays.\n\nNote that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document.\n",
+            "default": "<|endoftext|>",
+            "nullable": true,
+            "oneOf": [
+              {
+                "type": "string",
+                "default": "",
+                "example": "This is a test."
+              },
+              {
+                "type": "array",
+                "items": {
+                  "type": "string",
+                  "default": "",
+                  "example": "This is a test."
+                }
+              },
+              {
+                "type": "array",
+                "minItems": 1,
+                "items": {
+                  "type": "integer"
+                },
+                "example": "[1212, 318, 257, 1332, 13]"
+              },
+              {
+                "type": "array",
+                "minItems": 1,
+                "items": {
+                  "type": "array",
+                  "minItems": 1,
+                  "items": {
+                    "type": "integer"
+                  }
+                },
+                "example": "[[1212, 318, 257, 1332, 13]]"
+              }
+            ]
+          },
+          "best_of": {
+            "type": "integer",
+            "default": 1,
+            "minimum": 0,
+            "maximum": 20,
+            "nullable": true,
+            "description": "Generates `best_of` completions server-side and returns the \"best\" (the one with the highest log probability per token). Results cannot be streamed.\n\nWhen used with `n`, `best_of` controls the number of candidate completions and `n` specifies how many to return – `best_of` must be greater than `n`.\n\n**Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`.\n"
+          },
+          "echo": {
+            "type": "boolean",
+            "default": false,
+            "nullable": true,
+            "description": "Echo back the prompt in addition to the completion\n"
+          },
+          "frequency_penalty": {
+            "type": "number",
+            "default": 0,
+            "minimum": -2,
+            "maximum": 2,
+            "nullable": true,
+            "description": "Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.\n\n[See more information about frequency and presence penalties.](https://developers.openai.com/api/docs/guides/text)\n"
+          },
+          "logit_bias": {
+            "type": "object",
+            "x-oaiTypeLabel": "map",
+            "default": null,
+            "nullable": true,
+            "additionalProperties": {
+              "type": "integer"
+            },
+            "description": "Modify the likelihood of specified tokens appearing in the completion.\n\nAccepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this [tokenizer tool](https://platform.openai.com/tokenizer?view=bpe) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.\n\nAs an example, you can pass `{\"50256\": -100}` to prevent the <|endoftext|> token from being generated.\n"
+          },
+          "logprobs": {
+            "type": "integer",
+            "minimum": 0,
+            "maximum": 5,
+            "default": null,
+            "nullable": true,
+            "description": "Include the log probabilities on the `logprobs` most likely output tokens, as well the chosen tokens. For example, if `logprobs` is 5, the API will return a list of the 5 most likely tokens. The API will always return the `logprob` of the sampled token, so there may be up to `logprobs+1` elements in the response.\n\nThe maximum value for `logprobs` is 5.\n"
+          },
+          "max_tokens": {
+            "type": "integer",
+            "minimum": 0,
+            "default": 16,
+            "example": 16,
+            "nullable": true,
+            "description": "The maximum number of [tokens](https://platform.openai.com/tokenizer) that can be generated in the completion.\n\nThe token count of your prompt plus `max_tokens` cannot exceed the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens.\n"
+          },
+          "n": {
+            "type": "integer",
+            "minimum": 1,
+            "maximum": 128,
+            "default": 1,
+            "example": 1,
+            "nullable": true,
+            "description": "How many completions to generate for each prompt.\n\n**Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`.\n"
+          },
+          "presence_penalty": {
+            "type": "number",
+            "default": 0,
+            "minimum": -2,
+            "maximum": 2,
+            "nullable": true,
+            "description": "Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.\n\n[See more information about frequency and presence penalties.](https://developers.openai.com/api/docs/guides/text)\n"
+          },
+          "seed": {
+            "type": "integer",
+            "format": "int64",
+            "nullable": true,
+            "description": "If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result.\n\nDeterminism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend.\n"
+          },
+          "stop": {
+            "$ref": "#/components/schemas/StopConfiguration"
+          },
+          "stream": {
+            "description": "Whether to stream back partial progress. If set, tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).\n",
+            "type": "boolean",
+            "nullable": true,
+            "default": false
+          },
+          "stream_options": {
+            "$ref": "#/components/schemas/ChatCompletionStreamOptions"
+          },
+          "suffix": {
+            "description": "The suffix that comes after a completion of inserted text.\n\nThis parameter is only supported for `gpt-3.5-turbo-instruct`.\n",
+            "default": null,
+            "nullable": true,
+            "type": "string",
+            "example": "test."
+          },
+          "temperature": {
+            "type": "number",
+            "minimum": 0,
+            "maximum": 2,
+            "default": 1,
+            "example": 1,
+            "nullable": true,
+            "description": "What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.\n\nWe generally recommend altering this or `top_p` but not both.\n"
+          },
+          "top_p": {
+            "type": "number",
+            "minimum": 0,
+            "maximum": 1,
+            "default": 1,
+            "example": 1,
+            "nullable": true,
+            "description": "An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\n\nWe generally recommend altering this or `temperature` but not both.\n"
+          },
+          "user": {
+            "type": "string",
+            "example": "user-1234",
+            "description": "A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers).\n"
+          }
+        },
+        "required": [
+          "model",
+          "prompt"
+        ]
+      },
+      "CreateCompletionResponse": {
+        "type": "object",
+        "description": "Represents a completion response from the API. Note: both the streamed and non-streamed response objects share the same shape (unlike the chat endpoint).\n",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "A unique identifier for the completion."
+          },
+          "choices": {
+            "type": "array",
+            "description": "The list of completion choices the model generated for the input prompt.",
+            "items": {
+              "type": "object",
+              "required": [
+                "finish_reason",
+                "index",
+                "logprobs",
+                "text"
+              ],
+              "properties": {
+                "finish_reason": {
+                  "type": "string",
+                  "description": "The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence,\n`length` if the maximum number of tokens specified in the request was reached,\nor `content_filter` if content was omitted due to a flag from our content filters.\n",
+                  "enum": [
+                    "stop",
+                    "length",
+                    "content_filter"
+                  ]
+                },
+                "index": {
+                  "type": "integer"
+                },
+                "logprobs": {
+                  "anyOf": [
+                    {
+                      "type": "object",
+                      "properties": {
+                        "text_offset": {
+                          "type": "array",
+                          "items": {
+                            "type": "integer"
+                          }
+                        },
+                        "token_logprobs": {
+                          "type": "array",
+                          "items": {
+                            "type": "number"
+                          }
+                        },
+                        "tokens": {
+                          "type": "array",
+                          "items": {
+                            "type": "string"
+                          }
+                        },
+                        "top_logprobs": {
+                          "type": "array",
+                          "items": {
+                            "type": "object",
+                            "additionalProperties": {
+                              "type": "number"
+                            }
+                          }
+                        }
+                      }
+                    },
+                    {
+                      "type": "null"
+                    }
+                  ]
+                },
+                "text": {
+                  "type": "string"
+                }
+              }
+            }
+          },
+          "created": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the completion was created."
+          },
+          "model": {
+            "type": "string",
+            "description": "The model used for completion."
+          },
+          "system_fingerprint": {
+            "type": "string",
+            "description": "This fingerprint represents the backend configuration that the model runs with.\n\nCan be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism.\n"
+          },
+          "object": {
+            "type": "string",
+            "description": "The object type, which is always \"text_completion\"",
+            "enum": [
+              "text_completion"
+            ],
+            "x-stainless-const": true
+          },
+          "usage": {
+            "$ref": "#/components/schemas/CompletionUsage"
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "created",
+          "model",
+          "choices"
+        ],
+        "x-oaiMeta": {
+          "name": "The completion object",
+          "legacy": true,
+          "example": "{\n  \"id\": \"cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7\",\n  \"object\": \"text_completion\",\n  \"created\": 1589478378,\n  \"model\": \"gpt-3.5-turbo-instruct\",\n  \"choices\": [\n    {\n      \"text\": \"\\n\\nThis is indeed a test\",\n      \"index\": 0,\n      \"logprobs\": null,\n      \"finish_reason\": \"length\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 5,\n    \"completion_tokens\": 7,\n    \"total_tokens\": 12\n  }\n}\n"
+        }
+      },
+      "CreateContainerBody": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "Name of the container to create."
+          },
+          "file_ids": {
+            "type": "array",
+            "description": "IDs of files to copy to the container.",
+            "items": {
+              "type": "string"
+            }
+          },
+          "expires_after": {
+            "type": "object",
+            "description": "Container expiration time in seconds relative to the 'anchor' time.",
+            "properties": {
+              "anchor": {
+                "type": "string",
+                "enum": [
+                  "last_active_at"
+                ],
+                "description": "Time anchor for the expiration time. Currently only 'last_active_at' is supported."
+              },
+              "minutes": {
+                "type": "integer"
+              }
+            },
+            "required": [
+              "anchor",
+              "minutes"
+            ]
+          },
+          "skills": {
+            "type": "array",
+            "description": "An optional list of skills referenced by id or inline data.",
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/SkillReferenceParam"
+                },
+                {
+                  "$ref": "#/components/schemas/InlineSkillParam"
+                }
+              ],
+              "discriminator": {
+                "propertyName": "type"
+              }
+            }
+          },
+          "memory_limit": {
+            "type": "string",
+            "enum": [
+              "1g",
+              "4g",
+              "16g",
+              "64g"
+            ],
+            "description": "Optional memory limit for the container. Defaults to \"1g\"."
+          },
+          "network_policy": {
+            "description": "Network access policy for the container.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/ContainerNetworkPolicyDisabledParam"
+              },
+              {
+                "$ref": "#/components/schemas/ContainerNetworkPolicyAllowlistParam"
+              }
+            ],
+            "discriminator": {
+              "propertyName": "type"
+            }
+          }
+        },
+        "required": [
+          "name"
+        ]
+      },
+      "CreateContainerFileBody": {
+        "type": "object",
+        "properties": {
+          "file_id": {
+            "type": "string",
+            "description": "Name of the file to create."
+          },
+          "file": {
+            "description": "The File object (not file name) to be uploaded.\n",
+            "type": "string",
+            "format": "binary"
+          }
+        },
+        "required": []
+      },
+      "CreateEmbeddingRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "input": {
+            "description": "Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays. The input must not exceed the max input tokens for the model (8192 tokens for all embedding models), cannot be an empty string, and any array must be 2048 dimensions or less. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. In addition to the per-input token limit, all embedding models enforce a maximum of 300,000 tokens summed across all inputs in a single request.\n",
+            "example": "The quick brown fox jumped over the lazy dog",
+            "oneOf": [
+              {
+                "type": "string",
+                "title": "string",
+                "description": "The string that will be turned into an embedding.",
+                "default": "",
+                "example": "This is a test."
+              },
+              {
+                "type": "array",
+                "title": "array",
+                "description": "The array of strings that will be turned into an embedding.",
+                "minItems": 1,
+                "maxItems": 2048,
+                "items": {
+                  "type": "string",
+                  "default": "",
+                  "example": "['This is a test.']"
+                }
+              },
+              {
+                "type": "array",
+                "title": "array",
+                "description": "The array of integers that will be turned into an embedding.",
+                "minItems": 1,
+                "maxItems": 2048,
+                "items": {
+                  "type": "integer"
+                },
+                "example": "[1212, 318, 257, 1332, 13]"
+              },
+              {
+                "type": "array",
+                "title": "array",
+                "description": "The array of arrays containing integers that will be turned into an embedding.",
+                "minItems": 1,
+                "maxItems": 2048,
+                "items": {
+                  "type": "array",
+                  "minItems": 1,
+                  "items": {
+                    "type": "integer"
+                  }
+                },
+                "example": "[[1212, 318, 257, 1332, 13]]"
+              }
+            ]
+          },
+          "model": {
+            "description": "ID of the model to use. You can use the [List models](https://developers.openai.com/api/reference/resources/models/methods/list) API to see all of your available models, or see our [Model overview](https://developers.openai.com/api/docs/models) for descriptions of them.\n",
+            "example": "text-embedding-3-small",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "text-embedding-ada-002",
+                  "text-embedding-3-small",
+                  "text-embedding-3-large"
+                ]
+              }
+            ],
+            "x-oaiTypeLabel": "string"
+          },
+          "encoding_format": {
+            "description": "The format to return the embeddings in. Can be either `float` or [`base64`](https://pypi.org/project/pybase64/).",
+            "example": "float",
+            "default": "float",
+            "type": "string",
+            "enum": [
+              "float",
+              "base64"
+            ]
+          },
+          "dimensions": {
+            "description": "The number of dimensions the resulting output embeddings should have. Only supported in `text-embedding-3` and later models.\n",
+            "type": "integer",
+            "minimum": 1
+          },
+          "user": {
+            "type": "string",
+            "example": "user-1234",
+            "description": "A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers).\n"
+          }
+        },
+        "required": [
+          "model",
+          "input"
+        ]
+      },
+      "CreateEmbeddingResponse": {
+        "type": "object",
+        "properties": {
+          "data": {
+            "type": "array",
+            "description": "The list of embeddings generated by the model.",
+            "items": {
+              "$ref": "#/components/schemas/Embedding"
+            }
+          },
+          "model": {
+            "type": "string",
+            "description": "The name of the model used to generate the embedding."
+          },
+          "object": {
+            "type": "string",
+            "description": "The object type, which is always \"list\".",
+            "enum": [
+              "list"
+            ],
+            "x-stainless-const": true
+          },
+          "usage": {
+            "type": "object",
+            "description": "The usage information for the request.",
+            "properties": {
+              "prompt_tokens": {
+                "type": "integer",
+                "description": "The number of tokens used by the prompt."
+              },
+              "total_tokens": {
+                "type": "integer",
+                "description": "The total number of tokens used by the request."
+              }
+            },
+            "required": [
+              "prompt_tokens",
+              "total_tokens"
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "model",
+          "data",
+          "usage"
+        ]
+      },
+      "CreateEvalCompletionsRunDataSource": {
+        "type": "object",
+        "title": "CompletionsRunDataSource",
+        "description": "A CompletionsRunDataSource object describing a model sampling configuration.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "completions"
+            ],
+            "default": "completions",
+            "description": "The type of run data source. Always `completions`."
+          },
+          "input_messages": {
+            "description": "Used when sampling from a model. Dictates the structure of the messages passed into the model. Can either be a reference to a prebuilt trajectory (ie, `item.input_trajectory`), or a template with variable references to the `item` namespace.",
+            "oneOf": [
+              {
+                "type": "object",
+                "title": "TemplateInputMessages",
+                "properties": {
+                  "type": {
+                    "type": "string",
+                    "enum": [
+                      "template"
+                    ],
+                    "description": "The type of input messages. Always `template`."
+                  },
+                  "template": {
+                    "type": "array",
+                    "description": "A list of chat messages forming the prompt or context. May include variable references to the `item` namespace, ie {{item.name}}.",
+                    "items": {
+                      "oneOf": [
+                        {
+                          "$ref": "#/components/schemas/EasyInputMessage"
+                        },
+                        {
+                          "$ref": "#/components/schemas/EvalItem"
+                        }
+                      ]
+                    }
+                  }
+                },
+                "required": [
+                  "type",
+                  "template"
+                ]
+              },
+              {
+                "type": "object",
+                "title": "ItemReferenceInputMessages",
+                "properties": {
+                  "type": {
+                    "type": "string",
+                    "enum": [
+                      "item_reference"
+                    ],
+                    "description": "The type of input messages. Always `item_reference`."
+                  },
+                  "item_reference": {
+                    "type": "string",
+                    "description": "A reference to a variable in the `item` namespace. Ie, \"item.input_trajectory\""
+                  }
+                },
+                "required": [
+                  "type",
+                  "item_reference"
+                ]
+              }
+            ]
+          },
+          "sampling_params": {
+            "type": "object",
+            "properties": {
+              "reasoning_effort": {
+                "$ref": "#/components/schemas/ReasoningEffort"
+              },
+              "temperature": {
+                "type": "number",
+                "description": "A higher temperature increases randomness in the outputs.",
+                "default": 1
+              },
+              "max_completion_tokens": {
+                "type": "integer",
+                "description": "The maximum number of tokens in the generated output."
+              },
+              "top_p": {
+                "type": "number",
+                "description": "An alternative to temperature for nucleus sampling; 1.0 includes all tokens.",
+                "default": 1
+              },
+              "seed": {
+                "type": "integer",
+                "description": "A seed value to initialize the randomness, during sampling.",
+                "default": 42
+              },
+              "response_format": {
+                "description": "An object specifying the format that the model must output.\n\nSetting to `{ \"type\": \"json_schema\", \"json_schema\": {...} }` enables\nStructured Outputs which ensures the model will match your supplied JSON\nschema. Learn more in the [Structured Outputs\nguide](https://developers.openai.com/api/docs/guides/structured-outputs).\n\nSetting to `{ \"type\": \"json_object\" }` enables the older JSON mode, which\nensures the message the model generates is valid JSON. Using `json_schema`\nis preferred for models that support it.\n",
+                "oneOf": [
+                  {
+                    "$ref": "#/components/schemas/ResponseFormatText"
+                  },
+                  {
+                    "$ref": "#/components/schemas/ResponseFormatJsonSchema"
+                  },
+                  {
+                    "$ref": "#/components/schemas/ResponseFormatJsonObject"
+                  }
+                ]
+              },
+              "tools": {
+                "type": "array",
+                "description": "A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.\n",
+                "items": {
+                  "$ref": "#/components/schemas/ChatCompletionTool"
+                }
+              }
+            }
+          },
+          "model": {
+            "type": "string",
+            "description": "The name of the model to use for generating completions (e.g. \"o3-mini\")."
+          },
+          "source": {
+            "description": "Determines what populates the `item` namespace in this run's data source.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/EvalJsonlFileContentSource"
+              },
+              {
+                "$ref": "#/components/schemas/EvalJsonlFileIdSource"
+              },
+              {
+                "$ref": "#/components/schemas/EvalStoredCompletionsSource"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "source"
+        ],
+        "x-oaiMeta": {
+          "name": "The completions data source object used to configure an individual run",
+          "group": "eval runs",
+          "example": "{\n  \"name\": \"gpt-6-astra\",\n  \"data_source\": {\n    \"type\": \"completions\",\n    \"input_messages\": {\n      \"type\": \"item_reference\",\n      \"item_reference\": \"item.input\"\n    },\n    \"model\": \"gpt-6-astra\",\n    \"source\": {\n      \"type\": \"stored_completions\",\n      \"model\": \"gpt-6-astra\"\n    }\n  }\n}\n"
+        }
+      },
+      "CreateEvalCustomDataSourceConfig": {
+        "type": "object",
+        "title": "CustomDataSourceConfig",
+        "description": "A CustomDataSourceConfig object that defines the schema for the data source used for the evaluation runs.\nThis schema is used to define the shape of the data that will be:\n- Used to define your testing criteria and\n- What data is required when creating a run\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "custom"
+            ],
+            "default": "custom",
+            "description": "The type of data source. Always `custom`.",
+            "x-stainless-const": true
+          },
+          "item_schema": {
+            "type": "object",
+            "description": "The json schema for each row in the data source.",
+            "additionalProperties": true,
+            "example": "{\n  \"type\": \"object\",\n  \"properties\": {\n    \"name\": {\"type\": \"string\"},\n    \"age\": {\"type\": \"integer\"}\n  },\n  \"required\": [\"name\", \"age\"]\n}\n"
+          },
+          "include_sample_schema": {
+            "type": "boolean",
+            "default": false,
+            "description": "Whether the eval should expect you to populate the sample namespace (ie, by generating responses off of your data source)"
+          }
+        },
+        "required": [
+          "item_schema",
+          "type"
+        ],
+        "x-oaiMeta": {
+          "name": "The eval file data source config object",
+          "group": "evals",
+          "example": "{\n  \"type\": \"custom\",\n  \"item_schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"name\": {\"type\": \"string\"},\n      \"age\": {\"type\": \"integer\"}\n    },\n    \"required\": [\"name\", \"age\"]\n  },\n  \"include_sample_schema\": true\n}\n"
+        }
+      },
+      "CreateEvalItem": {
+        "title": "CreateEvalItem",
+        "description": "A chat message that makes up the prompt or context. May include variable references to the `item` namespace, ie {{item.name}}.",
+        "type": "object",
+        "oneOf": [
+          {
+            "type": "object",
+            "title": "SimpleInputMessage",
+            "properties": {
+              "role": {
+                "type": "string",
+                "description": "The role of the message (e.g. \"system\", \"assistant\", \"user\")."
+              },
+              "content": {
+                "type": "string",
+                "description": "The content of the message."
+              }
+            },
+            "required": [
+              "role",
+              "content"
+            ]
+          },
+          {
+            "$ref": "#/components/schemas/EvalItem"
+          }
+        ],
+        "x-oaiMeta": {
+          "name": "The chat message object used to configure an individual run"
+        }
+      },
+      "CreateEvalJsonlRunDataSource": {
+        "type": "object",
+        "title": "JsonlRunDataSource",
+        "description": "A JsonlRunDataSource object with that specifies a JSONL file that matches the eval \n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "jsonl"
+            ],
+            "default": "jsonl",
+            "description": "The type of data source. Always `jsonl`.",
+            "x-stainless-const": true
+          },
+          "source": {
+            "description": "Determines what populates the `item` namespace in the data source.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/EvalJsonlFileContentSource"
+              },
+              {
+                "$ref": "#/components/schemas/EvalJsonlFileIdSource"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "source"
+        ],
+        "x-oaiMeta": {
+          "name": "The file data source object for the eval run configuration",
+          "group": "evals",
+          "example": "{\n \"type\": \"jsonl\",\n \"source\": {\n   \"type\": \"file_id\",\n   \"id\": \"file-9GYS6xbkWgWhmE7VoLUWFg\"\n }\n}\n"
+        }
+      },
+      "CreateEvalLabelModelGrader": {
+        "type": "object",
+        "title": "LabelModelGrader",
+        "description": "A LabelModelGrader object which uses a model to assign labels to each item\nin the evaluation.\n",
+        "properties": {
+          "type": {
+            "description": "The object type, which is always `label_model`.",
+            "type": "string",
+            "enum": [
+              "label_model"
+            ],
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the grader."
+          },
+          "model": {
+            "type": "string",
+            "description": "The model to use for the evaluation. Must support structured outputs."
+          },
+          "input": {
+            "type": "array",
+            "description": "A list of chat messages forming the prompt or context. May include variable references to the `item` namespace, ie {{item.name}}.",
+            "items": {
+              "$ref": "#/components/schemas/CreateEvalItem"
+            }
+          },
+          "labels": {
+            "type": "array",
+            "items": {
+              "type": "string"
+            },
+            "description": "The labels to classify to each item in the evaluation."
+          },
+          "passing_labels": {
+            "type": "array",
+            "items": {
+              "type": "string"
+            },
+            "description": "The labels that indicate a passing result. Must be a subset of labels."
+          }
+        },
+        "required": [
+          "type",
+          "model",
+          "input",
+          "passing_labels",
+          "labels",
+          "name"
+        ],
+        "x-oaiMeta": {
+          "name": "The eval label model grader object",
+          "group": "evals",
+          "example": "{\n  \"type\": \"label_model\",\n  \"model\": \"gpt-4o-2024-08-06\",\n  \"input\": [\n    {\n      \"role\": \"system\",\n      \"content\": \"Classify the sentiment of the following statement as one of 'positive', 'neutral', or 'negative'\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": \"Statement: {{item.response}}\"\n    }\n  ],\n  \"passing_labels\": [\"positive\"],\n  \"labels\": [\"positive\", \"neutral\", \"negative\"],\n  \"name\": \"Sentiment label grader\"\n}\n"
+        }
+      },
+      "CreateEvalLogsDataSourceConfig": {
+        "type": "object",
+        "title": "LogsDataSourceConfig",
+        "description": "A data source config which specifies the metadata property of your logs query.\nThis is usually metadata like `usecase=chatbot` or `prompt-version=v2`, etc.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "logs"
+            ],
+            "default": "logs",
+            "description": "The type of data source. Always `logs`.",
+            "x-stainless-const": true
+          },
+          "metadata": {
+            "type": "object",
+            "description": "Metadata filters for the logs data source.",
+            "additionalProperties": true,
+            "example": "{\n  \"use_case\": \"customer_support_agent\"\n}\n"
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "x-oaiMeta": {
+          "name": "The logs data source object for evals",
+          "group": "evals",
+          "example": "{\n  \"type\": \"logs\",\n  \"metadata\": {\n    \"use_case\": \"customer_support_agent\"\n  }\n}\n"
+        }
+      },
+      "CreateEvalRequest": {
+        "type": "object",
+        "title": "CreateEvalRequest",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The name of the evaluation."
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          },
+          "data_source_config": {
+            "type": "object",
+            "description": "The configuration for the data source used for the evaluation runs. Dictates the schema of the data used in the evaluation.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/CreateEvalCustomDataSourceConfig"
+              },
+              {
+                "$ref": "#/components/schemas/CreateEvalLogsDataSourceConfig"
+              },
+              {
+                "$ref": "#/components/schemas/CreateEvalStoredCompletionsDataSourceConfig"
+              }
+            ]
+          },
+          "testing_criteria": {
+            "type": "array",
+            "description": "A list of graders for all eval runs in this group. Graders can reference variables in the data source using double curly braces notation, like `{{item.variable_name}}`. To reference the model's output, use the `sample` namespace (ie, `{{sample.output_text}}`).",
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/CreateEvalLabelModelGrader"
+                },
+                {
+                  "$ref": "#/components/schemas/EvalGraderStringCheck"
+                },
+                {
+                  "$ref": "#/components/schemas/EvalGraderTextSimilarity"
+                },
+                {
+                  "$ref": "#/components/schemas/EvalGraderPython"
+                },
+                {
+                  "$ref": "#/components/schemas/EvalGraderScoreModel"
+                }
+              ]
+            }
+          }
+        },
+        "required": [
+          "data_source_config",
+          "testing_criteria"
+        ]
+      },
+      "CreateEvalResponsesRunDataSource": {
+        "type": "object",
+        "title": "ResponsesRunDataSource",
+        "description": "A ResponsesRunDataSource object describing a model sampling configuration.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "responses"
+            ],
+            "default": "responses",
+            "description": "The type of run data source. Always `responses`."
+          },
+          "input_messages": {
+            "description": "Used when sampling from a model. Dictates the structure of the messages passed into the model. Can either be a reference to a prebuilt trajectory (ie, `item.input_trajectory`), or a template with variable references to the `item` namespace.",
+            "oneOf": [
+              {
+                "type": "object",
+                "title": "InputMessagesTemplate",
+                "properties": {
+                  "type": {
+                    "type": "string",
+                    "enum": [
+                      "template"
+                    ],
+                    "description": "The type of input messages. Always `template`."
+                  },
+                  "template": {
+                    "type": "array",
+                    "description": "A list of chat messages forming the prompt or context. May include variable references to the `item` namespace, ie {{item.name}}.",
+                    "items": {
+                      "oneOf": [
+                        {
+                          "type": "object",
+                          "title": "ChatMessage",
+                          "properties": {
+                            "role": {
+                              "type": "string",
+                              "description": "The role of the message (e.g. \"system\", \"assistant\", \"user\")."
+                            },
+                            "content": {
+                              "type": "string",
+                              "description": "The content of the message."
+                            }
+                          },
+                          "required": [
+                            "role",
+                            "content"
+                          ]
+                        },
+                        {
+                          "$ref": "#/components/schemas/EvalItem"
+                        }
+                      ]
+                    }
+                  }
+                },
+                "required": [
+                  "type",
+                  "template"
+                ]
+              },
+              {
+                "type": "object",
+                "title": "InputMessagesItemReference",
+                "properties": {
+                  "type": {
+                    "type": "string",
+                    "enum": [
+                      "item_reference"
+                    ],
+                    "description": "The type of input messages. Always `item_reference`."
+                  },
+                  "item_reference": {
+                    "type": "string",
+                    "description": "A reference to a variable in the `item` namespace. Ie, \"item.name\""
+                  }
+                },
+                "required": [
+                  "type",
+                  "item_reference"
+                ]
+              }
+            ]
+          },
+          "sampling_params": {
+            "type": "object",
+            "properties": {
+              "reasoning_effort": {
+                "$ref": "#/components/schemas/ReasoningEffort"
+              },
+              "temperature": {
+                "type": "number",
+                "description": "A higher temperature increases randomness in the outputs.",
+                "default": 1
+              },
+              "max_completion_tokens": {
+                "type": "integer",
+                "description": "The maximum number of tokens in the generated output."
+              },
+              "top_p": {
+                "type": "number",
+                "description": "An alternative to temperature for nucleus sampling; 1.0 includes all tokens.",
+                "default": 1
+              },
+              "seed": {
+                "type": "integer",
+                "description": "A seed value to initialize the randomness, during sampling.",
+                "default": 42
+              },
+              "tools": {
+                "type": "array",
+                "description": "An array of tools the model may call while generating a response. You\ncan specify which tool to use by setting the `tool_choice` parameter.\n\nThe two categories of tools you can provide the model are:\n\n- **Built-in tools**: Tools that are provided by OpenAI that extend the\n  model's capabilities, like [web search](https://developers.openai.com/api/docs/guides/tools-web-search)\n  or [file search](https://developers.openai.com/api/docs/guides/tools-file-search). Learn more about\n  [built-in tools](https://developers.openai.com/api/docs/guides/tools).\n- **Function calls (custom tools)**: Functions that are defined by you,\n  enabling the model to call your own code. Learn more about\n  [function calling](https://developers.openai.com/api/docs/guides/function-calling).\n",
+                "items": {
+                  "$ref": "#/components/schemas/Tool"
+                }
+              },
+              "text": {
+                "type": "object",
+                "description": "Configuration options for a text response from the model. Can be plain\ntext or structured JSON data. Learn more:\n- [Text inputs and outputs](https://developers.openai.com/api/docs/guides/text)\n- [Structured Outputs](https://developers.openai.com/api/docs/guides/structured-outputs)\n",
+                "properties": {
+                  "format": {
+                    "$ref": "#/components/schemas/TextResponseFormatConfiguration"
+                  }
+                }
+              }
+            }
+          },
+          "model": {
+            "type": "string",
+            "description": "The name of the model to use for generating completions (e.g. \"o3-mini\")."
+          },
+          "source": {
+            "description": "Determines what populates the `item` namespace in this run's data source.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/EvalJsonlFileContentSource"
+              },
+              {
+                "$ref": "#/components/schemas/EvalJsonlFileIdSource"
+              },
+              {
+                "$ref": "#/components/schemas/EvalResponsesSource"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "source"
+        ],
+        "x-oaiMeta": {
+          "name": "The completions data source object used to configure an individual run",
+          "group": "eval runs",
+          "example": "{\n  \"name\": \"gpt-6-astra\",\n  \"data_source\": {\n    \"type\": \"responses\",\n    \"input_messages\": {\n      \"type\": \"item_reference\",\n      \"item_reference\": \"item.input\"\n    },\n    \"model\": \"gpt-6-astra\",\n    \"source\": {\n      \"type\": \"responses\",\n      \"model\": \"gpt-6-astra\"\n    }\n  }\n}\n"
+        }
+      },
+      "CreateEvalRunRequest": {
+        "type": "object",
+        "title": "CreateEvalRunRequest",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The name of the run."
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          },
+          "data_source": {
+            "type": "object",
+            "description": "Details about the run's data source.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/CreateEvalJsonlRunDataSource"
+              },
+              {
+                "$ref": "#/components/schemas/CreateEvalCompletionsRunDataSource"
+              },
+              {
+                "$ref": "#/components/schemas/CreateEvalResponsesRunDataSource"
+              }
+            ]
+          }
+        },
+        "required": [
+          "data_source"
+        ]
+      },
+      "CreateEvalStoredCompletionsDataSourceConfig": {
+        "type": "object",
+        "title": "StoredCompletionsDataSourceConfig",
+        "description": "Deprecated in favor of LogsDataSourceConfig.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "stored_completions"
+            ],
+            "default": "stored_completions",
+            "description": "The type of data source. Always `stored_completions`.",
+            "x-stainless-const": true
+          },
+          "metadata": {
+            "type": "object",
+            "description": "Metadata filters for the stored completions data source.",
+            "additionalProperties": true,
+            "example": "{\n  \"use_case\": \"customer_support_agent\"\n}\n"
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "deprecated": true,
+        "x-oaiMeta": {
+          "name": "The stored completions data source object for evals",
+          "group": "evals",
+          "example": "{\n  \"type\": \"stored_completions\",\n  \"metadata\": {\n    \"use_case\": \"customer_support_agent\"\n  }\n}\n"
+        }
+      },
+      "CreateFileRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "file": {
+            "description": "The File object (not file name) to be uploaded.\n",
+            "type": "string",
+            "format": "binary"
+          },
+          "purpose": {
+            "description": "The intended purpose of the uploaded file. One of:\n- `assistants`: Used in the Assistants API\n- `batch`: Used in the Batch API\n- `fine-tune`: Used for fine-tuning\n- `vision`: Images used for vision fine-tuning\n- `user_data`: Flexible file type for any purpose\n- `evals`: Used for eval data sets\n",
+            "type": "string",
+            "enum": [
+              "assistants",
+              "batch",
+              "fine-tune",
+              "vision",
+              "user_data",
+              "evals"
+            ]
+          },
+          "expires_after": {
+            "$ref": "#/components/schemas/FileExpirationAfter"
+          }
+        },
+        "required": [
+          "file",
+          "purpose"
+        ]
+      },
+      "CreateFineTuningCheckpointPermissionRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "project_ids": {
+            "type": "array",
+            "description": "The project identifiers to grant access to.",
+            "items": {
+              "type": "string"
+            }
+          }
+        },
+        "required": [
+          "project_ids"
+        ]
+      },
+      "CreateFineTuningJobRequest": {
+        "type": "object",
+        "properties": {
+          "model": {
+            "description": "The name of the model to fine-tune. You can select one of the\n[supported models](https://developers.openai.com/api/docs/guides/model-optimization#fine-tuning-methods).\n",
+            "example": "gpt-4o-mini",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "babbage-002",
+                  "davinci-002",
+                  "gpt-3.5-turbo",
+                  "gpt-4o-mini"
+                ]
+              }
+            ],
+            "x-oaiTypeLabel": "string"
+          },
+          "training_file": {
+            "description": "The ID of an uploaded file that contains training data.\n\nSee [upload file](https://developers.openai.com/api/reference/resources/files/methods/create) for how to upload a file.\n\nYour dataset must be formatted as a JSONL file. Additionally, you must upload your file with the purpose `fine-tune`.\n\nThe contents of the file should differ depending on if the model uses the [chat](https://developers.openai.com/api/docs/guides/supervised-fine-tuning#formatting-your-data), [completions](https://developers.openai.com/api/docs/guides/supervised-fine-tuning#formatting-your-data) format, or if the fine-tuning method uses the [preference](https://developers.openai.com/api/docs/guides/direct-preference-optimization) format.\n\nSee the [fine-tuning guide](https://developers.openai.com/api/docs/guides/model-optimization) for more details.\n",
+            "type": "string",
+            "example": "file-abc123"
+          },
+          "hyperparameters": {
+            "type": "object",
+            "description": "The hyperparameters used for the fine-tuning job.\nThis value is now deprecated in favor of `method`, and should be passed in under the `method` parameter.\n",
+            "properties": {
+              "batch_size": {
+                "description": "Number of examples in each batch. A larger batch size means that model parameters\nare updated less frequently, but with lower variance.\n",
+                "oneOf": [
+                  {
+                    "type": "string",
+                    "enum": [
+                      "auto"
+                    ],
+                    "x-stainless-const": true
+                  },
+                  {
+                    "type": "integer",
+                    "minimum": 1,
+                    "maximum": 256
+                  }
+                ],
+                "default": "auto"
+              },
+              "learning_rate_multiplier": {
+                "description": "Scaling factor for the learning rate. A smaller learning rate may be useful to avoid\noverfitting.\n",
+                "oneOf": [
+                  {
+                    "type": "string",
+                    "enum": [
+                      "auto"
+                    ],
+                    "x-stainless-const": true
+                  },
+                  {
+                    "type": "number",
+                    "minimum": 0,
+                    "exclusiveMinimum": true
+                  }
+                ],
+                "default": "auto"
+              },
+              "n_epochs": {
+                "description": "The number of epochs to train the model for. An epoch refers to one full cycle\nthrough the training dataset.\n",
+                "oneOf": [
+                  {
+                    "type": "string",
+                    "enum": [
+                      "auto"
+                    ],
+                    "x-stainless-const": true
+                  },
+                  {
+                    "type": "integer",
+                    "minimum": 1,
+                    "maximum": 50
+                  }
+                ],
+                "default": "auto"
+              }
+            },
+            "deprecated": true
+          },
+          "suffix": {
+            "description": "A string of up to 64 characters that will be added to your fine-tuned model name.\n\nFor example, a `suffix` of \"custom-model-name\" would produce a model name like `ft:gpt-4o-mini:openai:custom-model-name:7p4lURel`.\n",
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 64,
+            "default": null,
+            "nullable": true
+          },
+          "validation_file": {
+            "description": "The ID of an uploaded file that contains validation data.\n\nIf you provide this file, the data is used to generate validation\nmetrics periodically during fine-tuning. These metrics can be viewed in\nthe fine-tuning results file.\nThe same data should not be present in both train and validation files.\n\nYour dataset must be formatted as a JSONL file. You must upload your file with the purpose `fine-tune`.\n\nSee the [fine-tuning guide](https://developers.openai.com/api/docs/guides/model-optimization) for more details.\n",
+            "type": "string",
+            "nullable": true,
+            "example": "file-abc123"
+          },
+          "integrations": {
+            "type": "array",
+            "description": "A list of integrations to enable for your fine-tuning job.",
+            "nullable": true,
+            "items": {
+              "type": "object",
+              "required": [
+                "type",
+                "wandb"
+              ],
+              "properties": {
+                "type": {
+                  "description": "The type of integration to enable. Currently, only \"wandb\" (Weights and Biases) is supported.\n",
+                  "oneOf": [
+                    {
+                      "type": "string",
+                      "enum": [
+                        "wandb"
+                      ],
+                      "x-stainless-const": true
+                    }
+                  ]
+                },
+                "wandb": {
+                  "type": "object",
+                  "description": "The settings for your integration with Weights and Biases. This payload specifies the project that\nmetrics will be sent to. Optionally, you can set an explicit display name for your run, add tags\nto your run, and set a default entity (team, username, etc) to be associated with your run.\n",
+                  "required": [
+                    "project"
+                  ],
+                  "properties": {
+                    "project": {
+                      "description": "The name of the project that the new run will be created under.\n",
+                      "type": "string",
+                      "example": "my-wandb-project"
+                    },
+                    "name": {
+                      "description": "A display name to set for the run. If not set, we will use the Job ID as the name.\n",
+                      "nullable": true,
+                      "type": "string"
+                    },
+                    "entity": {
+                      "description": "The entity to use for the run. This allows you to set the team or username of the WandB user that you would\nlike associated with the run. If not set, the default entity for the registered WandB API key is used.\n",
+                      "nullable": true,
+                      "type": "string"
+                    },
+                    "tags": {
+                      "description": "A list of tags to be attached to the newly created run. These tags are passed through directly to WandB. Some\ndefault tags are generated by OpenAI: \"openai/finetune\", \"openai/{base-model}\", \"openai/{ftjob-abcdef}\".\n",
+                      "type": "array",
+                      "items": {
+                        "type": "string",
+                        "example": "custom-tag"
+                      }
+                    }
+                  }
+                }
+              }
+            }
+          },
+          "seed": {
+            "description": "The seed controls the reproducibility of the job. Passing in the same seed and job parameters should produce the same results, but may differ in rare cases.\nIf a seed is not specified, one will be generated for you.\n",
+            "type": "integer",
+            "nullable": true,
+            "minimum": 0,
+            "maximum": 2147483647,
+            "example": 42
+          },
+          "method": {
+            "$ref": "#/components/schemas/FineTuneMethod"
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          }
+        },
+        "required": [
+          "model",
+          "training_file"
+        ]
+      },
+      "CreateGroupBody": {
+        "type": "object",
+        "description": "Request payload for creating a new group in the organization.",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "Human readable name for the group.",
+            "minLength": 1,
+            "maxLength": 255
+          }
+        },
+        "required": [
+          "name"
+        ],
+        "x-oaiMeta": {
+          "example": "{\n    \"name\": \"Support Team\"\n}\n"
+        }
+      },
+      "CreateGroupUserBody": {
+        "type": "object",
+        "description": "Request payload for adding a user to a group.",
+        "properties": {
+          "user_id": {
+            "type": "string",
+            "description": "Identifier of the user to add to the group."
+          }
+        },
+        "required": [
+          "user_id"
+        ],
+        "x-oaiMeta": {
+          "example": "{\n    \"user_id\": \"user_abc123\"\n}\n"
+        }
+      },
+      "CreateImageEditRequest": {
+        "type": "object",
+        "properties": {
+          "image": {
+            "anyOf": [
+              {
+                "type": "string",
+                "format": "binary"
+              },
+              {
+                "type": "array",
+                "maxItems": 16,
+                "items": {
+                  "type": "string",
+                  "format": "binary"
+                }
+              }
+            ],
+            "description": "The image(s) to edit. Must be a supported image file or an array of images.\n\nFor the GPT image models (`gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5`,\n`gpt-image-2`, `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`,\n`gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, and\n`gpt-image-2.5-flare-2026-09-08`), each image should be a `png`, `webp`, or `jpg`\nfile less than 50MB. You can provide up to 16 images. `chatgpt-image-latest`\nfollows the same input constraints as GPT image models.\n\nFor `dall-e-2`, you can only provide one image, and it should be a square `png`\nfile less than 4MB.\n"
+          },
+          "prompt": {
+            "description": "A text description of the desired image(s). The maximum length is 1000 characters for `dall-e-2`, and 32000 characters for the GPT image models.",
+            "type": "string",
+            "example": "A cute baby sea otter wearing a beret"
+          },
+          "mask": {
+            "description": "An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where `image` should be edited. If there are multiple images provided, the mask will be applied on the first image. Must be a valid PNG file, less than 4MB, and have the same dimensions as `image`.",
+            "type": "string",
+            "format": "binary"
+          },
+          "background": {
+            "type": "string",
+            "enum": [
+              "transparent",
+              "opaque",
+              "auto"
+            ],
+            "default": "auto",
+            "example": "transparent",
+            "nullable": true,
+            "description": "Set the background of the generated image(s). This parameter is only supported for\nthe GPT image models. Must be one of `transparent`, `opaque`, or `auto` (default\nvalue). When `auto` is used, the model will automatically determine the best\nbackground for the image.\n\n`gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`, including their `2026-09-08`\nsnapshots, support `opaque` and `transparent` backgrounds. Transparent backgrounds\nare available for supported GPT Image models. For `gpt-image-2` and\n`gpt-image-2-2026-04-21`, this support is in preview. When using `transparent`,\nset the output format to `png` or `webp`.\n"
+          },
+          "model": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "gpt-image-1.5",
+                  "gpt-image-2",
+                  "gpt-image-2-2026-04-21",
+                  "gpt-image-2.5-sunburst",
+                  "gpt-image-2.5-sunburst-2026-09-08",
+                  "gpt-image-2.5-flare",
+                  "gpt-image-2.5-flare-2026-09-08",
+                  "dall-e-2",
+                  "gpt-image-1",
+                  "gpt-image-1-mini",
+                  "chatgpt-image-latest"
+                ],
+                "x-stainless-const": true
+              }
+            ],
+            "x-oaiTypeLabel": "string",
+            "default": "gpt-image-1.5",
+            "example": "gpt-image-1.5",
+            "nullable": true,
+            "description": "The model to use for image generation. One of `dall-e-2` or a GPT image model (`gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5`, `gpt-image-2`, `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, `gpt-image-2.5-flare-2026-09-08`, or `chatgpt-image-latest`). Defaults to `gpt-image-1.5`."
+          },
+          "n": {
+            "type": "integer",
+            "minimum": 1,
+            "maximum": 10,
+            "default": 1,
+            "example": 1,
+            "nullable": true,
+            "description": "The number of images to generate. Must be between 1 and 10."
+          },
+          "size": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "256x256",
+                  "512x512",
+                  "1024x1024",
+                  "1536x1024",
+                  "1024x1536",
+                  "auto"
+                ]
+              }
+            ],
+            "default": "1024x1024",
+            "example": "1024x1024",
+            "nullable": true,
+            "description": "The size of the generated images. For `gpt-image-2`, `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, and `gpt-image-2.5-flare-2026-09-08`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`."
+          },
+          "response_format": {
+            "type": "string",
+            "enum": [
+              "url",
+              "b64_json"
+            ],
+            "example": "url",
+            "nullable": true,
+            "description": "The format in which the generated images are returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes after the image has been generated. This parameter is only supported for `dall-e-2` (default is `url` for `dall-e-2`), as GPT image models always return base64-encoded images."
+          },
+          "output_format": {
+            "type": "string",
+            "enum": [
+              "png",
+              "jpeg",
+              "webp"
+            ],
+            "default": "png",
+            "example": "png",
+            "nullable": true,
+            "description": "The format in which the generated images are returned. This parameter is\nonly supported for the GPT image models. Must be one of `png`, `jpeg`, or `webp`.\nThe default value is `png`.\n"
+          },
+          "output_compression": {
+            "type": "integer",
+            "default": 100,
+            "example": 100,
+            "nullable": true,
+            "description": "The compression level (0-100%) for the generated images. This parameter\nis only supported for the GPT image models with the `webp` or `jpeg` output\nformats, and defaults to 100.\n"
+          },
+          "user": {
+            "type": "string",
+            "example": "user-1234",
+            "description": "A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers).\n"
+          },
+          "input_fidelity": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/InputFidelity"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "stream": {
+            "type": "boolean",
+            "default": false,
+            "example": false,
+            "nullable": true,
+            "description": "Edit the image in streaming mode. Defaults to `false`. See the\n[Image generation guide](https://developers.openai.com/api/docs/guides/image-generation) for more information.\n"
+          },
+          "partial_images": {
+            "$ref": "#/components/schemas/PartialImages"
+          },
+          "quality": {
+            "type": "string",
+            "enum": [
+              "standard",
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max",
+              "auto"
+            ],
+            "default": "auto",
+            "example": "high",
+            "nullable": true,
+            "description": "The quality of the image that will be generated for GPT image models. The GPT image models support `low`, `medium`, and `high`. `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`, including their `2026-09-08` snapshots, also support `xhigh` and `max`. Defaults to `auto`.\n"
+          }
+        },
+        "required": [
+          "prompt",
+          "image"
+        ]
+      },
+      "CreateImageRequest": {
+        "type": "object",
+        "properties": {
+          "prompt": {
+            "description": "A text description of the desired image(s). The maximum length is 32000 characters for the GPT image models, 1000 characters for `dall-e-2` and 4000 characters for `dall-e-3`.",
+            "type": "string",
+            "example": "A cute baby sea otter"
+          },
+          "model": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "gpt-image-1.5",
+                  "gpt-image-2",
+                  "gpt-image-2-2026-04-21",
+                  "gpt-image-2.5-sunburst",
+                  "gpt-image-2.5-sunburst-2026-09-08",
+                  "gpt-image-2.5-flare",
+                  "gpt-image-2.5-flare-2026-09-08",
+                  "dall-e-2",
+                  "dall-e-3",
+                  "gpt-image-1",
+                  "gpt-image-1-mini"
+                ]
+              }
+            ],
+            "x-oaiTypeLabel": "string",
+            "default": "dall-e-2",
+            "example": "gpt-image-1.5",
+            "nullable": true,
+            "description": "The model to use for image generation. One of `dall-e-2`, `dall-e-3`, or a GPT image model (`gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5`, `gpt-image-2`, `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, `gpt-image-2.5-flare-2026-09-08`). Defaults to `dall-e-2` unless a parameter specific to the GPT image models is used."
+          },
+          "n": {
+            "type": "integer",
+            "minimum": 1,
+            "maximum": 10,
+            "default": 1,
+            "example": 1,
+            "nullable": true,
+            "description": "The number of images to generate. Must be between 1 and 10. For `dall-e-3`, only `n=1` is supported."
+          },
+          "quality": {
+            "type": "string",
+            "enum": [
+              "standard",
+              "hd",
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max",
+              "auto"
+            ],
+            "default": "auto",
+            "example": "medium",
+            "nullable": true,
+            "description": "The quality of the image that will be generated.\n\n- `auto` (default value) will automatically select the best quality for the given\n  model.\n- `high`, `medium` and `low` are supported for the GPT image models.\n- `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`, including their `2026-09-08`\n  snapshots, also support `xhigh` and `max`.\n- `hd` and `standard` are supported for `dall-e-3`.\n- `standard` is the only option for `dall-e-2`.\n"
+          },
+          "response_format": {
+            "type": "string",
+            "enum": [
+              "url",
+              "b64_json"
+            ],
+            "default": "url",
+            "example": "url",
+            "nullable": true,
+            "description": "The format in which generated images with `dall-e-2` and `dall-e-3` are returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes after the image has been generated. This parameter isn't supported for the GPT image models, which always return base64-encoded images."
+          },
+          "output_format": {
+            "type": "string",
+            "enum": [
+              "png",
+              "jpeg",
+              "webp"
+            ],
+            "default": "png",
+            "example": "png",
+            "nullable": true,
+            "description": "The format in which the generated images are returned. This parameter is only supported for the GPT image models. Must be one of `png`, `jpeg`, or `webp`."
+          },
+          "output_compression": {
+            "type": "integer",
+            "default": 100,
+            "example": 100,
+            "nullable": true,
+            "description": "The compression level (0-100%) for the generated images. This parameter is only supported for the GPT image models with the `webp` or `jpeg` output formats, and defaults to 100."
+          },
+          "stream": {
+            "type": "boolean",
+            "default": false,
+            "example": false,
+            "nullable": true,
+            "description": "Generate the image in streaming mode. Defaults to `false`. See the\n[Image generation guide](https://developers.openai.com/api/docs/guides/image-generation) for more information.\nThis parameter is only supported for the GPT image models.\n"
+          },
+          "partial_images": {
+            "$ref": "#/components/schemas/PartialImages"
+          },
+          "size": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "auto",
+                  "1024x1024",
+                  "1536x1024",
+                  "1024x1536",
+                  "256x256",
+                  "512x512",
+                  "1792x1024",
+                  "1024x1792"
+                ]
+              }
+            ],
+            "default": "auto",
+            "example": "1024x1024",
+            "nullable": true,
+            "description": "The size of the generated images. For `gpt-image-2`, `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, and `gpt-image-2.5-flare-2026-09-08`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`."
+          },
+          "moderation": {
+            "type": "string",
+            "enum": [
+              "low",
+              "auto"
+            ],
+            "default": "auto",
+            "example": "low",
+            "nullable": true,
+            "description": "Control the content-moderation level for images generated by the GPT image models. Must be either `low` for less restrictive filtering or `auto` (default value)."
+          },
+          "background": {
+            "type": "string",
+            "enum": [
+              "transparent",
+              "opaque",
+              "auto"
+            ],
+            "default": "auto",
+            "example": "transparent",
+            "nullable": true,
+            "description": "Set the background of the generated image(s). This parameter is only supported for\nthe GPT image models. Must be one of `transparent`, `opaque`, or `auto` (default\nvalue). When `auto` is used, the model will automatically determine the best\nbackground for the image.\n\n`gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`, including their `2026-09-08`\nsnapshots, support `opaque` and `transparent` backgrounds. Transparent backgrounds\nare available for supported GPT Image models. For `gpt-image-2` and\n`gpt-image-2-2026-04-21`, this support is in preview. When using `transparent`,\nset the output format to `png` or `webp`.\n"
+          },
+          "style": {
+            "type": "string",
+            "enum": [
+              "vivid",
+              "natural"
+            ],
+            "default": "vivid",
+            "example": "vivid",
+            "nullable": true,
+            "description": "The style of the generated images. This parameter is only supported for `dall-e-3`. Must be one of `vivid` or `natural`. Vivid causes the model to lean towards generating hyper-real and dramatic images. Natural causes the model to produce more natural, less hyper-real looking images."
+          },
+          "user": {
+            "type": "string",
+            "example": "user-1234",
+            "description": "A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers).\n"
+          }
+        },
+        "required": [
+          "prompt"
+        ]
+      },
+      "CreateImageVariationRequest": {
+        "type": "object",
+        "properties": {
+          "image": {
+            "description": "The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square.",
+            "type": "string",
+            "format": "binary"
+          },
+          "model": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "dall-e-2"
+                ],
+                "x-stainless-const": true
+              }
+            ],
+            "x-oaiTypeLabel": "string",
+            "default": "dall-e-2",
+            "example": "dall-e-2",
+            "nullable": true,
+            "description": "The model to use for image generation. Only `dall-e-2` is supported at this time."
+          },
+          "n": {
+            "type": "integer",
+            "minimum": 1,
+            "maximum": 10,
+            "default": 1,
+            "example": 1,
+            "nullable": true,
+            "description": "The number of images to generate. Must be between 1 and 10."
+          },
+          "response_format": {
+            "type": "string",
+            "enum": [
+              "url",
+              "b64_json"
+            ],
+            "default": "url",
+            "example": "url",
+            "nullable": true,
+            "description": "The format in which the generated images are returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes after the image has been generated."
+          },
+          "size": {
+            "type": "string",
+            "enum": [
+              "256x256",
+              "512x512",
+              "1024x1024"
+            ],
+            "default": "1024x1024",
+            "example": "1024x1024",
+            "nullable": true,
+            "description": "The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024`."
+          },
+          "user": {
+            "type": "string",
+            "example": "user-1234",
+            "description": "A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers).\n"
+          }
+        },
+        "required": [
+          "image"
+        ]
+      },
+      "CreateMessageRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": [
+          "role",
+          "content"
+        ],
+        "properties": {
+          "role": {
+            "type": "string",
+            "enum": [
+              "user",
+              "assistant"
+            ],
+            "description": "The role of the entity that is creating the message. Allowed values include:\n- `user`: Indicates the message is sent by an actual user and should be used in most cases to represent user-generated messages.\n- `assistant`: Indicates the message is generated by the assistant. Use this value to insert messages from the assistant into the conversation.\n"
+          },
+          "content": {
+            "oneOf": [
+              {
+                "type": "string",
+                "description": "The text contents of the message.",
+                "title": "Text content"
+              },
+              {
+                "type": "array",
+                "description": "An array of content parts with a defined type, each can be of type `text` or images can be passed with `image_url` or `image_file`. Image types are only supported on [Vision-compatible models](https://developers.openai.com/api/docs/models).",
+                "title": "Array of content parts",
+                "items": {
+                  "oneOf": [
+                    {
+                      "$ref": "#/components/schemas/MessageContentImageFileObject"
+                    },
+                    {
+                      "$ref": "#/components/schemas/MessageContentImageUrlObject"
+                    },
+                    {
+                      "$ref": "#/components/schemas/MessageRequestContentTextObject"
+                    }
+                  ]
+                },
+                "minItems": 1
+              }
+            ]
+          },
+          "attachments": {
+            "anyOf": [
+              {
+                "type": "array",
+                "items": {
+                  "type": "object",
+                  "properties": {
+                    "file_id": {
+                      "type": "string",
+                      "description": "The ID of the file to attach to the message."
+                    },
+                    "tools": {
+                      "description": "The tools to add this file to.",
+                      "type": "array",
+                      "items": {
+                        "oneOf": [
+                          {
+                            "$ref": "#/components/schemas/AssistantToolsCode"
+                          },
+                          {
+                            "$ref": "#/components/schemas/AssistantToolsFileSearchTypeOnly"
+                          }
+                        ]
+                      }
+                    }
+                  }
+                },
+                "description": "A list of files attached to the message, and the tools they should be added to.",
+                "required": [
+                  "file_id",
+                  "tools"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          }
+        }
+      },
+      "CreateModelResponseProperties": {
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/ModelResponseProperties"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "prompt_cache_options": {
+                "$ref": "#/components/schemas/PromptCacheOptionsParam"
+              },
+              "top_logprobs": {
+                "description": "An integer between 0 and 20 specifying the maximum number of most likely\ntokens to return at each token position, each with an associated log\nprobability. In some cases, the number of returned tokens may be fewer than\nrequested.\n",
+                "type": "integer",
+                "minimum": 0,
+                "maximum": 20
+              }
+            }
+          }
+        ]
+      },
+      "CreateModerationRequest": {
+        "type": "object",
+        "properties": {
+          "input": {
+            "description": "Input (or inputs) to classify. Can be a single string, an array of strings, or\nan array of multi-modal input objects similar to other models.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "description": "A string of text to classify for moderation.",
+                "default": "",
+                "example": "I want to kill them."
+              },
+              {
+                "type": "array",
+                "description": "An array of strings to classify for moderation.",
+                "items": {
+                  "type": "string",
+                  "default": "",
+                  "example": "I want to kill them."
+                }
+              },
+              {
+                "type": "array",
+                "description": "An array of multi-modal inputs to the moderation model.",
+                "items": {
+                  "oneOf": [
+                    {
+                      "type": "object",
+                      "description": "An object describing an image to classify.",
+                      "properties": {
+                        "type": {
+                          "description": "Always `image_url`.",
+                          "type": "string",
+                          "enum": [
+                            "image_url"
+                          ],
+                          "x-stainless-const": true
+                        },
+                        "image_url": {
+                          "type": "object",
+                          "description": "Contains either an image URL or a data URL for a base64 encoded image.",
+                          "properties": {
+                            "url": {
+                              "type": "string",
+                              "description": "Either a URL of the image or the base64 encoded image data.",
+                              "format": "uri",
+                              "example": "https://example.com/image.jpg"
+                            }
+                          },
+                          "required": [
+                            "url"
+                          ]
+                        }
+                      },
+                      "required": [
+                        "type",
+                        "image_url"
+                      ]
+                    },
+                    {
+                      "type": "object",
+                      "description": "An object describing text to classify.",
+                      "properties": {
+                        "type": {
+                          "description": "Always `text`.",
+                          "type": "string",
+                          "enum": [
+                            "text"
+                          ],
+                          "x-stainless-const": true
+                        },
+                        "text": {
+                          "description": "A string of text to classify.",
+                          "type": "string",
+                          "example": "I want to kill them"
+                        }
+                      },
+                      "required": [
+                        "type",
+                        "text"
+                      ]
+                    }
+                  ]
+                }
+              }
+            ]
+          },
+          "model": {
+            "description": "The content moderation model you would like to use. Learn more in\n[the moderation guide](https://developers.openai.com/api/docs/guides/moderation), and learn about\navailable models [here](https://developers.openai.com/api/docs/guides/moderation).\n",
+            "nullable": false,
+            "default": "omni-moderation-latest",
+            "example": "omni-moderation-2024-09-26",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "omni-moderation-latest",
+                  "omni-moderation-2024-09-26",
+                  "text-moderation-latest",
+                  "text-moderation-stable"
+                ]
+              }
+            ],
+            "x-oaiTypeLabel": "string"
+          }
+        },
+        "required": [
+          "input"
+        ]
+      },
+      "CreateModerationResponse": {
+        "type": "object",
+        "description": "Represents if a given text input is potentially harmful.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique identifier for the moderation request."
+          },
+          "model": {
+            "type": "string",
+            "description": "The model used to generate the moderation results."
+          },
+          "results": {
+            "type": "array",
+            "description": "A list of moderation objects.",
+            "items": {
+              "type": "object",
+              "properties": {
+                "flagged": {
+                  "type": "boolean",
+                  "description": "Whether any of the below categories are flagged."
+                },
+                "categories": {
+                  "type": "object",
+                  "description": "A list of the categories, and whether they are flagged or not.",
+                  "properties": {
+                    "hate": {
+                      "type": "boolean",
+                      "description": "Content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. Hateful content aimed at non-protected groups (e.g., chess players) is harassment."
+                    },
+                    "hate/threatening": {
+                      "type": "boolean",
+                      "description": "Hateful content that also includes violence or serious harm towards the targeted group based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste."
+                    },
+                    "harassment": {
+                      "type": "boolean",
+                      "description": "Content that expresses, incites, or promotes harassing language towards any target."
+                    },
+                    "harassment/threatening": {
+                      "type": "boolean",
+                      "description": "Harassment content that also includes violence or serious harm towards any target."
+                    },
+                    "illicit": {
+                      "anyOf": [
+                        {
+                          "type": "boolean",
+                          "description": "Content that includes instructions or advice that facilitate the planning or execution of wrongdoing, or that gives advice or instruction on how to commit illicit acts. For example, \"how to shoplift\" would fit this category."
+                        },
+                        {
+                          "type": "null"
+                        }
+                      ]
+                    },
+                    "illicit/violent": {
+                      "anyOf": [
+                        {
+                          "type": "boolean",
+                          "description": "Content that includes instructions or advice that facilitate the planning or execution of wrongdoing that also includes violence, or that gives advice or instruction on the procurement of any weapon."
+                        },
+                        {
+                          "type": "null"
+                        }
+                      ]
+                    },
+                    "self-harm": {
+                      "type": "boolean",
+                      "description": "Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders."
+                    },
+                    "self-harm/intent": {
+                      "type": "boolean",
+                      "description": "Content where the speaker expresses that they are engaging or intend to engage in acts of self-harm, such as suicide, cutting, and eating disorders."
+                    },
+                    "self-harm/instructions": {
+                      "type": "boolean",
+                      "description": "Content that encourages performing acts of self-harm, such as suicide, cutting, and eating disorders, or that gives instructions or advice on how to commit such acts."
+                    },
+                    "sexual": {
+                      "type": "boolean",
+                      "description": "Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness)."
+                    },
+                    "sexual/minors": {
+                      "type": "boolean",
+                      "description": "Sexual content that includes an individual who is under 18 years old."
+                    },
+                    "violence": {
+                      "type": "boolean",
+                      "description": "Content that depicts death, violence, or physical injury."
+                    },
+                    "violence/graphic": {
+                      "type": "boolean",
+                      "description": "Content that depicts death, violence, or physical injury in graphic detail."
+                    }
+                  },
+                  "required": [
+                    "hate",
+                    "hate/threatening",
+                    "harassment",
+                    "harassment/threatening",
+                    "illicit",
+                    "illicit/violent",
+                    "self-harm",
+                    "self-harm/intent",
+                    "self-harm/instructions",
+                    "sexual",
+                    "sexual/minors",
+                    "violence",
+                    "violence/graphic"
+                  ]
+                },
+                "category_scores": {
+                  "type": "object",
+                  "description": "A list of the categories along with their scores as predicted by model.",
+                  "properties": {
+                    "hate": {
+                      "type": "number",
+                      "description": "The score for the category 'hate'."
+                    },
+                    "hate/threatening": {
+                      "type": "number",
+                      "description": "The score for the category 'hate/threatening'."
+                    },
+                    "harassment": {
+                      "type": "number",
+                      "description": "The score for the category 'harassment'."
+                    },
+                    "harassment/threatening": {
+                      "type": "number",
+                      "description": "The score for the category 'harassment/threatening'."
+                    },
+                    "illicit": {
+                      "type": "number",
+                      "description": "The score for the category 'illicit'."
+                    },
+                    "illicit/violent": {
+                      "type": "number",
+                      "description": "The score for the category 'illicit/violent'."
+                    },
+                    "self-harm": {
+                      "type": "number",
+                      "description": "The score for the category 'self-harm'."
+                    },
+                    "self-harm/intent": {
+                      "type": "number",
+                      "description": "The score for the category 'self-harm/intent'."
+                    },
+                    "self-harm/instructions": {
+                      "type": "number",
+                      "description": "The score for the category 'self-harm/instructions'."
+                    },
+                    "sexual": {
+                      "type": "number",
+                      "description": "The score for the category 'sexual'."
+                    },
+                    "sexual/minors": {
+                      "type": "number",
+                      "description": "The score for the category 'sexual/minors'."
+                    },
+                    "violence": {
+                      "type": "number",
+                      "description": "The score for the category 'violence'."
+                    },
+                    "violence/graphic": {
+                      "type": "number",
+                      "description": "The score for the category 'violence/graphic'."
+                    }
+                  },
+                  "required": [
+                    "hate",
+                    "hate/threatening",
+                    "harassment",
+                    "harassment/threatening",
+                    "illicit",
+                    "illicit/violent",
+                    "self-harm",
+                    "self-harm/intent",
+                    "self-harm/instructions",
+                    "sexual",
+                    "sexual/minors",
+                    "violence",
+                    "violence/graphic"
+                  ]
+                },
+                "category_applied_input_types": {
+                  "type": "object",
+                  "description": "A list of the categories along with the input type(s) that the score applies to.",
+                  "properties": {
+                    "hate": {
+                      "type": "array",
+                      "description": "The applied input type(s) for the category 'hate'.",
+                      "items": {
+                        "type": "string",
+                        "enum": [
+                          "text"
+                        ],
+                        "x-stainless-const": true
+                      }
+                    },
+                    "hate/threatening": {
+                      "type": "array",
+                      "description": "The applied input type(s) for the category 'hate/threatening'.",
+                      "items": {
+                        "type": "string",
+                        "enum": [
+                          "text"
+                        ],
+                        "x-stainless-const": true
+                      }
+                    },
+                    "harassment": {
+                      "type": "array",
+                      "description": "The applied input type(s) for the category 'harassment'.",
+                      "items": {
+                        "type": "string",
+                        "enum": [
+                          "text"
+                        ],
+                        "x-stainless-const": true
+                      }
+                    },
+                    "harassment/threatening": {
+                      "type": "array",
+                      "description": "The applied input type(s) for the category 'harassment/threatening'.",
+                      "items": {
+                        "type": "string",
+                        "enum": [
+                          "text"
+                        ],
+                        "x-stainless-const": true
+                      }
+                    },
+                    "illicit": {
+                      "type": "array",
+                      "description": "The applied input type(s) for the category 'illicit'.",
+                      "items": {
+                        "type": "string",
+                        "enum": [
+                          "text"
+                        ],
+                        "x-stainless-const": true
+                      }
+                    },
+                    "illicit/violent": {
+                      "type": "array",
+                      "description": "The applied input type(s) for the category 'illicit/violent'.",
+                      "items": {
+                        "type": "string",
+                        "enum": [
+                          "text"
+                        ],
+                        "x-stainless-const": true
+                      }
+                    },
+                    "self-harm": {
+                      "type": "array",
+                      "description": "The applied input type(s) for the category 'self-harm'.",
+                      "items": {
+                        "type": "string",
+                        "enum": [
+                          "text",
+                          "image"
+                        ]
+                      }
+                    },
+                    "self-harm/intent": {
+                      "type": "array",
+                      "description": "The applied input type(s) for the category 'self-harm/intent'.",
+                      "items": {
+                        "type": "string",
+                        "enum": [
+                          "text",
+                          "image"
+                        ]
+                      }
+                    },
+                    "self-harm/instructions": {
+                      "type": "array",
+                      "description": "The applied input type(s) for the category 'self-harm/instructions'.",
+                      "items": {
+                        "type": "string",
+                        "enum": [
+                          "text",
+                          "image"
+                        ]
+                      }
+                    },
+                    "sexual": {
+                      "type": "array",
+                      "description": "The applied input type(s) for the category 'sexual'.",
+                      "items": {
+                        "type": "string",
+                        "enum": [
+                          "text",
+                          "image"
+                        ]
+                      }
+                    },
+                    "sexual/minors": {
+                      "type": "array",
+                      "description": "The applied input type(s) for the category 'sexual/minors'.",
+                      "items": {
+                        "type": "string",
+                        "enum": [
+                          "text"
+                        ],
+                        "x-stainless-const": true
+                      }
+                    },
+                    "violence": {
+                      "type": "array",
+                      "description": "The applied input type(s) for the category 'violence'.",
+                      "items": {
+                        "type": "string",
+                        "enum": [
+                          "text",
+                          "image"
+                        ]
+                      }
+                    },
+                    "violence/graphic": {
+                      "type": "array",
+                      "description": "The applied input type(s) for the category 'violence/graphic'.",
+                      "items": {
+                        "type": "string",
+                        "enum": [
+                          "text",
+                          "image"
+                        ]
+                      }
+                    }
+                  },
+                  "required": [
+                    "hate",
+                    "hate/threatening",
+                    "harassment",
+                    "harassment/threatening",
+                    "illicit",
+                    "illicit/violent",
+                    "self-harm",
+                    "self-harm/intent",
+                    "self-harm/instructions",
+                    "sexual",
+                    "sexual/minors",
+                    "violence",
+                    "violence/graphic"
+                  ]
+                }
+              },
+              "required": [
+                "flagged",
+                "categories",
+                "category_scores",
+                "category_applied_input_types"
+              ]
+            }
+          }
+        },
+        "required": [
+          "id",
+          "model",
+          "results"
+        ],
+        "x-oaiMeta": {
+          "name": "The moderation object",
+          "example": "{\n  \"id\": \"modr-0d9740456c391e43c445bf0f010940c7\",\n  \"model\": \"omni-moderation-latest\",\n  \"results\": [\n    {\n      \"flagged\": true,\n      \"categories\": {\n        \"harassment\": true,\n        \"harassment/threatening\": true,\n        \"sexual\": false,\n        \"hate\": false,\n        \"hate/threatening\": false,\n        \"illicit\": false,\n        \"illicit/violent\": false,\n        \"self-harm/intent\": false,\n        \"self-harm/instructions\": false,\n        \"self-harm\": false,\n        \"sexual/minors\": false,\n        \"violence\": true,\n        \"violence/graphic\": true\n      },\n      \"category_scores\": {\n        \"harassment\": 0.8189693396524255,\n        \"harassment/threatening\": 0.804985420696006,\n        \"sexual\": 1.573112165348997e-6,\n        \"hate\": 0.007562942636942845,\n        \"hate/threatening\": 0.004208854591835476,\n        \"illicit\": 0.030535955153511665,\n        \"illicit/violent\": 0.008925306722380033,\n        \"self-harm/intent\": 0.00023023930975076432,\n        \"self-harm/instructions\": 0.0002293869201073356,\n        \"self-harm\": 0.012598046106750154,\n        \"sexual/minors\": 2.212566909570261e-8,\n        \"violence\": 0.9999992735124786,\n        \"violence/graphic\": 0.843064871157054\n      },\n      \"category_applied_input_types\": {\n        \"harassment\": [\n          \"text\"\n        ],\n        \"harassment/threatening\": [\n          \"text\"\n        ],\n        \"sexual\": [\n          \"text\",\n          \"image\"\n        ],\n        \"hate\": [\n          \"text\"\n        ],\n        \"hate/threatening\": [\n          \"text\"\n        ],\n        \"illicit\": [\n          \"text\"\n        ],\n        \"illicit/violent\": [\n          \"text\"\n        ],\n        \"self-harm/intent\": [\n          \"text\",\n          \"image\"\n        ],\n        \"self-harm/instructions\": [\n          \"text\",\n          \"image\"\n        ],\n        \"self-harm\": [\n          \"text\",\n          \"image\"\n        ],\n        \"sexual/minors\": [\n          \"text\"\n        ],\n        \"violence\": [\n          \"text\",\n          \"image\"\n        ],\n        \"violence/graphic\": [\n          \"text\",\n          \"image\"\n        ]\n      }\n    }\n  ]\n}\n"
+        }
+      },
+      "CreateResponse": {
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/CreateModelResponseProperties"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseProperties"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "prompt_cache_options": {
+                "$ref": "#/components/schemas/ResponsePromptCacheOptionsParam"
+              },
+              "service_tier": {
+                "$ref": "#/components/schemas/ServiceTierResponses"
+              },
+              "truncation": {
+                "deprecated": true,
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "The truncation strategy to use for the model response.\n- `auto`: If the input to this Response exceeds\n  the model's context window size, the model will truncate the\n  response to fit the context window by dropping items from the beginning of the conversation.\n- `disabled` (default): If the input size will exceed the context window\n  size for a model, the request will fail with a 400 error.\n",
+                    "enum": [
+                      "auto",
+                      "disabled"
+                    ],
+                    "default": "disabled"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "reasoning": {
+                "anyOf": [
+                  {
+                    "$ref": "#/components/schemas/Reasoning"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "input": {
+                "$ref": "#/components/schemas/InputParam"
+              },
+              "include": {
+                "anyOf": [
+                  {
+                    "type": "array",
+                    "description": "Specify additional output data to include in the model response. Currently supported values are:\n- `web_search_call.action.sources`: Include the sources of the web search tool call.\n- `code_interpreter_call.outputs`: Includes the outputs of python code execution in code interpreter tool call items.\n- `computer_call_output.output.image_url`: Include image urls from the computer call output.\n- `file_search_call.results`: Include the search results of the file search tool call.\n- `message.input_image.image_url`: Include image urls from the input message.\n- `message.output_text.logprobs`: Include logprobs with assistant messages.\n- `reasoning.encrypted_content`: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when the `store` parameter is set to `false`, or when an organization is enrolled in the zero data retention program).",
+                    "items": {
+                      "$ref": "#/components/schemas/IncludeEnum"
+                    }
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "parallel_tool_calls": {
+                "anyOf": [
+                  {
+                    "type": "boolean",
+                    "description": "Whether to allow the model to run tool calls in parallel.\n",
+                    "default": true
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "store": {
+                "anyOf": [
+                  {
+                    "type": "boolean",
+                    "description": "Whether to store the generated model response for later retrieval via\nAPI.\nDefaults to true when omitted.\nIf set to true, response data will be stored for at least 30 days, subject to the [data retention exceptions](https://developers.openai.com/api/docs/guides/your-data#v1responses).\n",
+                    "default": true
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "instructions": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "A system (or developer) message inserted into the model's context.\n\nWhen using along with `previous_response_id`, the instructions from a previous\nresponse will not be carried over to the next response. This makes it simple\nto swap out system (or developer) messages in new responses.\n"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "moderation": {
+                "anyOf": [
+                  {
+                    "$ref": "#/components/schemas/ModerationParam",
+                    "description": "Configuration for running moderation on the input and output of this response.\n"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "stream": {
+                "anyOf": [
+                  {
+                    "description": "If set to true, the model response data will be streamed to the client\nas it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).\nSee the [Streaming section below](https://developers.openai.com/api/reference/resources/responses/streaming-events)\nfor more information.\n",
+                    "type": "boolean",
+                    "default": false
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "stream_options": {
+                "$ref": "#/components/schemas/ResponseStreamOptions"
+              },
+              "conversation": {
+                "anyOf": [
+                  {
+                    "$ref": "#/components/schemas/ConversationParam"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "context_management": {
+                "anyOf": [
+                  {
+                    "type": "array",
+                    "description": "Context management configuration for this request.\n",
+                    "minItems": 1,
+                    "items": {
+                      "$ref": "#/components/schemas/ContextManagementParam"
+                    }
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "max_output_tokens": {
+                "anyOf": [
+                  {
+                    "description": "An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](https://developers.openai.com/api/docs/guides/reasoning).\n",
+                    "type": "integer",
+                    "minimum": 16
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              }
+            }
+          }
+        ]
+      },
+      "CreateRunRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "assistant_id": {
+            "description": "The ID of the [assistant](https://developers.openai.com/api/docs/assistants/migration) to use to execute this run.",
+            "type": "string"
+          },
+          "model": {
+            "description": "The ID of the [Model](https://developers.openai.com/api/reference/resources/models) to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.",
+            "example": "gpt-5",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "$ref": "#/components/schemas/AssistantSupportedModels"
+              }
+            ],
+            "x-oaiTypeLabel": "string",
+            "nullable": true
+          },
+          "reasoning_effort": {
+            "$ref": "#/components/schemas/ReasoningEffort"
+          },
+          "instructions": {
+            "description": "Overrides the [instructions](https://developers.openai.com/api/docs/assistants/migration) of the assistant. This is useful for modifying the behavior on a per-run basis.",
+            "type": "string",
+            "nullable": true
+          },
+          "additional_instructions": {
+            "description": "Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions.",
+            "type": "string",
+            "nullable": true
+          },
+          "additional_messages": {
+            "description": "Adds additional messages to the thread before creating the run.",
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/CreateMessageRequest"
+            },
+            "nullable": true
+          },
+          "tools": {
+            "description": "Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.",
+            "nullable": true,
+            "type": "array",
+            "maxItems": 20,
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/AssistantToolsCode"
+                },
+                {
+                  "$ref": "#/components/schemas/AssistantToolsFileSearch"
+                },
+                {
+                  "$ref": "#/components/schemas/AssistantToolsFunction"
+                }
+              ]
+            }
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          },
+          "temperature": {
+            "type": "number",
+            "minimum": 0,
+            "maximum": 2,
+            "default": 1,
+            "example": 1,
+            "nullable": true,
+            "description": "What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.\n"
+          },
+          "top_p": {
+            "type": "number",
+            "minimum": 0,
+            "maximum": 1,
+            "default": 1,
+            "example": 1,
+            "nullable": true,
+            "description": "An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\n\nWe generally recommend altering this or temperature but not both.\n"
+          },
+          "stream": {
+            "type": "boolean",
+            "nullable": true,
+            "description": "If `true`, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a `data: [DONE]` message.\n"
+          },
+          "max_prompt_tokens": {
+            "type": "integer",
+            "nullable": true,
+            "description": "The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info.\n",
+            "minimum": 256
+          },
+          "max_completion_tokens": {
+            "type": "integer",
+            "nullable": true,
+            "description": "The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info.\n",
+            "minimum": 256
+          },
+          "truncation_strategy": {
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/TruncationObject"
+              },
+              {
+                "nullable": true
+              }
+            ]
+          },
+          "tool_choice": {
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/AssistantsApiToolChoiceOption"
+              },
+              {
+                "nullable": true
+              }
+            ]
+          },
+          "parallel_tool_calls": {
+            "$ref": "#/components/schemas/ParallelToolCalls"
+          },
+          "response_format": {
+            "$ref": "#/components/schemas/AssistantsApiResponseFormatOption",
+            "nullable": true
+          }
+        },
+        "required": [
+          "assistant_id"
+        ]
+      },
+      "CreateSpeechRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "model": {
+            "description": "One of the available [TTS models](https://developers.openai.com/api/docs/guides/text-to-speech): `tts-1`, `tts-1-hd`, `gpt-4o-mini-tts`, or `gpt-4o-mini-tts-2025-12-15`.\n",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "tts-1",
+                  "tts-1-hd",
+                  "gpt-4o-mini-tts",
+                  "gpt-4o-mini-tts-2025-12-15"
+                ]
+              }
+            ],
+            "x-oaiTypeLabel": "string"
+          },
+          "input": {
+            "type": "string",
+            "description": "The text to generate audio for. The maximum length is 4096 characters.",
+            "maxLength": 4096
+          },
+          "instructions": {
+            "type": "string",
+            "description": "Control the voice of your generated audio with additional instructions. Does not work with `tts-1` or `tts-1-hd`.",
+            "maxLength": 4096
+          },
+          "voice": {
+            "description": "The voice to use when generating the audio. Supported built-in voices are `alloy`, `ash`, `ballad`, `coral`, `echo`, `fable`, `onyx`, `nova`, `sage`, `shimmer`, `verse`, `marin`, and `cedar`. You may also provide a custom voice object with an `id`, for example `{ \"id\": \"voice_1234\" }`. Previews of the voices are available in the [Text to speech guide](https://developers.openai.com/api/docs/guides/text-to-speech#voice-options).",
+            "$ref": "#/components/schemas/VoiceIdsOrCustomVoice"
+          },
+          "response_format": {
+            "description": "The format to audio in. Supported formats are `mp3`, `opus`, `aac`, `flac`, `wav`, and `pcm`.",
+            "default": "mp3",
+            "type": "string",
+            "enum": [
+              "mp3",
+              "opus",
+              "aac",
+              "flac",
+              "wav",
+              "pcm"
+            ]
+          },
+          "speed": {
+            "description": "The speed of the generated audio. Select a value from `0.25` to `4.0`. `1.0` is the default.",
+            "type": "number",
+            "default": 1,
+            "minimum": 0.25,
+            "maximum": 4
+          },
+          "stream_format": {
+            "description": "The format to stream the audio in. Supported formats are `sse` and `audio`. `sse` is not supported for `tts-1` or `tts-1-hd`.",
+            "type": "string",
+            "default": "audio",
+            "enum": [
+              "sse",
+              "audio"
+            ]
+          }
+        },
+        "required": [
+          "model",
+          "input",
+          "voice"
+        ]
+      },
+      "CreateSpeechResponseStreamEvent": {
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/SpeechAudioDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/SpeechAudioDoneEvent"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "CreateSpendAlertBody": {
+        "type": "object",
+        "description": "Parameters for creating or updating a spend alert.",
+        "properties": {
+          "threshold_amount": {
+            "type": "integer",
+            "minimum": 0,
+            "description": "The alert threshold amount, in cents."
+          },
+          "currency": {
+            "type": "string",
+            "enum": [
+              "USD"
+            ],
+            "description": "The currency for the threshold amount."
+          },
+          "interval": {
+            "type": "string",
+            "enum": [
+              "month"
+            ],
+            "description": "The time interval for evaluating spend against the threshold."
+          },
+          "notification_channel": {
+            "$ref": "#/components/schemas/SpendAlertNotificationChannel"
+          }
+        },
+        "required": [
+          "threshold_amount",
+          "currency",
+          "interval",
+          "notification_channel"
+        ]
+      },
+      "CreateThreadAndRunRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "assistant_id": {
+            "description": "The ID of the [assistant](https://developers.openai.com/api/docs/assistants/migration) to use to execute this run.",
+            "type": "string"
+          },
+          "thread": {
+            "$ref": "#/components/schemas/CreateThreadRequest"
+          },
+          "model": {
+            "description": "The ID of the [Model](https://developers.openai.com/api/reference/resources/models) to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.",
+            "example": "gpt-5",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "gpt-5",
+                  "gpt-5-mini",
+                  "gpt-5-nano",
+                  "gpt-5-2025-08-07",
+                  "gpt-5-mini-2025-08-07",
+                  "gpt-5-nano-2025-08-07",
+                  "gpt-4.1",
+                  "gpt-4.1-mini",
+                  "gpt-4.1-nano",
+                  "gpt-4.1-2025-04-14",
+                  "gpt-4.1-mini-2025-04-14",
+                  "gpt-4.1-nano-2025-04-14",
+                  "gpt-4o",
+                  "gpt-4o-2024-11-20",
+                  "gpt-4o-2024-08-06",
+                  "gpt-4o-2024-05-13",
+                  "gpt-4o-mini",
+                  "gpt-4o-mini-2024-07-18",
+                  "gpt-4.5-preview",
+                  "gpt-4.5-preview-2025-02-27",
+                  "gpt-4-turbo",
+                  "gpt-4-turbo-2024-04-09",
+                  "gpt-4-0125-preview",
+                  "gpt-4-turbo-preview",
+                  "gpt-4-1106-preview",
+                  "gpt-4-vision-preview",
+                  "gpt-4",
+                  "gpt-4-0314",
+                  "gpt-4-0613",
+                  "gpt-4-32k",
+                  "gpt-4-32k-0314",
+                  "gpt-4-32k-0613",
+                  "gpt-3.5-turbo",
+                  "gpt-3.5-turbo-16k",
+                  "gpt-3.5-turbo-0613",
+                  "gpt-3.5-turbo-1106",
+                  "gpt-3.5-turbo-0125",
+                  "gpt-3.5-turbo-16k-0613"
+                ]
+              }
+            ],
+            "x-oaiTypeLabel": "string",
+            "nullable": true
+          },
+          "instructions": {
+            "description": "Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis.",
+            "type": "string",
+            "nullable": true
+          },
+          "tools": {
+            "description": "Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.",
+            "nullable": true,
+            "type": "array",
+            "maxItems": 20,
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/AssistantToolsCode"
+                },
+                {
+                  "$ref": "#/components/schemas/AssistantToolsFileSearch"
+                },
+                {
+                  "$ref": "#/components/schemas/AssistantToolsFunction"
+                }
+              ]
+            }
+          },
+          "tool_resources": {
+            "type": "object",
+            "description": "A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs.\n",
+            "properties": {
+              "code_interpreter": {
+                "type": "object",
+                "properties": {
+                  "file_ids": {
+                    "type": "array",
+                    "description": "A list of [file](https://developers.openai.com/api/reference/resources/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool.\n",
+                    "default": [],
+                    "maxItems": 20,
+                    "items": {
+                      "type": "string"
+                    }
+                  }
+                }
+              },
+              "file_search": {
+                "type": "object",
+                "properties": {
+                  "vector_store_ids": {
+                    "type": "array",
+                    "description": "The ID of the [vector store](https://developers.openai.com/api/reference/resources/vector_stores) attached to this assistant. There can be a maximum of 1 vector store attached to the assistant.\n",
+                    "maxItems": 1,
+                    "items": {
+                      "type": "string"
+                    }
+                  }
+                }
+              }
+            },
+            "nullable": true
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          },
+          "temperature": {
+            "type": "number",
+            "minimum": 0,
+            "maximum": 2,
+            "default": 1,
+            "example": 1,
+            "nullable": true,
+            "description": "What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.\n"
+          },
+          "top_p": {
+            "type": "number",
+            "minimum": 0,
+            "maximum": 1,
+            "default": 1,
+            "example": 1,
+            "nullable": true,
+            "description": "An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\n\nWe generally recommend altering this or temperature but not both.\n"
+          },
+          "stream": {
+            "type": "boolean",
+            "nullable": true,
+            "description": "If `true`, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a `data: [DONE]` message.\n"
+          },
+          "max_prompt_tokens": {
+            "type": "integer",
+            "nullable": true,
+            "description": "The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info.\n",
+            "minimum": 256
+          },
+          "max_completion_tokens": {
+            "type": "integer",
+            "nullable": true,
+            "description": "The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info.\n",
+            "minimum": 256
+          },
+          "truncation_strategy": {
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/TruncationObject"
+              },
+              {
+                "nullable": true
+              }
+            ]
+          },
+          "tool_choice": {
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/AssistantsApiToolChoiceOption"
+              },
+              {
+                "nullable": true
+              }
+            ]
+          },
+          "parallel_tool_calls": {
+            "$ref": "#/components/schemas/ParallelToolCalls"
+          },
+          "response_format": {
+            "$ref": "#/components/schemas/AssistantsApiResponseFormatOption",
+            "nullable": true
+          }
+        },
+        "required": [
+          "assistant_id"
+        ]
+      },
+      "CreateThreadRequest": {
+        "type": "object",
+        "description": "Options to create a new thread. If no thread is provided when running a\nrequest, an empty thread will be created.\n",
+        "additionalProperties": false,
+        "properties": {
+          "messages": {
+            "description": "A list of [messages](https://developers.openai.com/api/docs/assistants/migration) to start the thread with.",
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/CreateMessageRequest"
+            }
+          },
+          "tool_resources": {
+            "anyOf": [
+              {
+                "type": "object",
+                "description": "A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs.\n",
+                "properties": {
+                  "code_interpreter": {
+                    "type": "object",
+                    "properties": {
+                      "file_ids": {
+                        "type": "array",
+                        "description": "A list of [file](https://developers.openai.com/api/reference/resources/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool.\n",
+                        "default": [],
+                        "maxItems": 20,
+                        "items": {
+                          "type": "string"
+                        }
+                      }
+                    }
+                  },
+                  "file_search": {
+                    "type": "object",
+                    "properties": {
+                      "vector_store_ids": {
+                        "type": "array",
+                        "description": "The [vector store](https://developers.openai.com/api/reference/resources/vector_stores) attached to this thread. There can be a maximum of 1 vector store attached to the thread.\n",
+                        "maxItems": 1,
+                        "items": {
+                          "type": "string"
+                        }
+                      },
+                      "vector_stores": {
+                        "type": "array",
+                        "description": "A helper to create a [vector store](https://developers.openai.com/api/reference/resources/vector_stores) with file_ids and attach it to this thread. There can be a maximum of 1 vector store attached to the thread.\n",
+                        "maxItems": 1,
+                        "items": {
+                          "type": "object",
+                          "properties": {
+                            "file_ids": {
+                              "type": "array",
+                              "description": "A list of [file](https://developers.openai.com/api/reference/resources/files) IDs to add to the vector store. For vector stores created before Nov 2025, there can be a maximum of 10,000 files in a vector store. For vector stores created starting in Nov 2025, the limit is 100,000,000 files.\n",
+                              "maxItems": 100000000,
+                              "items": {
+                                "type": "string"
+                              }
+                            },
+                            "chunking_strategy": {
+                              "type": "object",
+                              "description": "The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy.",
+                              "oneOf": [
+                                {
+                                  "type": "object",
+                                  "title": "Auto Chunking Strategy",
+                                  "description": "The default strategy. This strategy currently uses a `max_chunk_size_tokens` of `800` and `chunk_overlap_tokens` of `400`.",
+                                  "additionalProperties": false,
+                                  "properties": {
+                                    "type": {
+                                      "type": "string",
+                                      "description": "Always `auto`.",
+                                      "enum": [
+                                        "auto"
+                                      ],
+                                      "x-stainless-const": true
+                                    }
+                                  },
+                                  "required": [
+                                    "type"
+                                  ]
+                                },
+                                {
+                                  "type": "object",
+                                  "title": "Static Chunking Strategy",
+                                  "additionalProperties": false,
+                                  "properties": {
+                                    "type": {
+                                      "type": "string",
+                                      "description": "Always `static`.",
+                                      "enum": [
+                                        "static"
+                                      ],
+                                      "x-stainless-const": true
+                                    },
+                                    "static": {
+                                      "type": "object",
+                                      "additionalProperties": false,
+                                      "properties": {
+                                        "max_chunk_size_tokens": {
+                                          "type": "integer",
+                                          "minimum": 100,
+                                          "maximum": 4096,
+                                          "description": "The maximum number of tokens in each chunk. The default value is `800`. The minimum value is `100` and the maximum value is `4096`."
+                                        },
+                                        "chunk_overlap_tokens": {
+                                          "type": "integer",
+                                          "description": "The number of tokens that overlap between chunks. The default value is `400`.\n\nNote that the overlap must not exceed half of `max_chunk_size_tokens`.\n"
+                                        }
+                                      },
+                                      "required": [
+                                        "max_chunk_size_tokens",
+                                        "chunk_overlap_tokens"
+                                      ]
+                                    }
+                                  },
+                                  "required": [
+                                    "type",
+                                    "static"
+                                  ]
+                                }
+                              ]
+                            },
+                            "metadata": {
+                              "$ref": "#/components/schemas/Metadata"
+                            }
+                          }
+                        }
+                      }
+                    },
+                    "oneOf": [
+                      {
+                        "required": [
+                          "vector_store_ids"
+                        ]
+                      },
+                      {
+                        "required": [
+                          "vector_stores"
+                        ]
+                      }
+                    ]
+                  }
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          }
+        }
+      },
+      "CreateTranscriptionRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "file": {
+            "description": "The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.\nThe request must include enough format metadata for the file to be identified. We recommend an extension-bearing filename and an appropriate content type.\n",
+            "type": "string",
+            "x-oaiTypeLabel": "file",
+            "format": "binary"
+          },
+          "model": {
+            "description": "ID of the model to use. The options are `gpt-transcribe`, `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `whisper-1` (which is powered by our open source Whisper V2 model), and `gpt-4o-transcribe-diarize`.\n",
+            "example": "gpt-4o-transcribe",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "whisper-1",
+                  "gpt-transcribe",
+                  "gpt-4o-transcribe",
+                  "gpt-4o-mini-transcribe",
+                  "gpt-4o-mini-transcribe-2025-12-15",
+                  "gpt-4o-transcribe-diarize"
+                ],
+                "x-stainless-const": true
+              }
+            ],
+            "x-oaiTypeLabel": "string"
+          },
+          "language": {
+            "description": "The language of the input audio. Supplying the input language in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format will improve accuracy and latency.\n",
+            "type": "string"
+          },
+          "languages": {
+            "description": "Possible languages of the input audio, in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format. Supported by `gpt-transcribe`.\n",
+            "type": "array",
+            "minItems": 1,
+            "items": {
+              "type": "string"
+            }
+          },
+          "keywords": {
+            "description": "Words or phrases to guide transcription of the input audio. Supported by `gpt-transcribe`.\n",
+            "type": "array",
+            "items": {
+              "type": "string"
+            }
+          },
+          "prompt": {
+            "description": "An optional text to guide the model's style or continue a previous audio segment. The [prompt](https://developers.openai.com/api/docs/guides/speech-to-text#prompting) should match the audio language. This field is not supported when using `gpt-4o-transcribe-diarize`.\n",
+            "type": "string"
+          },
+          "response_format": {
+            "$ref": "#/components/schemas/AudioResponseFormat"
+          },
+          "temperature": {
+            "description": "The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit.\n",
+            "type": "number",
+            "default": 0
+          },
+          "include": {
+            "description": "Additional information to include in the transcription response.\n`logprobs` will return the log probabilities of the tokens in the\nresponse to understand the model's confidence in the transcription.\n`logprobs` only works with response_format set to `json` and only with\nthe models `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is not supported when using `gpt-4o-transcribe-diarize`.\n",
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/TranscriptionInclude"
+            }
+          },
+          "timestamp_granularities": {
+            "description": "The timestamp granularities to populate for this transcription. `response_format` must be set `verbose_json` to use timestamp granularities. Either or both of these options are supported: `word`, or `segment`. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency.\nThis option is not available for `gpt-4o-transcribe-diarize`.\n",
+            "type": "array",
+            "items": {
+              "type": "string",
+              "enum": [
+                "word",
+                "segment"
+              ]
+            },
+            "default": [
+              "segment"
+            ]
+          },
+          "stream": {
+            "anyOf": [
+              {
+                "description": "If set to true, the model response data will be streamed to the client\nas it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).\nSee the [Streaming section of the Speech-to-Text guide](https://developers.openai.com/api/docs/guides/speech-to-text?lang=curl#streaming)\nfor more information.\n\nNote: Streaming is not supported for the `whisper-1` model and will be ignored.\n",
+                "type": "boolean",
+                "default": false
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "chunking_strategy": {
+            "anyOf": [
+              {
+                "description": "Controls how the audio is cut into chunks. When set to `\"auto\"`, the server first normalizes loudness and then uses voice activity detection (VAD) to choose boundaries. `server_vad` object can be provided to tweak VAD detection parameters manually. If unset, the audio is transcribed as a single block. Required when using `gpt-4o-transcribe-diarize` for inputs longer than 30 seconds. ",
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "enum": [
+                      "auto"
+                    ],
+                    "default": "auto",
+                    "description": "Automatically set chunking parameters based on the audio. Must be set to `\"auto\"`.\n",
+                    "x-stainless-const": true
+                  },
+                  {
+                    "$ref": "#/components/schemas/VadConfig"
+                  }
+                ],
+                "x-oaiTypeLabel": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "known_speaker_names": {
+            "description": "Optional list of speaker names that correspond to the audio samples provided in `known_speaker_references[]`. Each entry should be a short identifier (for example `customer` or `agent`). Up to 4 speakers are supported.\n",
+            "type": "array",
+            "maxItems": 4,
+            "items": {
+              "type": "string"
+            }
+          },
+          "known_speaker_references": {
+            "description": "Optional list of audio samples (as [data URLs](https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URLs)) that contain known speaker references matching `known_speaker_names[]`. Each sample must be between 2 and 10 seconds, and can use any of the same input audio formats supported by `file`.\n",
+            "type": "array",
+            "maxItems": 4,
+            "items": {
+              "type": "string"
+            }
+          }
+        },
+        "required": [
+          "file",
+          "model"
+        ]
+      },
+      "CreateTranscriptionResponseDiarizedJson": {
+        "type": "object",
+        "description": "Represents a diarized transcription response returned by the model, including the combined transcript and speaker-segment annotations.\n",
+        "properties": {
+          "task": {
+            "type": "string",
+            "description": "The type of task that was run. Always `transcribe`.",
+            "enum": [
+              "transcribe"
+            ],
+            "x-stainless-const": true
+          },
+          "duration": {
+            "type": "number",
+            "format": "double",
+            "description": "Duration of the input audio in seconds."
+          },
+          "text": {
+            "type": "string",
+            "description": "The concatenated transcript text for the entire audio input."
+          },
+          "segments": {
+            "type": "array",
+            "description": "Segments of the transcript annotated with timestamps and speaker labels.",
+            "items": {
+              "$ref": "#/components/schemas/TranscriptionDiarizedSegment"
+            }
+          },
+          "usage": {
+            "type": "object",
+            "description": "Token or duration usage statistics for the request.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/TranscriptTextUsageTokens",
+                "title": "Token Usage"
+              },
+              {
+                "$ref": "#/components/schemas/TranscriptTextUsageDuration",
+                "title": "Duration Usage"
+              }
+            ],
+            "discriminator": {
+              "propertyName": "type"
+            }
+          }
+        },
+        "required": [
+          "task",
+          "duration",
+          "text",
+          "segments"
+        ],
+        "x-oaiMeta": {
+          "name": "The transcription object (Diarized JSON)",
+          "group": "audio",
+          "example": "{\n  \"task\": \"transcribe\",\n  \"duration\": 42.7,\n  \"text\": \"Agent: Thanks for calling OpenAI support.\\nCustomer: Hi, I need help with diarization.\",\n  \"segments\": [\n    {\n      \"type\": \"transcript.text.segment\",\n      \"id\": \"seg_001\",\n      \"start\": 0.0,\n      \"end\": 5.2,\n      \"text\": \"Thanks for calling OpenAI support.\",\n      \"speaker\": \"agent\"\n    },\n    {\n      \"type\": \"transcript.text.segment\",\n      \"id\": \"seg_002\",\n      \"start\": 5.2,\n      \"end\": 12.8,\n      \"text\": \"Hi, I need help with diarization.\",\n      \"speaker\": \"A\"\n    }\n  ],\n  \"usage\": {\n    \"type\": \"duration\",\n    \"seconds\": 43\n  }\n}\n"
+        }
+      },
+      "CreateTranscriptionResponseJson": {
+        "type": "object",
+        "description": "Represents a transcription response returned by model, based on the provided input.",
+        "properties": {
+          "text": {
+            "type": "string",
+            "description": "The transcribed text."
+          },
+          "languages": {
+            "type": "array",
+            "description": "The languages detected in the audio. Returned by `gpt-transcribe`. An empty array indicates that no language could be reliably detected.\n",
+            "items": {
+              "$ref": "#/components/schemas/TranscriptionLanguage"
+            }
+          },
+          "logprobs": {
+            "type": "array",
+            "optional": true,
+            "description": "The log probabilities of the tokens in the transcription. Only returned with the models `gpt-4o-transcribe` and `gpt-4o-mini-transcribe` if `logprobs` is added to the `include` array.\n",
+            "items": {
+              "type": "object",
+              "properties": {
+                "token": {
+                  "type": "string",
+                  "description": "The token in the transcription."
+                },
+                "logprob": {
+                  "type": "number",
+                  "description": "The log probability of the token."
+                },
+                "bytes": {
+                  "type": "array",
+                  "items": {
+                    "type": "number"
+                  },
+                  "description": "The bytes of the token."
+                }
+              }
+            }
+          },
+          "usage": {
+            "type": "object",
+            "description": "Token usage statistics for the request.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/TranscriptTextUsageTokens",
+                "title": "Token Usage"
+              },
+              {
+                "$ref": "#/components/schemas/TranscriptTextUsageDuration",
+                "title": "Duration Usage"
+              }
+            ]
+          }
+        },
+        "required": [
+          "text"
+        ],
+        "x-oaiMeta": {
+          "name": "The transcription object (JSON)",
+          "group": "audio",
+          "example": "{\n  \"text\": \"Imagine the wildest idea that you've ever had, and you're curious about how it might scale to something that's a 100, a 1,000 times bigger. This is a place where you can get to do that.\",\n  \"usage\": {\n    \"type\": \"tokens\",\n    \"input_tokens\": 14,\n    \"input_token_details\": {\n      \"text_tokens\": 10,\n      \"audio_tokens\": 4\n    },\n    \"output_tokens\": 101,\n    \"total_tokens\": 115\n  }\n}\n"
+        }
+      },
+      "CreateTranscriptionResponseStreamEvent": {
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/TranscriptTextSegmentEvent"
+          },
+          {
+            "$ref": "#/components/schemas/TranscriptTextDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/TranscriptTextDoneEvent"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "CreateTranscriptionResponseVerboseJson": {
+        "type": "object",
+        "description": "Represents a verbose json transcription response returned by model, based on the provided input.",
+        "properties": {
+          "language": {
+            "type": "string",
+            "description": "The language of the input audio."
+          },
+          "duration": {
+            "type": "number",
+            "format": "double",
+            "description": "The duration of the input audio."
+          },
+          "text": {
+            "type": "string",
+            "description": "The transcribed text."
+          },
+          "words": {
+            "type": "array",
+            "description": "Extracted words and their corresponding timestamps.",
+            "items": {
+              "$ref": "#/components/schemas/TranscriptionWord"
+            }
+          },
+          "segments": {
+            "type": "array",
+            "description": "Segments of the transcribed text and their corresponding details.",
+            "items": {
+              "$ref": "#/components/schemas/TranscriptionSegment"
+            }
+          },
+          "usage": {
+            "$ref": "#/components/schemas/TranscriptTextUsageDuration"
+          }
+        },
+        "required": [
+          "language",
+          "duration",
+          "text"
+        ],
+        "x-oaiMeta": {
+          "name": "The transcription object (Verbose JSON)",
+          "group": "audio",
+          "example": "{\n  \"task\": \"transcribe\",\n  \"language\": \"english\",\n  \"duration\": 8.470000267028809,\n  \"text\": \"The beach was a popular spot on a hot summer day. People were swimming in the ocean, building sandcastles, and playing beach volleyball.\",\n  \"segments\": [\n    {\n      \"id\": 0,\n      \"seek\": 0,\n      \"start\": 0.0,\n      \"end\": 3.319999933242798,\n      \"text\": \" The beach was a popular spot on a hot summer day.\",\n      \"tokens\": [\n        50364, 440, 7534, 390, 257, 3743, 4008, 322, 257, 2368, 4266, 786, 13, 50530\n      ],\n      \"temperature\": 0.0,\n      \"avg_logprob\": -0.2860786020755768,\n      \"compression_ratio\": 1.2363636493682861,\n      \"no_speech_prob\": 0.00985979475080967\n    },\n    ...\n  ],\n  \"usage\": {\n    \"type\": \"duration\",\n    \"seconds\": 9\n  }\n}\n"
+        }
+      },
+      "CreateTranslationRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "file": {
+            "description": "The audio file object (not file name) translate, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. The request must include enough format metadata for the file to be identified. We recommend an extension-bearing filename and an appropriate content type.\n",
+            "type": "string",
+            "x-oaiTypeLabel": "file",
+            "format": "binary"
+          },
+          "model": {
+            "description": "ID of the model to use. Only `whisper-1` (which is powered by our open source Whisper V2 model) is currently available.\n",
+            "example": "whisper-1",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "whisper-1"
+                ],
+                "x-stainless-const": true
+              }
+            ],
+            "x-oaiTypeLabel": "string"
+          },
+          "prompt": {
+            "description": "An optional text to guide the model's style or continue a previous audio segment. The [prompt](https://developers.openai.com/api/docs/guides/speech-to-text#prompting) should be in English.\n",
+            "type": "string"
+          },
+          "response_format": {
+            "description": "The format of the output, in one of these options: `json`, `text`, `srt`, `verbose_json`, or `vtt`.\n",
+            "type": "string",
+            "enum": [
+              "json",
+              "text",
+              "srt",
+              "verbose_json",
+              "vtt"
+            ],
+            "default": "json"
+          },
+          "temperature": {
+            "description": "The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit.\n",
+            "type": "number",
+            "default": 0
+          }
+        },
+        "required": [
+          "file",
+          "model"
+        ]
+      },
+      "CreateTranslationResponseJson": {
+        "type": "object",
+        "properties": {
+          "text": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "text"
+        ]
+      },
+      "CreateTranslationResponseVerboseJson": {
+        "type": "object",
+        "properties": {
+          "language": {
+            "type": "string",
+            "description": "The language of the output translation (always `english`)."
+          },
+          "duration": {
+            "type": "number",
+            "format": "double",
+            "description": "The duration of the input audio."
+          },
+          "text": {
+            "type": "string",
+            "description": "The translated text."
+          },
+          "segments": {
+            "type": "array",
+            "description": "Segments of the translated text and their corresponding details.",
+            "items": {
+              "$ref": "#/components/schemas/TranscriptionSegment"
+            }
+          }
+        },
+        "required": [
+          "language",
+          "duration",
+          "text"
+        ]
+      },
+      "CreateUploadRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "filename": {
+            "description": "The name of the file to upload.\n",
+            "type": "string"
+          },
+          "purpose": {
+            "description": "The intended purpose of the uploaded file.\n\nSee the [documentation on File\npurposes](https://developers.openai.com/api/reference/resources/files/methods/create#%28resource%29%20files%20%3E%20%28method%29%20create%20%3E%20%28params%29%200%20%3E%20%28param%29%20purpose%20%3E%20%28schema%29).\n",
+            "type": "string",
+            "enum": [
+              "assistants",
+              "batch",
+              "fine-tune",
+              "vision"
+            ]
+          },
+          "bytes": {
+            "description": "The number of bytes in the file you are uploading.\n",
+            "type": "integer"
+          },
+          "mime_type": {
+            "description": "The MIME type of the file.\n\n\nThis must fall within the supported MIME types for your file purpose. See\nthe supported MIME types for assistants and vision.\n",
+            "type": "string"
+          },
+          "expires_after": {
+            "$ref": "#/components/schemas/FileExpirationAfter"
+          }
+        },
+        "required": [
+          "filename",
+          "purpose",
+          "bytes",
+          "mime_type"
+        ]
+      },
+      "CreateVectorStoreFileBatchRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "file_ids": {
+            "description": "A list of [File](https://developers.openai.com/api/reference/resources/files) IDs that the vector store should use. Useful for tools like `file_search` that can access files. If `attributes` or `chunking_strategy` are provided, they will be applied to all files in the batch. The maximum batch size is 2000 files. This endpoint is recommended for multi-file ingestion and helps reduce per-vector-store write request pressure. Mutually exclusive with `files`.",
+            "type": "array",
+            "minItems": 1,
+            "maxItems": 2000,
+            "items": {
+              "type": "string"
+            }
+          },
+          "files": {
+            "description": "A list of objects that each include a `file_id` plus optional `attributes` or `chunking_strategy`. Use this when you need to override metadata for specific files. The global `attributes` or `chunking_strategy` will be ignored and must be specified for each file. The maximum batch size is 2000 files. This endpoint is recommended for multi-file ingestion and helps reduce per-vector-store write request pressure. Mutually exclusive with `file_ids`.",
+            "type": "array",
+            "minItems": 1,
+            "maxItems": 2000,
+            "items": {
+              "$ref": "#/components/schemas/CreateVectorStoreFileRequest"
+            }
+          },
+          "chunking_strategy": {
+            "$ref": "#/components/schemas/ChunkingStrategyRequestParam"
+          },
+          "attributes": {
+            "$ref": "#/components/schemas/VectorStoreFileAttributes"
+          }
+        },
+        "anyOf": [
+          {
+            "required": [
+              "file_ids"
+            ]
+          },
+          {
+            "required": [
+              "files"
+            ]
+          }
+        ]
+      },
+      "CreateVectorStoreFileRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "file_id": {
+            "description": "A [File](https://developers.openai.com/api/reference/resources/files) ID that the vector store should use. Useful for tools like `file_search` that can access files. For multi-file ingestion, we recommend [`file_batches`](https://developers.openai.com/api/reference/resources/vector_stores/subresources/file_batches/methods/create) to minimize per-vector-store write requests.",
+            "type": "string"
+          },
+          "chunking_strategy": {
+            "$ref": "#/components/schemas/ChunkingStrategyRequestParam"
+          },
+          "attributes": {
+            "$ref": "#/components/schemas/VectorStoreFileAttributes"
+          }
+        },
+        "required": [
+          "file_id"
+        ]
+      },
+      "CreateVectorStoreRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "file_ids": {
+            "description": "A list of [File](https://developers.openai.com/api/reference/resources/files) IDs that the vector store should use. Useful for tools like `file_search` that can access files.",
+            "type": "array",
+            "maxItems": 500,
+            "items": {
+              "type": "string"
+            }
+          },
+          "name": {
+            "description": "The name of the vector store.",
+            "type": "string"
+          },
+          "description": {
+            "description": "A description for the vector store. Can be used to describe the vector store's purpose.",
+            "type": "string"
+          },
+          "expires_after": {
+            "$ref": "#/components/schemas/VectorStoreExpirationAfter"
+          },
+          "chunking_strategy": {
+            "type": "object",
+            "description": "The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy. Only applicable if `file_ids` is non-empty.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/AutoChunkingStrategyRequestParam"
+              },
+              {
+                "$ref": "#/components/schemas/StaticChunkingStrategyRequestParam"
+              }
+            ]
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          }
+        }
+      },
+      "CreateVoiceConsentRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The label to use for this consent recording."
+          },
+          "recording": {
+            "type": "string",
+            "format": "binary",
+            "x-oaiTypeLabel": "file",
+            "description": "The consent audio recording file. Maximum size is 10 MiB.\n\nSupported MIME types:\n`audio/mpeg`, `audio/wav`, `audio/x-wav`, `audio/ogg`, `audio/aac`, `audio/flac`, `audio/webm`, `audio/mp4`.\n"
+          },
+          "language": {
+            "type": "string",
+            "description": "The BCP 47 language tag for the consent phrase (for example, `en-US`)."
+          }
+        },
+        "required": [
+          "name",
+          "recording",
+          "language"
+        ]
+      },
+      "CreateVoiceRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The name of the new voice."
+          },
+          "audio_sample": {
+            "type": "string",
+            "format": "binary",
+            "x-oaiTypeLabel": "file",
+            "description": "The sample audio recording file. Maximum size is 10 MiB.\n\nSupported MIME types:\n`audio/mpeg`, `audio/wav`, `audio/x-wav`, `audio/ogg`, `audio/aac`, `audio/flac`, `audio/webm`, `audio/mp4`.\n"
+          },
+          "consent": {
+            "type": "string",
+            "description": "The consent recording ID (for example, `cons_1234`)."
+          }
+        },
+        "required": [
+          "name",
+          "audio_sample",
+          "consent"
+        ]
+      },
+      "CustomToolCall": {
+        "type": "object",
+        "title": "Custom tool call",
+        "description": "A call to a custom tool created by the model.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "custom_tool_call"
+            ],
+            "x-stainless-const": true,
+            "description": "The type of the custom tool call. Always `custom_tool_call`.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the custom tool call in the OpenAI platform.\n"
+          },
+          "call_id": {
+            "type": "string",
+            "description": "An identifier used to map this custom tool call to a tool call output.\n"
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ToolCallCaller"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "namespace": {
+            "type": "string",
+            "description": "The namespace of the custom tool being called.\n"
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the custom tool being called.\n"
+          },
+          "input": {
+            "type": "string",
+            "description": "The input for the custom tool call generated by the model.\n"
+          },
+          "async": {
+            "type": "boolean",
+            "description": "Whether the custom tool call runs asynchronously.\n"
+          }
+        },
+        "required": [
+          "type",
+          "call_id",
+          "name",
+          "input"
+        ]
+      },
+      "CustomToolCallOutput": {
+        "type": "object",
+        "title": "Custom tool call output",
+        "description": "The output of a custom tool call from your code, being sent back to the model.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "custom_tool_call_output"
+            ],
+            "x-stainless-const": true,
+            "description": "The type of the custom tool call output. Always `custom_tool_call_output`.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the custom tool call output in the OpenAI platform.\n"
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The call ID, used to map this custom tool call output to a custom tool call.\n"
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ToolCallCallerParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "output": {
+            "description": "The output from the custom tool call generated by your code.\nCan be a string or an list of output content.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "description": "A string of the output of the custom tool call.\n",
+                "title": "string output"
+              },
+              {
+                "type": "array",
+                "items": {
+                  "$ref": "#/components/schemas/FunctionAndCustomToolCallOutput"
+                },
+                "title": "output content list",
+                "description": "Text, image, or file output of the custom tool call.\n"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "call_id",
+          "output"
+        ]
+      },
+      "CustomToolCallOutputResource": {
+        "title": "ResponseCustomToolCallOutputItem",
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/CustomToolCallOutput"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the custom tool call output item.\n"
+              },
+              "status": {
+                "description": "The status of the item. One of `in_progress`, `completed`, or\n`incomplete`. Populated when items are returned via API.\n",
+                "$ref": "#/components/schemas/FunctionCallOutputStatusEnum"
+              },
+              "created_by": {
+                "type": "string",
+                "description": "The identifier of the actor that created the item.\n"
+              }
+            },
+            "required": [
+              "id",
+              "status"
+            ]
+          }
+        ]
+      },
+      "CustomToolCallResource": {
+        "title": "ResponseCustomToolCallItem",
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/CustomToolCall"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the custom tool call item.\n"
+              },
+              "status": {
+                "description": "The status of the item. One of `in_progress`, `completed`, or\n`incomplete`. Populated when items are returned via API.\n",
+                "$ref": "#/components/schemas/FunctionCallStatus"
+              },
+              "created_by": {
+                "type": "string",
+                "description": "The identifier of the actor that created the item.\n"
+              }
+            },
+            "required": [
+              "id",
+              "status"
+            ]
+          }
+        ]
+      },
+      "CustomToolChatCompletions": {
+        "type": "object",
+        "title": "Custom tool",
+        "description": "A custom tool that processes input using a specified format.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "custom"
+            ],
+            "description": "The type of the custom tool. Always `custom`.",
+            "x-stainless-const": true
+          },
+          "custom": {
+            "type": "object",
+            "title": "Custom tool properties",
+            "description": "Properties of the custom tool.\n",
+            "properties": {
+              "name": {
+                "type": "string",
+                "description": "The name of the custom tool, used to identify it in tool calls."
+              },
+              "description": {
+                "type": "string",
+                "description": "Optional description of the custom tool, used to provide more context.\n"
+              },
+              "format": {
+                "description": "The input format for the custom tool. Default is unconstrained text.\n",
+                "oneOf": [
+                  {
+                    "type": "object",
+                    "title": "Text format",
+                    "description": "Unconstrained free-form text.",
+                    "properties": {
+                      "type": {
+                        "type": "string",
+                        "enum": [
+                          "text"
+                        ],
+                        "description": "Unconstrained text format. Always `text`.",
+                        "x-stainless-const": true
+                      }
+                    },
+                    "required": [
+                      "type"
+                    ],
+                    "additionalProperties": false
+                  },
+                  {
+                    "type": "object",
+                    "title": "Grammar format",
+                    "description": "A grammar defined by the user.",
+                    "properties": {
+                      "type": {
+                        "type": "string",
+                        "enum": [
+                          "grammar"
+                        ],
+                        "description": "Grammar format. Always `grammar`.",
+                        "x-stainless-const": true
+                      },
+                      "grammar": {
+                        "type": "object",
+                        "title": "Grammar format",
+                        "description": "Your chosen grammar.",
+                        "properties": {
+                          "definition": {
+                            "type": "string",
+                            "description": "The grammar definition."
+                          },
+                          "syntax": {
+                            "type": "string",
+                            "description": "The syntax of the grammar definition. One of `lark` or `regex`.",
+                            "enum": [
+                              "lark",
+                              "regex"
+                            ]
+                          }
+                        },
+                        "required": [
+                          "definition",
+                          "syntax"
+                        ]
+                      }
+                    },
+                    "required": [
+                      "type",
+                      "grammar"
+                    ],
+                    "additionalProperties": false
+                  }
+                ]
+              }
+            },
+            "required": [
+              "name"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "custom"
+        ]
+      },
+      "DeleteAssistantResponse": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string"
+          },
+          "deleted": {
+            "type": "boolean"
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "assistant.deleted"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ]
+      },
+      "DeleteCertificateResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "description": "The object type, must be `certificate.deleted`.",
+            "enum": [
+              "certificate.deleted"
+            ],
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The ID of the certificate that was deleted."
+          }
+        },
+        "required": [
+          "object",
+          "id"
+        ]
+      },
+      "DeleteFileResponse": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string"
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "file"
+            ],
+            "x-stainless-const": true
+          },
+          "deleted": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ]
+      },
+      "DeleteFineTuningCheckpointPermissionResponse": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The ID of the fine-tuned model checkpoint permission that was deleted."
+          },
+          "object": {
+            "type": "string",
+            "description": "The object type, which is always \"checkpoint.permission\".",
+            "enum": [
+              "checkpoint.permission"
+            ],
+            "x-stainless-const": true
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the fine-tuned model checkpoint permission was successfully deleted."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ]
+      },
+      "DeleteMessageResponse": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string"
+          },
+          "deleted": {
+            "type": "boolean"
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "thread.message.deleted"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ]
+      },
+      "DeleteModelResponse": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string"
+          },
+          "deleted": {
+            "type": "boolean"
+          },
+          "object": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ]
+      },
+      "DeleteThreadResponse": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string"
+          },
+          "deleted": {
+            "type": "boolean"
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "thread.deleted"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ]
+      },
+      "DeleteVectorStoreFileResponse": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string"
+          },
+          "deleted": {
+            "type": "boolean"
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "vector_store.file.deleted"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ]
+      },
+      "DeleteVectorStoreResponse": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string"
+          },
+          "deleted": {
+            "type": "boolean"
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "vector_store.deleted"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ]
+      },
+      "DeletedConversation": {
+        "title": "The deleted conversation object",
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/DeletedConversationResource"
+          }
+        ],
+        "x-oaiMeta": {
+          "name": "The deleted conversation object",
+          "group": "conversations"
+        }
+      },
+      "DeletedRoleAssignmentResource": {
+        "type": "object",
+        "description": "Confirmation payload returned after unassigning a role.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "description": "Identifier for the deleted assignment, such as `group.role.deleted` or `user.role.deleted`."
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the assignment was removed."
+          }
+        },
+        "required": [
+          "object",
+          "deleted"
+        ],
+        "x-oaiMeta": {
+          "name": "Role assignment deletion confirmation",
+          "example": "{\n    \"object\": \"group.role.deleted\",\n    \"deleted\": true\n}\n"
+        }
+      },
+      "DoneEvent": {
+        "type": "object",
+        "properties": {
+          "event": {
+            "type": "string",
+            "enum": [
+              "done"
+            ],
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "string",
+            "enum": [
+              "[DONE]"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "event",
+          "data"
+        ],
+        "description": "Occurs when a stream ends.",
+        "x-oaiMeta": {
+          "dataDescription": "`data` is `[DONE]`"
+        }
+      },
+      "EasyInputMessage": {
+        "type": "object",
+        "title": "Input message",
+        "description": "A message input to the model with a role indicating instruction following\nhierarchy. Instructions given with the `developer` or `system` role take\nprecedence over instructions given with the `user` role. Messages with the\n`assistant` role are presumed to have been generated by the model in previous\ninteractions.\n",
+        "properties": {
+          "role": {
+            "type": "string",
+            "description": "The role of the message input. One of `user`, `assistant`, `system`, or\n`developer`.\n",
+            "enum": [
+              "user",
+              "assistant",
+              "system",
+              "developer"
+            ]
+          },
+          "content": {
+            "description": "Text, image, or audio input to the model, used to generate a response.\nCan also contain previous assistant responses.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "title": "Text input",
+                "description": "A text input to the model.\n"
+              },
+              {
+                "$ref": "#/components/schemas/InputMessageContentList"
+              }
+            ]
+          },
+          "phase": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/MessagePhase"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the message input. Always `message`.\n",
+            "enum": [
+              "message"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "role",
+          "content"
+        ]
+      },
+      "EditImageBodyJsonParam": {
+        "type": "object",
+        "description": "JSON request body for image edits.\n\nUse `images` (array of `ImageRefParam`) instead of multipart `image` uploads.\nYou can reference images via external URLs, data URLs, or uploaded file IDs.\nJSON edits support GPT image models only; DALL-E edits require multipart (`dall-e-2` only).\n",
+        "properties": {
+          "model": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "gpt-image-1.5",
+                  "gpt-image-2",
+                  "gpt-image-2-2026-04-21",
+                  "gpt-image-2.5-sunburst",
+                  "gpt-image-2.5-sunburst-2026-09-08",
+                  "gpt-image-2.5-flare",
+                  "gpt-image-2.5-flare-2026-09-08",
+                  "gpt-image-1",
+                  "gpt-image-1-mini",
+                  "chatgpt-image-latest"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "x-oaiTypeLabel": "string",
+            "default": "gpt-image-1.5",
+            "example": "gpt-image-1.5",
+            "description": "The GPT image model to use for image editing, including `gpt-image-2`, its dated snapshot `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, and `gpt-image-2.5-flare-2026-09-08`."
+          },
+          "images": {
+            "type": "array",
+            "minItems": 1,
+            "maxItems": 16,
+            "description": "Input image references to edit.\nFor GPT image models, you can provide up to 16 images.\n",
+            "items": {
+              "$ref": "#/components/schemas/ImageRefParam"
+            }
+          },
+          "mask": {
+            "$ref": "#/components/schemas/ImageRefParam"
+          },
+          "prompt": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 32000,
+            "example": "Add a watercolor effect and keep the subject centered",
+            "description": "A text description of the desired image edit."
+          },
+          "n": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "minimum": 1,
+                "maximum": 10
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": 1,
+            "example": 1,
+            "description": "The number of edited images to generate."
+          },
+          "quality": {
+            "anyOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "low",
+                  "medium",
+                  "high",
+                  "xhigh",
+                  "max",
+                  "auto"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": "auto",
+            "example": "high",
+            "description": "Output quality for GPT image models. The GPT image models support `low`, `medium`,\nand `high`. `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`, including their\n`2026-09-08` snapshots, also support `xhigh` and `max`. Defaults to `auto`.\n"
+          },
+          "input_fidelity": {
+            "anyOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "high",
+                  "low"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Controls fidelity to the original input image(s)."
+          },
+          "size": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "auto",
+                  "1024x1024",
+                  "1536x1024",
+                  "1024x1536"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": "auto",
+            "example": "1024x1024",
+            "description": "The size of the generated images. For `gpt-image-2`, `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, and `gpt-image-2.5-flare-2026-09-08`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing."
+          },
+          "user": {
+            "type": "string",
+            "example": "user-1234",
+            "description": "A unique identifier representing your end-user, which can help OpenAI\nmonitor and detect abuse.\n"
+          },
+          "output_format": {
+            "anyOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "png",
+                  "jpeg",
+                  "webp"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": "png",
+            "example": "png",
+            "description": "Output image format. Supported for GPT image models."
+          },
+          "output_compression": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "minimum": 0,
+                "maximum": 100
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "example": 100,
+            "description": "Compression level for `jpeg` or `webp` output."
+          },
+          "moderation": {
+            "anyOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "low",
+                  "auto"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": "auto",
+            "example": "auto",
+            "description": "Moderation level for GPT image models."
+          },
+          "background": {
+            "anyOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "transparent",
+                  "opaque",
+                  "auto"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": "auto",
+            "example": "transparent",
+            "description": "Set the background of the generated image output. `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`, including their `2026-09-08` snapshots, support `opaque` and `transparent` backgrounds. Transparent backgrounds are available for supported GPT Image models. For `gpt-image-2` and `gpt-image-2-2026-04-21`, this support is in preview. When using `transparent`, set the output format to `png` or `webp`."
+          },
+          "stream": {
+            "anyOf": [
+              {
+                "type": "boolean"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": false,
+            "example": false,
+            "description": "Stream partial image results as events."
+          },
+          "partial_images": {
+            "$ref": "#/components/schemas/PartialImages"
+          }
+        },
+        "required": [
+          "images",
+          "prompt"
+        ]
+      },
+      "Embedding": {
+        "type": "object",
+        "description": "Represents an embedding vector returned by embedding endpoint.\n",
+        "properties": {
+          "index": {
+            "type": "integer",
+            "description": "The index of the embedding in the list of embeddings."
+          },
+          "embedding": {
+            "type": "array",
+            "description": "The embedding vector, which is a list of floats. The length of vector depends on the model as listed in the [embedding guide](https://developers.openai.com/api/docs/guides/embeddings).\n",
+            "items": {
+              "type": "number",
+              "format": "float"
+            }
+          },
+          "object": {
+            "type": "string",
+            "description": "The object type, which is always \"embedding\".",
+            "enum": [
+              "embedding"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "index",
+          "object",
+          "embedding"
+        ],
+        "x-oaiMeta": {
+          "name": "The embedding object",
+          "example": "{\n  \"object\": \"embedding\",\n  \"embedding\": [\n    0.0023064255,\n    -0.009327292,\n    .... (1536 floats total for ada-002)\n    -0.0028842222,\n  ],\n  \"index\": 0\n}\n"
+        }
+      },
+      "Error": {
+        "type": "object",
+        "properties": {
+          "code": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "message": {
+            "type": "string"
+          },
+          "param": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string"
+          },
+          "misalignment": {
+            "$ref": "#/components/schemas/MisalignmentErrorDetailsResource"
+          }
+        },
+        "required": [
+          "type",
+          "message",
+          "param",
+          "code"
+        ]
+      },
+      "ErrorEvent": {
+        "type": "object",
+        "properties": {
+          "event": {
+            "type": "string",
+            "enum": [
+              "error"
+            ],
+            "x-stainless-const": true
+          },
+          "data": {
+            "$ref": "#/components/schemas/Error"
+          }
+        },
+        "required": [
+          "event",
+          "data"
+        ],
+        "description": "Occurs when an [error](https://developers.openai.com/api/docs/guides/error-codes#api-errors) occurs. This can happen due to an internal server error or a timeout.",
+        "x-oaiMeta": {
+          "dataDescription": "`data` is an [error](https://developers.openai.com/api/docs/guides/error-codes#api-errors)"
+        }
+      },
+      "ErrorResponse": {
+        "type": "object",
+        "properties": {
+          "error": {
+            "$ref": "#/components/schemas/Error"
+          }
+        },
+        "required": [
+          "error"
+        ]
+      },
+      "Eval": {
+        "type": "object",
+        "title": "Eval",
+        "description": "An Eval object with a data source config and testing criteria.\nAn Eval represents a task to be done for your LLM integration.\nLike:\n - Improve the quality of my chatbot\n - See how well my chatbot handles customer support\n - Check if o4-mini is better at my usecase than gpt-6-astra\n",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "eval"
+            ],
+            "default": "eval",
+            "description": "The object type.",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "Unique identifier for the evaluation."
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the evaluation.",
+            "example": "Chatbot effectiveness Evaluation"
+          },
+          "data_source_config": {
+            "type": "object",
+            "description": "Configuration of data sources used in runs of the evaluation.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/EvalCustomDataSourceConfig"
+              },
+              {
+                "$ref": "#/components/schemas/EvalLogsDataSourceConfig"
+              },
+              {
+                "$ref": "#/components/schemas/EvalStoredCompletionsDataSourceConfig"
+              }
+            ]
+          },
+          "testing_criteria": {
+            "description": "A list of testing criteria.",
+            "type": "array",
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/EvalGraderLabelModel"
+                },
+                {
+                  "$ref": "#/components/schemas/EvalGraderStringCheck"
+                },
+                {
+                  "$ref": "#/components/schemas/EvalGraderTextSimilarity"
+                },
+                {
+                  "$ref": "#/components/schemas/EvalGraderPython"
+                },
+                {
+                  "$ref": "#/components/schemas/EvalGraderScoreModel"
+                }
+              ]
+            }
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the eval was created."
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          }
+        },
+        "required": [
+          "id",
+          "data_source_config",
+          "object",
+          "testing_criteria",
+          "name",
+          "created_at",
+          "metadata"
+        ],
+        "x-oaiMeta": {
+          "name": "The eval object",
+          "group": "evals",
+          "example": "{\n  \"object\": \"eval\",\n  \"id\": \"eval_67abd54d9b0081909a86353f6fb9317a\",\n  \"data_source_config\": {\n    \"type\": \"custom\",\n    \"item_schema\": {\n      \"type\": \"object\",\n      \"properties\": {\n        \"label\": {\"type\": \"string\"},\n      },\n      \"required\": [\"label\"]\n    },\n    \"include_sample_schema\": true\n  },\n  \"testing_criteria\": [\n    {\n      \"name\": \"My string check grader\",\n      \"type\": \"string_check\",\n      \"input\": \"{{sample.output_text}}\",\n      \"reference\": \"{{item.label}}\",\n      \"operation\": \"eq\",\n    }\n  ],\n  \"name\": \"External Data Eval\",\n  \"created_at\": 1739314509,\n  \"metadata\": {\n    \"test\": \"synthetics\",\n  }\n}\n"
+        }
+      },
+      "EvalApiError": {
+        "type": "object",
+        "title": "EvalApiError",
+        "description": "An object representing an error response from the Eval API.\n",
+        "properties": {
+          "code": {
+            "type": "string",
+            "description": "The error code."
+          },
+          "message": {
+            "type": "string",
+            "description": "The error message."
+          }
+        },
+        "required": [
+          "code",
+          "message"
+        ],
+        "x-oaiMeta": {
+          "name": "The API error object",
+          "group": "evals",
+          "example": "{\n  \"code\": \"internal_error\",\n  \"message\": \"The eval run failed due to an internal error.\"\n}\n"
+        }
+      },
+      "EvalCustomDataSourceConfig": {
+        "type": "object",
+        "title": "CustomDataSourceConfig",
+        "description": "A CustomDataSourceConfig which specifies the schema of your `item` and optionally `sample` namespaces.\nThe response schema defines the shape of the data that will be:\n- Used to define your testing criteria and\n- What data is required when creating a run\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "custom"
+            ],
+            "default": "custom",
+            "description": "The type of data source. Always `custom`.",
+            "x-stainless-const": true
+          },
+          "schema": {
+            "type": "object",
+            "description": "The json schema for the run data source items.\nLearn how to build JSON schemas [here](https://json-schema.org/).\n",
+            "additionalProperties": true,
+            "example": "{\n  \"type\": \"object\",\n  \"properties\": {\n    \"item\": {\n      \"type\": \"object\",\n      \"properties\": {\n        \"label\": {\"type\": \"string\"},\n      },\n      \"required\": [\"label\"]\n    }\n  },\n  \"required\": [\"item\"]\n}\n"
+          }
+        },
+        "required": [
+          "type",
+          "schema"
+        ],
+        "x-oaiMeta": {
+          "name": "The eval custom data source config object",
+          "group": "evals",
+          "example": "{\n  \"type\": \"custom\",\n  \"schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"item\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"label\": {\"type\": \"string\"},\n        },\n        \"required\": [\"label\"]\n      }\n    },\n    \"required\": [\"item\"]\n  }\n}\n"
+        }
+      },
+      "EvalGraderLabelModel": {
+        "type": "object",
+        "title": "LabelModelGrader",
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/GraderLabelModel"
+          }
+        ]
+      },
+      "EvalGraderPython": {
+        "type": "object",
+        "title": "PythonGrader",
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/GraderPython"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "pass_threshold": {
+                "type": "number",
+                "description": "The threshold for the score."
+              }
+            },
+            "x-oaiMeta": {
+              "name": "Eval Python Grader",
+              "group": "graders",
+              "example": "{\n  \"type\": \"python\",\n  \"name\": \"Example python grader\",\n  \"image_tag\": \"2025-05-08\",\n  \"source\": \"\"\"\ndef grade(sample: dict, item: dict) -> float:\n    \\\"\"\"\n    Returns 1.0 if `output_text` equals `label`, otherwise 0.0.\n    \\\"\"\"\n    output = sample.get(\"output_text\")\n    label = item.get(\"label\")\n    return 1.0 if output == label else 0.0\n\"\"\",\n  \"pass_threshold\": 0.8\n}\n"
+            }
+          }
+        ]
+      },
+      "EvalGraderScoreModel": {
+        "type": "object",
+        "title": "ScoreModelGrader",
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/GraderScoreModel"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "pass_threshold": {
+                "type": "number",
+                "description": "The threshold for the score."
+              }
+            }
+          }
+        ]
+      },
+      "EvalGraderStringCheck": {
+        "type": "object",
+        "title": "StringCheckGrader",
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/GraderStringCheck"
+          }
+        ]
+      },
+      "EvalGraderTextSimilarity": {
+        "type": "object",
+        "title": "TextSimilarityGrader",
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/GraderTextSimilarity"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "pass_threshold": {
+                "type": "number",
+                "description": "The threshold for the score."
+              }
+            },
+            "required": [
+              "pass_threshold"
+            ],
+            "x-oaiMeta": {
+              "name": "Text Similarity Grader",
+              "group": "graders",
+              "example": "{\n  \"type\": \"text_similarity\",\n  \"name\": \"Example text similarity grader\",\n  \"input\": \"{{sample.output_text}}\",\n  \"reference\": \"{{item.label}}\",\n  \"pass_threshold\": 0.8,\n  \"evaluation_metric\": \"fuzzy_match\"\n}\n"
+            }
+          }
+        ]
+      },
+      "EvalItem": {
+        "type": "object",
+        "title": "Eval message object",
+        "description": "A message input to the model with a role indicating instruction following\nhierarchy. Instructions given with the `developer` or `system` role take\nprecedence over instructions given with the `user` role. Messages with the\n`assistant` role are presumed to have been generated by the model in previous\ninteractions.\n",
+        "properties": {
+          "role": {
+            "type": "string",
+            "description": "The role of the message input. One of `user`, `assistant`, `system`, or\n`developer`.\n",
+            "enum": [
+              "user",
+              "assistant",
+              "system",
+              "developer"
+            ]
+          },
+          "content": {
+            "$ref": "#/components/schemas/EvalItemContent"
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the message input. Always `message`.\n",
+            "enum": [
+              "message"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "role",
+          "content"
+        ]
+      },
+      "EvalItemContent": {
+        "title": "Eval content",
+        "description": "Inputs to the model - can contain template strings. Supports text, output text, input images, and input audio, either as a single item or an array of items.\n",
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/EvalItemContentItem"
+          },
+          {
+            "$ref": "#/components/schemas/EvalItemContentArray"
+          }
+        ]
+      },
+      "EvalItemContentArray": {
+        "type": "array",
+        "title": "An array of Input text, Output text, Input image, and Input audio",
+        "description": "A list of inputs, each of which may be either an input text, output text, input\nimage, or input audio object.\n",
+        "items": {
+          "$ref": "#/components/schemas/EvalItemContentItem"
+        }
+      },
+      "EvalItemContentItem": {
+        "title": "Eval content item",
+        "description": "A single content item: input text, output text, input image, or input audio.\n",
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/EvalItemContentText"
+          },
+          {
+            "$ref": "#/components/schemas/InputTextContent"
+          },
+          {
+            "$ref": "#/components/schemas/EvalItemContentOutputText"
+          },
+          {
+            "$ref": "#/components/schemas/EvalItemInputImage"
+          },
+          {
+            "$ref": "#/components/schemas/InputAudio"
+          }
+        ]
+      },
+      "EvalItemContentOutputText": {
+        "type": "object",
+        "title": "Output text",
+        "description": "A text output from the model.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the output text. Always `output_text`.\n",
+            "enum": [
+              "output_text"
+            ],
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string",
+            "description": "The text output from the model.\n"
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ]
+      },
+      "EvalItemContentText": {
+        "type": "string",
+        "title": "Text input",
+        "description": "A text input to the model.\n"
+      },
+      "EvalItemInputImage": {
+        "title": "Input image",
+        "description": "An image input block used within EvalItem content arrays.",
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the image input. Always `input_image`.\n",
+            "enum": [
+              "input_image"
+            ],
+            "x-stainless-const": true
+          },
+          "image_url": {
+            "type": "string",
+            "format": "uri",
+            "description": "The URL of the image input.\n"
+          },
+          "detail": {
+            "type": "string",
+            "description": "The detail level of the image to be sent to the model. One of `high`, `low`, or `auto`. Defaults to `auto`.\n"
+          }
+        },
+        "required": [
+          "type",
+          "image_url"
+        ]
+      },
+      "EvalJsonlFileContentSource": {
+        "type": "object",
+        "title": "EvalJsonlFileContentSource",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "file_content"
+            ],
+            "default": "file_content",
+            "description": "The type of jsonl source. Always `file_content`.",
+            "x-stainless-const": true
+          },
+          "content": {
+            "type": "array",
+            "items": {
+              "type": "object",
+              "properties": {
+                "item": {
+                  "type": "object",
+                  "additionalProperties": true
+                },
+                "sample": {
+                  "type": "object",
+                  "additionalProperties": true
+                }
+              },
+              "required": [
+                "item"
+              ]
+            },
+            "description": "The content of the jsonl file."
+          }
+        },
+        "required": [
+          "type",
+          "content"
+        ]
+      },
+      "EvalJsonlFileIdSource": {
+        "type": "object",
+        "title": "EvalJsonlFileIdSource",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "file_id"
+            ],
+            "default": "file_id",
+            "description": "The type of jsonl source. Always `file_id`.",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The identifier of the file."
+          }
+        },
+        "required": [
+          "type",
+          "id"
+        ]
+      },
+      "EvalList": {
+        "type": "object",
+        "title": "EvalList",
+        "description": "An object representing a list of evals.\n",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "description": "The type of this object. It is always set to \"list\".\n",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "description": "An array of eval objects.\n",
+            "items": {
+              "$ref": "#/components/schemas/Eval"
+            }
+          },
+          "first_id": {
+            "type": "string",
+            "description": "The identifier of the first eval in the data array."
+          },
+          "last_id": {
+            "type": "string",
+            "description": "The identifier of the last eval in the data array."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Indicates whether there are more evals available."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "x-oaiMeta": {
+          "name": "The eval list object",
+          "group": "evals",
+          "example": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\": \"eval\",\n      \"id\": \"eval_67abd54d9b0081909a86353f6fb9317a\",\n      \"data_source_config\": {\n        \"type\": \"custom\",\n        \"schema\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"item\": {\n              \"type\": \"object\",\n              \"properties\": {\n                \"input\": {\n                  \"type\": \"string\"\n                },\n                \"ground_truth\": {\n                  \"type\": \"string\"\n                }\n              },\n              \"required\": [\n                \"input\",\n                \"ground_truth\"\n              ]\n            }\n          },\n          \"required\": [\n            \"item\"\n          ]\n        }\n      },\n      \"testing_criteria\": [\n        {\n          \"name\": \"String check\",\n          \"id\": \"String check-2eaf2d8d-d649-4335-8148-9535a7ca73c2\",\n          \"type\": \"string_check\",\n          \"input\": \"{{item.input}}\",\n          \"reference\": \"{{item.ground_truth}}\",\n          \"operation\": \"eq\"\n        }\n      ],\n      \"name\": \"External Data Eval\",\n      \"created_at\": 1739314509,\n      \"metadata\": {},\n    }\n  ],\n  \"first_id\": \"eval_67abd54d9b0081909a86353f6fb9317a\",\n  \"last_id\": \"eval_67abd54d9b0081909a86353f6fb9317a\",\n  \"has_more\": true\n}\n"
+        }
+      },
+      "EvalLogsDataSourceConfig": {
+        "type": "object",
+        "title": "LogsDataSourceConfig",
+        "description": "A LogsDataSourceConfig which specifies the metadata property of your logs query.\nThis is usually metadata like `usecase=chatbot` or `prompt-version=v2`, etc.\nThe schema returned by this data source config is used to defined what variables are available in your evals.\n`item` and `sample` are both defined when using this data source config.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "logs"
+            ],
+            "default": "logs",
+            "description": "The type of data source. Always `logs`.",
+            "x-stainless-const": true
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          },
+          "schema": {
+            "type": "object",
+            "description": "The json schema for the run data source items.\nLearn how to build JSON schemas [here](https://json-schema.org/).\n",
+            "additionalProperties": true
+          }
+        },
+        "required": [
+          "type",
+          "schema"
+        ],
+        "x-oaiMeta": {
+          "name": "The logs data source object for evals",
+          "group": "evals",
+          "example": "{\n  \"type\": \"logs\",\n  \"metadata\": {\n    \"language\": \"english\"\n  },\n  \"schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"item\": {\n        \"type\": \"object\"\n      },\n      \"sample\": {\n        \"type\": \"object\"\n      }\n    },\n    \"required\": [\n      \"item\",\n      \"sample\"\n    }\n}\n"
+        }
+      },
+      "EvalResponsesSource": {
+        "type": "object",
+        "title": "EvalResponsesSource",
+        "description": "A EvalResponsesSource object describing a run data source configuration.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "responses"
+            ],
+            "description": "The type of run data source. Always `responses`."
+          },
+          "metadata": {
+            "anyOf": [
+              {
+                "type": "object",
+                "description": "Metadata filter for the responses. This is a query parameter used to select responses."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "model": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The name of the model to find responses for. This is a query parameter used to select responses."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "instructions_search": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Optional string to search the 'instructions' field. This is a query parameter used to select responses."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "created_after": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "minimum": 0,
+                "description": "Only include items created after this timestamp (inclusive). This is a query parameter used to select responses."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "created_before": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "minimum": 0,
+                "description": "Only include items created before this timestamp (inclusive). This is a query parameter used to select responses."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "reasoning_effort": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ReasoningEffort",
+                "description": "Optional reasoning effort parameter. This is a query parameter used to select responses."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "temperature": {
+            "anyOf": [
+              {
+                "type": "number",
+                "description": "Sampling temperature. This is a query parameter used to select responses."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "top_p": {
+            "anyOf": [
+              {
+                "type": "number",
+                "description": "Nucleus sampling parameter. This is a query parameter used to select responses."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "users": {
+            "anyOf": [
+              {
+                "type": "array",
+                "items": {
+                  "type": "string"
+                },
+                "description": "List of user identifiers. This is a query parameter used to select responses."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "tools": {
+            "anyOf": [
+              {
+                "type": "array",
+                "items": {
+                  "type": "string"
+                },
+                "description": "List of tool names. This is a query parameter used to select responses."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "x-oaiMeta": {
+          "name": "The run data source object used to configure an individual run",
+          "group": "eval runs",
+          "example": "{\n  \"type\": \"responses\",\n  \"model\": \"gpt-6-astra\",\n  \"users\": [\"user1\", \"user2\"],\n  \"tools\": [\"tool1\", \"tool2\"],\n  \"instructions_search\": \"You are a coding assistant\"\n}\n"
+        }
+      },
+      "EvalRun": {
+        "type": "object",
+        "title": "EvalRun",
+        "description": "A schema representing an evaluation run.\n",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "eval.run"
+            ],
+            "default": "eval.run",
+            "description": "The type of the object. Always \"eval.run\".",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "Unique identifier for the evaluation run."
+          },
+          "eval_id": {
+            "type": "string",
+            "description": "The identifier of the associated evaluation."
+          },
+          "status": {
+            "type": "string",
+            "description": "The status of the evaluation run."
+          },
+          "model": {
+            "type": "string",
+            "description": "The model that is evaluated, if applicable."
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the evaluation run."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (in seconds) when the evaluation run was created."
+          },
+          "report_url": {
+            "type": "string",
+            "format": "uri",
+            "description": "The URL to the rendered evaluation run report on the UI dashboard."
+          },
+          "result_counts": {
+            "type": "object",
+            "description": "Counters summarizing the outcomes of the evaluation run.",
+            "properties": {
+              "total": {
+                "type": "integer",
+                "description": "Total number of executed output items."
+              },
+              "errored": {
+                "type": "integer",
+                "description": "Number of output items that resulted in an error."
+              },
+              "failed": {
+                "type": "integer",
+                "description": "Number of output items that failed to pass the evaluation."
+              },
+              "passed": {
+                "type": "integer",
+                "description": "Number of output items that passed the evaluation."
+              }
+            },
+            "required": [
+              "total",
+              "errored",
+              "failed",
+              "passed"
+            ]
+          },
+          "per_model_usage": {
+            "type": "array",
+            "description": "Usage statistics for each model during the evaluation run.",
+            "items": {
+              "type": "object",
+              "properties": {
+                "model_name": {
+                  "type": "string",
+                  "description": "The name of the model."
+                },
+                "invocation_count": {
+                  "type": "integer",
+                  "description": "The number of invocations."
+                },
+                "prompt_tokens": {
+                  "type": "integer",
+                  "description": "The number of prompt tokens used."
+                },
+                "completion_tokens": {
+                  "type": "integer",
+                  "description": "The number of completion tokens generated."
+                },
+                "total_tokens": {
+                  "type": "integer",
+                  "description": "The total number of tokens used."
+                },
+                "cached_tokens": {
+                  "type": "integer",
+                  "description": "The number of tokens retrieved from cache."
+                }
+              },
+              "required": [
+                "model_name",
+                "invocation_count",
+                "prompt_tokens",
+                "completion_tokens",
+                "total_tokens",
+                "cached_tokens"
+              ]
+            }
+          },
+          "per_testing_criteria_results": {
+            "type": "array",
+            "description": "Results per testing criteria applied during the evaluation run.",
+            "items": {
+              "type": "object",
+              "properties": {
+                "testing_criteria": {
+                  "type": "string",
+                  "description": "A description of the testing criteria."
+                },
+                "passed": {
+                  "type": "integer",
+                  "description": "Number of tests passed for this criteria."
+                },
+                "failed": {
+                  "type": "integer",
+                  "description": "Number of tests failed for this criteria."
+                }
+              },
+              "required": [
+                "testing_criteria",
+                "passed",
+                "failed"
+              ]
+            }
+          },
+          "data_source": {
+            "type": "object",
+            "description": "Information about the run's data source.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/CreateEvalJsonlRunDataSource"
+              },
+              {
+                "$ref": "#/components/schemas/CreateEvalCompletionsRunDataSource"
+              },
+              {
+                "$ref": "#/components/schemas/CreateEvalResponsesRunDataSource"
+              }
+            ]
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          },
+          "error": {
+            "$ref": "#/components/schemas/EvalApiError"
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "eval_id",
+          "status",
+          "model",
+          "name",
+          "created_at",
+          "report_url",
+          "result_counts",
+          "per_model_usage",
+          "per_testing_criteria_results",
+          "data_source",
+          "metadata",
+          "error"
+        ],
+        "x-oaiMeta": {
+          "name": "The eval run object",
+          "group": "evals",
+          "example": "{\n  \"object\": \"eval.run\",\n  \"id\": \"evalrun_67e57965b480819094274e3a32235e4c\",\n  \"eval_id\": \"eval_67e579652b548190aaa83ada4b125f47\",\n  \"report_url\": \"https://platform.openai.com/evaluations/eval_67e579652b548190aaa83ada4b125f47?run_id=evalrun_67e57965b480819094274e3a32235e4c\",\n  \"status\": \"queued\",\n  \"model\": \"gpt-6-astra\",\n  \"name\": \"gpt-6-astra\",\n  \"created_at\": 1743092069,\n  \"result_counts\": {\n    \"total\": 0,\n    \"errored\": 0,\n    \"failed\": 0,\n    \"passed\": 0\n  },\n  \"per_model_usage\": null,\n  \"per_testing_criteria_results\": null,\n  \"data_source\": {\n    \"type\": \"completions\",\n    \"source\": {\n      \"type\": \"file_content\",\n      \"content\": [\n        {\n          \"item\": {\n            \"input\": \"Tech Company Launches Advanced Artificial Intelligence Platform\",\n            \"ground_truth\": \"Technology\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Central Bank Increases Interest Rates Amid Inflation Concerns\",\n            \"ground_truth\": \"Markets\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"International Summit Addresses Climate Change Strategies\",\n            \"ground_truth\": \"World\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Major Retailer Reports Record-Breaking Holiday Sales\",\n            \"ground_truth\": \"Business\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"National Team Qualifies for World Championship Finals\",\n            \"ground_truth\": \"Sports\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Stock Markets Rally After Positive Economic Data Released\",\n            \"ground_truth\": \"Markets\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Global Manufacturer Announces Merger with Competitor\",\n            \"ground_truth\": \"Business\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Breakthrough in Renewable Energy Technology Unveiled\",\n            \"ground_truth\": \"Technology\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"World Leaders Sign Historic Climate Agreement\",\n            \"ground_truth\": \"World\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Professional Athlete Sets New Record in Championship Event\",\n            \"ground_truth\": \"Sports\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Financial Institutions Adapt to New Regulatory Requirements\",\n            \"ground_truth\": \"Business\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Tech Conference Showcases Advances in Artificial Intelligence\",\n            \"ground_truth\": \"Technology\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Global Markets Respond to Oil Price Fluctuations\",\n            \"ground_truth\": \"Markets\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"International Cooperation Strengthened Through New Treaty\",\n            \"ground_truth\": \"World\"\n          }\n        },\n        {\n          \"item\": {\n            \"input\": \"Sports League Announces Revised Schedule for Upcoming Season\",\n            \"ground_truth\": \"Sports\"\n          }\n        }\n      ]\n    },\n    \"input_messages\": {\n      \"type\": \"template\",\n      \"template\": [\n        {\n          \"type\": \"message\",\n          \"role\": \"developer\",\n          \"content\": {\n            \"type\": \"input_text\",\n            \"text\": \"Categorize a given news headline into one of the following topics: Technology, Markets, World, Business, or Sports.\\n\\n# Steps\\n\\n1. Analyze the content of the news headline to understand its primary focus.\\n2. Extract the subject matter, identifying any key indicators or keywords.\\n3. Use the identified indicators to determine the most suitable category out of the five options: Technology, Markets, World, Business, or Sports.\\n4. Ensure only one category is selected per headline.\\n\\n# Output Format\\n\\nRespond with the chosen category as a single word. For instance: \\\"Technology\\\", \\\"Markets\\\", \\\"World\\\", \\\"Business\\\", or \\\"Sports\\\".\\n\\n# Examples\\n\\n**Input**: \\\"Apple Unveils New iPhone Model, Featuring Advanced AI Features\\\"  \\n**Output**: \\\"Technology\\\"\\n\\n**Input**: \\\"Global Stocks Mixed as Investors Await Central Bank Decisions\\\"  \\n**Output**: \\\"Markets\\\"\\n\\n**Input**: \\\"War in Ukraine: Latest Updates on Negotiation Status\\\"  \\n**Output**: \\\"World\\\"\\n\\n**Input**: \\\"Microsoft in Talks to Acquire Gaming Company for $2 Billion\\\"  \\n**Output**: \\\"Business\\\"\\n\\n**Input**: \\\"Manchester United Secures Win in Premier League Football Match\\\"  \\n**Output**: \\\"Sports\\\" \\n\\n# Notes\\n\\n- If the headline appears to fit into more than one category, choose the most dominant theme.\\n- Keywords or phrases such as \\\"stocks\\\", \\\"company acquisition\\\", \\\"match\\\", or technological brands can be good indicators for classification.\\n\"\n          }\n        },\n        {\n          \"type\": \"message\",\n          \"role\": \"user\",\n          \"content\": {\n            \"type\": \"input_text\",\n            \"text\": \"{{item.input}}\"\n          }\n        }\n      ]\n    },\n    \"model\": \"gpt-6-astra\",\n    \"sampling_params\": {\n      \"max_completions_tokens\": 2048\n    }\n  },\n  \"error\": null,\n  \"metadata\": {}\n}\n"
+        }
+      },
+      "EvalRunList": {
+        "type": "object",
+        "title": "EvalRunList",
+        "description": "An object representing a list of runs for an evaluation.\n",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "description": "The type of this object. It is always set to \"list\".\n",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "description": "An array of eval run objects.\n",
+            "items": {
+              "$ref": "#/components/schemas/EvalRun"
+            }
+          },
+          "first_id": {
+            "type": "string",
+            "description": "The identifier of the first eval run in the data array."
+          },
+          "last_id": {
+            "type": "string",
+            "description": "The identifier of the last eval run in the data array."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Indicates whether there are more evals available."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "x-oaiMeta": {
+          "name": "The eval run list object",
+          "group": "evals",
+          "example": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\": \"eval.run\",\n      \"id\": \"evalrun_67b7fbdad46c819092f6fe7a14189620\",\n      \"eval_id\": \"eval_67b7fa9a81a88190ab4aa417e397ea21\",\n      \"report_url\": \"https://platform.openai.com/evaluations/eval_67b7fa9a81a88190ab4aa417e397ea21?run_id=evalrun_67b7fbdad46c819092f6fe7a14189620\",\n      \"status\": \"completed\",\n      \"model\": \"o3-mini\",\n      \"name\": \"Academic Assistant\",\n      \"created_at\": 1740110812,\n      \"result_counts\": {\n        \"total\": 171,\n        \"errored\": 0,\n        \"failed\": 80,\n        \"passed\": 91\n      },\n      \"per_model_usage\": null,\n      \"per_testing_criteria_results\": [\n        {\n          \"testing_criteria\": \"String check grader\",\n          \"passed\": 91,\n          \"failed\": 80\n        }\n      ],\n      \"run_data_source\": {\n        \"type\": \"completions\",\n        \"template_messages\": [\n          {\n            \"type\": \"message\",\n            \"role\": \"system\",\n            \"content\": {\n              \"type\": \"input_text\",\n              \"text\": \"You are a helpful assistant.\"\n            }\n          },\n          {\n            \"type\": \"message\",\n            \"role\": \"user\",\n            \"content\": {\n              \"type\": \"input_text\",\n              \"text\": \"Hello, can you help me with my homework?\"\n            }\n          }\n        ],\n        \"datasource_reference\": null,\n        \"model\": \"o3-mini\",\n        \"max_completion_tokens\": null,\n        \"seed\": null,\n        \"temperature\": null,\n        \"top_p\": null\n      },\n      \"error\": null,\n      \"metadata\": {\"test\": \"synthetics\"}\n    }\n  ],\n  \"first_id\": \"evalrun_67abd54d60ec8190832b46859da808f7\",\n  \"last_id\": \"evalrun_67abd54d60ec8190832b46859da808f7\",\n  \"has_more\": false\n}\n"
+        }
+      },
+      "EvalRunOutputItem": {
+        "type": "object",
+        "title": "EvalRunOutputItem",
+        "description": "A schema representing an evaluation run output item.\n",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "eval.run.output_item"
+            ],
+            "default": "eval.run.output_item",
+            "description": "The type of the object. Always \"eval.run.output_item\".",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "Unique identifier for the evaluation run output item."
+          },
+          "run_id": {
+            "type": "string",
+            "description": "The identifier of the evaluation run associated with this output item."
+          },
+          "eval_id": {
+            "type": "string",
+            "description": "The identifier of the evaluation group."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (in seconds) when the evaluation run was created."
+          },
+          "status": {
+            "type": "string",
+            "description": "The status of the evaluation run."
+          },
+          "datasource_item_id": {
+            "type": "integer",
+            "description": "The identifier for the data source item."
+          },
+          "datasource_item": {
+            "type": "object",
+            "description": "Details of the input data source item.",
+            "additionalProperties": true
+          },
+          "results": {
+            "type": "array",
+            "description": "A list of grader results for this output item.",
+            "items": {
+              "$ref": "#/components/schemas/EvalRunOutputItemResult"
+            }
+          },
+          "sample": {
+            "type": "object",
+            "description": "A sample containing the input and output of the evaluation run.",
+            "properties": {
+              "input": {
+                "type": "array",
+                "description": "An array of input messages.",
+                "items": {
+                  "type": "object",
+                  "description": "An input message.",
+                  "properties": {
+                    "role": {
+                      "type": "string",
+                      "description": "The role of the message sender (e.g., system, user, developer)."
+                    },
+                    "content": {
+                      "type": "string",
+                      "description": "The content of the message."
+                    }
+                  },
+                  "required": [
+                    "role",
+                    "content"
+                  ]
+                }
+              },
+              "output": {
+                "type": "array",
+                "description": "An array of output messages.",
+                "items": {
+                  "type": "object",
+                  "properties": {
+                    "role": {
+                      "type": "string",
+                      "description": "The role of the message (e.g. \"system\", \"assistant\", \"user\")."
+                    },
+                    "content": {
+                      "type": "string",
+                      "description": "The content of the message."
+                    }
+                  }
+                }
+              },
+              "finish_reason": {
+                "type": "string",
+                "description": "The reason why the sample generation was finished."
+              },
+              "model": {
+                "type": "string",
+                "description": "The model used for generating the sample."
+              },
+              "usage": {
+                "type": "object",
+                "description": "Token usage details for the sample.",
+                "properties": {
+                  "total_tokens": {
+                    "type": "integer",
+                    "description": "The total number of tokens used."
+                  },
+                  "completion_tokens": {
+                    "type": "integer",
+                    "description": "The number of completion tokens generated."
+                  },
+                  "prompt_tokens": {
+                    "type": "integer",
+                    "description": "The number of prompt tokens used."
+                  },
+                  "cached_tokens": {
+                    "type": "integer",
+                    "description": "The number of tokens retrieved from cache."
+                  }
+                },
+                "required": [
+                  "total_tokens",
+                  "completion_tokens",
+                  "prompt_tokens",
+                  "cached_tokens"
+                ]
+              },
+              "error": {
+                "$ref": "#/components/schemas/EvalApiError"
+              },
+              "temperature": {
+                "type": "number",
+                "description": "The sampling temperature used."
+              },
+              "max_completion_tokens": {
+                "type": "integer",
+                "description": "The maximum number of tokens allowed for completion."
+              },
+              "top_p": {
+                "type": "number",
+                "description": "The top_p value used for sampling."
+              },
+              "seed": {
+                "type": "integer",
+                "description": "The seed used for generating the sample."
+              }
+            },
+            "required": [
+              "input",
+              "output",
+              "finish_reason",
+              "model",
+              "usage",
+              "error",
+              "temperature",
+              "max_completion_tokens",
+              "top_p",
+              "seed"
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "run_id",
+          "eval_id",
+          "created_at",
+          "status",
+          "datasource_item_id",
+          "datasource_item",
+          "results",
+          "sample"
+        ],
+        "x-oaiMeta": {
+          "name": "The eval run output item object",
+          "group": "evals",
+          "example": "{\n  \"object\": \"eval.run.output_item\",\n  \"id\": \"outputitem_67abd55eb6548190bb580745d5644a33\",\n  \"run_id\": \"evalrun_67abd54d60ec8190832b46859da808f7\",\n  \"eval_id\": \"eval_67abd54d9b0081909a86353f6fb9317a\",\n  \"created_at\": 1739314509,\n  \"status\": \"pass\",\n  \"datasource_item_id\": 137,\n  \"datasource_item\": {\n      \"teacher\": \"To grade essays, I only check for style, content, and grammar.\",\n      \"student\": \"I am a student who is trying to write the best essay.\"\n  },\n  \"results\": [\n    {\n      \"name\": \"String Check Grader\",\n      \"type\": \"string-check-grader\",\n      \"score\": 1.0,\n      \"passed\": true,\n    }\n  ],\n  \"sample\": {\n    \"input\": [\n      {\n        \"role\": \"system\",\n        \"content\": \"You are an evaluator bot...\"\n      },\n      {\n        \"role\": \"user\",\n        \"content\": \"You are assessing...\"\n      }\n    ],\n    \"output\": [\n      {\n        \"role\": \"assistant\",\n        \"content\": \"The rubric is not clear nor concise.\"\n      }\n    ],\n    \"finish_reason\": \"stop\",\n    \"model\": \"gpt-6-astra\",\n    \"usage\": {\n      \"total_tokens\": 521,\n      \"completion_tokens\": 2,\n      \"prompt_tokens\": 519,\n      \"cached_tokens\": 0\n    },\n    \"error\": null,\n    \"temperature\": 1.0,\n    \"max_completion_tokens\": 2048,\n    \"top_p\": 1.0,\n    \"seed\": 42\n  }\n}\n"
+        }
+      },
+      "EvalRunOutputItemList": {
+        "type": "object",
+        "title": "EvalRunOutputItemList",
+        "description": "An object representing a list of output items for an evaluation run.\n",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "description": "The type of this object. It is always set to \"list\".\n",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "description": "An array of eval run output item objects.\n",
+            "items": {
+              "$ref": "#/components/schemas/EvalRunOutputItem"
+            }
+          },
+          "first_id": {
+            "type": "string",
+            "description": "The identifier of the first eval run output item in the data array."
+          },
+          "last_id": {
+            "type": "string",
+            "description": "The identifier of the last eval run output item in the data array."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Indicates whether there are more eval run output items available."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "x-oaiMeta": {
+          "name": "The eval run output item list object",
+          "group": "evals",
+          "example": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\": \"eval.run.output_item\",\n      \"id\": \"outputitem_67abd55eb6548190bb580745d5644a33\",\n      \"run_id\": \"evalrun_67abd54d60ec8190832b46859da808f7\",\n      \"eval_id\": \"eval_67abd54d9b0081909a86353f6fb9317a\",\n      \"created_at\": 1739314509,\n      \"status\": \"pass\",\n      \"datasource_item_id\": 137,\n      \"datasource_item\": {\n          \"teacher\": \"To grade essays, I only check for style, content, and grammar.\",\n          \"student\": \"I am a student who is trying to write the best essay.\"\n      },\n      \"results\": [\n        {\n          \"name\": \"String Check Grader\",\n          \"type\": \"string-check-grader\",\n          \"score\": 1.0,\n          \"passed\": true,\n        }\n      ],\n      \"sample\": {\n        \"input\": [\n          {\n            \"role\": \"system\",\n            \"content\": \"You are an evaluator bot...\"\n          },\n          {\n            \"role\": \"user\",\n            \"content\": \"You are assessing...\"\n          }\n        ],\n        \"output\": [\n          {\n            \"role\": \"assistant\",\n            \"content\": \"The rubric is not clear nor concise.\"\n          }\n        ],\n        \"finish_reason\": \"stop\",\n        \"model\": \"gpt-6-astra\",\n        \"usage\": {\n          \"total_tokens\": 521,\n          \"completion_tokens\": 2,\n          \"prompt_tokens\": 519,\n          \"cached_tokens\": 0\n        },\n        \"error\": null,\n        \"temperature\": 1.0,\n        \"max_completion_tokens\": 2048,\n        \"top_p\": 1.0,\n        \"seed\": 42\n      }\n    },\n  ],\n  \"first_id\": \"outputitem_67abd55eb6548190bb580745d5644a33\",\n  \"last_id\": \"outputitem_67abd55eb6548190bb580745d5644a33\",\n  \"has_more\": false\n}\n"
+        }
+      },
+      "EvalRunOutputItemResult": {
+        "type": "object",
+        "title": "EvalRunOutputItemResult",
+        "description": "A single grader result for an evaluation run output item.\n",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The name of the grader."
+          },
+          "type": {
+            "type": "string",
+            "description": "The grader type (for example, \"string-check-grader\")."
+          },
+          "score": {
+            "type": "number",
+            "description": "The numeric score produced by the grader."
+          },
+          "passed": {
+            "type": "boolean",
+            "description": "Whether the grader considered the output a pass."
+          },
+          "sample": {
+            "anyOf": [
+              {
+                "type": "object",
+                "additionalProperties": true
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Optional sample or intermediate data produced by the grader."
+          }
+        },
+        "additionalProperties": true,
+        "required": [
+          "name",
+          "score",
+          "passed"
+        ]
+      },
+      "EvalStoredCompletionsDataSourceConfig": {
+        "type": "object",
+        "title": "StoredCompletionsDataSourceConfig",
+        "description": "Deprecated in favor of LogsDataSourceConfig.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "stored_completions"
+            ],
+            "default": "stored_completions",
+            "description": "The type of data source. Always `stored_completions`.",
+            "x-stainless-const": true
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          },
+          "schema": {
+            "type": "object",
+            "description": "The json schema for the run data source items.\nLearn how to build JSON schemas [here](https://json-schema.org/).\n",
+            "additionalProperties": true
+          }
+        },
+        "required": [
+          "type",
+          "schema"
+        ],
+        "deprecated": true,
+        "x-oaiMeta": {
+          "name": "The stored completions data source object for evals",
+          "group": "evals",
+          "example": "{\n  \"type\": \"stored_completions\",\n  \"metadata\": {\n    \"language\": \"english\"\n  },\n  \"schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"item\": {\n        \"type\": \"object\"\n      },\n      \"sample\": {\n        \"type\": \"object\"\n      }\n    },\n    \"required\": [\n      \"item\",\n      \"sample\"\n    }\n}\n"
+        }
+      },
+      "EvalStoredCompletionsSource": {
+        "type": "object",
+        "title": "StoredCompletionsRunDataSource",
+        "description": "A StoredCompletionsRunDataSource configuration describing a set of filters\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "stored_completions"
+            ],
+            "default": "stored_completions",
+            "description": "The type of source. Always `stored_completions`.",
+            "x-stainless-const": true
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          },
+          "model": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "An optional model to filter by (e.g., 'gpt-6-astra')."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "created_after": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "An optional Unix timestamp to filter items created after this time."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "created_before": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "An optional Unix timestamp to filter items created before this time."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "limit": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "An optional maximum number of items to return."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "x-oaiMeta": {
+          "name": "The stored completions data source object used to configure an individual run",
+          "group": "eval runs",
+          "example": "{\n  \"type\": \"stored_completions\",\n  \"model\": \"gpt-6-astra\",\n  \"created_after\": 1668124800,\n  \"created_before\": 1668124900,\n  \"limit\": 100,\n  \"metadata\": {}\n}\n"
+        }
+      },
+      "FileExpirationAfter": {
+        "type": "object",
+        "title": "File expiration policy",
+        "description": "The expiration policy for a file. By default, files with `purpose=batch` expire after 30 days and all other files are persisted until they are manually deleted.",
+        "properties": {
+          "anchor": {
+            "description": "Anchor timestamp after which the expiration policy applies. Supported anchors: `created_at`.",
+            "type": "string",
+            "enum": [
+              "created_at"
+            ],
+            "x-stainless-const": true
+          },
+          "seconds": {
+            "description": "The number of seconds after the anchor time that the file will expire. Must be between 3600 (1 hour) and 2592000 (30 days).",
+            "type": "integer",
+            "format": "int64",
+            "minimum": 3600,
+            "maximum": 2592000
+          }
+        },
+        "required": [
+          "anchor",
+          "seconds"
+        ]
+      },
+      "FilePath": {
+        "type": "object",
+        "title": "File path",
+        "description": "A path to a file.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the file path. Always `file_path`.\n",
+            "enum": [
+              "file_path"
+            ],
+            "x-stainless-const": true
+          },
+          "file_id": {
+            "type": "string",
+            "description": "The ID of the file.\n"
+          },
+          "index": {
+            "type": "integer",
+            "description": "The index of the file in the list of files.\n"
+          }
+        },
+        "required": [
+          "type",
+          "file_id",
+          "index"
+        ]
+      },
+      "FileSearchRanker": {
+        "type": "string",
+        "description": "The ranker to use for the file search. If not specified will use the `auto` ranker.",
+        "enum": [
+          "auto",
+          "default_2024_08_21"
+        ]
+      },
+      "FileSearchRankingOptions": {
+        "title": "File search tool call ranking options",
+        "type": "object",
+        "description": "The ranking options for the file search. If not specified, the file search tool will use the `auto` ranker and a score_threshold of 0.\n\nSee the [file search tool documentation](https://developers.openai.com/api/docs/guides/tools-file-search#retrieval-customization) for more information.\n",
+        "properties": {
+          "ranker": {
+            "$ref": "#/components/schemas/FileSearchRanker"
+          },
+          "score_threshold": {
+            "type": "number",
+            "description": "The score threshold for the file search. All values must be a floating point number between 0 and 1.",
+            "minimum": 0,
+            "maximum": 1
+          }
+        },
+        "required": [
+          "score_threshold"
+        ]
+      },
+      "FileSearchToolCall": {
+        "type": "object",
+        "title": "File search tool call",
+        "description": "The results of a file search tool call. See the\n[file search guide](https://developers.openai.com/api/docs/guides/tools-file-search) for more information.\n",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the file search tool call.\n"
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "file_search_call"
+            ],
+            "description": "The type of the file search tool call. Always `file_search_call`.\n",
+            "x-stainless-const": true
+          },
+          "status": {
+            "type": "string",
+            "description": "The status of the file search tool call. One of `in_progress`,\n`searching`, `incomplete` or `failed`,\n",
+            "enum": [
+              "in_progress",
+              "searching",
+              "completed",
+              "incomplete",
+              "failed"
+            ]
+          },
+          "queries": {
+            "type": "array",
+            "items": {
+              "type": "string"
+            },
+            "description": "The queries used to search for files.\n"
+          },
+          "results": {
+            "anyOf": [
+              {
+                "type": "array",
+                "description": "The results of the file search tool call.\n",
+                "items": {
+                  "type": "object",
+                  "properties": {
+                    "file_id": {
+                      "type": "string",
+                      "description": "The unique ID of the file.\n"
+                    },
+                    "text": {
+                      "type": "string",
+                      "description": "The text that was retrieved from the file.\n"
+                    },
+                    "filename": {
+                      "type": "string",
+                      "description": "The name of the file.\n"
+                    },
+                    "attributes": {
+                      "$ref": "#/components/schemas/VectorStoreFileAttributes"
+                    },
+                    "score": {
+                      "type": "number",
+                      "format": "float",
+                      "description": "The relevance score of the file - a value between 0 and 1.\n"
+                    }
+                  }
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "type",
+          "status",
+          "queries"
+        ]
+      },
+      "FineTuneChatCompletionRequestAssistantMessage": {
+        "allOf": [
+          {
+            "type": "object",
+            "title": "Assistant message",
+            "deprecated": false,
+            "properties": {
+              "weight": {
+                "type": "integer",
+                "enum": [
+                  0,
+                  1
+                ],
+                "description": "Controls whether the assistant message is trained against (0 or 1)"
+              }
+            }
+          },
+          {
+            "$ref": "#/components/schemas/ChatCompletionRequestAssistantMessage"
+          }
+        ],
+        "required": [
+          "role"
+        ]
+      },
+      "FineTuneDPOHyperparameters": {
+        "type": "object",
+        "description": "The hyperparameters used for the DPO fine-tuning job.",
+        "properties": {
+          "beta": {
+            "description": "The beta value for the DPO method. A higher beta value will increase the weight of the penalty between the policy and reference model.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "auto"
+                ],
+                "x-stainless-const": true
+              },
+              {
+                "type": "number",
+                "minimum": 0,
+                "maximum": 2,
+                "exclusiveMinimum": true
+              }
+            ],
+            "default": "auto"
+          },
+          "batch_size": {
+            "description": "Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "auto"
+                ],
+                "x-stainless-const": true
+              },
+              {
+                "type": "integer",
+                "minimum": 1,
+                "maximum": 256
+              }
+            ],
+            "default": "auto"
+          },
+          "learning_rate_multiplier": {
+            "description": "Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "auto"
+                ],
+                "x-stainless-const": true
+              },
+              {
+                "type": "number",
+                "minimum": 0,
+                "exclusiveMinimum": true
+              }
+            ],
+            "default": "auto"
+          },
+          "n_epochs": {
+            "description": "The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "auto"
+                ],
+                "x-stainless-const": true
+              },
+              {
+                "type": "integer",
+                "minimum": 1,
+                "maximum": 50
+              }
+            ],
+            "default": "auto"
+          }
+        }
+      },
+      "FineTuneDPOMethod": {
+        "type": "object",
+        "description": "Configuration for the DPO fine-tuning method.",
+        "properties": {
+          "hyperparameters": {
+            "$ref": "#/components/schemas/FineTuneDPOHyperparameters"
+          }
+        }
+      },
+      "FineTuneMethod": {
+        "type": "object",
+        "description": "The method used for fine-tuning.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of method. Is either `supervised`, `dpo`, or `reinforcement`.",
+            "enum": [
+              "supervised",
+              "dpo",
+              "reinforcement"
+            ]
+          },
+          "supervised": {
+            "$ref": "#/components/schemas/FineTuneSupervisedMethod"
+          },
+          "dpo": {
+            "$ref": "#/components/schemas/FineTuneDPOMethod"
+          },
+          "reinforcement": {
+            "$ref": "#/components/schemas/FineTuneReinforcementMethod"
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "FineTuneReinforcementHyperparameters": {
+        "type": "object",
+        "description": "The hyperparameters used for the reinforcement fine-tuning job.",
+        "properties": {
+          "batch_size": {
+            "description": "Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "auto"
+                ],
+                "x-stainless-const": true
+              },
+              {
+                "type": "integer",
+                "minimum": 1,
+                "maximum": 256
+              }
+            ],
+            "default": "auto"
+          },
+          "learning_rate_multiplier": {
+            "description": "Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "auto"
+                ],
+                "x-stainless-const": true
+              },
+              {
+                "type": "number",
+                "minimum": 0,
+                "exclusiveMinimum": true
+              }
+            ],
+            "default": "auto"
+          },
+          "n_epochs": {
+            "description": "The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "auto"
+                ],
+                "x-stainless-const": true
+              },
+              {
+                "type": "integer",
+                "minimum": 1,
+                "maximum": 50
+              }
+            ],
+            "default": "auto"
+          },
+          "reasoning_effort": {
+            "description": "Level of reasoning effort.\n",
+            "type": "string",
+            "enum": [
+              "default",
+              "low",
+              "medium",
+              "high"
+            ],
+            "default": "default"
+          },
+          "compute_multiplier": {
+            "description": "Multiplier on amount of compute used for exploring search space during training.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "auto"
+                ],
+                "x-stainless-const": true
+              },
+              {
+                "type": "number",
+                "minimum": 0.00001,
+                "maximum": 10,
+                "exclusiveMinimum": true
+              }
+            ],
+            "default": "auto"
+          },
+          "eval_interval": {
+            "description": "The number of training steps between evaluation runs.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "auto"
+                ],
+                "x-stainless-const": true
+              },
+              {
+                "type": "integer",
+                "minimum": 1
+              }
+            ],
+            "default": "auto"
+          },
+          "eval_samples": {
+            "description": "Number of evaluation samples to generate per training step.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "auto"
+                ],
+                "x-stainless-const": true
+              },
+              {
+                "type": "integer",
+                "minimum": 1
+              }
+            ],
+            "default": "auto"
+          }
+        }
+      },
+      "FineTuneReinforcementMethod": {
+        "type": "object",
+        "description": "Configuration for the reinforcement fine-tuning method.",
+        "properties": {
+          "grader": {
+            "type": "object",
+            "description": "The grader used for the fine-tuning job.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/GraderStringCheck"
+              },
+              {
+                "$ref": "#/components/schemas/GraderTextSimilarity"
+              },
+              {
+                "$ref": "#/components/schemas/GraderPython"
+              },
+              {
+                "$ref": "#/components/schemas/GraderScoreModel"
+              },
+              {
+                "$ref": "#/components/schemas/GraderMulti"
+              }
+            ]
+          },
+          "hyperparameters": {
+            "$ref": "#/components/schemas/FineTuneReinforcementHyperparameters"
+          }
+        },
+        "required": [
+          "grader"
+        ]
+      },
+      "FineTuneSupervisedHyperparameters": {
+        "type": "object",
+        "description": "The hyperparameters used for the fine-tuning job.",
+        "properties": {
+          "batch_size": {
+            "description": "Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "auto"
+                ],
+                "x-stainless-const": true
+              },
+              {
+                "type": "integer",
+                "minimum": 1,
+                "maximum": 256
+              }
+            ],
+            "default": "auto"
+          },
+          "learning_rate_multiplier": {
+            "description": "Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "auto"
+                ],
+                "x-stainless-const": true
+              },
+              {
+                "type": "number",
+                "minimum": 0,
+                "exclusiveMinimum": true
+              }
+            ],
+            "default": "auto"
+          },
+          "n_epochs": {
+            "description": "The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "auto"
+                ],
+                "x-stainless-const": true
+              },
+              {
+                "type": "integer",
+                "minimum": 1,
+                "maximum": 50
+              }
+            ],
+            "default": "auto"
+          }
+        }
+      },
+      "FineTuneSupervisedMethod": {
+        "type": "object",
+        "description": "Configuration for the supervised fine-tuning method.",
+        "properties": {
+          "hyperparameters": {
+            "$ref": "#/components/schemas/FineTuneSupervisedHyperparameters"
+          }
+        }
+      },
+      "FineTuningCheckpointPermission": {
+        "type": "object",
+        "title": "FineTuningCheckpointPermission",
+        "description": "The `checkpoint.permission` object represents a permission for a fine-tuned model checkpoint.\n",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The permission identifier, which can be referenced in the API endpoints."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the permission was created."
+          },
+          "project_id": {
+            "type": "string",
+            "description": "The project identifier that the permission is for."
+          },
+          "object": {
+            "type": "string",
+            "description": "The object type, which is always \"checkpoint.permission\".",
+            "enum": [
+              "checkpoint.permission"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "created_at",
+          "id",
+          "object",
+          "project_id"
+        ],
+        "x-oaiMeta": {
+          "name": "The fine-tuned model checkpoint permission object",
+          "example": "{\n  \"object\": \"checkpoint.permission\",\n  \"id\": \"cp_zc4Q7MP6XxulcVzj4MZdwsAB\",\n  \"created_at\": 1712211699,\n  \"project_id\": \"proj_abGMw1llN8IrBb6SvvY5A1iH\"\n}\n"
+        }
+      },
+      "FineTuningIntegration": {
+        "type": "object",
+        "title": "Fine-Tuning Job Integration",
+        "required": [
+          "type",
+          "wandb"
+        ],
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the integration being enabled for the fine-tuning job",
+            "enum": [
+              "wandb"
+            ],
+            "x-stainless-const": true
+          },
+          "wandb": {
+            "type": "object",
+            "description": "The settings for your integration with Weights and Biases. This payload specifies the project that\nmetrics will be sent to. Optionally, you can set an explicit display name for your run, add tags\nto your run, and set a default entity (team, username, etc) to be associated with your run.\n",
+            "required": [
+              "project"
+            ],
+            "properties": {
+              "project": {
+                "description": "The name of the project that the new run will be created under.\n",
+                "type": "string",
+                "example": "my-wandb-project"
+              },
+              "name": {
+                "anyOf": [
+                  {
+                    "description": "A display name to set for the run. If not set, we will use the Job ID as the name.\n",
+                    "type": "string"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "entity": {
+                "anyOf": [
+                  {
+                    "description": "The entity to use for the run. This allows you to set the team or username of the WandB user that you would\nlike associated with the run. If not set, the default entity for the registered WandB API key is used.\n",
+                    "type": "string"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "tags": {
+                "description": "A list of tags to be attached to the newly created run. These tags are passed through directly to WandB. Some\ndefault tags are generated by OpenAI: \"openai/finetune\", \"openai/{base-model}\", \"openai/{ftjob-abcdef}\".\n",
+                "type": "array",
+                "items": {
+                  "type": "string",
+                  "example": "custom-tag"
+                }
+              }
+            }
+          }
+        }
+      },
+      "FineTuningJob": {
+        "type": "object",
+        "title": "FineTuningJob",
+        "description": "The `fine_tuning.job` object represents a fine-tuning job that has been created through the API.\n",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The object identifier, which can be referenced in the API endpoints."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the fine-tuning job was created."
+          },
+          "error": {
+            "anyOf": [
+              {
+                "type": "object",
+                "description": "For fine-tuning jobs that have `failed`, this will contain more information on the cause of the failure.",
+                "properties": {
+                  "code": {
+                    "type": "string",
+                    "description": "A machine-readable error code."
+                  },
+                  "message": {
+                    "type": "string",
+                    "description": "A human-readable error message."
+                  },
+                  "param": {
+                    "anyOf": [
+                      {
+                        "type": "string",
+                        "description": "The parameter that was invalid, usually `training_file` or `validation_file`. This field will be null if the failure was not parameter-specific."
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ]
+                  }
+                },
+                "required": [
+                  "code",
+                  "message",
+                  "param"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "fine_tuned_model": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The name of the fine-tuned model that is being created. The value will be null if the fine-tuning job is still running."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "finished_at": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "format": "unixtime",
+                "description": "The Unix timestamp (in seconds) for when the fine-tuning job was finished. The value will be null if the fine-tuning job is still running."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "hyperparameters": {
+            "type": "object",
+            "description": "The hyperparameters used for the fine-tuning job. This value will only be returned when running `supervised` jobs.",
+            "properties": {
+              "batch_size": {
+                "anyOf": [
+                  {
+                    "description": "Number of examples in each batch. A larger batch size means that model parameters\nare updated less frequently, but with lower variance.\n",
+                    "oneOf": [
+                      {
+                        "type": "string",
+                        "enum": [
+                          "auto"
+                        ],
+                        "x-stainless-const": true
+                      },
+                      {
+                        "type": "integer",
+                        "minimum": 1,
+                        "maximum": 256
+                      }
+                    ],
+                    "default": "auto"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "learning_rate_multiplier": {
+                "description": "Scaling factor for the learning rate. A smaller learning rate may be useful to avoid\noverfitting.\n",
+                "oneOf": [
+                  {
+                    "type": "string",
+                    "enum": [
+                      "auto"
+                    ],
+                    "x-stainless-const": true
+                  },
+                  {
+                    "type": "number",
+                    "minimum": 0,
+                    "exclusiveMinimum": true
+                  }
+                ],
+                "default": "auto"
+              },
+              "n_epochs": {
+                "description": "The number of epochs to train the model for. An epoch refers to one full cycle\nthrough the training dataset.\n",
+                "oneOf": [
+                  {
+                    "type": "string",
+                    "enum": [
+                      "auto"
+                    ],
+                    "x-stainless-const": true
+                  },
+                  {
+                    "type": "integer",
+                    "minimum": 1,
+                    "maximum": 50
+                  }
+                ],
+                "default": "auto"
+              }
+            }
+          },
+          "model": {
+            "type": "string",
+            "description": "The base model that is being fine-tuned."
+          },
+          "object": {
+            "type": "string",
+            "description": "The object type, which is always \"fine_tuning.job\".",
+            "enum": [
+              "fine_tuning.job"
+            ],
+            "x-stainless-const": true
+          },
+          "organization_id": {
+            "type": "string",
+            "description": "The organization that owns the fine-tuning job."
+          },
+          "result_files": {
+            "type": "array",
+            "description": "The compiled results file ID(s) for the fine-tuning job. You can retrieve the results with the [Files API](https://developers.openai.com/api/reference/resources/files/methods/content).",
+            "items": {
+              "type": "string",
+              "example": "file-abc123"
+            }
+          },
+          "status": {
+            "type": "string",
+            "description": "The current status of the fine-tuning job, which can be either `validating_files`, `queued`, `running`, `succeeded`, `failed`, or `cancelled`.",
+            "enum": [
+              "validating_files",
+              "queued",
+              "running",
+              "succeeded",
+              "failed",
+              "cancelled"
+            ]
+          },
+          "trained_tokens": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "The total number of billable tokens processed by this fine-tuning job. The value will be null if the fine-tuning job is still running."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "training_file": {
+            "type": "string",
+            "description": "The file ID used for training. You can retrieve the training data with the [Files API](https://developers.openai.com/api/reference/resources/files/methods/content)."
+          },
+          "validation_file": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The file ID used for validation. You can retrieve the validation results with the [Files API](https://developers.openai.com/api/reference/resources/files/methods/content)."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "integrations": {
+            "anyOf": [
+              {
+                "type": "array",
+                "description": "A list of integrations to enable for this fine-tuning job.",
+                "maxItems": 5,
+                "items": {
+                  "oneOf": [
+                    {
+                      "$ref": "#/components/schemas/FineTuningIntegration"
+                    }
+                  ]
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "seed": {
+            "type": "integer",
+            "description": "The seed used for the fine-tuning job."
+          },
+          "estimated_finish": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "format": "unixtime",
+                "description": "The Unix timestamp (in seconds) for when the fine-tuning job is estimated to finish. The value will be null if the fine-tuning job is not running."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "method": {
+            "$ref": "#/components/schemas/FineTuneMethod"
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          }
+        },
+        "required": [
+          "created_at",
+          "error",
+          "finished_at",
+          "fine_tuned_model",
+          "hyperparameters",
+          "id",
+          "model",
+          "object",
+          "organization_id",
+          "result_files",
+          "status",
+          "trained_tokens",
+          "training_file",
+          "validation_file",
+          "seed"
+        ],
+        "x-oaiMeta": {
+          "name": "The fine-tuning job object",
+          "example": "{\n  \"object\": \"fine_tuning.job\",\n  \"id\": \"ftjob-abc123\",\n  \"model\": \"davinci-002\",\n  \"created_at\": 1692661014,\n  \"finished_at\": 1692661190,\n  \"fine_tuned_model\": \"ft:davinci-002:my-org:custom_suffix:7q8mpxmy\",\n  \"organization_id\": \"org-123\",\n  \"result_files\": [\n      \"file-abc123\"\n  ],\n  \"status\": \"succeeded\",\n  \"validation_file\": null,\n  \"training_file\": \"file-abc123\",\n  \"hyperparameters\": {\n      \"n_epochs\": 4,\n      \"batch_size\": 1,\n      \"learning_rate_multiplier\": 1.0\n  },\n  \"trained_tokens\": 5768,\n  \"integrations\": [],\n  \"seed\": 0,\n  \"estimated_finish\": 0,\n  \"method\": {\n    \"type\": \"supervised\",\n    \"supervised\": {\n      \"hyperparameters\": {\n        \"n_epochs\": 4,\n        \"batch_size\": 1,\n        \"learning_rate_multiplier\": 1.0\n      }\n    }\n  },\n  \"metadata\": {\n    \"key\": \"value\"\n  }\n}\n"
+        }
+      },
+      "FineTuningJobCheckpoint": {
+        "type": "object",
+        "title": "FineTuningJobCheckpoint",
+        "description": "The `fine_tuning.job.checkpoint` object represents a model checkpoint for a fine-tuning job that is ready to use.\n",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The checkpoint identifier, which can be referenced in the API endpoints."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the checkpoint was created."
+          },
+          "fine_tuned_model_checkpoint": {
+            "type": "string",
+            "description": "The name of the fine-tuned checkpoint model that is created."
+          },
+          "step_number": {
+            "type": "integer",
+            "description": "The step number that the checkpoint was created at."
+          },
+          "metrics": {
+            "type": "object",
+            "description": "Metrics at the step number during the fine-tuning job.",
+            "properties": {
+              "step": {
+                "type": "number"
+              },
+              "train_loss": {
+                "type": "number"
+              },
+              "train_mean_token_accuracy": {
+                "type": "number"
+              },
+              "valid_loss": {
+                "type": "number"
+              },
+              "valid_mean_token_accuracy": {
+                "type": "number"
+              },
+              "full_valid_loss": {
+                "type": "number"
+              },
+              "full_valid_mean_token_accuracy": {
+                "type": "number"
+              }
+            }
+          },
+          "fine_tuning_job_id": {
+            "type": "string",
+            "description": "The name of the fine-tuning job that this checkpoint was created from."
+          },
+          "object": {
+            "type": "string",
+            "description": "The object type, which is always \"fine_tuning.job.checkpoint\".",
+            "enum": [
+              "fine_tuning.job.checkpoint"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "created_at",
+          "fine_tuning_job_id",
+          "fine_tuned_model_checkpoint",
+          "id",
+          "metrics",
+          "object",
+          "step_number"
+        ],
+        "x-oaiMeta": {
+          "name": "The fine-tuning job checkpoint object",
+          "example": "{\n  \"object\": \"fine_tuning.job.checkpoint\",\n  \"id\": \"ftckpt_qtZ5Gyk4BLq1SfLFWp3RtO3P\",\n  \"created_at\": 1712211699,\n  \"fine_tuned_model_checkpoint\": \"ft:gpt-4o-mini-2024-07-18:my-org:custom_suffix:9ABel2dg:ckpt-step-88\",\n  \"fine_tuning_job_id\": \"ftjob-fpbNQ3H1GrMehXRf8cO97xTN\",\n  \"metrics\": {\n    \"step\": 88,\n    \"train_loss\": 0.478,\n    \"train_mean_token_accuracy\": 0.924,\n    \"valid_loss\": 10.112,\n    \"valid_mean_token_accuracy\": 0.145,\n    \"full_valid_loss\": 0.567,\n    \"full_valid_mean_token_accuracy\": 0.944\n  },\n  \"step_number\": 88\n}\n"
+        }
+      },
+      "FineTuningJobEvent": {
+        "type": "object",
+        "description": "Fine-tuning job event object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "description": "The object type, which is always \"fine_tuning.job.event\".",
+            "enum": [
+              "fine_tuning.job.event"
+            ],
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The object identifier."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the fine-tuning job was created."
+          },
+          "level": {
+            "type": "string",
+            "description": "The log level of the event.",
+            "enum": [
+              "info",
+              "warn",
+              "error"
+            ]
+          },
+          "message": {
+            "type": "string",
+            "description": "The message of the event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of event.",
+            "enum": [
+              "message",
+              "metrics"
+            ]
+          },
+          "data": {
+            "type": "object",
+            "description": "The data associated with the event."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "created_at",
+          "level",
+          "message"
+        ],
+        "x-oaiMeta": {
+          "name": "The fine-tuning job event object",
+          "example": "{\n  \"object\": \"fine_tuning.job.event\",\n  \"id\": \"ftevent-abc123\"\n  \"created_at\": 1677610602,\n  \"level\": \"info\",\n  \"message\": \"Created fine-tuning job\",\n  \"data\": {},\n  \"type\": \"message\"\n}\n"
+        }
+      },
+      "FunctionAndCustomToolCallOutput": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/InputTextContent"
+          },
+          {
+            "$ref": "#/components/schemas/InputImageContent"
+          },
+          {
+            "$ref": "#/components/schemas/InputFileContent"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "FunctionObject": {
+        "type": "object",
+        "properties": {
+          "description": {
+            "type": "string",
+            "description": "A description of what the function does, used by the model to choose when and how to call the function."
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64."
+          },
+          "parameters": {
+            "$ref": "#/components/schemas/FunctionParameters"
+          },
+          "strict": {
+            "anyOf": [
+              {
+                "type": "boolean",
+                "default": false,
+                "description": "Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the `parameters` field. Only a subset of JSON Schema is supported when `strict` is `true`. Learn more about Structured Outputs in the [function calling guide](https://developers.openai.com/api/docs/guides/function-calling)."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "name"
+        ]
+      },
+      "FunctionParameters": {
+        "type": "object",
+        "description": "The parameters the functions accepts, described as a JSON Schema object. See the [guide](https://developers.openai.com/api/docs/guides/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format.\n\nOmitting `parameters` defines a function with an empty parameter list.",
+        "additionalProperties": true
+      },
+      "FunctionToolCall": {
+        "type": "object",
+        "title": "Function tool call",
+        "description": "A tool call to run a function. See the\n[function calling guide](https://developers.openai.com/api/docs/guides/function-calling) for more information.\n",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the function tool call.\n"
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "function_call"
+            ],
+            "description": "The type of the function tool call. Always `function_call`.\n",
+            "x-stainless-const": true
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The unique ID of the function tool call generated by the model.\n"
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ToolCallCaller"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "namespace": {
+            "type": "string",
+            "description": "The namespace of the function to run.\n"
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the function to run.\n"
+          },
+          "arguments": {
+            "type": "string",
+            "description": "A JSON string of the arguments to pass to the function.\n"
+          },
+          "status": {
+            "type": "string",
+            "description": "The status of the item. One of `in_progress`, `completed`, or\n`incomplete`. Populated when items are returned via API.\n",
+            "enum": [
+              "in_progress",
+              "completed",
+              "incomplete"
+            ]
+          },
+          "async": {
+            "type": "boolean",
+            "description": "Whether the function tool call runs asynchronously.\n"
+          }
+        },
+        "required": [
+          "type",
+          "call_id",
+          "name",
+          "arguments"
+        ]
+      },
+      "FunctionToolCallOutput": {
+        "type": "object",
+        "title": "Function tool call output",
+        "description": "The output of a function tool call.\n",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the function tool call output. Populated when this item\nis returned via API.\n"
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "function_call_output"
+            ],
+            "description": "The type of the function tool call output. Always `function_call_output`.\n",
+            "x-stainless-const": true
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The unique ID of the function tool call generated by the model.\n"
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the tool that produced the output.\n"
+          },
+          "namespace": {
+            "type": "string",
+            "description": "The namespace of the tool that produced the output.\n"
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ToolCallCallerParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "output": {
+            "description": "The output from the function call generated by your code.\nCan be a string or an list of output content.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "description": "A string of the output of the function call.\n",
+                "title": "string output"
+              },
+              {
+                "type": "array",
+                "items": {
+                  "$ref": "#/components/schemas/FunctionAndCustomToolCallOutput"
+                },
+                "title": "output content list",
+                "description": "Text, image, or file output of the function call.\n"
+              }
+            ]
+          },
+          "status": {
+            "type": "string",
+            "description": "The status of the item. One of `in_progress`, `completed`, or\n`incomplete`. Populated when items are returned via API.\n",
+            "enum": [
+              "in_progress",
+              "completed",
+              "incomplete"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "output"
+        ]
+      },
+      "FunctionToolCallOutputResource": {
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/FunctionToolCallOutput"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the function call tool output.\n"
+              },
+              "status": {
+                "description": "The status of the item. One of `in_progress`, `completed`, or\n`incomplete`. Populated when items are returned via API.\n",
+                "$ref": "#/components/schemas/FunctionCallOutputStatusEnum"
+              },
+              "created_by": {
+                "type": "string",
+                "description": "The identifier of the actor that created the item.\n"
+              }
+            },
+            "required": [
+              "id",
+              "status"
+            ]
+          }
+        ]
+      },
+      "FunctionToolCallResource": {
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/FunctionToolCall"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the function tool call.\n"
+              },
+              "status": {
+                "description": "The status of the item. One of `in_progress`, `completed`, or\n`incomplete`. Populated when items are returned via API.\n",
+                "$ref": "#/components/schemas/FunctionCallStatus"
+              },
+              "created_by": {
+                "type": "string",
+                "description": "The identifier of the actor that created the item.\n"
+              }
+            },
+            "required": [
+              "id",
+              "status"
+            ]
+          }
+        ]
+      },
+      "GraderLabelModel": {
+        "type": "object",
+        "title": "LabelModelGrader",
+        "description": "A LabelModelGrader object which uses a model to assign labels to each item\nin the evaluation.\n",
+        "properties": {
+          "type": {
+            "description": "The object type, which is always `label_model`.",
+            "type": "string",
+            "enum": [
+              "label_model"
+            ],
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the grader."
+          },
+          "model": {
+            "type": "string",
+            "description": "The model to use for the evaluation. Must support structured outputs."
+          },
+          "input": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/EvalItem"
+            }
+          },
+          "labels": {
+            "type": "array",
+            "items": {
+              "type": "string"
+            },
+            "description": "The labels to assign to each item in the evaluation."
+          },
+          "passing_labels": {
+            "type": "array",
+            "items": {
+              "type": "string"
+            },
+            "description": "The labels that indicate a passing result. Must be a subset of labels."
+          }
+        },
+        "required": [
+          "type",
+          "model",
+          "input",
+          "passing_labels",
+          "labels",
+          "name"
+        ],
+        "x-oaiMeta": {
+          "name": "Label Model Grader",
+          "group": "graders",
+          "example": "{\n  \"name\": \"First label grader\",\n  \"type\": \"label_model\",\n  \"model\": \"gpt-4o-2024-08-06\",\n  \"input\": [\n    {\n      \"type\": \"message\",\n      \"role\": \"system\",\n      \"content\": {\n        \"type\": \"input_text\",\n        \"text\": \"Classify the sentiment of the following statement as one of positive, neutral, or negative\"\n      }\n    },\n    {\n      \"type\": \"message\",\n      \"role\": \"user\",\n      \"content\": {\n        \"type\": \"input_text\",\n        \"text\": \"Statement: {{item.response}}\"\n      }\n    }\n  ],\n  \"passing_labels\": [\n    \"positive\"\n  ],\n  \"labels\": [\n    \"positive\",\n    \"neutral\",\n    \"negative\"\n  ]\n}\n"
+        }
+      },
+      "GraderMulti": {
+        "type": "object",
+        "title": "MultiGrader",
+        "description": "A MultiGrader object combines the output of multiple graders to produce a single score.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "multi"
+            ],
+            "default": "multi",
+            "description": "The object type, which is always `multi`.",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the grader."
+          },
+          "graders": {
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/GraderStringCheck"
+              },
+              {
+                "$ref": "#/components/schemas/GraderTextSimilarity"
+              },
+              {
+                "$ref": "#/components/schemas/GraderPython"
+              },
+              {
+                "$ref": "#/components/schemas/GraderScoreModel"
+              },
+              {
+                "$ref": "#/components/schemas/GraderLabelModel"
+              }
+            ]
+          },
+          "calculate_output": {
+            "type": "string",
+            "description": "A formula to calculate the output based on grader results."
+          }
+        },
+        "required": [
+          "name",
+          "type",
+          "graders",
+          "calculate_output"
+        ],
+        "x-oaiMeta": {
+          "name": "Multi Grader",
+          "group": "graders",
+          "example": "{\n  \"type\": \"multi\",\n  \"name\": \"example multi grader\",\n  \"graders\": [\n    {\n      \"type\": \"text_similarity\",\n      \"name\": \"example text similarity grader\",\n      \"input\": \"The graded text\",\n      \"reference\": \"The reference text\",\n      \"evaluation_metric\": \"fuzzy_match\"\n    },\n    {\n      \"type\": \"string_check\",\n      \"name\": \"Example string check grader\",\n      \"input\": \"{{sample.output_text}}\",\n      \"reference\": \"{{item.label}}\",\n      \"operation\": \"eq\"\n    }\n  ],\n  \"calculate_output\": \"0.5 * text_similarity_score +  0.5 * string_check_score)\"\n}\n"
+        }
+      },
+      "GraderPython": {
+        "type": "object",
+        "title": "PythonGrader",
+        "description": "A PythonGrader object that runs a python script on the input.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "python"
+            ],
+            "description": "The object type, which is always `python`.",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the grader."
+          },
+          "source": {
+            "type": "string",
+            "description": "The source code of the python script."
+          },
+          "image_tag": {
+            "type": "string",
+            "description": "The image tag to use for the python script."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "source"
+        ],
+        "x-oaiMeta": {
+          "name": "Python Grader",
+          "group": "graders",
+          "example": "{\n  \"type\": \"python\",\n  \"name\": \"Example python grader\",\n  \"image_tag\": \"2025-05-08\",\n  \"source\": \"\"\"\ndef grade(sample: dict, item: dict) -> float:\n    \\\"\"\"\n    Returns 1.0 if `output_text` equals `label`, otherwise 0.0.\n    \\\"\"\"\n    output = sample.get(\"output_text\")\n    label = item.get(\"label\")\n    return 1.0 if output == label else 0.0\n\"\"\",\n}\n"
+        }
+      },
+      "GraderScoreModel": {
+        "type": "object",
+        "title": "ScoreModelGrader",
+        "description": "A ScoreModelGrader object that uses a model to assign a score to the input.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "score_model"
+            ],
+            "description": "The object type, which is always `score_model`.",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the grader."
+          },
+          "model": {
+            "type": "string",
+            "description": "The model to use for the evaluation."
+          },
+          "sampling_params": {
+            "type": "object",
+            "description": "The sampling parameters for the model.",
+            "properties": {
+              "seed": {
+                "anyOf": [
+                  {
+                    "type": "integer",
+                    "description": "A seed value to initialize the randomness, during sampling.\n"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "top_p": {
+                "anyOf": [
+                  {
+                    "type": "number",
+                    "default": 1,
+                    "example": 1,
+                    "description": "An alternative to temperature for nucleus sampling; 1.0 includes all tokens.\n"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "temperature": {
+                "anyOf": [
+                  {
+                    "type": "number",
+                    "description": "A higher temperature increases randomness in the outputs.\n"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "max_completions_tokens": {
+                "anyOf": [
+                  {
+                    "type": "integer",
+                    "minimum": 1,
+                    "description": "The maximum number of tokens the grader model may generate in its response.\n"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "reasoning_effort": {
+                "$ref": "#/components/schemas/ReasoningEffort"
+              }
+            }
+          },
+          "input": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/EvalItem"
+            },
+            "description": "The input messages evaluated by the grader. Supports text, output text, input image, and input audio content blocks, and may include template strings.\n"
+          },
+          "range": {
+            "type": "array",
+            "items": {
+              "type": "number",
+              "min_items": 2,
+              "max_items": 2
+            },
+            "description": "The range of the score. Defaults to `[0, 1]`."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "input",
+          "model"
+        ],
+        "x-oaiMeta": {
+          "name": "Score Model Grader",
+          "group": "graders",
+          "example": "{\n    \"type\": \"score_model\",\n    \"name\": \"Example score model grader\",\n    \"input\": [\n        {\n            \"role\": \"user\",\n            \"content\": [\n                {\n                    \"type\": \"input_text\",\n                    \"text\": (\n                        \"Score how close the reference answer is to the model answer. Score 1.0 if they are the same and 0.0 if they are different.\"\n                        \" Return just a floating point score\\n\\n\"\n                        \" Reference answer: {{item.label}}\\n\\n\"\n                        \" Model answer: {{sample.output_text}}\"\n                    )\n                },\n                {\n                    \"type\": \"input_image\",\n                    \"image_url\": \"https://example.com/reference.png\",\n                    \"file_id\": null,\n                    \"detail\": \"auto\"\n                }\n            ],\n        }\n    ],\n    \"model\": \"gpt-5-mini\",\n    \"sampling_params\": {\n        \"temperature\": 1,\n        \"top_p\": 1,\n        \"seed\": 42,\n        \"max_completions_tokens\": 32768,\n        \"reasoning_effort\": \"medium\"\n    },\n}\n"
+        }
+      },
+      "GraderStringCheck": {
+        "type": "object",
+        "title": "StringCheckGrader",
+        "description": "A StringCheckGrader object that performs a string comparison between input and reference using a specified operation.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "string_check"
+            ],
+            "description": "The object type, which is always `string_check`.",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the grader."
+          },
+          "input": {
+            "type": "string",
+            "description": "The input text. This may include template strings."
+          },
+          "reference": {
+            "type": "string",
+            "description": "The reference text. This may include template strings."
+          },
+          "operation": {
+            "type": "string",
+            "enum": [
+              "eq",
+              "ne",
+              "like",
+              "ilike"
+            ],
+            "description": "The string check operation to perform. One of `eq`, `ne`, `like`, or `ilike`."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "input",
+          "reference",
+          "operation"
+        ],
+        "x-oaiMeta": {
+          "name": "String Check Grader",
+          "group": "graders",
+          "example": "{\n  \"type\": \"string_check\",\n  \"name\": \"Example string check grader\",\n  \"input\": \"{{sample.output_text}}\",\n  \"reference\": \"{{item.label}}\",\n  \"operation\": \"eq\"\n}\n"
+        }
+      },
+      "GraderTextSimilarity": {
+        "type": "object",
+        "title": "TextSimilarityGrader",
+        "description": "A TextSimilarityGrader object which grades text based on similarity metrics.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "text_similarity"
+            ],
+            "default": "text_similarity",
+            "description": "The type of grader.",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the grader."
+          },
+          "input": {
+            "type": "string",
+            "description": "The text being graded."
+          },
+          "reference": {
+            "type": "string",
+            "description": "The text being graded against."
+          },
+          "evaluation_metric": {
+            "type": "string",
+            "enum": [
+              "cosine",
+              "fuzzy_match",
+              "bleu",
+              "gleu",
+              "meteor",
+              "rouge_1",
+              "rouge_2",
+              "rouge_3",
+              "rouge_4",
+              "rouge_5",
+              "rouge_l"
+            ],
+            "description": "The evaluation metric to use. One of `cosine`, `fuzzy_match`, `bleu`, \n`gleu`, `meteor`, `rouge_1`, `rouge_2`, `rouge_3`, `rouge_4`, `rouge_5`, \nor `rouge_l`.\n"
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "input",
+          "reference",
+          "evaluation_metric"
+        ],
+        "x-oaiMeta": {
+          "name": "Text Similarity Grader",
+          "group": "graders",
+          "example": "{\n  \"type\": \"text_similarity\",\n  \"name\": \"Example text similarity grader\",\n  \"input\": \"{{sample.output_text}}\",\n  \"reference\": \"{{item.label}}\",\n  \"evaluation_metric\": \"fuzzy_match\"\n}\n"
+        }
+      },
+      "Group": {
+        "type": "object",
+        "description": "Summary information about a group returned in role assignment responses.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "group"
+            ],
+            "description": "Always `group`.",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "Identifier for the group."
+          },
+          "name": {
+            "type": "string",
+            "description": "Display name of the group."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (in seconds) when the group was created."
+          },
+          "scim_managed": {
+            "type": "boolean",
+            "description": "Whether the group is managed through SCIM."
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "name",
+          "created_at",
+          "scim_managed"
+        ],
+        "x-oaiMeta": {
+          "name": "The group object",
+          "example": "{\n    \"object\": \"group\",\n    \"id\": \"group_01J1F8ABCDXYZ\",\n    \"name\": \"Support Team\",\n    \"created_at\": 1711471533,\n    \"scim_managed\": false\n}\n"
+        }
+      },
+      "GroupDeletedResource": {
+        "type": "object",
+        "description": "Confirmation payload returned after deleting a group.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "group.deleted"
+            ],
+            "description": "Always `group.deleted`.",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "Identifier of the deleted group."
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the group was deleted."
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "deleted"
+        ],
+        "x-oaiMeta": {
+          "example": "{\n    \"object\": \"group.deleted\",\n    \"id\": \"group_01J1F8ABCDXYZ\",\n    \"deleted\": true\n}\n"
+        }
+      },
+      "GroupListResource": {
+        "type": "object",
+        "description": "Paginated list of organization groups.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "description": "Always `list`.",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "description": "Groups returned in the current page.",
+            "items": {
+              "$ref": "#/components/schemas/GroupResponse"
+            }
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether additional groups are available when paginating."
+          },
+          "next": {
+            "description": "Cursor to fetch the next page of results, or `null` if there are no more results.",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more",
+          "next"
+        ],
+        "x-oaiMeta": {
+          "name": "Group list",
+          "example": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"id\": \"group_01J1F8ABCDXYZ\",\n            \"name\": \"Support Team\",\n            \"created_at\": 1711471533,\n            \"is_scim_managed\": false\n        },\n        {\n            \"id\": \"group_01J1F8PQRMNO\",\n            \"name\": \"Sales\",\n            \"created_at\": 1711472599,\n            \"is_scim_managed\": true\n        }\n    ],\n    \"has_more\": false,\n    \"next\": null\n}\n"
+        }
+      },
+      "GroupMemberUser": {
+        "type": "object",
+        "description": "Details about a user returned from an organization group membership lookup.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Identifier for the user."
+          },
+          "name": {
+            "type": "string",
+            "description": "Display name of the user."
+          },
+          "email": {
+            "description": "Email address of the user, or `null` for users without an email.",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "picture": {
+            "description": "URL of the user's profile picture, if available.",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "is_service_account": {
+            "description": "Whether the user is a service account.",
+            "anyOf": [
+              {
+                "type": "boolean"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "user_type": {
+            "type": "string",
+            "enum": [
+              "user",
+              "tenant_user"
+            ],
+            "description": "The type of user."
+          }
+        },
+        "required": [
+          "id",
+          "name",
+          "email",
+          "picture",
+          "is_service_account",
+          "user_type"
+        ],
+        "x-oaiMeta": {
+          "name": "The group member user object",
+          "example": "{\n    \"id\": \"user_abc123\",\n    \"name\": \"Ada Lovelace\",\n    \"email\": \"ada@example.com\",\n    \"picture\": null,\n    \"is_service_account\": false,\n    \"user_type\": \"user\"\n}\n"
+        }
+      },
+      "GroupResourceWithSuccess": {
+        "type": "object",
+        "description": "Response returned after updating a group.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Identifier for the group."
+          },
+          "name": {
+            "type": "string",
+            "description": "Updated display name for the group."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (in seconds) when the group was created."
+          },
+          "is_scim_managed": {
+            "type": "boolean",
+            "description": "Whether the group is managed through SCIM and controlled by your identity provider."
+          }
+        },
+        "required": [
+          "id",
+          "name",
+          "created_at",
+          "is_scim_managed"
+        ],
+        "x-oaiMeta": {
+          "example": "{\n    \"id\": \"group_01J1F8ABCDXYZ\",\n    \"name\": \"Escalations\",\n    \"created_at\": 1711471533,\n    \"is_scim_managed\": false\n}\n"
+        }
+      },
+      "GroupResponse": {
+        "type": "object",
+        "description": "Details about an organization group.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Identifier for the group."
+          },
+          "name": {
+            "type": "string",
+            "description": "Display name of the group."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (in seconds) when the group was created."
+          },
+          "is_scim_managed": {
+            "type": "boolean",
+            "description": "Whether the group is managed through SCIM and controlled by your identity provider."
+          },
+          "group_type": {
+            "type": "string",
+            "enum": [
+              "group",
+              "tenant_group"
+            ],
+            "description": "The type of the group."
+          }
+        },
+        "required": [
+          "id",
+          "name",
+          "created_at",
+          "is_scim_managed",
+          "group_type"
+        ],
+        "x-oaiMeta": {
+          "name": "Group",
+          "example": "{\n    \"id\": \"group_01J1F8ABCDXYZ\",\n    \"name\": \"Support Team\",\n    \"created_at\": 1711471533,\n    \"is_scim_managed\": false,\n    \"group_type\": \"group\"\n}\n"
+        }
+      },
+      "GroupRoleAssignment": {
+        "type": "object",
+        "description": "Role assignment linking a group to a role.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "group.role"
+            ],
+            "description": "Always `group.role`.",
+            "x-stainless-const": true
+          },
+          "group": {
+            "$ref": "#/components/schemas/Group"
+          },
+          "role": {
+            "$ref": "#/components/schemas/Role"
+          }
+        },
+        "required": [
+          "object",
+          "group",
+          "role"
+        ],
+        "x-oaiMeta": {
+          "name": "The group role object",
+          "example": "{\n    \"object\": \"group.role\",\n    \"group\": {\n        \"object\": \"group\",\n        \"id\": \"group_01J1F8ABCDXYZ\",\n        \"name\": \"Support Team\",\n        \"created_at\": 1711471533,\n        \"scim_managed\": false\n    },\n    \"role\": {\n        \"object\": \"role\",\n        \"id\": \"role_01J1F8ROLE01\",\n        \"name\": \"API Group Manager\",\n        \"description\": \"Allows managing organization groups\",\n        \"permissions\": [\n            \"api.groups.read\",\n            \"api.groups.write\"\n        ],\n        \"resource_type\": \"api.organization\",\n        \"predefined_role\": false\n    }\n}\n"
+        }
+      },
+      "GroupUser": {
+        "type": "object",
+        "description": "Represents an individual user returned when inspecting group membership.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The identifier, which can be referenced in API endpoints"
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the user."
+          },
+          "email": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The email address of the user."
+          }
+        },
+        "required": [
+          "id",
+          "name",
+          "email"
+        ]
+      },
+      "GroupUserAssignment": {
+        "type": "object",
+        "description": "Confirmation payload returned after adding a user to a group.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "group.user"
+            ],
+            "description": "Always `group.user`.",
+            "x-stainless-const": true
+          },
+          "user_id": {
+            "type": "string",
+            "description": "Identifier of the user that was added."
+          },
+          "group_id": {
+            "type": "string",
+            "description": "Identifier of the group the user was added to."
+          }
+        },
+        "required": [
+          "object",
+          "user_id",
+          "group_id"
+        ],
+        "x-oaiMeta": {
+          "name": "The group user object",
+          "example": "{\n    \"object\": \"group.user\",\n    \"user_id\": \"user_abc123\",\n    \"group_id\": \"group_01J1F8ABCDXYZ\"\n}\n"
+        }
+      },
+      "GroupUserDeletedResource": {
+        "type": "object",
+        "description": "Confirmation payload returned after removing a user from a group.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "group.user.deleted"
+            ],
+            "description": "Always `group.user.deleted`.",
+            "x-stainless-const": true
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the group membership was removed."
+          }
+        },
+        "required": [
+          "object",
+          "deleted"
+        ],
+        "x-oaiMeta": {
+          "name": "Group user deletion confirmation",
+          "example": "{\n    \"object\": \"group.user.deleted\",\n    \"deleted\": true\n}\n"
+        }
+      },
+      "HostedToolPermission": {
+        "type": "object",
+        "description": "Permission state for a single hosted tool on a project.",
+        "properties": {
+          "enabled": {
+            "type": "boolean",
+            "description": "Whether the hosted tool is enabled for the project."
+          }
+        },
+        "required": [
+          "enabled"
+        ]
+      },
+      "HostedToolPermissionUpdate": {
+        "type": "object",
+        "properties": {
+          "enabled": {
+            "type": "boolean",
+            "description": "Whether to enable the hosted tool for the project."
+          }
+        },
+        "required": [
+          "enabled"
+        ]
+      },
+      "Image": {
+        "type": "object",
+        "description": "Represents the content or the URL of an image generated by the OpenAI API.",
+        "properties": {
+          "b64_json": {
+            "type": "string",
+            "description": "The base64-encoded JSON of the generated image. Returned by default for the GPT image models, and only present if `response_format` is set to `b64_json` for `dall-e-2` and `dall-e-3`."
+          },
+          "url": {
+            "type": "string",
+            "format": "uri",
+            "description": "When using `dall-e-2` or `dall-e-3`, the URL of the generated image if `response_format` is set to `url` (default value). Unsupported for the GPT image models."
+          },
+          "revised_prompt": {
+            "type": "string",
+            "description": "For `dall-e-3` only, the revised prompt that was used to generate the image."
+          }
+        }
+      },
+      "ImageEditCompletedEvent": {
+        "type": "object",
+        "description": "Emitted when image editing has completed and the final image is available.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `image_edit.completed`.\n",
+            "enum": [
+              "image_edit.completed"
+            ],
+            "x-stainless-const": true
+          },
+          "b64_json": {
+            "type": "string",
+            "description": "Base64-encoded final edited image data, suitable for rendering as an image.\n"
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp when the event was created.\n"
+          },
+          "size": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "1024x1024",
+                  "1024x1536",
+                  "1536x1024",
+                  "auto"
+                ]
+              }
+            ],
+            "description": "The image dimensions as a `WIDTHxHEIGHT` string, for example `1536x864`."
+          },
+          "quality": {
+            "type": "string",
+            "description": "The quality setting for the edited image.\n",
+            "enum": [
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max",
+              "auto"
+            ]
+          },
+          "background": {
+            "type": "string",
+            "description": "The background setting for the edited image.\n",
+            "enum": [
+              "transparent",
+              "opaque",
+              "auto"
+            ]
+          },
+          "output_format": {
+            "type": "string",
+            "description": "The output format for the edited image.\n",
+            "enum": [
+              "png",
+              "webp",
+              "jpeg"
+            ]
+          },
+          "usage": {
+            "$ref": "#/components/schemas/ImagesUsage"
+          }
+        },
+        "required": [
+          "type",
+          "b64_json",
+          "created_at",
+          "size",
+          "quality",
+          "background",
+          "output_format",
+          "usage"
+        ],
+        "x-oaiMeta": {
+          "name": "image_edit.completed",
+          "group": "images",
+          "example": "{\n  \"type\": \"image_edit.completed\",\n  \"b64_json\": \"...\",\n  \"created_at\": 1620000000,\n  \"size\": \"1024x1024\",\n  \"quality\": \"high\",\n  \"background\": \"transparent\",\n  \"output_format\": \"png\",\n  \"usage\": {\n    \"total_tokens\": 100,\n    \"input_tokens\": 50,\n    \"output_tokens\": 50,\n    \"input_tokens_details\": {\n      \"text_tokens\": 10,\n      \"image_tokens\": 40\n    }\n  }\n}\n"
+        }
+      },
+      "ImageEditPartialImageEvent": {
+        "type": "object",
+        "description": "Emitted when a partial image is available during image editing streaming.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `image_edit.partial_image`.\n",
+            "enum": [
+              "image_edit.partial_image"
+            ],
+            "x-stainless-const": true
+          },
+          "b64_json": {
+            "type": "string",
+            "description": "Base64-encoded partial image data, suitable for rendering as an image.\n"
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp when the event was created.\n"
+          },
+          "size": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "1024x1024",
+                  "1024x1536",
+                  "1536x1024",
+                  "auto"
+                ]
+              }
+            ],
+            "description": "The image dimensions as a `WIDTHxHEIGHT` string, for example `1536x864`."
+          },
+          "quality": {
+            "type": "string",
+            "description": "The quality setting for the requested edited image.\n",
+            "enum": [
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max",
+              "auto"
+            ]
+          },
+          "background": {
+            "type": "string",
+            "description": "The background setting for the requested edited image.\n",
+            "enum": [
+              "transparent",
+              "opaque",
+              "auto"
+            ]
+          },
+          "output_format": {
+            "type": "string",
+            "description": "The output format for the requested edited image.\n",
+            "enum": [
+              "png",
+              "webp",
+              "jpeg"
+            ]
+          },
+          "partial_image_index": {
+            "type": "integer",
+            "description": "0-based index for the partial image (streaming).\n"
+          }
+        },
+        "required": [
+          "type",
+          "b64_json",
+          "created_at",
+          "size",
+          "quality",
+          "background",
+          "output_format",
+          "partial_image_index"
+        ],
+        "x-oaiMeta": {
+          "name": "image_edit.partial_image",
+          "group": "images",
+          "example": "{\n  \"type\": \"image_edit.partial_image\",\n  \"b64_json\": \"...\",\n  \"created_at\": 1620000000,\n  \"size\": \"1024x1024\",\n  \"quality\": \"high\",\n  \"background\": \"transparent\",\n  \"output_format\": \"png\",\n  \"partial_image_index\": 0\n}\n"
+        }
+      },
+      "ImageEditStreamEvent": {
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/ImageEditPartialImageEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ImageEditCompletedEvent"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "ImageGenCompletedEvent": {
+        "type": "object",
+        "description": "Emitted when image generation has completed and the final image is available.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `image_generation.completed`.\n",
+            "enum": [
+              "image_generation.completed"
+            ],
+            "x-stainless-const": true
+          },
+          "b64_json": {
+            "type": "string",
+            "description": "Base64-encoded image data, suitable for rendering as an image.\n"
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp when the event was created.\n"
+          },
+          "size": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "1024x1024",
+                  "1024x1536",
+                  "1536x1024",
+                  "auto"
+                ]
+              }
+            ],
+            "description": "The image dimensions as a `WIDTHxHEIGHT` string, for example `1536x864`."
+          },
+          "quality": {
+            "type": "string",
+            "description": "The quality setting for the generated image.\n",
+            "enum": [
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max",
+              "auto"
+            ]
+          },
+          "background": {
+            "type": "string",
+            "description": "The background setting for the generated image.\n",
+            "enum": [
+              "transparent",
+              "opaque",
+              "auto"
+            ]
+          },
+          "output_format": {
+            "type": "string",
+            "description": "The output format for the generated image.\n",
+            "enum": [
+              "png",
+              "webp",
+              "jpeg"
+            ]
+          },
+          "usage": {
+            "$ref": "#/components/schemas/ImagesUsage"
+          }
+        },
+        "required": [
+          "type",
+          "b64_json",
+          "created_at",
+          "size",
+          "quality",
+          "background",
+          "output_format",
+          "usage"
+        ],
+        "x-oaiMeta": {
+          "name": "image_generation.completed",
+          "group": "images",
+          "example": "{\n  \"type\": \"image_generation.completed\",\n  \"b64_json\": \"...\",\n  \"created_at\": 1620000000,\n  \"size\": \"1024x1024\",\n  \"quality\": \"high\",\n  \"background\": \"transparent\",\n  \"output_format\": \"png\",\n  \"usage\": {\n    \"total_tokens\": 100,\n    \"input_tokens\": 50,\n    \"output_tokens\": 50,\n    \"input_tokens_details\": {\n      \"text_tokens\": 10,\n      \"image_tokens\": 40\n    }\n  }\n}\n"
+        }
+      },
+      "ImageGenPartialImageEvent": {
+        "type": "object",
+        "description": "Emitted when a partial image is available during image generation streaming.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `image_generation.partial_image`.\n",
+            "enum": [
+              "image_generation.partial_image"
+            ],
+            "x-stainless-const": true
+          },
+          "b64_json": {
+            "type": "string",
+            "description": "Base64-encoded partial image data, suitable for rendering as an image.\n"
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp when the event was created.\n"
+          },
+          "size": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "1024x1024",
+                  "1024x1536",
+                  "1536x1024",
+                  "auto"
+                ]
+              }
+            ],
+            "description": "The image dimensions as a `WIDTHxHEIGHT` string, for example `1536x864`."
+          },
+          "quality": {
+            "type": "string",
+            "description": "The quality setting for the requested image.\n",
+            "enum": [
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max",
+              "auto"
+            ]
+          },
+          "background": {
+            "type": "string",
+            "description": "The background setting for the requested image.\n",
+            "enum": [
+              "transparent",
+              "opaque",
+              "auto"
+            ]
+          },
+          "output_format": {
+            "type": "string",
+            "description": "The output format for the requested image.\n",
+            "enum": [
+              "png",
+              "webp",
+              "jpeg"
+            ]
+          },
+          "partial_image_index": {
+            "type": "integer",
+            "description": "0-based index for the partial image (streaming).\n"
+          }
+        },
+        "required": [
+          "type",
+          "b64_json",
+          "created_at",
+          "size",
+          "quality",
+          "background",
+          "output_format",
+          "partial_image_index"
+        ],
+        "x-oaiMeta": {
+          "name": "image_generation.partial_image",
+          "group": "images",
+          "example": "{\n  \"type\": \"image_generation.partial_image\",\n  \"b64_json\": \"...\",\n  \"created_at\": 1620000000,\n  \"size\": \"1024x1024\",\n  \"quality\": \"high\",\n  \"background\": \"transparent\",\n  \"output_format\": \"png\",\n  \"partial_image_index\": 0\n}\n"
+        }
+      },
+      "ImageGenStreamEvent": {
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/ImageGenPartialImageEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ImageGenCompletedEvent"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "ImageGenTool": {
+        "type": "object",
+        "title": "Image generation tool",
+        "description": "A tool that generates images using the GPT image models.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "image_generation"
+            ],
+            "description": "The type of the image generation tool. Always `image_generation`.\n",
+            "x-stainless-const": true
+          },
+          "model": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "gpt-image-1",
+                  "gpt-image-1-mini",
+                  "gpt-image-1.5",
+                  "gpt-image-2",
+                  "gpt-image-2-2026-04-21",
+                  "gpt-image-2.5-sunburst",
+                  "gpt-image-2.5-sunburst-2026-09-08",
+                  "gpt-image-2.5-flare",
+                  "gpt-image-2.5-flare-2026-09-08"
+                ],
+                "description": "The image generation model to use. One of `gpt-image-1`,\n`gpt-image-1-mini`, `gpt-image-1.5`, `gpt-image-2`,\n`gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`,\n`gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`,\n`gpt-image-2.5-flare-2026-09-08`, or `chatgpt-image-latest`. Default:\n`gpt-image-1`.\n",
+                "default": "gpt-image-1"
+              }
+            ]
+          },
+          "quality": {
+            "type": "string",
+            "enum": [
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max",
+              "auto"
+            ],
+            "description": "The quality of the generated image. The GPT image models support `low`,\n`medium`, and `high`. `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`,\nincluding their `2026-09-08` snapshots, also support `xhigh` and `max`.\nDefault: `auto`.\n",
+            "default": "auto"
+          },
+          "size": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "1024x1024",
+                  "1024x1536",
+                  "1536x1024",
+                  "auto"
+                ]
+              }
+            ],
+            "description": "The size of the generated images. For `gpt-image-2`, `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, and `gpt-image-2.5-flare-2026-09-08`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`.",
+            "default": "auto"
+          },
+          "output_format": {
+            "type": "string",
+            "enum": [
+              "png",
+              "webp",
+              "jpeg"
+            ],
+            "description": "The output format of the generated image. One of `png`, `webp`, or\n`jpeg`. Default: `png`.\n",
+            "default": "png"
+          },
+          "output_compression": {
+            "type": "integer",
+            "minimum": 0,
+            "maximum": 100,
+            "description": "Compression level for the output image. Default: 100.\n",
+            "default": 100
+          },
+          "moderation": {
+            "type": "string",
+            "enum": [
+              "auto",
+              "low"
+            ],
+            "description": "Moderation level for the generated image. Default: `auto`.\n",
+            "default": "auto"
+          },
+          "background": {
+            "type": "string",
+            "enum": [
+              "transparent",
+              "opaque",
+              "auto"
+            ],
+            "description": "Set the background of the generated image. One of `transparent`, `opaque`,\nor `auto`. `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`, including\ntheir `2026-09-08` snapshots, support `opaque` and `transparent`\nbackgrounds. Transparent backgrounds are available for supported GPT Image\nmodels. For `gpt-image-2` and `gpt-image-2-2026-04-21`, this support is in\npreview. When using `transparent`, set the output format to `png` or `webp`.\nDefault: `auto`.\n",
+            "default": "auto"
+          },
+          "input_fidelity": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/InputFidelity"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "input_image_mask": {
+            "type": "object",
+            "description": "Optional mask for inpainting. Contains `image_url`\n(string, optional) and `file_id` (string, optional).\n",
+            "properties": {
+              "image_url": {
+                "type": "string",
+                "description": "Base64-encoded mask image.\n"
+              },
+              "file_id": {
+                "type": "string",
+                "description": "File ID for the mask image.\n"
+              }
+            },
+            "required": [],
+            "additionalProperties": false
+          },
+          "partial_images": {
+            "type": "integer",
+            "minimum": 0,
+            "maximum": 3,
+            "description": "Number of partial images to generate in streaming mode, from 0 (default value) to 3.\n",
+            "default": 0
+          },
+          "action": {
+            "description": "Whether to generate a new image or edit an existing image. Default: `auto`.\n",
+            "$ref": "#/components/schemas/ImageGenActionEnum"
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "ImageRefParam": {
+        "type": "object",
+        "description": "Reference an input image by either URL or uploaded file ID.\nProvide exactly one of `image_url` or `file_id`.\n",
+        "properties": {
+          "image_url": {
+            "type": "string",
+            "format": "uri",
+            "maxLength": 20971520,
+            "description": "A fully qualified URL or base64-encoded data URL.",
+            "example": "https://example.com/source-image.png"
+          },
+          "file_id": {
+            "type": "string",
+            "description": "The File API ID of an uploaded image to use as input.",
+            "example": "file-abc123"
+          }
+        },
+        "anyOf": [
+          {
+            "required": [
+              "image_url"
+            ]
+          },
+          {
+            "required": [
+              "file_id"
+            ]
+          }
+        ],
+        "not": {
+          "required": [
+            "image_url",
+            "file_id"
+          ]
+        },
+        "additionalProperties": false
+      },
+      "ImagesResponse": {
+        "type": "object",
+        "title": "Image generation response",
+        "description": "The response from the image generation endpoint.",
+        "properties": {
+          "created": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the image was created."
+          },
+          "data": {
+            "type": "array",
+            "description": "The list of generated images.",
+            "items": {
+              "$ref": "#/components/schemas/Image"
+            }
+          },
+          "background": {
+            "type": "string",
+            "description": "The background parameter used for the image generation. Either `transparent` or `opaque`.",
+            "enum": [
+              "transparent",
+              "opaque"
+            ]
+          },
+          "output_format": {
+            "type": "string",
+            "description": "The output format of the image generation. Either `png`, `webp`, or `jpeg`.",
+            "enum": [
+              "png",
+              "webp",
+              "jpeg"
+            ]
+          },
+          "size": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "1024x1024",
+                  "1024x1536",
+                  "1536x1024"
+                ]
+              }
+            ],
+            "description": "The image dimensions as a `WIDTHxHEIGHT` string, for example `1536x864`."
+          },
+          "quality": {
+            "type": "string",
+            "description": "The quality of the image generated. One of `low`, `medium`, `high`, `xhigh`, or `max`.",
+            "enum": [
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max"
+            ]
+          },
+          "usage": {
+            "$ref": "#/components/schemas/ImageGenUsage"
+          }
+        },
+        "required": [
+          "created"
+        ],
+        "x-oaiMeta": {
+          "name": "The image generation response",
+          "group": "images",
+          "example": "{\n  \"created\": 1713833628,\n  \"data\": [\n    {\n      \"b64_json\": \"...\"\n    }\n  ],\n  \"background\": \"transparent\",\n  \"output_format\": \"png\",\n  \"size\": \"1024x1024\",\n  \"quality\": \"high\",\n  \"usage\": {\n    \"total_tokens\": 100,\n    \"input_tokens\": 50,\n    \"output_tokens\": 50,\n    \"input_tokens_details\": {\n      \"text_tokens\": 10,\n      \"image_tokens\": 40\n    }\n  }\n}\n"
+        }
+      },
+      "ImagesUsage": {
+        "type": "object",
+        "description": "For the GPT image models only, the token usage information for the image generation.\n",
+        "required": [
+          "total_tokens",
+          "input_tokens",
+          "output_tokens",
+          "input_tokens_details"
+        ],
+        "properties": {
+          "total_tokens": {
+            "type": "integer",
+            "description": "The total number of tokens (images and text) used for the image generation.\n"
+          },
+          "input_tokens": {
+            "type": "integer",
+            "description": "The number of tokens (images and text) in the input prompt."
+          },
+          "output_tokens": {
+            "type": "integer",
+            "description": "The number of image tokens in the output image."
+          },
+          "input_tokens_details": {
+            "type": "object",
+            "description": "The input tokens detailed information for the image generation.",
+            "required": [
+              "text_tokens",
+              "image_tokens"
+            ],
+            "properties": {
+              "text_tokens": {
+                "type": "integer",
+                "description": "The number of text tokens in the input prompt."
+              },
+              "image_tokens": {
+                "type": "integer",
+                "description": "The number of image tokens in the input prompt."
+              }
+            }
+          }
+        }
+      },
+      "InputAudio": {
+        "type": "object",
+        "title": "Input audio",
+        "description": "An audio input to the model.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the input item. Always `input_audio`.\n",
+            "enum": [
+              "input_audio"
+            ],
+            "x-stainless-const": true
+          },
+          "input_audio": {
+            "type": "object",
+            "properties": {
+              "data": {
+                "type": "string",
+                "description": "Base64-encoded audio data.\n"
+              },
+              "format": {
+                "type": "string",
+                "description": "The format of the audio data. Currently supported formats are `mp3` and\n`wav`.\n",
+                "enum": [
+                  "mp3",
+                  "wav"
+                ]
+              }
+            },
+            "required": [
+              "data",
+              "format"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "input_audio"
+        ]
+      },
+      "InputContent": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/InputTextContent"
+          },
+          {
+            "$ref": "#/components/schemas/InputImageContent"
+          },
+          {
+            "$ref": "#/components/schemas/InputFileContent"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "InputItem": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/EasyInputMessage"
+          },
+          {
+            "type": "object",
+            "title": "Item",
+            "description": "An item representing part of the context for the response to be\ngenerated by the model. Can contain text, images, and audio inputs,\nas well as previous assistant responses and tool call outputs.\n",
+            "$ref": "#/components/schemas/Item"
+          },
+          {
+            "$ref": "#/components/schemas/CompactionTriggerItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/ItemReferenceParam"
+          },
+          {
+            "$ref": "#/components/schemas/ProgramItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/ProgramOutputItemParam"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "InputMessage": {
+        "type": "object",
+        "title": "Input message",
+        "description": "A message input to the model with a role indicating instruction following\nhierarchy. Instructions given with the `developer` or `system` role take\nprecedence over instructions given with the `user` role.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the message input. Always set to `message`.\n",
+            "enum": [
+              "message"
+            ],
+            "x-stainless-const": true
+          },
+          "role": {
+            "type": "string",
+            "description": "The role of the message input. One of `user`, `system`, or `developer`.\n",
+            "enum": [
+              "user",
+              "system",
+              "developer"
+            ]
+          },
+          "status": {
+            "type": "string",
+            "description": "The status of item. One of `in_progress`, `completed`, or\n`incomplete`. Populated when items are returned via API.\n",
+            "enum": [
+              "in_progress",
+              "completed",
+              "incomplete"
+            ]
+          },
+          "content": {
+            "$ref": "#/components/schemas/InputMessageContentList"
+          }
+        },
+        "required": [
+          "role",
+          "content"
+        ]
+      },
+      "InputMessageContentList": {
+        "type": "array",
+        "title": "Input item content list",
+        "description": "A list of one or many input items to the model, containing different content \ntypes.\n",
+        "items": {
+          "$ref": "#/components/schemas/InputContent"
+        }
+      },
+      "InputMessageResource": {
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/InputMessage"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the message input.\n"
+              }
+            },
+            "required": [
+              "id",
+              "type"
+            ]
+          }
+        ]
+      },
+      "InputParam": {
+        "description": "Text, image, or file inputs to the model, used to generate a response.\n\nLearn more:\n- [Text inputs and outputs](https://developers.openai.com/api/docs/guides/text)\n- [Image inputs](https://developers.openai.com/api/docs/guides/images-vision)\n- [File inputs](https://developers.openai.com/api/docs/guides/file-inputs)\n- [Conversation state](https://developers.openai.com/api/docs/guides/conversation-state)\n- [Function calling](https://developers.openai.com/api/docs/guides/function-calling)\n",
+        "oneOf": [
+          {
+            "type": "string",
+            "title": "Text input",
+            "description": "A text input to the model, equivalent to a text input with the\n`user` role.\n"
+          },
+          {
+            "type": "array",
+            "title": "Input item list",
+            "description": "A list of one or many input items to the model, containing\ndifferent content types.\n",
+            "items": {
+              "$ref": "#/components/schemas/InputItem"
+            }
+          }
+        ]
+      },
+      "Invite": {
+        "type": "object",
+        "description": "Represents an individual `invite` to the organization.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.invite"
+            ],
+            "description": "The object type, which is always `organization.invite`",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The identifier, which can be referenced in API endpoints"
+          },
+          "email": {
+            "type": "string",
+            "description": "The email address of the individual to whom the invite was sent"
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "owner",
+              "reader"
+            ],
+            "description": "`owner` or `reader`"
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "accepted",
+              "expired",
+              "pending"
+            ],
+            "description": "`accepted`,`expired`, or `pending`"
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the invite was sent."
+          },
+          "expires_at": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "format": "unixtime"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The Unix timestamp (in seconds) of when the invite expires."
+          },
+          "accepted_at": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "format": "unixtime"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The Unix timestamp (in seconds) of when the invite was accepted."
+          },
+          "projects": {
+            "type": "array",
+            "description": "The projects that were granted membership upon acceptance of the invite.",
+            "items": {
+              "type": "object",
+              "properties": {
+                "id": {
+                  "type": "string",
+                  "description": "Project's public ID"
+                },
+                "role": {
+                  "type": "string",
+                  "enum": [
+                    "member",
+                    "owner"
+                  ],
+                  "description": "Project membership role"
+                }
+              },
+              "required": [
+                "id",
+                "role"
+              ]
+            }
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "email",
+          "role",
+          "status",
+          "created_at",
+          "projects"
+        ],
+        "x-oaiMeta": {
+          "name": "The invite object",
+          "example": "{\n  \"object\": \"organization.invite\",\n  \"id\": \"invite-abc\",\n  \"email\": \"user@example.com\",\n  \"role\": \"owner\",\n  \"status\": \"accepted\",\n  \"created_at\": 1711471533,\n  \"expires_at\": 1711471533,\n  \"accepted_at\": 1711471533,\n  \"projects\": [\n    {\n      \"id\": \"project-xyz\",\n      \"role\": \"member\"\n    }\n  ]\n}\n"
+        }
+      },
+      "InviteDeleteResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.invite.deleted"
+            ],
+            "description": "The object type, which is always `organization.invite.deleted`",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string"
+          },
+          "deleted": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "deleted"
+        ]
+      },
+      "InviteListResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "description": "The object type, which is always `list`",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/Invite"
+            }
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The first `invite_id` in the retrieved `list`"
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The last `invite_id` in the retrieved `list`"
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "The `has_more` property is used for pagination to indicate there are additional results."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more"
+        ]
+      },
+      "InviteProjectGroupBody": {
+        "type": "object",
+        "description": "Request payload for granting a group access to a project.",
+        "properties": {
+          "group_id": {
+            "type": "string",
+            "description": "Identifier of the group to add to the project."
+          },
+          "role": {
+            "type": "string",
+            "description": "Identifier of the project role to grant to the group."
+          }
+        },
+        "required": [
+          "group_id",
+          "role"
+        ],
+        "x-oaiMeta": {
+          "example": "{\n    \"group_id\": \"group_01J1F8ABCDXYZ\",\n    \"role\": \"role_01J1F8PROJ\"\n}\n"
+        }
+      },
+      "InviteRequest": {
+        "type": "object",
+        "properties": {
+          "email": {
+            "type": "string",
+            "description": "Send an email to this address"
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "reader",
+              "owner"
+            ],
+            "description": "`owner` or `reader`"
+          },
+          "projects": {
+            "type": "array",
+            "description": "An array of projects to which membership is granted at the same time the org invite is accepted. If omitted, the user will be invited to the default project for compatibility with legacy behavior. If empty list is passed, the user will not be invited to any projects, including the default one.",
+            "items": {
+              "type": "object",
+              "properties": {
+                "id": {
+                  "type": "string",
+                  "description": "Project's public ID"
+                },
+                "role": {
+                  "type": "string",
+                  "enum": [
+                    "member",
+                    "owner"
+                  ],
+                  "description": "Project membership role"
+                }
+              },
+              "required": [
+                "id",
+                "role"
+              ]
+            }
+          }
+        },
+        "required": [
+          "email",
+          "role"
+        ]
+      },
+      "Item": {
+        "type": "object",
+        "description": "Content item used to generate a response.\n",
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/InputMessage"
+          },
+          {
+            "$ref": "#/components/schemas/OutputMessage"
+          },
+          {
+            "$ref": "#/components/schemas/FileSearchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/ComputerToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/ComputerCallOutputItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/WebSearchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionCallOutputItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/ToolSearchCallItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/ToolSearchOutputItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/AdditionalToolsItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseConfigurationUpdateItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/ReasoningItem"
+          },
+          {
+            "$ref": "#/components/schemas/CompactionSummaryItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/ImageGenToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/CodeInterpreterToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/LocalShellToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/LocalShellToolCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionShellCallItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionShellCallOutputItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/ApplyPatchToolCallItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/ApplyPatchToolCallOutputItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/MCPListTools"
+          },
+          {
+            "$ref": "#/components/schemas/MCPApprovalRequest"
+          },
+          {
+            "$ref": "#/components/schemas/MCPApprovalResponse"
+          },
+          {
+            "$ref": "#/components/schemas/MCPToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/CustomToolCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/CustomToolCall"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "ItemResource": {
+        "description": "Content item used to generate a response.\n",
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/InputMessageResource"
+          },
+          {
+            "$ref": "#/components/schemas/OutputMessage"
+          },
+          {
+            "$ref": "#/components/schemas/FileSearchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/ComputerToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/ComputerToolCallOutputResource"
+          },
+          {
+            "$ref": "#/components/schemas/WebSearchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionToolCallResource"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionToolCallOutputResource"
+          },
+          {
+            "$ref": "#/components/schemas/ToolSearchCall"
+          },
+          {
+            "$ref": "#/components/schemas/ToolSearchOutput"
+          },
+          {
+            "$ref": "#/components/schemas/AdditionalTools"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseConfigurationUpdate"
+          },
+          {
+            "$ref": "#/components/schemas/ReasoningItem"
+          },
+          {
+            "$ref": "#/components/schemas/Program"
+          },
+          {
+            "$ref": "#/components/schemas/ProgramOutput"
+          },
+          {
+            "$ref": "#/components/schemas/CompactionBody"
+          },
+          {
+            "$ref": "#/components/schemas/ImageGenToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/CodeInterpreterToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/LocalShellToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/LocalShellToolCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionShellCall"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionShellCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/ApplyPatchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/ApplyPatchToolCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/MCPListTools"
+          },
+          {
+            "$ref": "#/components/schemas/MCPApprovalRequest"
+          },
+          {
+            "$ref": "#/components/schemas/MCPApprovalResponseResource"
+          },
+          {
+            "$ref": "#/components/schemas/MCPToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/CustomToolCallResource"
+          },
+          {
+            "$ref": "#/components/schemas/CustomToolCallOutputResource"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "ListAssistantsResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "example": "list"
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/AssistantObject"
+            }
+          },
+          "first_id": {
+            "type": "string",
+            "example": "asst_abc123"
+          },
+          "last_id": {
+            "type": "string",
+            "example": "asst_abc456"
+          },
+          "has_more": {
+            "type": "boolean",
+            "example": false
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "x-oaiMeta": {
+          "name": "List assistants response object",
+          "group": "chat",
+          "example": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"id\": \"asst_abc123\",\n      \"object\": \"assistant\",\n      \"created_at\": 1698982736,\n      \"name\": \"Coding Tutor\",\n      \"description\": null,\n      \"model\": \"gpt-5\",\n      \"instructions\": \"You are a helpful assistant designed to make me better at coding!\",\n      \"tools\": [],\n      \"tool_resources\": {},\n      \"metadata\": {},\n      \"top_p\": 1.0,\n      \"temperature\": 1.0,\n      \"response_format\": \"auto\"\n    },\n    {\n      \"id\": \"asst_abc456\",\n      \"object\": \"assistant\",\n      \"created_at\": 1698982718,\n      \"name\": \"My Assistant\",\n      \"description\": null,\n      \"model\": \"gpt-5\",\n      \"instructions\": \"You are a helpful assistant designed to make me better at coding!\",\n      \"tools\": [],\n      \"tool_resources\": {},\n      \"metadata\": {},\n      \"top_p\": 1.0,\n      \"temperature\": 1.0,\n      \"response_format\": \"auto\"\n    },\n    {\n      \"id\": \"asst_abc789\",\n      \"object\": \"assistant\",\n      \"created_at\": 1698982643,\n      \"name\": null,\n      \"description\": null,\n      \"model\": \"gpt-5\",\n      \"instructions\": null,\n      \"tools\": [],\n      \"tool_resources\": {},\n      \"metadata\": {},\n      \"top_p\": 1.0,\n      \"temperature\": 1.0,\n      \"response_format\": \"auto\"\n    }\n  ],\n  \"first_id\": \"asst_abc123\",\n  \"last_id\": \"asst_abc789\",\n  \"has_more\": false\n}\n"
+        }
+      },
+      "ListAuditLogsResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/AuditLog"
+            }
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "example": "audit_log-defb456h8dks"
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "example": "audit_log-hnbkd8s93s"
+          },
+          "has_more": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more"
+        ]
+      },
+      "ListBatchesResponse": {
+        "type": "object",
+        "properties": {
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/Batch"
+            }
+          },
+          "first_id": {
+            "type": "string",
+            "example": "batch_abc123"
+          },
+          "last_id": {
+            "type": "string",
+            "example": "batch_abc456"
+          },
+          "has_more": {
+            "type": "boolean"
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more"
+        ]
+      },
+      "ListCertificatesResponse": {
+        "type": "object",
+        "properties": {
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/OrganizationCertificate"
+            }
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "example": "cert_abc"
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "example": "cert_abc"
+          },
+          "has_more": {
+            "type": "boolean"
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more",
+          "first_id",
+          "last_id"
+        ]
+      },
+      "ListFilesResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "example": "list"
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/OpenAIFile"
+            }
+          },
+          "first_id": {
+            "type": "string",
+            "example": "file-abc123"
+          },
+          "last_id": {
+            "type": "string",
+            "example": "file-abc456"
+          },
+          "has_more": {
+            "type": "boolean",
+            "example": false
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ]
+      },
+      "ListFineTuningCheckpointPermissionResponse": {
+        "type": "object",
+        "properties": {
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/FineTuningCheckpointPermission"
+            }
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "x-stainless-const": true
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "has_more": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more"
+        ]
+      },
+      "ListFineTuningJobCheckpointsResponse": {
+        "type": "object",
+        "properties": {
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/FineTuningJobCheckpoint"
+            }
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "x-stainless-const": true
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "has_more": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more"
+        ]
+      },
+      "ListFineTuningJobEventsResponse": {
+        "type": "object",
+        "properties": {
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/FineTuningJobEvent"
+            }
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "x-stainless-const": true
+          },
+          "has_more": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more"
+        ]
+      },
+      "ListMessagesResponse": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "example": "list"
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/MessageObject"
+            }
+          },
+          "first_id": {
+            "type": "string",
+            "example": "msg_abc123"
+          },
+          "last_id": {
+            "type": "string",
+            "example": "msg_abc123"
+          },
+          "has_more": {
+            "type": "boolean",
+            "example": false
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ]
+      },
+      "ListModelsResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/Model"
+            }
+          }
+        },
+        "required": [
+          "object",
+          "data"
+        ]
+      },
+      "ListPaginatedFineTuningJobsResponse": {
+        "type": "object",
+        "properties": {
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/FineTuningJob"
+            }
+          },
+          "has_more": {
+            "type": "boolean"
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more"
+        ]
+      },
+      "ListProjectCertificatesResponse": {
+        "type": "object",
+        "properties": {
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/OrganizationProjectCertificate"
+            }
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "example": "cert_abc"
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "example": "cert_abc"
+          },
+          "has_more": {
+            "type": "boolean"
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more",
+          "first_id",
+          "last_id"
+        ]
+      },
+      "ListRunStepsResponse": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "example": "list"
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/RunStepObject"
+            }
+          },
+          "first_id": {
+            "type": "string",
+            "example": "step_abc123"
+          },
+          "last_id": {
+            "type": "string",
+            "example": "step_abc456"
+          },
+          "has_more": {
+            "type": "boolean",
+            "example": false
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ]
+      },
+      "ListRunsResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "example": "list"
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/RunObject"
+            }
+          },
+          "first_id": {
+            "type": "string",
+            "example": "run_abc123"
+          },
+          "last_id": {
+            "type": "string",
+            "example": "run_abc456"
+          },
+          "has_more": {
+            "type": "boolean",
+            "example": false
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ]
+      },
+      "ListVectorStoreFilesResponse": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "example": "list"
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/VectorStoreFileObject"
+            }
+          },
+          "first_id": {
+            "type": "string",
+            "example": "file-abc123"
+          },
+          "last_id": {
+            "type": "string",
+            "example": "file-abc456"
+          },
+          "has_more": {
+            "type": "boolean",
+            "example": false
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ]
+      },
+      "ListVectorStoresResponse": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "example": "list"
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/VectorStoreObject"
+            }
+          },
+          "first_id": {
+            "type": "string",
+            "example": "vs_abc123"
+          },
+          "last_id": {
+            "type": "string",
+            "example": "vs_abc456"
+          },
+          "has_more": {
+            "type": "boolean",
+            "example": false
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ]
+      },
+      "LiveCallAcceptRequest": {
+        "type": "object",
+        "description": "Accept an incoming SIP call with Live startup configuration.",
+        "properties": {
+          "session": {
+            "$ref": "#/components/schemas/LiveCallAcceptSession",
+            "description": "Model and startup configuration for the Live session that answers the incoming SIP call."
+          }
+        },
+        "required": [
+          "session"
+        ],
+        "additionalProperties": false
+      },
+      "LiveCallAcceptSession": {
+        "type": "object",
+        "description": "Startup configuration for accepting an incoming Live SIP call. Follow the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) when writing frontend and backend instructions.",
+        "properties": {
+          "model": {
+            "$ref": "#/components/schemas/ModelIdsLive",
+            "description": "The Live model to use for the accepted call.",
+            "minLength": 1
+          },
+          "instructions": {
+            "$ref": "#/components/schemas/instructions"
+          },
+          "audio": {
+            "$ref": "#/components/schemas/LiveMediaSessionAudioParam",
+            "description": "Startup audio output configuration. SIP negotiates the media format; audio.format is only accepted for primary WebSockets. Voice cannot change after startup."
+          },
+          "delegation": {
+            "$ref": "#/components/schemas/delegation"
+          },
+          "store": {
+            "$ref": "#/components/schemas/store"
+          },
+          "input": {
+            "$ref": "#/components/schemas/input"
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "live"
+            ],
+            "default": "live",
+            "x-stainless-const": true,
+            "description": "The session type. Always `live`."
+          }
+        },
+        "required": [
+          "model",
+          "type"
+        ],
+        "additionalProperties": false
+      },
+      "LiveCallReferRequest": {
+        "type": "object",
+        "description": "Parameters used to transfer a Live SIP call to another destination.",
+        "properties": {
+          "target_uri": {
+            "$ref": "#/components/schemas/target_uri",
+            "minLength": 1,
+            "pattern": "\\S",
+            "description": "Nonblank URI for the SIP Refer-To header, such as tel:+14155550123 or sip:agent@example.com."
+          }
+        },
+        "required": [
+          "target_uri"
+        ],
+        "additionalProperties": false
+      },
+      "LiveCallRejectRequest": {
+        "type": "object",
+        "description": "Parameters used to reject an incoming Live SIP call.",
+        "properties": {
+          "status_code": {
+            "type": "integer",
+            "minimum": 300,
+            "maximum": 699,
+            "description": "SIP rejection status sent to the caller. This field is required.",
+            "example": 486
+          }
+        },
+        "required": [
+          "status_code"
+        ],
+        "additionalProperties": false
+      },
+      "LiveClientEvent": {
+        "description": "Client events for Live. Initialize a primary WebSocket with session.start and wait for session.started. WebRTC creation already starts the session. Audio append is primary WebSocket-only. See the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) before writing frontend instructions and delegation policies.",
+        "discriminator": {
+          "propertyName": "type"
+        },
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/LiveSessionStartEvent"
+          },
+          {
+            "$ref": "#/components/schemas/LiveSessionUpdateParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInputAudioAppendEvent"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInputAudioMuteParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInputAudioUnmuteParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInstructionsAppendParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveThinkingAppendParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveCommentaryAppendParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveResponseItemCreateParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveResponseCreateParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveSessionCloseParam"
+          }
+        ]
+      },
+      "LiveConnectParams": {
+        "type": "object",
+        "x-stainless-empty-object": true,
+        "description": "Primary Live WebSocket connections accept no query parameters. Supply the model and startup configuration in the first session.start event.",
+        "properties": {},
+        "additionalProperties": false
+      },
+      "LiveCreateRequest": {
+        "type": "object",
+        "description": "Create a Live WebRTC session with JSON session configuration and an SDP offer. Follow the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) before choosing frontend and backend instructions. The request starts the session; do not send session.start on the data channel.",
+        "properties": {
+          "session": {
+            "$ref": "#/components/schemas/LiveMediaSessionCreateParams",
+            "description": "Startup configuration for the Live session."
+          },
+          "transport": {
+            "$ref": "#/components/schemas/LiveWebRTCTransport",
+            "description": "WebRTC transport with the browser's SDP offer."
+          }
+        },
+        "required": [
+          "session",
+          "transport"
+        ],
+        "additionalProperties": false
+      },
+      "LiveCreateResponse": {
+        "type": "object",
+        "description": "The created Live session identifier and WebRTC answer. Apply transport.sdp as the peer's remote answer and wait for session.started on the data channel before sending commands.",
+        "properties": {
+          "session": {
+            "type": "object",
+            "description": "The newly created Live session. Use its ID for session controls and sideband connections.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "Opaque session identifier. Preserve the returned value unchanged, including its prefix."
+              }
+            },
+            "required": [
+              "id"
+            ]
+          },
+          "transport": {
+            "$ref": "#/components/schemas/LiveWebRTCTransport",
+            "description": "WebRTC transport with the SDP answer."
+          }
+        },
+        "required": [
+          "session",
+          "transport"
+        ]
+      },
+      "LiveForkClientEvent": {
+        "description": "Client events for a Live fork WebSocket. First send session.start with an overrides object (which may be empty), then wait for session.started before sending other commands. The model and conversation are inherited from the stored session.",
+        "discriminator": {
+          "propertyName": "type"
+        },
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/LiveForkSessionStartEvent"
+          },
+          {
+            "$ref": "#/components/schemas/LiveSessionUpdateParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInputAudioAppendEvent"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInputAudioMuteParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInputAudioUnmuteParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInstructionsAppendParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveThinkingAppendParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveCommentaryAppendParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveResponseItemCreateParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveResponseCreateParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveSessionCloseParam"
+          }
+        ]
+      },
+      "LiveForkPathParams": {
+        "type": "object",
+        "description": "Identifies the stored Live session whose conversation and configuration are used to create a fork.",
+        "required": [
+          "session_id"
+        ],
+        "properties": {
+          "session_id": {
+            "type": "string",
+            "description": "The ID of the stored Live session to fork."
+          }
+        }
+      },
+      "LiveForkRequest": {
+        "type": "object",
+        "description": "Fork a stored Live session onto a new WebRTC connection. Omit session or send an empty object to inherit its configuration.",
+        "properties": {
+          "session": {
+            "$ref": "#/components/schemas/LiveMediaSessionForkParams",
+            "description": "Optional configuration overrides for the new Live session. Omit this object or send an empty object to inherit the stored session's settings."
+          },
+          "transport": {
+            "$ref": "#/components/schemas/LiveWebRTCTransport",
+            "description": "WebRTC transport with an SDP offer for the new connection to the forked session."
+          }
+        },
+        "required": [
+          "transport"
+        ],
+        "additionalProperties": false
+      },
+      "LiveForkServerEvent": {
+        "$ref": "#/components/schemas/LiveServerEvent"
+      },
+      "LiveMediaSessionAudioParam": {
+        "type": "object",
+        "description": "Startup audio output configuration. WebRTC and SIP negotiate the media format; audio.format is only accepted for primary WebSockets. Voice cannot change after startup.",
+        "properties": {
+          "output": {
+            "$ref": "#/components/schemas/LiveInitialSessionAudioOutputParam"
+          }
+        },
+        "additionalProperties": false
+      },
+      "LiveMediaSessionCreateParams": {
+        "type": "object",
+        "description": "Startup configuration for a Live media session. Follow the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) when writing frontend instructions and the backend prompt under delegation.responses.instructions.",
+        "properties": {
+          "model": {
+            "$ref": "#/components/schemas/ModelIdsLive"
+          },
+          "instructions": {
+            "$ref": "#/components/schemas/instructions"
+          },
+          "audio": {
+            "$ref": "#/components/schemas/LiveMediaSessionAudioParam",
+            "description": "Startup audio configuration. WebRTC and SIP negotiate their audio format on the media transport."
+          },
+          "delegation": {
+            "$ref": "#/components/schemas/delegation"
+          },
+          "store": {
+            "$ref": "#/components/schemas/store"
+          },
+          "input": {
+            "$ref": "#/components/schemas/input"
+          },
+          "client": {
+            "$ref": "#/components/schemas/LiveClientConfigParam"
+          }
+        },
+        "required": [
+          "model"
+        ],
+        "additionalProperties": false
+      },
+      "LiveMediaSessionForkParams": {
+        "type": "object",
+        "description": "Optional overrides for a stored Live session. Omitted settings are inherited. The model, voice, frontend instructions, and prior conversation come from the stored session. WebRTC negotiates its audio format; audio.format is only supported on WebSocket forks.",
+        "properties": {
+          "store": {
+            "$ref": "#/components/schemas/properties-store"
+          },
+          "delegation": {
+            "$ref": "#/components/schemas/LiveResponsesDelegationUpdateParam"
+          },
+          "client": {
+            "$ref": "#/components/schemas/LiveClientConfigParam"
+          }
+        },
+        "additionalProperties": false
+      },
+      "LiveServerEvent": {
+        "description": "Server events for Live. Response lifecycle events are wrapped inside response.event; dispatch the nested event by its full type and tolerate new response event types. Follow the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) when designing the conversation and delegation policy.",
+        "discriminator": {
+          "propertyName": "type"
+        },
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/LiveServerEvent-2"
+          }
+        ]
+      },
+      "LiveSidebandClientEvent": {
+        "description": "Client events accepted by an attached Live sideband WebSocket. The session is already started; send audio over the primary connection.",
+        "discriminator": {
+          "propertyName": "type"
+        },
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/LiveSessionUpdateParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInputAudioMuteParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInputAudioUnmuteParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInstructionsAppendParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveThinkingAppendParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveCommentaryAppendParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveResponseItemCreateParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveResponseCreateParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveSessionCloseParam"
+          }
+        ]
+      },
+      "LiveSidebandConnectParams": {
+        "type": "object",
+        "description": "Connection options for a sideband WebSocket attached to an existing Live session.",
+        "properties": {
+          "graceful_close": {
+            "type": "boolean",
+            "description": "Opt in to the graceful WebSocket closing handshake when the session ends. The server may also enable this behavior by default."
+          }
+        },
+        "additionalProperties": false
+      },
+      "LiveSidebandPathParams": {
+        "type": "object",
+        "description": "Identifies the Live session to observe and control through a sideband WebSocket.",
+        "required": [
+          "session_id"
+        ],
+        "properties": {
+          "session_id": {
+            "type": "string",
+            "description": "The ID of the existing Live session to attach to."
+          }
+        }
+      },
+      "LiveSidebandServerEvent": {
+        "description": "Server events received by an attached Live sideband WebSocket. Audio deltas are delivered over the primary connection.",
+        "discriminator": {
+          "propertyName": "type"
+        },
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/LiveSessionStarted"
+          },
+          {
+            "$ref": "#/components/schemas/LiveSessionUpdated"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInputAudioMuted"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInputAudioUnmuted"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInstructionsAppended"
+          },
+          {
+            "$ref": "#/components/schemas/LiveThinkingAppended"
+          },
+          {
+            "$ref": "#/components/schemas/LiveCommentaryAppended"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInputTranscriptDelta"
+          },
+          {
+            "$ref": "#/components/schemas/LiveOutputTranscriptDelta"
+          },
+          {
+            "$ref": "#/components/schemas/LiveDelegationCreated"
+          },
+          {
+            "$ref": "#/components/schemas/LiveResponseEvent"
+          },
+          {
+            "$ref": "#/components/schemas/LiveSessionUsageUpdated"
+          },
+          {
+            "$ref": "#/components/schemas/LiveSessionClosed"
+          },
+          {
+            "$ref": "#/components/schemas/LiveErrorEvent"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInfoEvent"
+          }
+        ]
+      },
+      "LiveWebRTCTransport": {
+        "type": "object",
+        "description": "WebRTC transport carrying the offer SDP in a creation request or answer SDP in its response.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The transport used for the Live session. Always `webrtc`.",
+            "enum": [
+              "webrtc"
+            ],
+            "x-stainless-const": true
+          },
+          "sdp": {
+            "type": "string",
+            "minLength": 1,
+            "description": "Session Description Protocol message for the WebRTC connection."
+          }
+        },
+        "required": [
+          "type",
+          "sdp"
+        ],
+        "additionalProperties": false
+      },
+      "LocalShellToolCall": {
+        "type": "object",
+        "title": "Local shell call",
+        "description": "A tool call to run a command on the local shell.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "local_shell_call"
+            ],
+            "description": "The type of the local shell call. Always `local_shell_call`.\n",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the local shell call.\n"
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The unique ID of the local shell tool call generated by the model.\n"
+          },
+          "action": {
+            "$ref": "#/components/schemas/LocalShellExecAction"
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "in_progress",
+              "completed",
+              "incomplete"
+            ],
+            "description": "The status of the local shell call.\n"
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "action",
+          "status"
+        ]
+      },
+      "LocalShellToolCallOutput": {
+        "type": "object",
+        "title": "Local shell call output",
+        "description": "The output of a local shell tool call.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "local_shell_call_output"
+            ],
+            "description": "The type of the local shell tool call output. Always `local_shell_call_output`.\n",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the local shell tool call generated by the model.\n"
+          },
+          "output": {
+            "type": "string",
+            "description": "A JSON string of the output of the local shell tool call.\n"
+          },
+          "status": {
+            "anyOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "in_progress",
+                  "completed",
+                  "incomplete"
+                ],
+                "description": "The status of the item. One of `in_progress`, `completed`, or `incomplete`.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "type",
+          "call_id",
+          "output"
+        ]
+      },
+      "LogProbProperties": {
+        "type": "object",
+        "description": "A log probability object.\n",
+        "properties": {
+          "token": {
+            "type": "string",
+            "description": "The token that was used to generate the log probability.\n"
+          },
+          "logprob": {
+            "type": "number",
+            "description": "The log probability of the token.\n"
+          },
+          "bytes": {
+            "type": "array",
+            "items": {
+              "type": "integer"
+            },
+            "description": "The bytes that were used to generate the log probability.\n"
+          }
+        },
+        "required": [
+          "token",
+          "logprob",
+          "bytes"
+        ]
+      },
+      "MCPApprovalRequest": {
+        "type": "object",
+        "title": "MCP approval request",
+        "description": "A request for human approval of a tool invocation.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_approval_request"
+            ],
+            "description": "The type of the item. Always `mcp_approval_request`.\n",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the approval request.\n"
+          },
+          "server_label": {
+            "type": "string",
+            "description": "The label of the MCP server making the request.\n"
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the tool to run.\n"
+          },
+          "arguments": {
+            "type": "string",
+            "description": "A JSON string of arguments for the tool.\n"
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "server_label",
+          "name",
+          "arguments"
+        ]
+      },
+      "MCPApprovalResponse": {
+        "type": "object",
+        "title": "MCP approval response",
+        "description": "A response to an MCP approval request.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_approval_response"
+            ],
+            "description": "The type of the item. Always `mcp_approval_response`.\n",
+            "x-stainless-const": true
+          },
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the approval response\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "approval_request_id": {
+            "type": "string",
+            "description": "The ID of the approval request being answered.\n"
+          },
+          "approve": {
+            "type": "boolean",
+            "description": "Whether the request was approved.\n"
+          },
+          "reason": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Optional reason for the decision.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "request_id",
+          "approve",
+          "approval_request_id"
+        ]
+      },
+      "MCPApprovalResponseResource": {
+        "type": "object",
+        "title": "MCP approval response",
+        "description": "A response to an MCP approval request.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_approval_response"
+            ],
+            "description": "The type of the item. Always `mcp_approval_response`.\n",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the approval response\n"
+          },
+          "approval_request_id": {
+            "type": "string",
+            "description": "The ID of the approval request being answered.\n"
+          },
+          "approve": {
+            "type": "boolean",
+            "description": "Whether the request was approved.\n"
+          },
+          "reason": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Optional reason for the decision.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "request_id",
+          "approve",
+          "approval_request_id"
+        ]
+      },
+      "MCPListTools": {
+        "type": "object",
+        "title": "MCP list tools",
+        "description": "A list of tools available on an MCP server.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_list_tools"
+            ],
+            "description": "The type of the item. Always `mcp_list_tools`.\n",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the list.\n"
+          },
+          "server_label": {
+            "type": "string",
+            "description": "The label of the MCP server.\n"
+          },
+          "tools": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/MCPListToolsTool"
+            },
+            "description": "The tools available on the server.\n"
+          },
+          "error": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Error message if the server could not list tools.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "server_label",
+          "tools"
+        ]
+      },
+      "MCPListToolsTool": {
+        "type": "object",
+        "title": "MCP list tools tool",
+        "description": "A tool available on an MCP server.\n",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The name of the tool.\n"
+          },
+          "description": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The description of the tool.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "input_schema": {
+            "type": "object",
+            "description": "The JSON schema describing the tool's input.\n"
+          },
+          "annotations": {
+            "anyOf": [
+              {
+                "type": "object",
+                "description": "Additional annotations about the tool.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "name",
+          "input_schema"
+        ]
+      },
+      "MCPTool": {
+        "type": "object",
+        "title": "MCP tool",
+        "description": "Give the model access to additional tools via remote Model Context Protocol\n(MCP) servers. [Learn more about MCP](https://developers.openai.com/api/docs/guides/tools-connectors-mcp).\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp"
+            ],
+            "description": "The type of the MCP tool. Always `mcp`.",
+            "x-stainless-const": true
+          },
+          "server_label": {
+            "type": "string",
+            "description": "A label for this MCP server, used to identify it in tool calls.\n"
+          },
+          "server_url": {
+            "type": "string",
+            "format": "uri",
+            "description": "The URL for the MCP server. One of `server_url`, `connector_id`, or\n`tunnel_id` must be provided.\n"
+          },
+          "connector_id": {
+            "type": "string",
+            "enum": [
+              "connector_dropbox",
+              "connector_gmail",
+              "connector_googlecalendar",
+              "connector_googledrive",
+              "connector_microsoftteams",
+              "connector_outlookcalendar",
+              "connector_outlookemail",
+              "connector_sharepoint"
+            ],
+            "description": "Identifier for service connectors, like those available in ChatGPT. One of\n`server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more\nabout service connectors [here](https://developers.openai.com/api/docs/guides/tools-connectors-mcp#connectors).\n\nCurrently supported `connector_id` values are:\n\n- Dropbox: `connector_dropbox`\n- Gmail: `connector_gmail`\n- Google Calendar: `connector_googlecalendar`\n- Google Drive: `connector_googledrive`\n- Microsoft Teams: `connector_microsoftteams`\n- Outlook Calendar: `connector_outlookcalendar`\n- Outlook Email: `connector_outlookemail`\n- SharePoint: `connector_sharepoint`\n"
+          },
+          "tunnel_id": {
+            "type": "string",
+            "pattern": "^tunnel_[a-z0-9]{32}$",
+            "description": "The Secure MCP Tunnel ID to use instead of a direct server URL. One of\n`server_url`, `connector_id`, or `tunnel_id` must be provided.\n"
+          },
+          "authorization": {
+            "type": "string",
+            "description": "An OAuth access token that can be used with a remote MCP server, either\nwith a custom MCP server URL or a service connector. Your application\nmust handle the OAuth authorization flow and provide the token here.\n"
+          },
+          "server_description": {
+            "type": "string",
+            "description": "Optional description of the MCP server, used to provide more context.\n"
+          },
+          "headers": {
+            "anyOf": [
+              {
+                "type": "object",
+                "additionalProperties": {
+                  "type": "string"
+                },
+                "description": "Optional HTTP headers to send to the MCP server. Use for authentication\nor other purposes.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "allowed_tools": {
+            "anyOf": [
+              {
+                "description": "List of allowed tool names or a filter object.\n",
+                "oneOf": [
+                  {
+                    "type": "array",
+                    "title": "MCP allowed tools",
+                    "description": "A string array of allowed tool names",
+                    "items": {
+                      "type": "string"
+                    }
+                  },
+                  {
+                    "$ref": "#/components/schemas/MCPToolFilter"
+                  }
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "allowed_callers": {
+            "anyOf": [
+              {
+                "type": "array",
+                "minItems": 1,
+                "items": {
+                  "$ref": "#/components/schemas/CallableToolAllowedCaller"
+                },
+                "description": "The tool invocation context(s)."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "require_approval": {
+            "anyOf": [
+              {
+                "description": "Specify which of the MCP server's tools require approval.",
+                "oneOf": [
+                  {
+                    "type": "object",
+                    "title": "MCP tool approval filter",
+                    "description": "Specify which of the MCP server's tools require approval. Can be\n`always`, `never`, or a filter object associated with tools\nthat require approval.\n",
+                    "properties": {
+                      "always": {
+                        "$ref": "#/components/schemas/MCPToolFilter"
+                      },
+                      "never": {
+                        "$ref": "#/components/schemas/MCPToolFilter"
+                      }
+                    },
+                    "additionalProperties": false
+                  },
+                  {
+                    "type": "string",
+                    "title": "MCP tool approval setting",
+                    "description": "Specify a single approval policy for all tools. One of `always` or\n`never`. When set to `always`, all tools will require approval. When\nset to `never`, all tools will not require approval.\n",
+                    "enum": [
+                      "always",
+                      "never"
+                    ]
+                  }
+                ],
+                "default": "always"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "defer_loading": {
+            "type": "boolean",
+            "description": "Whether this MCP tool is deferred and discovered via tool search.\n"
+          }
+        },
+        "required": [
+          "type",
+          "server_label"
+        ]
+      },
+      "MCPToolCall": {
+        "type": "object",
+        "title": "MCP tool call",
+        "description": "An invocation of a tool on an MCP server.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_call"
+            ],
+            "description": "The type of the item. Always `mcp_call`.\n",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the tool call.\n"
+          },
+          "server_label": {
+            "type": "string",
+            "description": "The label of the MCP server running the tool.\n"
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the tool that was run.\n"
+          },
+          "arguments": {
+            "type": "string",
+            "description": "A JSON string of the arguments passed to the tool.\n"
+          },
+          "output": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The output from the tool call.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "error": {
+            "description": "The error from the tool call, if any.",
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/MCPToolCallError"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "$ref": "#/components/schemas/MCPToolCallStatus",
+            "description": "The status of the tool call. One of `in_progress`, `completed`, `incomplete`, `calling`, or `failed`.\n"
+          },
+          "approval_request_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Unique identifier for the MCP tool call approval request.\nInclude this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "server_label",
+          "name",
+          "arguments"
+        ]
+      },
+      "MCPToolCallError": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/MCPProtocolError"
+          },
+          {
+            "$ref": "#/components/schemas/MCPToolExecutionError"
+          },
+          {
+            "$ref": "#/components/schemas/HTTPError"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "MCPToolFilter": {
+        "type": "object",
+        "title": "MCP tool filter",
+        "description": "A filter object to specify which tools are allowed.\n",
+        "properties": {
+          "tool_names": {
+            "type": "array",
+            "title": "MCP allowed tools",
+            "items": {
+              "type": "string"
+            },
+            "description": "List of allowed tool names."
+          },
+          "read_only": {
+            "type": "boolean",
+            "description": "Indicates whether or not a tool modifies data or is read-only. If an\nMCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint),\nit will match this filter.\n"
+          }
+        },
+        "required": [],
+        "additionalProperties": false
+      },
+      "MessageContentImageFileObject": {
+        "title": "Image file",
+        "type": "object",
+        "description": "References an image [File](https://developers.openai.com/api/reference/resources/files) in the content of a message.",
+        "properties": {
+          "type": {
+            "description": "Always `image_file`.",
+            "type": "string",
+            "enum": [
+              "image_file"
+            ],
+            "x-stainless-const": true
+          },
+          "image_file": {
+            "type": "object",
+            "properties": {
+              "file_id": {
+                "description": "The [File](https://developers.openai.com/api/reference/resources/files) ID of the image in the message content. Set `purpose=\"vision\"` when uploading the File if you need to later display the file content.",
+                "type": "string"
+              },
+              "detail": {
+                "type": "string",
+                "description": "Specifies the detail level of the image if specified by the user. `low` uses fewer tokens, you can opt in to high resolution using `high`.",
+                "enum": [
+                  "auto",
+                  "low",
+                  "high"
+                ],
+                "default": "auto"
+              }
+            },
+            "required": [
+              "file_id"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "image_file"
+        ]
+      },
+      "MessageContentImageUrlObject": {
+        "title": "Image URL",
+        "type": "object",
+        "description": "References an image URL in the content of a message.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "image_url"
+            ],
+            "description": "The type of the content part.",
+            "x-stainless-const": true
+          },
+          "image_url": {
+            "type": "object",
+            "properties": {
+              "url": {
+                "type": "string",
+                "description": "The external URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp.",
+                "format": "uri"
+              },
+              "detail": {
+                "type": "string",
+                "description": "Specifies the detail level of the image. `low` uses fewer tokens, you can opt in to high resolution using `high`. Default value is `auto`",
+                "enum": [
+                  "auto",
+                  "low",
+                  "high"
+                ],
+                "default": "auto"
+              }
+            },
+            "required": [
+              "url"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "image_url"
+        ]
+      },
+      "MessageContentRefusalObject": {
+        "title": "Refusal",
+        "type": "object",
+        "description": "The refusal content generated by the assistant.",
+        "properties": {
+          "type": {
+            "description": "Always `refusal`.",
+            "type": "string",
+            "enum": [
+              "refusal"
+            ],
+            "x-stainless-const": true
+          },
+          "refusal": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "type",
+          "refusal"
+        ]
+      },
+      "MessageContentTextAnnotationsFileCitationObject": {
+        "title": "File citation",
+        "type": "object",
+        "description": "A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the \"file_search\" tool to search files.",
+        "properties": {
+          "type": {
+            "description": "Always `file_citation`.",
+            "type": "string",
+            "enum": [
+              "file_citation"
+            ],
+            "x-stainless-const": true
+          },
+          "text": {
+            "description": "The text in the message content that needs to be replaced.",
+            "type": "string"
+          },
+          "file_citation": {
+            "type": "object",
+            "properties": {
+              "file_id": {
+                "description": "The ID of the specific File the citation is from.",
+                "type": "string"
+              }
+            },
+            "required": [
+              "file_id"
+            ]
+          },
+          "start_index": {
+            "type": "integer",
+            "minimum": 0
+          },
+          "end_index": {
+            "type": "integer",
+            "minimum": 0
+          }
+        },
+        "required": [
+          "type",
+          "text",
+          "file_citation",
+          "start_index",
+          "end_index"
+        ]
+      },
+      "MessageContentTextAnnotationsFilePathObject": {
+        "title": "File path",
+        "type": "object",
+        "description": "A URL for the file that's generated when the assistant used the `code_interpreter` tool to generate a file.",
+        "properties": {
+          "type": {
+            "description": "Always `file_path`.",
+            "type": "string",
+            "enum": [
+              "file_path"
+            ],
+            "x-stainless-const": true
+          },
+          "text": {
+            "description": "The text in the message content that needs to be replaced.",
+            "type": "string"
+          },
+          "file_path": {
+            "type": "object",
+            "properties": {
+              "file_id": {
+                "description": "The ID of the file that was generated.",
+                "type": "string"
+              }
+            },
+            "required": [
+              "file_id"
+            ]
+          },
+          "start_index": {
+            "type": "integer",
+            "minimum": 0
+          },
+          "end_index": {
+            "type": "integer",
+            "minimum": 0
+          }
+        },
+        "required": [
+          "type",
+          "text",
+          "file_path",
+          "start_index",
+          "end_index"
+        ]
+      },
+      "MessageContentTextObject": {
+        "title": "Text",
+        "type": "object",
+        "description": "The text content that is part of a message.",
+        "properties": {
+          "type": {
+            "description": "Always `text`.",
+            "type": "string",
+            "enum": [
+              "text"
+            ],
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "object",
+            "properties": {
+              "value": {
+                "description": "The data that makes up the text.",
+                "type": "string"
+              },
+              "annotations": {
+                "type": "array",
+                "items": {
+                  "oneOf": [
+                    {
+                      "$ref": "#/components/schemas/MessageContentTextAnnotationsFileCitationObject"
+                    },
+                    {
+                      "$ref": "#/components/schemas/MessageContentTextAnnotationsFilePathObject"
+                    }
+                  ]
+                }
+              }
+            },
+            "required": [
+              "value",
+              "annotations"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ]
+      },
+      "MessageDeltaContentImageFileObject": {
+        "title": "Image file",
+        "type": "object",
+        "description": "References an image [File](https://developers.openai.com/api/reference/resources/files) in the content of a message.",
+        "properties": {
+          "index": {
+            "type": "integer",
+            "description": "The index of the content part in the message."
+          },
+          "type": {
+            "description": "Always `image_file`.",
+            "type": "string",
+            "enum": [
+              "image_file"
+            ],
+            "x-stainless-const": true
+          },
+          "image_file": {
+            "type": "object",
+            "properties": {
+              "file_id": {
+                "description": "The [File](https://developers.openai.com/api/reference/resources/files) ID of the image in the message content. Set `purpose=\"vision\"` when uploading the File if you need to later display the file content.",
+                "type": "string"
+              },
+              "detail": {
+                "type": "string",
+                "description": "Specifies the detail level of the image if specified by the user. `low` uses fewer tokens, you can opt in to high resolution using `high`.",
+                "enum": [
+                  "auto",
+                  "low",
+                  "high"
+                ],
+                "default": "auto"
+              }
+            }
+          }
+        },
+        "required": [
+          "index",
+          "type"
+        ]
+      },
+      "MessageDeltaContentImageUrlObject": {
+        "title": "Image URL",
+        "type": "object",
+        "description": "References an image URL in the content of a message.",
+        "properties": {
+          "index": {
+            "type": "integer",
+            "description": "The index of the content part in the message."
+          },
+          "type": {
+            "description": "Always `image_url`.",
+            "type": "string",
+            "enum": [
+              "image_url"
+            ],
+            "x-stainless-const": true
+          },
+          "image_url": {
+            "type": "object",
+            "properties": {
+              "url": {
+                "description": "The URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp.",
+                "type": "string",
+                "format": "uri"
+              },
+              "detail": {
+                "type": "string",
+                "description": "Specifies the detail level of the image. `low` uses fewer tokens, you can opt in to high resolution using `high`.",
+                "enum": [
+                  "auto",
+                  "low",
+                  "high"
+                ],
+                "default": "auto"
+              }
+            }
+          }
+        },
+        "required": [
+          "index",
+          "type"
+        ]
+      },
+      "MessageDeltaContentRefusalObject": {
+        "title": "Refusal",
+        "type": "object",
+        "description": "The refusal content that is part of a message.",
+        "properties": {
+          "index": {
+            "type": "integer",
+            "description": "The index of the refusal part in the message."
+          },
+          "type": {
+            "description": "Always `refusal`.",
+            "type": "string",
+            "enum": [
+              "refusal"
+            ],
+            "x-stainless-const": true
+          },
+          "refusal": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "index",
+          "type"
+        ]
+      },
+      "MessageDeltaContentTextAnnotationsFileCitationObject": {
+        "title": "File citation",
+        "type": "object",
+        "description": "A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the \"file_search\" tool to search files.",
+        "properties": {
+          "index": {
+            "type": "integer",
+            "description": "The index of the annotation in the text content part."
+          },
+          "type": {
+            "description": "Always `file_citation`.",
+            "type": "string",
+            "enum": [
+              "file_citation"
+            ],
+            "x-stainless-const": true
+          },
+          "text": {
+            "description": "The text in the message content that needs to be replaced.",
+            "type": "string"
+          },
+          "file_citation": {
+            "type": "object",
+            "properties": {
+              "file_id": {
+                "description": "The ID of the specific File the citation is from.",
+                "type": "string"
+              },
+              "quote": {
+                "description": "The specific quote in the file.",
+                "type": "string"
+              }
+            }
+          },
+          "start_index": {
+            "type": "integer",
+            "minimum": 0
+          },
+          "end_index": {
+            "type": "integer",
+            "minimum": 0
+          }
+        },
+        "required": [
+          "index",
+          "type"
+        ]
+      },
+      "MessageDeltaContentTextAnnotationsFilePathObject": {
+        "title": "File path",
+        "type": "object",
+        "description": "A URL for the file that's generated when the assistant used the `code_interpreter` tool to generate a file.",
+        "properties": {
+          "index": {
+            "type": "integer",
+            "description": "The index of the annotation in the text content part."
+          },
+          "type": {
+            "description": "Always `file_path`.",
+            "type": "string",
+            "enum": [
+              "file_path"
+            ],
+            "x-stainless-const": true
+          },
+          "text": {
+            "description": "The text in the message content that needs to be replaced.",
+            "type": "string"
+          },
+          "file_path": {
+            "type": "object",
+            "properties": {
+              "file_id": {
+                "description": "The ID of the file that was generated.",
+                "type": "string"
+              }
+            }
+          },
+          "start_index": {
+            "type": "integer",
+            "minimum": 0
+          },
+          "end_index": {
+            "type": "integer",
+            "minimum": 0
+          }
+        },
+        "required": [
+          "index",
+          "type"
+        ]
+      },
+      "MessageDeltaContentTextObject": {
+        "title": "Text",
+        "type": "object",
+        "description": "The text content that is part of a message.",
+        "properties": {
+          "index": {
+            "type": "integer",
+            "description": "The index of the content part in the message."
+          },
+          "type": {
+            "description": "Always `text`.",
+            "type": "string",
+            "enum": [
+              "text"
+            ],
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "object",
+            "properties": {
+              "value": {
+                "description": "The data that makes up the text.",
+                "type": "string"
+              },
+              "annotations": {
+                "type": "array",
+                "items": {
+                  "oneOf": [
+                    {
+                      "$ref": "#/components/schemas/MessageDeltaContentTextAnnotationsFileCitationObject"
+                    },
+                    {
+                      "$ref": "#/components/schemas/MessageDeltaContentTextAnnotationsFilePathObject"
+                    }
+                  ]
+                }
+              }
+            }
+          }
+        },
+        "required": [
+          "index",
+          "type"
+        ]
+      },
+      "MessageDeltaObject": {
+        "type": "object",
+        "title": "Message delta object",
+        "description": "Represents a message delta i.e. any changed fields on a message during streaming.\n",
+        "properties": {
+          "id": {
+            "description": "The identifier of the message, which can be referenced in API endpoints.",
+            "type": "string"
+          },
+          "object": {
+            "description": "The object type, which is always `thread.message.delta`.",
+            "type": "string",
+            "enum": [
+              "thread.message.delta"
+            ],
+            "x-stainless-const": true
+          },
+          "delta": {
+            "description": "The delta containing the fields that have changed on the Message.",
+            "type": "object",
+            "properties": {
+              "role": {
+                "description": "The entity that produced the message. One of `user` or `assistant`.",
+                "type": "string",
+                "enum": [
+                  "user",
+                  "assistant"
+                ]
+              },
+              "content": {
+                "description": "The content of the message in array of text and/or images.",
+                "type": "array",
+                "items": {
+                  "oneOf": [
+                    {
+                      "$ref": "#/components/schemas/MessageDeltaContentImageFileObject"
+                    },
+                    {
+                      "$ref": "#/components/schemas/MessageDeltaContentTextObject"
+                    },
+                    {
+                      "$ref": "#/components/schemas/MessageDeltaContentRefusalObject"
+                    },
+                    {
+                      "$ref": "#/components/schemas/MessageDeltaContentImageUrlObject"
+                    }
+                  ]
+                }
+              }
+            }
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "delta"
+        ],
+        "x-oaiMeta": {
+          "name": "The message delta object",
+          "beta": true,
+          "example": "{\n  \"id\": \"msg_123\",\n  \"object\": \"thread.message.delta\",\n  \"delta\": {\n    \"content\": [\n      {\n        \"index\": 0,\n        \"type\": \"text\",\n        \"text\": { \"value\": \"Hello\", \"annotations\": [] }\n      }\n    ]\n  }\n}\n"
+        }
+      },
+      "MessageObject": {
+        "type": "object",
+        "title": "The message object",
+        "description": "Represents a message within a [thread](https://developers.openai.com/api/docs/assistants/migration).",
+        "properties": {
+          "id": {
+            "description": "The identifier, which can be referenced in API endpoints.",
+            "type": "string"
+          },
+          "object": {
+            "description": "The object type, which is always `thread.message`.",
+            "type": "string",
+            "enum": [
+              "thread.message"
+            ],
+            "x-stainless-const": true
+          },
+          "created_at": {
+            "description": "The Unix timestamp (in seconds) for when the message was created.",
+            "type": "integer",
+            "format": "unixtime"
+          },
+          "thread_id": {
+            "description": "The [thread](https://developers.openai.com/api/docs/assistants/migration) ID that this message belongs to.",
+            "type": "string"
+          },
+          "status": {
+            "description": "The status of the message, which can be either `in_progress`, `incomplete`, or `completed`.",
+            "type": "string",
+            "enum": [
+              "in_progress",
+              "incomplete",
+              "completed"
+            ]
+          },
+          "incomplete_details": {
+            "anyOf": [
+              {
+                "description": "On an incomplete message, details about why the message is incomplete.",
+                "type": "object",
+                "properties": {
+                  "reason": {
+                    "type": "string",
+                    "description": "The reason the message is incomplete.",
+                    "enum": [
+                      "content_filter",
+                      "max_tokens",
+                      "run_cancelled",
+                      "run_expired",
+                      "run_failed"
+                    ]
+                  }
+                },
+                "required": [
+                  "reason"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "completed_at": {
+            "anyOf": [
+              {
+                "description": "The Unix timestamp (in seconds) for when the message was completed.",
+                "type": "integer",
+                "format": "unixtime"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "incomplete_at": {
+            "anyOf": [
+              {
+                "description": "The Unix timestamp (in seconds) for when the message was marked as incomplete.",
+                "type": "integer",
+                "format": "unixtime"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "role": {
+            "description": "The entity that produced the message. One of `user` or `assistant`.",
+            "type": "string",
+            "enum": [
+              "user",
+              "assistant"
+            ]
+          },
+          "content": {
+            "description": "The content of the message in array of text and/or images.",
+            "type": "array",
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/MessageContentImageFileObject"
+                },
+                {
+                  "$ref": "#/components/schemas/MessageContentImageUrlObject"
+                },
+                {
+                  "$ref": "#/components/schemas/MessageContentTextObject"
+                },
+                {
+                  "$ref": "#/components/schemas/MessageContentRefusalObject"
+                }
+              ]
+            }
+          },
+          "assistant_id": {
+            "anyOf": [
+              {
+                "description": "If applicable, the ID of the [assistant](https://developers.openai.com/api/docs/assistants/migration) that authored this message.",
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "run_id": {
+            "anyOf": [
+              {
+                "description": "The ID of the [run](https://developers.openai.com/api/docs/assistants/migration) associated with the creation of this message. Value is `null` when messages are created manually using the create message or create thread endpoints.",
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "attachments": {
+            "anyOf": [
+              {
+                "type": "array",
+                "items": {
+                  "type": "object",
+                  "properties": {
+                    "file_id": {
+                      "type": "string",
+                      "description": "The ID of the file to attach to the message."
+                    },
+                    "tools": {
+                      "description": "The tools to add this file to.",
+                      "type": "array",
+                      "items": {
+                        "oneOf": [
+                          {
+                            "$ref": "#/components/schemas/AssistantToolsCode"
+                          },
+                          {
+                            "$ref": "#/components/schemas/AssistantToolsFileSearchTypeOnly"
+                          }
+                        ]
+                      }
+                    }
+                  }
+                },
+                "description": "A list of files attached to the message, and the tools they were added to."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "created_at",
+          "thread_id",
+          "status",
+          "incomplete_details",
+          "completed_at",
+          "incomplete_at",
+          "role",
+          "content",
+          "assistant_id",
+          "run_id",
+          "attachments",
+          "metadata"
+        ],
+        "x-oaiMeta": {
+          "name": "The message object",
+          "beta": true,
+          "example": "{\n  \"id\": \"msg_abc123\",\n  \"object\": \"thread.message\",\n  \"created_at\": 1698983503,\n  \"thread_id\": \"thread_abc123\",\n  \"role\": \"assistant\",\n  \"content\": [\n    {\n      \"type\": \"text\",\n      \"text\": {\n        \"value\": \"Hi! How can I help you today?\",\n        \"annotations\": []\n      }\n    }\n  ],\n  \"assistant_id\": \"asst_abc123\",\n  \"run_id\": \"run_abc123\",\n  \"attachments\": [],\n  \"metadata\": {}\n}\n"
+        }
+      },
+      "MessagePhase": {
+        "type": "string",
+        "description": "Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`).\nFor models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend\nphase on all assistant messages — dropping it can degrade performance. Not used for user messages.\n",
+        "enum": [
+          "commentary",
+          "final_answer"
+        ]
+      },
+      "MessageRequestContentTextObject": {
+        "title": "Text",
+        "type": "object",
+        "description": "The text content that is part of a message.",
+        "properties": {
+          "type": {
+            "description": "Always `text`.",
+            "type": "string",
+            "enum": [
+              "text"
+            ],
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string",
+            "description": "Text content to be sent to the model"
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ]
+      },
+      "MessageStreamEvent": {
+        "oneOf": [
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.message.created"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/MessageObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a [message](https://developers.openai.com/api/docs/assistants/migration) is created.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [message](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          },
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.message.in_progress"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/MessageObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a [message](https://developers.openai.com/api/docs/assistants/migration) moves to an `in_progress` state.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [message](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          },
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.message.delta"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/MessageDeltaObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when parts of a [Message](https://developers.openai.com/api/docs/assistants/migration) are being streamed.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [message delta](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          },
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.message.completed"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/MessageObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a [message](https://developers.openai.com/api/docs/assistants/migration) is completed.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [message](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          },
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.message.incomplete"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/MessageObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a [message](https://developers.openai.com/api/docs/assistants/migration) ends before it is completed.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [message](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          }
+        ]
+      },
+      "Metadata": {
+        "anyOf": [
+          {
+            "type": "object",
+            "description": "Set of 16 key-value pairs that can be attached to an object. This can be\nuseful for storing additional information about the object in a structured\nformat, and querying for objects via API or the dashboard.\n\nKeys are strings with a maximum length of 64 characters. Values are strings\nwith a maximum length of 512 characters.\n",
+            "additionalProperties": {
+              "type": "string"
+            },
+            "x-oaiTypeLabel": "map"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "Model": {
+        "title": "Model",
+        "description": "Describes an OpenAI model offering that can be used with the API.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The model identifier, which can be referenced in the API endpoints."
+          },
+          "created": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) when the model was created."
+          },
+          "object": {
+            "type": "string",
+            "description": "The object type, which is always \"model\".",
+            "enum": [
+              "model"
+            ],
+            "x-stainless-const": true
+          },
+          "owned_by": {
+            "type": "string",
+            "description": "The organization that owns the model."
+          },
+          "shutdown_date": {
+            "anyOf": [
+              {
+                "type": "string",
+                "format": "date"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The date when the model will shut down, or null if not announced."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "created",
+          "owned_by"
+        ],
+        "x-oaiMeta": {
+          "name": "The model object",
+          "example": "{\n  \"id\": \"gpt-6-astra\",\n  \"object\": \"model\",\n  \"created\": 1686935002,\n  \"owned_by\": \"openai\",\n  \"shutdown_date\": \"2026-10-23\"\n}\n"
+        }
+      },
+      "ModelIds": {
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/ModelIdsShared"
+          },
+          {
+            "$ref": "#/components/schemas/ModelIdsResponses"
+          }
+        ]
+      },
+      "ModelIdsCompaction": {
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/ModelIdsResponses"
+          },
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "description": "Model ID used to generate the response, like `gpt-6-astra`. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the [model guide](https://developers.openai.com/api/docs/models) to browse and compare available models."
+      },
+      "ModelIdsLive": {
+        "description": "The Live model. Required in the session configuration for every transport; do not pass it as a URL query parameter.",
+        "example": "gpt-live-1",
+        "anyOf": [
+          {
+            "type": "string",
+            "minLength": 1
+          },
+          {
+            "type": "string",
+            "enum": [
+              "gpt-live-1"
+            ]
+          }
+        ]
+      },
+      "ModelIdsResponses": {
+        "example": "gpt-6-astra",
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/ModelIdsShared"
+          },
+          {
+            "type": "string",
+            "title": "ResponsesOnlyModel",
+            "enum": [
+              "o1-pro",
+              "o1-pro-2025-03-19",
+              "o3-pro",
+              "o3-pro-2025-06-10",
+              "o3-deep-research",
+              "o3-deep-research-2025-06-26",
+              "o4-mini-deep-research",
+              "o4-mini-deep-research-2025-06-26",
+              "computer-use-preview",
+              "computer-use-preview-2025-03-11",
+              "gpt-5.5-pro",
+              "gpt-5.5-pro-2026-04-23",
+              "gpt-5-codex",
+              "gpt-5-pro",
+              "gpt-5-pro-2025-10-06",
+              "gpt-5.1-codex-max",
+              "gpt-daybreak-blue-latest",
+              "gpt-daybreak-red-latest",
+              "gpt-5.6-cyber"
+            ]
+          }
+        ]
+      },
+      "ModelIdsShared": {
+        "example": "gpt-6-astra",
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "string",
+            "enum": [
+              "gpt-6-astra",
+              "gpt-5.6-sol",
+              "gpt-5.6-terra",
+              "gpt-5.6-luna",
+              "gpt-5.5",
+              "gpt-5.5-2026-04-23",
+              "gpt-5.4",
+              "gpt-5.4-mini",
+              "gpt-5.4-nano",
+              "gpt-5.4-mini-2026-03-17",
+              "gpt-5.4-nano-2026-03-17",
+              "gpt-5.3-chat-latest",
+              "gpt-5.2",
+              "gpt-5.2-2025-12-11",
+              "gpt-5.2-chat-latest",
+              "gpt-5.2-pro",
+              "gpt-5.2-pro-2025-12-11",
+              "gpt-5.1",
+              "gpt-5.1-2025-11-13",
+              "gpt-5.1-codex",
+              "gpt-5.1-mini",
+              "gpt-5.1-chat-latest",
+              "gpt-5",
+              "gpt-5-mini",
+              "gpt-5-nano",
+              "gpt-5-2025-08-07",
+              "gpt-5-mini-2025-08-07",
+              "gpt-5-nano-2025-08-07",
+              "gpt-5-chat-latest",
+              "gpt-4.1",
+              "gpt-4.1-mini",
+              "gpt-4.1-nano",
+              "gpt-4.1-2025-04-14",
+              "gpt-4.1-mini-2025-04-14",
+              "gpt-4.1-nano-2025-04-14",
+              "o4-mini",
+              "o4-mini-2025-04-16",
+              "o3",
+              "o3-2025-04-16",
+              "o3-mini",
+              "o3-mini-2025-01-31",
+              "o1",
+              "o1-2024-12-17",
+              "o1-preview",
+              "o1-preview-2024-09-12",
+              "o1-mini",
+              "o1-mini-2024-09-12",
+              "gpt-4o",
+              "gpt-4o-2024-11-20",
+              "gpt-4o-2024-08-06",
+              "gpt-4o-2024-05-13",
+              "gpt-4o-audio-preview",
+              "gpt-4o-audio-preview-2024-10-01",
+              "gpt-4o-audio-preview-2024-12-17",
+              "gpt-4o-audio-preview-2025-06-03",
+              "gpt-4o-mini-audio-preview",
+              "gpt-4o-mini-audio-preview-2024-12-17",
+              "gpt-4o-search-preview",
+              "gpt-4o-mini-search-preview",
+              "gpt-4o-search-preview-2025-03-11",
+              "gpt-4o-mini-search-preview-2025-03-11",
+              "chatgpt-4o-latest",
+              "codex-mini-latest",
+              "gpt-4o-mini",
+              "gpt-4o-mini-2024-07-18",
+              "gpt-4-turbo",
+              "gpt-4-turbo-2024-04-09",
+              "gpt-4-0125-preview",
+              "gpt-4-turbo-preview",
+              "gpt-4-1106-preview",
+              "gpt-4-vision-preview",
+              "gpt-4",
+              "gpt-4-0314",
+              "gpt-4-0613",
+              "gpt-4-32k",
+              "gpt-4-32k-0314",
+              "gpt-4-32k-0613",
+              "gpt-3.5-turbo",
+              "gpt-3.5-turbo-16k",
+              "gpt-3.5-turbo-0301",
+              "gpt-3.5-turbo-0613",
+              "gpt-3.5-turbo-1106",
+              "gpt-3.5-turbo-0125",
+              "gpt-3.5-turbo-16k-0613"
+            ]
+          }
+        ]
+      },
+      "ModelResponseProperties": {
+        "type": "object",
+        "properties": {
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          },
+          "top_logprobs": {
+            "anyOf": [
+              {
+                "description": "An integer between 0 and 20 specifying the maximum number of most likely\ntokens to return at each token position, each with an associated log\nprobability. In some cases, the number of returned tokens may be fewer than\nrequested.\n",
+                "type": "integer",
+                "minimum": 0,
+                "maximum": 20
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "temperature": {
+            "anyOf": [
+              {
+                "type": "number",
+                "minimum": 0,
+                "maximum": 2,
+                "default": 1,
+                "example": 1,
+                "description": "What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.\nWe generally recommend altering this or `top_p` but not both.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "top_p": {
+            "anyOf": [
+              {
+                "type": "number",
+                "minimum": 0,
+                "maximum": 1,
+                "default": 1,
+                "example": 1,
+                "description": "An alternative to sampling with temperature, called nucleus sampling,\nwhere the model considers the results of the tokens with top_p probability\nmass. So 0.1 means only the tokens comprising the top 10% probability mass\nare considered.\n\nWe generally recommend altering this or `temperature` but not both.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "user": {
+            "type": "string",
+            "example": "user-1234",
+            "deprecated": true,
+            "description": "This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations.\nA stable identifier for your end-users.\nUsed to boost cache hit rates by better bucketing similar requests and  to help OpenAI detect and prevent abuse. [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers).\n"
+          },
+          "safety_identifier": {
+            "anyOf": [
+              {
+                "type": "string",
+                "maxLength": 64,
+                "example": "safety-identifier-1234",
+                "description": "A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies.\nThe IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers).\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "prompt_cache_key": {
+            "anyOf": [
+              {
+                "type": "string",
+                "example": "prompt-cache-key-1234",
+                "description": "Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](https://developers.openai.com/api/docs/guides/prompt-caching).\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "prompt_cache_retention": {
+            "deprecated": true,
+            "anyOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "in_memory",
+                  "24h"
+                ],
+                "description": "Deprecated. Use `prompt_cache_options.ttl` instead.\n\nThe retention policy for the prompt cache. Set to `24h` to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. [Learn more](https://developers.openai.com/api/docs/guides/prompt-caching#prompt-cache-retention).\nThis field expresses a maximum retention policy, while\n`prompt_cache_options.ttl` expresses a minimum cache lifetime. The two\nfields are independent and do not interact.\nFor `gpt-5.5`, `gpt-5.5-pro`, and future models, only `24h` is supported.\n\nFor older models that support both `in_memory` and `24h`, the default depends on your organization's data retention policy:\n  - Organizations without ZDR enabled default to `24h`.\n  - Organizations with ZDR enabled default to `in_memory` when `prompt_cache_retention` is not specified.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        }
+      },
+      "ModifyAssistantRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "model": {
+            "description": "ID of the model to use. You can use the [List models](https://developers.openai.com/api/reference/resources/models/methods/list) API to see all of your available models, or see our [Model overview](https://developers.openai.com/api/docs/models) for descriptions of them.\n",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "$ref": "#/components/schemas/AssistantSupportedModels"
+              }
+            ]
+          },
+          "reasoning_effort": {
+            "$ref": "#/components/schemas/ReasoningEffort"
+          },
+          "name": {
+            "anyOf": [
+              {
+                "description": "The name of the assistant. The maximum length is 256 characters.\n",
+                "type": "string",
+                "maxLength": 256
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "description": {
+            "anyOf": [
+              {
+                "description": "The description of the assistant. The maximum length is 512 characters.\n",
+                "type": "string",
+                "maxLength": 512
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "instructions": {
+            "anyOf": [
+              {
+                "description": "The system instructions that the assistant uses. The maximum length is 256,000 characters.\n",
+                "type": "string",
+                "maxLength": 256000
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "tools": {
+            "description": "A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types `code_interpreter`, `file_search`, or `function`.\n",
+            "default": [],
+            "type": "array",
+            "maxItems": 128,
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/AssistantToolsCode"
+                },
+                {
+                  "$ref": "#/components/schemas/AssistantToolsFileSearch"
+                },
+                {
+                  "$ref": "#/components/schemas/AssistantToolsFunction"
+                }
+              ]
+            }
+          },
+          "tool_resources": {
+            "anyOf": [
+              {
+                "type": "object",
+                "description": "A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs.\n",
+                "properties": {
+                  "code_interpreter": {
+                    "type": "object",
+                    "properties": {
+                      "file_ids": {
+                        "type": "array",
+                        "description": "Overrides the list of [file](https://developers.openai.com/api/reference/resources/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool.\n",
+                        "default": [],
+                        "maxItems": 20,
+                        "items": {
+                          "type": "string"
+                        }
+                      }
+                    }
+                  },
+                  "file_search": {
+                    "type": "object",
+                    "properties": {
+                      "vector_store_ids": {
+                        "type": "array",
+                        "description": "Overrides the [vector store](https://developers.openai.com/api/reference/resources/vector_stores) attached to this assistant. There can be a maximum of 1 vector store attached to the assistant.\n",
+                        "maxItems": 1,
+                        "items": {
+                          "type": "string"
+                        }
+                      }
+                    }
+                  }
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          },
+          "temperature": {
+            "anyOf": [
+              {
+                "description": "What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.\n",
+                "type": "number",
+                "minimum": 0,
+                "maximum": 2,
+                "default": 1,
+                "example": 1
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "top_p": {
+            "anyOf": [
+              {
+                "type": "number",
+                "minimum": 0,
+                "maximum": 1,
+                "default": 1,
+                "example": 1,
+                "description": "An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\n\nWe generally recommend altering this or temperature but not both.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "response_format": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/AssistantsApiResponseFormatOption"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        }
+      },
+      "ModifyCertificateRequest": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The updated name for the certificate"
+          }
+        }
+      },
+      "ModifyMessageRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          }
+        }
+      },
+      "ModifyRunRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          }
+        }
+      },
+      "ModifyThreadRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "tool_resources": {
+            "anyOf": [
+              {
+                "type": "object",
+                "description": "A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs.\n",
+                "properties": {
+                  "code_interpreter": {
+                    "type": "object",
+                    "properties": {
+                      "file_ids": {
+                        "type": "array",
+                        "description": "A list of [file](https://developers.openai.com/api/reference/resources/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool.\n",
+                        "default": [],
+                        "maxItems": 20,
+                        "items": {
+                          "type": "string"
+                        }
+                      }
+                    }
+                  },
+                  "file_search": {
+                    "type": "object",
+                    "properties": {
+                      "vector_store_ids": {
+                        "type": "array",
+                        "description": "The [vector store](https://developers.openai.com/api/reference/resources/vector_stores) attached to this thread. There can be a maximum of 1 vector store attached to the thread.\n",
+                        "maxItems": 1,
+                        "items": {
+                          "type": "string"
+                        }
+                      }
+                    }
+                  }
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          }
+        }
+      },
+      "NoiseReductionType": {
+        "type": "string",
+        "enum": [
+          "near_field",
+          "far_field"
+        ],
+        "description": "Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones.\n"
+      },
+      "OpenAIFile": {
+        "title": "OpenAIFile",
+        "description": "The `File` object represents a document that has been uploaded to OpenAI.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The file identifier, which can be referenced in the API endpoints."
+          },
+          "bytes": {
+            "type": "integer",
+            "description": "The size of the file, in bytes."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the file was created."
+          },
+          "expires_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the file will expire."
+          },
+          "filename": {
+            "type": "string",
+            "description": "The name of the file."
+          },
+          "object": {
+            "type": "string",
+            "description": "The object type, which is always `file`.",
+            "enum": [
+              "file"
+            ],
+            "x-stainless-const": true
+          },
+          "purpose": {
+            "type": "string",
+            "description": "The intended purpose of the file. Supported values are `assistants`, `assistants_output`, `batch`, `batch_output`, `fine-tune`, `fine-tune-results`, `vision`, and `user_data`.",
+            "enum": [
+              "assistants",
+              "assistants_output",
+              "batch",
+              "batch_output",
+              "fine-tune",
+              "fine-tune-results",
+              "vision",
+              "user_data"
+            ]
+          },
+          "status": {
+            "type": "string",
+            "deprecated": true,
+            "description": "Deprecated. The current status of the file, which can be either `uploaded`, `processed`, or `error`.",
+            "enum": [
+              "uploaded",
+              "processed",
+              "error"
+            ]
+          },
+          "status_details": {
+            "type": "string",
+            "deprecated": true,
+            "description": "Deprecated. For details on why a fine-tuning training file failed validation, see the `error` field on `fine_tuning.job`."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "bytes",
+          "created_at",
+          "filename",
+          "purpose",
+          "status"
+        ],
+        "x-oaiMeta": {
+          "name": "The file object",
+          "example": "{\n  \"id\": \"file-abc123\",\n  \"object\": \"file\",\n  \"bytes\": 120000,\n  \"created_at\": 1677610602,\n  \"expires_at\": 1680202602,\n  \"filename\": \"salesOverview.pdf\",\n  \"purpose\": \"assistants\",\n}\n"
+        }
+      },
+      "OrganizationCertificate": {
+        "type": "object",
+        "description": "Represents an individual certificate configured at the organization level.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.certificate"
+            ],
+            "description": "The object type, which is always `organization.certificate`.",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The identifier, which can be referenced in API endpoints"
+          },
+          "name": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The name of the certificate."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the certificate was uploaded."
+          },
+          "certificate_details": {
+            "type": "object",
+            "properties": {
+              "valid_at": {
+                "type": "integer",
+                "format": "unixtime",
+                "description": "The Unix timestamp (in seconds) of when the certificate becomes valid."
+              },
+              "expires_at": {
+                "type": "integer",
+                "format": "unixtime",
+                "description": "The Unix timestamp (in seconds) of when the certificate expires."
+              }
+            }
+          },
+          "active": {
+            "type": "boolean",
+            "description": "Whether the certificate is currently active at the organization level."
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "name",
+          "created_at",
+          "certificate_details",
+          "active"
+        ]
+      },
+      "OrganizationCertificateActivationResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.certificate.activation"
+            ],
+            "description": "The organization certificate activation result type.",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/OrganizationCertificate"
+            }
+          }
+        },
+        "required": [
+          "object",
+          "data"
+        ]
+      },
+      "OrganizationCertificateDeactivationResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.certificate.deactivation"
+            ],
+            "description": "The organization certificate deactivation result type.",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/OrganizationCertificate"
+            }
+          }
+        },
+        "required": [
+          "object",
+          "data"
+        ]
+      },
+      "OrganizationDataRetention": {
+        "type": "object",
+        "description": "Represents the organization's data retention control setting.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.data_retention"
+            ],
+            "description": "The object type, which is always `organization.data_retention`.",
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "zero_data_retention",
+              "modified_abuse_monitoring",
+              "enhanced_zero_data_retention",
+              "enhanced_modified_abuse_monitoring"
+            ],
+            "description": "The configured organization data retention type."
+          }
+        },
+        "required": [
+          "object",
+          "type"
+        ],
+        "x-oaiMeta": {
+          "name": "The organization data retention object",
+          "example": "{\n    \"object\": \"organization.data_retention\",\n    \"type\": \"modified_abuse_monitoring\"\n}\n"
+        }
+      },
+      "OrganizationProjectCertificate": {
+        "type": "object",
+        "description": "Represents an individual certificate configured at the project level.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.project.certificate"
+            ],
+            "description": "The object type, which is always `organization.project.certificate`.",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The identifier, which can be referenced in API endpoints"
+          },
+          "name": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The name of the certificate."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the certificate was uploaded."
+          },
+          "certificate_details": {
+            "type": "object",
+            "properties": {
+              "valid_at": {
+                "type": "integer",
+                "format": "unixtime",
+                "description": "The Unix timestamp (in seconds) of when the certificate becomes valid."
+              },
+              "expires_at": {
+                "type": "integer",
+                "format": "unixtime",
+                "description": "The Unix timestamp (in seconds) of when the certificate expires."
+              }
+            }
+          },
+          "active": {
+            "type": "boolean",
+            "description": "Whether the certificate is currently active at the project level."
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "name",
+          "created_at",
+          "certificate_details",
+          "active"
+        ]
+      },
+      "OrganizationProjectCertificateActivationResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.project.certificate.activation"
+            ],
+            "description": "The project certificate activation result type.",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/OrganizationProjectCertificate"
+            }
+          }
+        },
+        "required": [
+          "object",
+          "data"
+        ]
+      },
+      "OrganizationProjectCertificateDeactivationResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.project.certificate.deactivation"
+            ],
+            "description": "The project certificate deactivation result type.",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/OrganizationProjectCertificate"
+            }
+          }
+        },
+        "required": [
+          "object",
+          "data"
+        ]
+      },
+      "OrganizationSpendAlert": {
+        "type": "object",
+        "description": "Represents a spend alert configured at the organization level.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The identifier, which can be referenced in API endpoints."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.spend_alert"
+            ],
+            "description": "The object type, which is always `organization.spend_alert`.",
+            "x-stainless-const": true
+          },
+          "threshold_amount": {
+            "type": "integer",
+            "description": "The alert threshold amount, in cents."
+          },
+          "currency": {
+            "type": "string",
+            "enum": [
+              "USD"
+            ],
+            "description": "The currency for the threshold amount."
+          },
+          "interval": {
+            "type": "string",
+            "enum": [
+              "month"
+            ],
+            "description": "The time interval for evaluating spend against the threshold."
+          },
+          "notification_channel": {
+            "$ref": "#/components/schemas/SpendAlertNotificationChannel"
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "threshold_amount",
+          "currency",
+          "interval",
+          "notification_channel"
+        ],
+        "x-oaiMeta": {
+          "name": "The organization spend alert object",
+          "example": "{\n    \"id\": \"alert_abc123\",\n    \"object\": \"organization.spend_alert\",\n    \"threshold_amount\": 100000,\n    \"currency\": \"USD\",\n    \"interval\": \"month\",\n    \"notification_channel\": {\n        \"type\": \"email\",\n        \"recipients\": [\"finance@example.com\"],\n        \"subject_prefix\": \"OpenAI spend alert\"\n    }\n}\n"
+        }
+      },
+      "OrganizationSpendAlertDeletedResource": {
+        "type": "object",
+        "description": "Confirmation payload returned after deleting an organization spend alert.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The deleted spend alert ID."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.spend_alert.deleted"
+            ],
+            "description": "Always `organization.spend_alert.deleted`.",
+            "x-stainless-const": true
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the spend alert was deleted."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ]
+      },
+      "OrganizationSpendAlertListResource": {
+        "type": "object",
+        "description": "Paginated list of organization spend alerts.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "description": "Always `list`.",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "description": "Spend alerts returned in the current page.",
+            "items": {
+              "$ref": "#/components/schemas/OrganizationSpendAlert"
+            }
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The ID of the first spend alert in this page."
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The ID of the last spend alert in this page."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether more spend alerts are available when paginating."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ]
+      },
+      "OtherChunkingStrategyResponseParam": {
+        "type": "object",
+        "title": "Other Chunking Strategy",
+        "description": "This is returned when the chunking strategy is unknown. Typically, this is because the file was indexed before the `chunking_strategy` concept was introduced in the API.",
+        "additionalProperties": false,
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "Always `other`.",
+            "enum": [
+              "other"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "OutputAudio": {
+        "type": "object",
+        "title": "Output audio",
+        "description": "An audio output from the model.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the output audio. Always `output_audio`.\n",
+            "enum": [
+              "output_audio"
+            ],
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "string",
+            "description": "Base64-encoded audio data from the model.\n"
+          },
+          "transcript": {
+            "type": "string",
+            "description": "The transcript of the audio data from the model.\n"
+          }
+        },
+        "required": [
+          "type",
+          "data",
+          "transcript"
+        ]
+      },
+      "OutputContent": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/OutputTextContent"
+          },
+          {
+            "$ref": "#/components/schemas/RefusalContent"
+          },
+          {
+            "$ref": "#/components/schemas/ReasoningTextContent"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "OutputItem": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/OutputMessage"
+          },
+          {
+            "$ref": "#/components/schemas/FileSearchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionToolCallOutputResource"
+          },
+          {
+            "$ref": "#/components/schemas/WebSearchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/ComputerToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/ComputerToolCallOutputResource"
+          },
+          {
+            "$ref": "#/components/schemas/ReasoningItem"
+          },
+          {
+            "$ref": "#/components/schemas/Program"
+          },
+          {
+            "$ref": "#/components/schemas/ProgramOutput"
+          },
+          {
+            "$ref": "#/components/schemas/ToolSearchCall"
+          },
+          {
+            "$ref": "#/components/schemas/ToolSearchOutput"
+          },
+          {
+            "$ref": "#/components/schemas/AdditionalTools"
+          },
+          {
+            "$ref": "#/components/schemas/CompactionBody"
+          },
+          {
+            "$ref": "#/components/schemas/ImageGenToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/CodeInterpreterToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/LocalShellToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/LocalShellToolCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionShellCall"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionShellCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/ApplyPatchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/ApplyPatchToolCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/MCPToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/MCPListTools"
+          },
+          {
+            "$ref": "#/components/schemas/MCPApprovalRequest"
+          },
+          {
+            "$ref": "#/components/schemas/MCPApprovalResponseResource"
+          },
+          {
+            "$ref": "#/components/schemas/CustomToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/CustomToolCallOutputResource"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "OutputMessage": {
+        "type": "object",
+        "title": "Output message",
+        "description": "An output message from the model.\n",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the output message.\n"
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the output message. Always `message`.\n",
+            "enum": [
+              "message"
+            ],
+            "x-stainless-const": true
+          },
+          "role": {
+            "type": "string",
+            "description": "The role of the output message. Always `assistant`.\n",
+            "enum": [
+              "assistant"
+            ],
+            "x-stainless-const": true
+          },
+          "content": {
+            "type": "array",
+            "description": "The content of the output message.\n",
+            "items": {
+              "$ref": "#/components/schemas/OutputMessageContent"
+            }
+          },
+          "phase": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/MessagePhase"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "type": "string",
+            "description": "The status of the message input. One of `in_progress`, `completed`, or\n`incomplete`. Populated when input items are returned via API.\n",
+            "enum": [
+              "in_progress",
+              "completed",
+              "incomplete"
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "type",
+          "role",
+          "content",
+          "status"
+        ]
+      },
+      "OutputMessageContent": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/OutputTextContent"
+          },
+          {
+            "$ref": "#/components/schemas/RefusalContent"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "ParallelToolCalls": {
+        "description": "Whether to enable [parallel function calling](https://developers.openai.com/api/docs/guides/function-calling#parallel-function-calling) during tool use.",
+        "type": "boolean",
+        "default": true
+      },
+      "PartialImages": {
+        "anyOf": [
+          {
+            "type": "integer",
+            "maximum": 3,
+            "minimum": 0,
+            "default": 0,
+            "example": 1,
+            "description": "The number of partial images to generate. This parameter is used for\nstreaming responses that return partial images. Value must be between 0 and 3.\nWhen set to 0, the response will be a single image sent in one streaming event.\n\nNote that the final image may be sent before the full number of partial images\nare generated if the full image is generated more quickly.\n"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "PredictionContent": {
+        "type": "object",
+        "title": "Static Content",
+        "description": "Static predicted output content, such as the content of a text file that is\nbeing regenerated.\n",
+        "required": [
+          "type",
+          "content"
+        ],
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "content"
+            ],
+            "description": "The type of the predicted content you want to provide. This type is\ncurrently always `content`.\n",
+            "x-stainless-const": true
+          },
+          "content": {
+            "description": "The content that should be matched when generating a model response.\nIf generated tokens would match this content, the entire model response\ncan be returned much more quickly.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "title": "Text content",
+                "description": "The content used for a Predicted Output. This is often the\ntext of a file you are regenerating with minor changes.\n"
+              },
+              {
+                "type": "array",
+                "description": "An array of content parts with a defined type. Supported options differ based on the [model](https://developers.openai.com/api/docs/models) being used to generate the response. Can contain text inputs.",
+                "title": "Array of content parts",
+                "items": {
+                  "$ref": "#/components/schemas/ChatCompletionRequestMessageContentPartText"
+                },
+                "minItems": 1
+              }
+            ]
+          }
+        }
+      },
+      "Project": {
+        "type": "object",
+        "description": "Represents an individual project.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The identifier, which can be referenced in API endpoints"
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.project"
+            ],
+            "description": "The object type, which is always `organization.project`",
+            "x-stainless-const": true
+          },
+          "name": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The name of the project. This appears in reporting."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the project was created."
+          },
+          "archived_at": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "format": "unixtime",
+                "description": "The Unix timestamp (in seconds) of when the project was archived or `null`."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "`active` or `archived`"
+          },
+          "external_key_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The external key associated with the project."
+          },
+          "residency": {
+            "$ref": "#/components/schemas/PublicProjectResidency",
+            "description": "The residency configuration for the project."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "created_at"
+        ],
+        "x-oaiMeta": {
+          "name": "The project object",
+          "example": "{\n    \"id\": \"proj_abc\",\n    \"object\": \"organization.project\",\n    \"name\": \"Project example\",\n    \"created_at\": 1711471533,\n    \"archived_at\": null,\n    \"status\": \"active\",\n    \"external_key_id\": null\n}\n"
+        }
+      },
+      "ProjectApiKey": {
+        "type": "object",
+        "description": "Represents an individual API key in a project.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.project.api_key"
+            ],
+            "description": "The object type, which is always `organization.project.api_key`",
+            "x-stainless-const": true
+          },
+          "redacted_value": {
+            "type": "string",
+            "description": "The redacted value of the API key"
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the API key"
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the API key was created"
+          },
+          "expires_at": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "format": "unixtime"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The Unix timestamp (in seconds) when the API key expires, or null if it does not expire."
+          },
+          "last_used_at": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "format": "unixtime"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The Unix timestamp (in seconds) of when the API key was last used."
+          },
+          "id": {
+            "type": "string",
+            "description": "The identifier, which can be referenced in API endpoints"
+          },
+          "owner_project_access": {
+            "type": "string",
+            "enum": [
+              "active",
+              "inactive"
+            ],
+            "description": "Whether the API key's owner currently has effective access to the project."
+          },
+          "owner": {
+            "type": "object",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "user",
+                  "service_account"
+                ],
+                "description": "`user` or `service_account`"
+              },
+              "user": {
+                "$ref": "#/components/schemas/ProjectApiKeyOwnerUser"
+              },
+              "service_account": {
+                "$ref": "#/components/schemas/ProjectApiKeyOwnerServiceAccount"
+              }
+            }
+          }
+        },
+        "required": [
+          "object",
+          "redacted_value",
+          "name",
+          "created_at",
+          "last_used_at",
+          "id",
+          "owner_project_access",
+          "owner"
+        ],
+        "x-oaiMeta": {
+          "name": "The project API key object",
+          "example": "{\n    \"object\": \"organization.project.api_key\",\n    \"redacted_value\": \"sk-abc...def\",\n    \"name\": \"My API Key\",\n    \"created_at\": 1711471533,\n    \"expires_at\": 1714063533,\n    \"last_used_at\": 1711471534,\n    \"id\": \"key_abc\",\n    \"owner_project_access\": \"active\",\n    \"owner\": {\n        \"type\": \"user\",\n        \"user\": {\n            \"id\": \"user_abc\",\n            \"name\": \"First Last\",\n            \"email\": \"user@example.com\",\n            \"role\": \"owner\",\n            \"created_at\": 1711471533\n        }\n    }\n}\n"
+        }
+      },
+      "ProjectApiKeyDeleteResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.project.api_key.deleted"
+            ],
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string"
+          },
+          "deleted": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "deleted"
+        ]
+      },
+      "ProjectApiKeyListResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/ProjectApiKey"
+            }
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "has_more": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more"
+        ]
+      },
+      "ProjectApiKeyOwnerServiceAccount": {
+        "type": "object",
+        "description": "The service account that owns a project API key.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The identifier, which can be referenced in API endpoints"
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the service account."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the service account was created."
+          },
+          "role": {
+            "type": "string",
+            "description": "The service account's project role."
+          }
+        },
+        "required": [
+          "id",
+          "name",
+          "created_at",
+          "role"
+        ]
+      },
+      "ProjectApiKeyOwnerUser": {
+        "type": "object",
+        "description": "The user that owns a project API key.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The identifier, which can be referenced in API endpoints"
+          },
+          "email": {
+            "type": "string",
+            "description": "The email address of the user."
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the user."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the user was created."
+          },
+          "role": {
+            "type": "string",
+            "description": "The user's project role."
+          }
+        },
+        "required": [
+          "id",
+          "email",
+          "name",
+          "created_at",
+          "role"
+        ]
+      },
+      "ProjectCreateRequest": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The friendly name of the project, this name appears in reports."
+          },
+          "geography": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "deprecated": true,
+            "description": "Create the project with the specified data residency region. Your organization must have access to Data residency functionality in order to use. See [data residency controls](https://developers.openai.com/api/docs/guides/your-data#data-residency-controls) to review the functionality and limitations of setting this field.\nDeprecated: use `residency` instead. Do not provide both `geography` and `residency`."
+          },
+          "residency": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/PublicProjectResidency"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Create the project with the specified residency configuration. Your organization must have access to the requested residency configuration in order to use it. See [data residency controls](https://developers.openai.com/api/docs/guides/your-data#data-residency-controls) to review the functionality and limitations of setting this field."
+          },
+          "external_key_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "External key ID to associate with the project."
+          }
+        },
+        "required": [
+          "name"
+        ]
+      },
+      "ProjectDataRetention": {
+        "type": "object",
+        "description": "Represents a project's data retention control setting.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "project.data_retention"
+            ],
+            "description": "The object type, which is always `project.data_retention`.",
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "organization_default",
+              "none",
+              "zero_data_retention",
+              "modified_abuse_monitoring",
+              "enhanced_zero_data_retention",
+              "enhanced_modified_abuse_monitoring"
+            ],
+            "description": "The configured project data retention type."
+          }
+        },
+        "required": [
+          "object",
+          "type"
+        ],
+        "x-oaiMeta": {
+          "name": "The project data retention object",
+          "example": "{\n    \"object\": \"project.data_retention\",\n    \"type\": \"organization_default\"\n}\n"
+        }
+      },
+      "ProjectGroup": {
+        "type": "object",
+        "description": "Details about a group's membership in a project.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "project.group"
+            ],
+            "description": "Always `project.group`.",
+            "x-stainless-const": true
+          },
+          "project_id": {
+            "type": "string",
+            "description": "Identifier of the project."
+          },
+          "group_id": {
+            "type": "string",
+            "description": "Identifier of the group that has access to the project."
+          },
+          "group_name": {
+            "type": "string",
+            "description": "Display name of the group."
+          },
+          "group_type": {
+            "type": "string",
+            "enum": [
+              "group",
+              "tenant_group"
+            ],
+            "description": "The type of the group."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (in seconds) when the group was granted project access."
+          }
+        },
+        "required": [
+          "object",
+          "project_id",
+          "group_id",
+          "group_name",
+          "group_type",
+          "created_at"
+        ],
+        "x-oaiMeta": {
+          "name": "The project group object",
+          "example": "{\n    \"object\": \"project.group\",\n    \"project_id\": \"proj_abc123\",\n    \"group_id\": \"group_01J1F8ABCDXYZ\",\n    \"group_name\": \"Support Team\",\n    \"group_type\": \"group\",\n    \"created_at\": 1711471533\n}\n"
+        }
+      },
+      "ProjectGroupDeletedResource": {
+        "type": "object",
+        "description": "Confirmation payload returned after removing a group from a project.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "project.group.deleted"
+            ],
+            "description": "Always `project.group.deleted`.",
+            "x-stainless-const": true
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the group membership in the project was removed."
+          }
+        },
+        "required": [
+          "object",
+          "deleted"
+        ],
+        "x-oaiMeta": {
+          "name": "Project group deletion confirmation",
+          "example": "{\n    \"object\": \"project.group.deleted\",\n    \"deleted\": true\n}\n"
+        }
+      },
+      "ProjectGroupListResource": {
+        "type": "object",
+        "description": "Paginated list of groups that have access to a project.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "description": "Always `list`.",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "description": "Project group memberships returned in the current page.",
+            "items": {
+              "$ref": "#/components/schemas/ProjectGroup"
+            }
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether additional project group memberships are available."
+          },
+          "next": {
+            "description": "Cursor to fetch the next page of results, or `null` when there are no more results.",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more",
+          "next"
+        ],
+        "x-oaiMeta": {
+          "name": "Project group list",
+          "example": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"object\": \"project.group\",\n            \"project_id\": \"proj_abc123\",\n            \"group_id\": \"group_01J1F8ABCDXYZ\",\n            \"group_name\": \"Support Team\",\n            \"created_at\": 1711471533\n        }\n    ],\n    \"has_more\": false,\n    \"next\": null\n}\n"
+        }
+      },
+      "ProjectHostedToolPermissions": {
+        "type": "object",
+        "description": "Represents hosted tool permissions for a project.",
+        "properties": {
+          "file_search": {
+            "$ref": "#/components/schemas/HostedToolPermission"
+          },
+          "web_search": {
+            "$ref": "#/components/schemas/HostedToolPermission"
+          },
+          "image_generation": {
+            "$ref": "#/components/schemas/HostedToolPermission"
+          },
+          "mcp": {
+            "$ref": "#/components/schemas/HostedToolPermission"
+          },
+          "code_interpreter": {
+            "$ref": "#/components/schemas/HostedToolPermission"
+          }
+        },
+        "required": [
+          "file_search",
+          "web_search",
+          "image_generation",
+          "mcp",
+          "code_interpreter"
+        ],
+        "x-oaiMeta": {
+          "name": "The project hosted tool permissions object",
+          "example": "{\n    \"file_search\": {\n        \"enabled\": true\n    },\n    \"web_search\": {\n        \"enabled\": true\n    },\n    \"image_generation\": {\n        \"enabled\": true\n    },\n    \"mcp\": {\n        \"enabled\": true\n    },\n    \"code_interpreter\": {\n        \"enabled\": true\n    }\n}\n"
+        }
+      },
+      "ProjectHostedToolPermissionsUpdateRequest": {
+        "type": "object",
+        "properties": {
+          "file_search": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/HostedToolPermissionUpdate"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The file search permission update."
+          },
+          "web_search": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/HostedToolPermissionUpdate"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The web search permission update."
+          },
+          "image_generation": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/HostedToolPermissionUpdate"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The image generation permission update."
+          },
+          "mcp": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/HostedToolPermissionUpdate"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The MCP permission update."
+          },
+          "code_interpreter": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/HostedToolPermissionUpdate"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The code interpreter permission update."
+          }
+        }
+      },
+      "ProjectListResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/Project"
+            }
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "has_more": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more"
+        ]
+      },
+      "ProjectModelPermissions": {
+        "type": "object",
+        "description": "Represents the model allowlist or denylist policy for a project.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "project.model_permissions"
+            ],
+            "description": "The object type, which is always `project.model_permissions`.",
+            "x-stainless-const": true
+          },
+          "mode": {
+            "type": "string",
+            "enum": [
+              "allow_list",
+              "deny_list"
+            ],
+            "description": "Whether the project uses an allowlist or a denylist."
+          },
+          "model_ids": {
+            "type": "array",
+            "items": {
+              "type": "string"
+            },
+            "description": "The model IDs included in the model permissions policy."
+          }
+        },
+        "required": [
+          "object",
+          "mode",
+          "model_ids"
+        ],
+        "x-oaiMeta": {
+          "name": "The project model permissions object",
+          "example": "{\n    \"object\": \"project.model_permissions\",\n    \"mode\": \"allow_list\",\n    \"model_ids\": [\n        \"gpt-6-astra\",\n        \"o3\"\n    ]\n}\n"
+        }
+      },
+      "ProjectModelPermissionsDeleteResponse": {
+        "type": "object",
+        "description": "Confirmation payload returned after deleting project model permissions.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "project.model_permissions.deleted"
+            ],
+            "description": "The object type, which is always `project.model_permissions.deleted`.",
+            "x-stainless-const": true
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the project model permissions were deleted."
+          }
+        },
+        "required": [
+          "object",
+          "deleted"
+        ],
+        "x-oaiMeta": {
+          "name": "Project model permissions deletion confirmation",
+          "example": "{\n    \"object\": \"project.model_permissions.deleted\",\n    \"deleted\": true\n}\n"
+        }
+      },
+      "ProjectModelPermissionsUpdateRequest": {
+        "type": "object",
+        "properties": {
+          "mode": {
+            "type": "string",
+            "enum": [
+              "allow_list",
+              "deny_list"
+            ],
+            "description": "The model permissions mode to apply."
+          },
+          "model_ids": {
+            "type": "array",
+            "items": {
+              "type": "string"
+            },
+            "description": "The model IDs included in this permissions policy."
+          }
+        },
+        "required": [
+          "mode",
+          "model_ids"
+        ]
+      },
+      "ProjectRateLimit": {
+        "type": "object",
+        "description": "Represents a project rate limit config.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "project.rate_limit"
+            ],
+            "description": "The object type, which is always `project.rate_limit`",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The identifier, which can be referenced in API endpoints."
+          },
+          "model": {
+            "type": "string",
+            "description": "The model this rate limit applies to."
+          },
+          "max_requests_per_1_minute": {
+            "type": "integer",
+            "description": "The maximum requests per minute."
+          },
+          "max_tokens_per_1_minute": {
+            "type": "integer",
+            "description": "The maximum tokens per minute."
+          },
+          "max_images_per_1_minute": {
+            "type": "integer",
+            "description": "The maximum images per minute. Only present for relevant models."
+          },
+          "max_audio_megabytes_per_1_minute": {
+            "type": "integer",
+            "description": "The maximum audio megabytes per minute. Only present for relevant models."
+          },
+          "max_requests_per_1_day": {
+            "type": "integer",
+            "description": "The maximum requests per day. Only present for relevant models."
+          },
+          "batch_1_day_max_input_tokens": {
+            "type": "integer",
+            "description": "The maximum batch input tokens per day. Only present for relevant models."
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "model",
+          "max_requests_per_1_minute",
+          "max_tokens_per_1_minute"
+        ],
+        "x-oaiMeta": {
+          "name": "The project rate limit object",
+          "example": "{\n    \"object\": \"project.rate_limit\",\n    \"id\": \"rl_ada\",\n    \"model\": \"ada\",\n    \"max_requests_per_1_minute\": 600,\n    \"max_tokens_per_1_minute\": 150000,\n    \"max_images_per_1_minute\": 10\n}\n"
+        }
+      },
+      "ProjectRateLimitListResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/ProjectRateLimit"
+            }
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "has_more": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more"
+        ]
+      },
+      "ProjectRateLimitUpdateRequest": {
+        "type": "object",
+        "properties": {
+          "max_requests_per_1_minute": {
+            "type": "integer",
+            "description": "The maximum requests per minute."
+          },
+          "max_tokens_per_1_minute": {
+            "type": "integer",
+            "description": "The maximum tokens per minute."
+          },
+          "max_images_per_1_minute": {
+            "type": "integer",
+            "description": "The maximum images per minute. Only relevant for certain models."
+          },
+          "max_audio_megabytes_per_1_minute": {
+            "type": "integer",
+            "description": "The maximum audio megabytes per minute. Only relevant for certain models."
+          },
+          "max_requests_per_1_day": {
+            "type": "integer",
+            "description": "The maximum requests per day. Only relevant for certain models."
+          },
+          "batch_1_day_max_input_tokens": {
+            "type": "integer",
+            "description": "The maximum batch input tokens per day. Only relevant for certain models."
+          }
+        }
+      },
+      "ProjectServiceAccount": {
+        "type": "object",
+        "description": "Represents an individual service account in a project.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.project.service_account"
+            ],
+            "description": "The object type, which is always `organization.project.service_account`",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The identifier, which can be referenced in API endpoints"
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the service account"
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "owner",
+              "member",
+              "none"
+            ],
+            "description": "`owner`, `member`, or `none`"
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the service account was created"
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "name",
+          "role",
+          "created_at"
+        ],
+        "x-oaiMeta": {
+          "name": "The project service account object",
+          "example": "{\n    \"object\": \"organization.project.service_account\",\n    \"id\": \"svc_acct_abc\",\n    \"name\": \"Service Account\",\n    \"role\": \"owner\",\n    \"created_at\": 1711471533\n}\n"
+        }
+      },
+      "ProjectServiceAccountApiKey": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.project.service_account.api_key"
+            ],
+            "description": "The object type, which is always `organization.project.service_account.api_key`",
+            "x-stainless-const": true
+          },
+          "value": {
+            "type": "string"
+          },
+          "name": {
+            "type": "string"
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime"
+          },
+          "expires_at": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "format": "unixtime"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The Unix timestamp (in seconds) when the API key expires, or null if it does not expire."
+          },
+          "id": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "object",
+          "value",
+          "name",
+          "created_at",
+          "id"
+        ]
+      },
+      "ProjectServiceAccountCreateRequest": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The name of the service account being created."
+          },
+          "create_service_account_only": {
+            "anyOf": [
+              {
+                "type": "boolean",
+                "description": "Create the service account without default roles or an API key."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "expires_in_seconds": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "minimum": 1,
+                "maximum": 31536000
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Number of seconds until the initial API key expires. If omitted or null, the key does not expire unless the effective organization or project policy requires an expiration. When a policy sets a maximum lifetime, this value must be provided and must not exceed that limit. A non-null value cannot be used when `create_service_account_only` is true."
+          }
+        },
+        "required": [
+          "name"
+        ]
+      },
+      "ProjectServiceAccountCreateResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.project.service_account"
+            ],
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string"
+          },
+          "name": {
+            "type": "string"
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "member",
+              "none"
+            ],
+            "description": "Service accounts created with default project membership have role `member`. Accounts created with `create_service_account_only` have role `none`.\n"
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime"
+          },
+          "api_key": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ProjectServiceAccountApiKey"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "name",
+          "role",
+          "created_at",
+          "api_key"
+        ]
+      },
+      "ProjectServiceAccountDeleteResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.project.service_account.deleted"
+            ],
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string"
+          },
+          "deleted": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "deleted"
+        ]
+      },
+      "ProjectServiceAccountListResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/ProjectServiceAccount"
+            }
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "has_more": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more"
+        ]
+      },
+      "ProjectSpendAlert": {
+        "type": "object",
+        "description": "Represents a spend alert configured at the project level.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The identifier, which can be referenced in API endpoints."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "project.spend_alert"
+            ],
+            "description": "The object type, which is always `project.spend_alert`.",
+            "x-stainless-const": true
+          },
+          "threshold_amount": {
+            "type": "integer",
+            "description": "The alert threshold amount, in cents."
+          },
+          "currency": {
+            "type": "string",
+            "enum": [
+              "USD"
+            ],
+            "description": "The currency for the threshold amount."
+          },
+          "interval": {
+            "type": "string",
+            "enum": [
+              "month"
+            ],
+            "description": "The time interval for evaluating spend against the threshold."
+          },
+          "notification_channel": {
+            "$ref": "#/components/schemas/SpendAlertNotificationChannel"
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "threshold_amount",
+          "currency",
+          "interval",
+          "notification_channel"
+        ],
+        "x-oaiMeta": {
+          "name": "The project spend alert object",
+          "example": "{\n    \"id\": \"alert_abc123\",\n    \"object\": \"project.spend_alert\",\n    \"threshold_amount\": 100000,\n    \"currency\": \"USD\",\n    \"interval\": \"month\",\n    \"notification_channel\": {\n        \"type\": \"email\",\n        \"recipients\": [\"finance@example.com\"],\n        \"subject_prefix\": \"OpenAI spend alert\"\n    }\n}\n"
+        }
+      },
+      "ProjectSpendAlertDeletedResource": {
+        "type": "object",
+        "description": "Confirmation payload returned after deleting a project spend alert.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The deleted spend alert ID."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "project.spend_alert.deleted"
+            ],
+            "description": "Always `project.spend_alert.deleted`.",
+            "x-stainless-const": true
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the spend alert was deleted."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ]
+      },
+      "ProjectSpendAlertListResource": {
+        "type": "object",
+        "description": "Paginated list of project spend alerts.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "description": "Always `list`.",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "description": "Spend alerts returned in the current page.",
+            "items": {
+              "$ref": "#/components/schemas/ProjectSpendAlert"
+            }
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The ID of the first spend alert in this page."
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The ID of the last spend alert in this page."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether more spend alerts are available when paginating."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ]
+      },
+      "ProjectUpdateRequest": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The updated name of the project, this name appears in reports."
+          },
+          "external_key_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "External key ID to associate with the project."
+          },
+          "geography": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "deprecated": true,
+            "description": "Geography for the project.\nDeprecated: use `residency` when creating a project to configure data residency. This field is retained for backward compatibility."
+          }
+        }
+      },
+      "ProjectUser": {
+        "type": "object",
+        "description": "Represents an individual user in a project.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.project.user"
+            ],
+            "description": "The object type, which is always `organization.project.user`",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The identifier, which can be referenced in API endpoints"
+          },
+          "name": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The name of the user"
+          },
+          "email": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The email address of the user"
+          },
+          "role": {
+            "type": "string",
+            "description": "`owner` or `member`"
+          },
+          "added_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the project was added."
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "role",
+          "added_at"
+        ],
+        "x-oaiMeta": {
+          "name": "The project user object",
+          "example": "{\n    \"object\": \"organization.project.user\",\n    \"id\": \"user_abc\",\n    \"name\": \"First Last\",\n    \"email\": \"user@example.com\",\n    \"role\": \"owner\",\n    \"added_at\": 1711471533\n}\n"
+        }
+      },
+      "ProjectUserCreateRequest": {
+        "type": "object",
+        "properties": {
+          "user_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The ID of the user."
+          },
+          "email": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Email of the user to add."
+          },
+          "role": {
+            "type": "string",
+            "description": "`owner` or `member`"
+          }
+        },
+        "required": [
+          "role"
+        ]
+      },
+      "ProjectUserDeleteResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.project.user.deleted"
+            ],
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string"
+          },
+          "deleted": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "deleted"
+        ]
+      },
+      "ProjectUserListResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string"
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/ProjectUser"
+            }
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "has_more": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more"
+        ]
+      },
+      "ProjectUserUpdateRequest": {
+        "type": "object",
+        "properties": {
+          "role": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "`owner` or `member`"
+          }
+        }
+      },
+      "Prompt": {
+        "anyOf": [
+          {
+            "type": "object",
+            "description": "Reference to a prompt template and its variables.\n[Learn more](https://developers.openai.com/api/docs/guides/text?api-mode=responses#version-prompts-in-code).\n",
+            "required": [
+              "id"
+            ],
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique identifier of the prompt template to use."
+              },
+              "version": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "Optional version of the prompt template."
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "variables": {
+                "$ref": "#/components/schemas/ResponsePromptVariables"
+              }
+            }
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "PublicAssignOrganizationGroupRoleBody": {
+        "type": "object",
+        "description": "Request payload for assigning a role to a group or user.",
+        "properties": {
+          "role_id": {
+            "type": "string",
+            "description": "Identifier of the role to assign."
+          }
+        },
+        "required": [
+          "role_id"
+        ],
+        "x-oaiMeta": {
+          "example": "{\n    \"role_id\": \"role_01J1F8ROLE01\"\n}\n"
+        }
+      },
+      "PublicCreateOrganizationRoleBody": {
+        "type": "object",
+        "description": "Request payload for creating a custom role.",
+        "properties": {
+          "role_name": {
+            "type": "string",
+            "description": "Unique name for the role."
+          },
+          "permissions": {
+            "type": "array",
+            "description": "Permissions to grant to the role.",
+            "items": {
+              "type": "string"
+            }
+          },
+          "description": {
+            "description": "Optional description of the role.",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "role_name",
+          "permissions"
+        ],
+        "x-oaiMeta": {
+          "example": "{\n    \"role_name\": \"API Group Manager\",\n    \"permissions\": [\n        \"api.groups.read\",\n        \"api.groups.write\"\n    ],\n    \"description\": \"Allows managing organization groups\"\n}\n"
+        }
+      },
+      "PublicRoleListResource": {
+        "type": "object",
+        "description": "Paginated list of roles available on an organization or project.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "description": "Always `list`.",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "description": "Roles returned in the current page.",
+            "items": {
+              "$ref": "#/components/schemas/Role"
+            }
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether more roles are available when paginating."
+          },
+          "next": {
+            "description": "Cursor to fetch the next page of results, or `null` when there are no additional roles.",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more",
+          "next"
+        ],
+        "x-oaiMeta": {
+          "name": "Role list",
+          "example": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"object\": \"role\",\n            \"id\": \"role_01J1F8ROLE01\",\n            \"name\": \"API Group Manager\",\n            \"description\": \"Allows managing organization groups\",\n            \"permissions\": [\n                \"api.groups.read\",\n                \"api.groups.write\"\n            ],\n            \"resource_type\": \"api.organization\",\n            \"predefined_role\": false\n        }\n    ],\n    \"has_more\": false,\n    \"next\": null\n}\n"
+        }
+      },
+      "PublicUpdateOrganizationRoleBody": {
+        "type": "object",
+        "description": "Request payload for updating an existing role.",
+        "properties": {
+          "permissions": {
+            "description": "Updated set of permissions for the role.",
+            "anyOf": [
+              {
+                "type": "array",
+                "items": {
+                  "type": "string"
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "description": {
+            "description": "New description for the role.",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "role_name": {
+            "description": "New name for the role.",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "x-oaiMeta": {
+          "example": "{\n    \"role_name\": \"API Group Manager\",\n    \"permissions\": [\n        \"api.groups.read\",\n        \"api.groups.write\"\n    ],\n    \"description\": \"Allows managing organization groups\"\n}\n"
+        }
+      },
+      "RealtimeAudioFormats": {
+        "anyOf": [
+          {
+            "type": "object",
+            "title": "PCM audio format",
+            "description": "The PCM audio format. Only a 24kHz sample rate is supported.",
+            "properties": {
+              "type": {
+                "type": "string",
+                "description": "The audio format. Always `audio/pcm`.",
+                "enum": [
+                  "audio/pcm"
+                ]
+              },
+              "rate": {
+                "type": "integer",
+                "description": "The sample rate of the audio. Always `24000`.",
+                "enum": [
+                  24000
+                ]
+              }
+            }
+          },
+          {
+            "type": "object",
+            "title": "PCMU audio format",
+            "description": "The G.711 μ-law format.",
+            "properties": {
+              "type": {
+                "type": "string",
+                "description": "The audio format. Always `audio/pcmu`.",
+                "enum": [
+                  "audio/pcmu"
+                ]
+              }
+            }
+          },
+          {
+            "type": "object",
+            "title": "PCMA audio format",
+            "description": "The G.711 A-law format.",
+            "properties": {
+              "type": {
+                "type": "string",
+                "description": "The audio format. Always `audio/pcma`.",
+                "enum": [
+                  "audio/pcma"
+                ]
+              }
+            }
+          }
+        ]
+      },
+      "RealtimeBetaClientEventConversationItemCreate": {
+        "type": "object",
+        "description": "Add a new Item to the Conversation's context, including messages, function \ncalls, and function call responses. This event can be used both to populate a \n\"history\" of the conversation and to add new items mid-stream, but has the \ncurrent limitation that it cannot populate assistant audio messages.\n\nIf successful, the server will respond with a `conversation.item.created` \nevent, otherwise an `error` event will be sent.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "maxLength": 512,
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.create"
+            ],
+            "description": "The event type, must be `conversation.item.create`.",
+            "x-stainless-const": true
+          },
+          "previous_item_id": {
+            "type": "string",
+            "description": "The ID of the preceding item after which the new item will be inserted. \nIf not set, the new item will be appended to the end of the conversation.\nIf set to `root`, the new item will be added to the beginning of the conversation.\nIf set to an existing ID, it allows an item to be inserted mid-conversation. If the\nID cannot be found, an error will be returned and the item will not be added.\n"
+          },
+          "item": {
+            "$ref": "#/components/schemas/RealtimeConversationItem"
+          }
+        },
+        "required": [
+          "type",
+          "item"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.create",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"conversation.item.create\",\n  \"item\": {\n    \"type\": \"message\",\n    \"role\": \"user\",\n    \"content\": [\n      {\n        \"type\": \"input_text\",\n        \"text\": \"hi\"\n      }\n    ]\n  },\n  \"event_id\": \"b904fba0-0ec4-40af-8bbb-f908a9b26793\",\n}\n"
+        }
+      },
+      "RealtimeBetaClientEventConversationItemDelete": {
+        "type": "object",
+        "description": "Send this event when you want to remove any item from the conversation \nhistory. The server will respond with a `conversation.item.deleted` event, \nunless the item does not exist in the conversation history, in which case the \nserver will respond with an error.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.delete"
+            ],
+            "description": "The event type, must be `conversation.item.delete`.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item to delete."
+          }
+        },
+        "required": [
+          "type",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.delete",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_901\",\n    \"type\": \"conversation.item.delete\",\n    \"item_id\": \"msg_003\"\n}\n"
+        }
+      },
+      "RealtimeBetaClientEventConversationItemRetrieve": {
+        "type": "object",
+        "description": "Send this event when you want to retrieve the server's representation of a specific item in the conversation history. This is useful, for example, to inspect user audio after noise cancellation and VAD.\nThe server will respond with a `conversation.item.retrieved` event, \nunless the item does not exist in the conversation history, in which case the \nserver will respond with an error.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.retrieve"
+            ],
+            "description": "The event type, must be `conversation.item.retrieve`.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item to retrieve."
+          }
+        },
+        "required": [
+          "type",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.retrieve",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_901\",\n    \"type\": \"conversation.item.retrieve\",\n    \"item_id\": \"msg_003\"\n}\n"
+        }
+      },
+      "RealtimeBetaClientEventConversationItemTruncate": {
+        "type": "object",
+        "description": "Send this event to truncate a previous assistant message’s audio. The server \nwill produce audio faster than realtime, so this event is useful when the user \ninterrupts to truncate audio that has already been sent to the client but not \nyet played. This will synchronize the server's understanding of the audio with \nthe client's playback.\n\nTruncating audio will delete the server-side text transcript to ensure there \nis not text in the context that hasn't been heard by the user.\n\nIf successful, the server will respond with a `conversation.item.truncated` \nevent. \n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.truncate"
+            ],
+            "description": "The event type, must be `conversation.item.truncate`.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the assistant message item to truncate. Only assistant message \nitems can be truncated.\n"
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part to truncate. Set this to 0."
+          },
+          "audio_end_ms": {
+            "type": "integer",
+            "description": "Inclusive duration up to which audio is truncated, in milliseconds. If \nthe audio_end_ms is greater than the actual audio duration, the server \nwill respond with an error.\n"
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "content_index",
+          "audio_end_ms"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.truncate",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_678\",\n    \"type\": \"conversation.item.truncate\",\n    \"item_id\": \"msg_002\",\n    \"content_index\": 0,\n    \"audio_end_ms\": 1500\n}\n"
+        }
+      },
+      "RealtimeBetaClientEventInputAudioBufferAppend": {
+        "type": "object",
+        "description": "Send this event to append audio bytes to the input audio buffer. The audio \nbuffer is temporary storage you can write to and later commit. In Server VAD \nmode, the audio buffer is used to detect speech and the server will decide \nwhen to commit. When Server VAD is disabled, you must commit the audio buffer\nmanually.\n\nThe client may choose how much audio to place in each event up to a maximum \nof 15 MiB, for example streaming smaller chunks from the client may allow the \nVAD to be more responsive. Unlike made other client events, the server will \nnot send a confirmation response to this event.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_audio_buffer.append"
+            ],
+            "description": "The event type, must be `input_audio_buffer.append`.",
+            "x-stainless-const": true
+          },
+          "audio": {
+            "type": "string",
+            "description": "Base64-encoded audio bytes. This must be in the format specified by the \n`input_audio_format` field in the session configuration.\n"
+          }
+        },
+        "required": [
+          "type",
+          "audio"
+        ],
+        "x-oaiMeta": {
+          "name": "input_audio_buffer.append",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_456\",\n    \"type\": \"input_audio_buffer.append\",\n    \"audio\": \"Base64EncodedAudioData\"\n}\n"
+        }
+      },
+      "RealtimeBetaClientEventInputAudioBufferClear": {
+        "type": "object",
+        "description": "Send this event to clear the audio bytes in the buffer. The server will \nrespond with an `input_audio_buffer.cleared` event.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_audio_buffer.clear"
+            ],
+            "description": "The event type, must be `input_audio_buffer.clear`.",
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "x-oaiMeta": {
+          "name": "input_audio_buffer.clear",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_012\",\n    \"type\": \"input_audio_buffer.clear\"\n}\n"
+        }
+      },
+      "RealtimeBetaClientEventInputAudioBufferCommit": {
+        "type": "object",
+        "description": "Send this event to commit the user input audio buffer, which will create a \nnew user message item in the conversation. This event will produce an error \nif the input audio buffer is empty. When in Server VAD mode, the client does \nnot need to send this event, the server will commit the audio buffer \nautomatically.\n\nCommitting the input audio buffer will trigger input audio transcription \n(if enabled in session configuration), but it will not create a response \nfrom the model. The server will respond with an `input_audio_buffer.committed` \nevent.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_audio_buffer.commit"
+            ],
+            "description": "The event type, must be `input_audio_buffer.commit`.",
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "x-oaiMeta": {
+          "name": "input_audio_buffer.commit",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_789\",\n    \"type\": \"input_audio_buffer.commit\"\n}\n"
+        }
+      },
+      "RealtimeBetaClientEventOutputAudioBufferClear": {
+        "type": "object",
+        "description": "**WebRTC/SIP Only:** Emit to cut off the current audio response. This will trigger the server to\nstop generating audio and emit a `output_audio_buffer.cleared` event. This\nevent should be preceded by a `response.cancel` client event to stop the\ngeneration of the current response.\n[Learn more](https://developers.openai.com/api/docs/guides/realtime-conversations#client-and-server-events-for-audio-in-webrtc).\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the client event used for error handling."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "output_audio_buffer.clear"
+            ],
+            "description": "The event type, must be `output_audio_buffer.clear`.",
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "x-oaiMeta": {
+          "name": "output_audio_buffer.clear",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"optional_client_event_id\",\n    \"type\": \"output_audio_buffer.clear\"\n}\n"
+        }
+      },
+      "RealtimeBetaClientEventResponseCancel": {
+        "type": "object",
+        "description": "Send this event to cancel an in-progress response. The server will respond \nwith a `response.done` event with a status of `response.status=cancelled`. If \nthere is no response to cancel, the server will respond with an error.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.cancel"
+            ],
+            "description": "The event type, must be `response.cancel`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "A specific response ID to cancel - if not provided, will cancel an \nin-progress response in the default conversation.\n"
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "x-oaiMeta": {
+          "name": "response.cancel",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_567\",\n    \"type\": \"response.cancel\"\n}\n"
+        }
+      },
+      "RealtimeBetaClientEventResponseCreate": {
+        "type": "object",
+        "description": "This event instructs the server to create a Response, which means triggering \nmodel inference. When in Server VAD mode, the server will create Responses \nautomatically.\n\nA Response will include at least one Item, and may have two, in which case \nthe second will be a function call. These Items will be appended to the \nconversation history.\n\nThe server will respond with a `response.created` event, events for Items \nand content created, and finally a `response.done` event to indicate the \nResponse is complete.\n\nThe `response.create` event can optionally include inference configuration like \n`instructions`, and `temperature`. These fields will override the Session's \nconfiguration for this Response only.\n\nResponses can be created out-of-band of the default Conversation, meaning that they can\nhave arbitrary input, and it's possible to disable writing the output to the Conversation.\nOnly one Response can write to the default Conversation at a time, but otherwise multiple\nResponses can be created in parallel.\n\nClients can set `conversation` to `none` to create a Response that does not write to the default\nConversation. Arbitrary input can be provided with the `input` field, which is an array accepting\nraw Items and references to existing Items.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.create"
+            ],
+            "description": "The event type, must be `response.create`.",
+            "x-stainless-const": true
+          },
+          "response": {
+            "$ref": "#/components/schemas/RealtimeBetaResponseCreateParams"
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "x-oaiMeta": {
+          "name": "response.create",
+          "group": "realtime",
+          "example": "// Trigger a response with the default Conversation and no special parameters\n{\n  \"type\": \"response.create\",\n}\n\n// Trigger an out-of-band response that does not write to the default Conversation\n{\n  \"type\": \"response.create\",\n  \"response\": {\n    \"instructions\": \"Provide a concise answer.\",\n    \"tools\": [], // clear any session tools\n    \"conversation\": \"none\",\n    \"output_modalities\": [\"text\"],\n    \"input\": [\n      {\n        \"type\": \"item_reference\",\n        \"id\": \"item_12345\",\n      },\n      {\n        \"type\": \"message\",\n        \"role\": \"user\",\n        \"content\": [\n          {\n            \"type\": \"input_text\",\n            \"text\": \"Summarize the above message in one sentence.\"\n          }\n        ]\n      }\n    ],\n  }\n}\n"
+        }
+      },
+      "RealtimeBetaClientEventSessionUpdate": {
+        "type": "object",
+        "description": "Send this event to update the session’s default configuration.\nThe client may send this event at any time to update any field,\nexcept for `voice`. However, note that once a session has been\ninitialized with a particular `model`, it can’t be changed to\nanother model using `session.update`.\n\nWhen the server receives a `session.update`, it will respond\nwith a `session.updated` event showing the full, effective configuration.\nOnly the fields that are present are updated. To clear a field like\n`instructions`, pass an empty string.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "session.update"
+            ],
+            "description": "The event type, must be `session.update`.",
+            "x-stainless-const": true
+          },
+          "session": {
+            "$ref": "#/components/schemas/RealtimeSessionCreateRequest"
+          }
+        },
+        "required": [
+          "type",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "name": "session.update",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"session.update\",\n  \"session\": {\n    \"tools\": [\n      {\n        \"type\": \"function\",\n        \"name\": \"display_color_palette\",\n        \"description\": \"Call this function when a user asks for a color palette.\",\n        \"parameters\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"theme\": {\n              \"type\": \"string\",\n              \"description\": \"Description of the theme for the color scheme.\"\n            },\n            \"colors\": {\n              \"type\": \"array\",\n              \"description\": \"Array of five hex color codes based on the theme.\",\n              \"items\": {\n                \"type\": \"string\",\n                \"description\": \"Hex color code\"\n              }\n            }\n          },\n          \"required\": [\n            \"theme\",\n            \"colors\"\n          ]\n        }\n      }\n    ],\n    \"tool_choice\": \"auto\"\n  }\n}\n"
+        }
+      },
+      "RealtimeBetaClientEventTranscriptionSessionUpdate": {
+        "type": "object",
+        "description": "Send this event to update a transcription session.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "transcription_session.update"
+            ],
+            "description": "The event type, must be `transcription_session.update`.",
+            "x-stainless-const": true
+          },
+          "session": {
+            "$ref": "#/components/schemas/RealtimeTranscriptionSessionCreateRequest"
+          }
+        },
+        "required": [
+          "type",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "name": "transcription_session.update",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"transcription_session.update\",\n  \"session\": {\n    \"input_audio_format\": \"pcm16\",\n    \"input_audio_transcription\": {\n      \"model\": \"gpt-4o-transcribe\",\n      \"prompt\": \"\",\n      \"language\": \"\"\n    },\n    \"turn_detection\": {\n      \"type\": \"server_vad\",\n      \"threshold\": 0.5,\n      \"prefix_padding_ms\": 300,\n      \"silence_duration_ms\": 500,\n      \"create_response\": true,\n    },\n    \"input_audio_noise_reduction\": {\n      \"type\": \"near_field\"\n    },\n    \"include\": [\n      \"item.input_audio_transcription.logprobs\",\n    ]\n  }\n}\n"
+        }
+      },
+      "RealtimeBetaResponse": {
+        "type": "object",
+        "description": "The response resource.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the response."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "realtime.response"
+            ],
+            "description": "The object type, must be `realtime.response`.",
+            "x-stainless-const": true
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "completed",
+              "cancelled",
+              "failed",
+              "incomplete",
+              "in_progress"
+            ],
+            "description": "The final status of the response (`completed`, `cancelled`, `failed`, or \n`incomplete`, `in_progress`).\n"
+          },
+          "status_details": {
+            "type": "object",
+            "description": "Additional details about the status.",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "completed",
+                  "cancelled",
+                  "failed",
+                  "incomplete"
+                ],
+                "description": "The type of error that caused the response to fail, corresponding \nwith the `status` field (`completed`, `cancelled`, `incomplete`, \n`failed`).\n"
+              },
+              "reason": {
+                "type": "string",
+                "enum": [
+                  "turn_detected",
+                  "client_cancelled",
+                  "max_output_tokens",
+                  "content_filter"
+                ],
+                "description": "The reason the Response did not complete. For a `cancelled` Response, \none of `turn_detected` (the server VAD detected a new start of speech) \nor `client_cancelled` (the client sent a cancel event). For an \n`incomplete` Response, one of `max_output_tokens` or `content_filter` \n(the server-side safety filter activated and cut off the response).\n"
+              },
+              "error": {
+                "type": "object",
+                "description": "A description of the error that caused the response to fail, \npopulated when the `status` is `failed`.\n",
+                "properties": {
+                  "type": {
+                    "type": "string",
+                    "description": "The type of error."
+                  },
+                  "code": {
+                    "type": "string",
+                    "description": "Error code, if any."
+                  }
+                }
+              }
+            }
+          },
+          "output": {
+            "type": "array",
+            "description": "The list of output items generated by the response.",
+            "items": {
+              "$ref": "#/components/schemas/RealtimeConversationItem"
+            }
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          },
+          "usage": {
+            "type": "object",
+            "description": "Usage statistics for the Response, this will correspond to billing. A \nRealtime API session will maintain a conversation context and append new \nItems to the Conversation, thus output from previous turns (text and \naudio tokens) will become the input for later turns.\n",
+            "properties": {
+              "total_tokens": {
+                "type": "integer",
+                "description": "The total number of tokens in the Response including input and output \ntext and audio tokens.\n"
+              },
+              "input_tokens": {
+                "type": "integer",
+                "description": "The number of input tokens used in the Response, including text and \naudio tokens.\n"
+              },
+              "output_tokens": {
+                "type": "integer",
+                "description": "The number of output tokens sent in the Response, including text and \naudio tokens.\n"
+              },
+              "input_token_details": {
+                "type": "object",
+                "description": "Details about the input tokens used in the Response.",
+                "properties": {
+                  "cached_tokens": {
+                    "type": "integer",
+                    "description": "The number of cached tokens used as input for the Response."
+                  },
+                  "text_tokens": {
+                    "type": "integer",
+                    "description": "The number of text tokens used as input for the Response."
+                  },
+                  "image_tokens": {
+                    "type": "integer",
+                    "description": "The number of image tokens used as input for the Response."
+                  },
+                  "audio_tokens": {
+                    "type": "integer",
+                    "description": "The number of audio tokens used as input for the Response."
+                  },
+                  "cached_tokens_details": {
+                    "type": "object",
+                    "description": "Details about the cached tokens used as input for the Response.",
+                    "properties": {
+                      "text_tokens": {
+                        "type": "integer",
+                        "description": "The number of cached text tokens used as input for the Response."
+                      },
+                      "image_tokens": {
+                        "type": "integer",
+                        "description": "The number of cached image tokens used as input for the Response."
+                      },
+                      "audio_tokens": {
+                        "type": "integer",
+                        "description": "The number of cached audio tokens used as input for the Response."
+                      }
+                    }
+                  }
+                }
+              },
+              "output_token_details": {
+                "type": "object",
+                "description": "Details about the output tokens used in the Response.",
+                "properties": {
+                  "text_tokens": {
+                    "type": "integer",
+                    "description": "The number of text tokens used in the Response."
+                  },
+                  "audio_tokens": {
+                    "type": "integer",
+                    "description": "The number of audio tokens used in the Response."
+                  }
+                }
+              }
+            }
+          },
+          "conversation_id": {
+            "description": "Which conversation the response is added to, determined by the `conversation`\nfield in the `response.create` event. If `auto`, the response will be added to\nthe default conversation and the value of `conversation_id` will be an id like\n`conv_1234`. If `none`, the response will not be added to any conversation and\nthe value of `conversation_id` will be `null`. If responses are being triggered\nby server VAD, the response will be added to the default conversation, thus\nthe `conversation_id` will be an id like `conv_1234`.\n",
+            "type": "string"
+          },
+          "voice": {
+            "$ref": "#/components/schemas/VoiceIdsShared",
+            "description": "The voice the model used to respond.\nCurrent voice options are `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`,\n`shimmer`, and `verse`.\n"
+          },
+          "modalities": {
+            "type": "array",
+            "description": "The set of modalities the model used to respond. If there are multiple modalities,\nthe model will pick one, for example if `modalities` is `[\"text\", \"audio\"]`, the model\ncould be responding in either text or audio.\n",
+            "items": {
+              "type": "string",
+              "enum": [
+                "text",
+                "audio"
+              ]
+            }
+          },
+          "output_audio_format": {
+            "type": "string",
+            "enum": [
+              "pcm16",
+              "g711_ulaw",
+              "g711_alaw"
+            ],
+            "description": "The format of output audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.\n"
+          },
+          "temperature": {
+            "type": "number",
+            "description": "Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.\n"
+          },
+          "max_output_tokens": {
+            "oneOf": [
+              {
+                "type": "integer"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "inf"
+                ],
+                "x-stainless-const": true
+              }
+            ],
+            "description": "Maximum number of output tokens for a single assistant response,\ninclusive of tool calls, that was used in this response.\n"
+          }
+        }
+      },
+      "RealtimeBetaResponseCreateParams": {
+        "type": "object",
+        "description": "Create a new Realtime response with these parameters",
+        "properties": {
+          "modalities": {
+            "type": "array",
+            "description": "The set of modalities the model can respond with. To disable audio,\nset this to [\"text\"].\n",
+            "items": {
+              "type": "string",
+              "enum": [
+                "text",
+                "audio"
+              ]
+            }
+          },
+          "instructions": {
+            "type": "string",
+            "description": "The default system instructions (i.e. system message) prepended to model \ncalls. This field allows the client to guide the model on desired \nresponses. The model can be instructed on response content and format, \n(e.g. \"be extremely succinct\", \"act friendly\", \"here are examples of good \nresponses\") and on audio behavior (e.g. \"talk quickly\", \"inject emotion \ninto your voice\", \"laugh frequently\"). The instructions are not guaranteed \nto be followed by the model, but they provide guidance to the model on the \ndesired behavior.\n\nNote that the server sets default instructions which will be used if this \nfield is not set and are visible in the `session.created` event at the \nstart of the session.\n"
+          },
+          "voice": {
+            "$ref": "#/components/schemas/VoiceIdsOrCustomVoice",
+            "description": "The voice the model uses to respond. Supported built-in voices are\n`alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, `verse`,\n`marin`, and `cedar`. You may also provide a custom voice object with an\n`id`, for example `{ \"id\": \"voice_1234\" }`. Voice cannot be changed during\nthe session once the model has responded with audio at least once.\n"
+          },
+          "output_audio_format": {
+            "type": "string",
+            "enum": [
+              "pcm16",
+              "g711_ulaw",
+              "g711_alaw"
+            ],
+            "description": "The format of output audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.\n"
+          },
+          "tools": {
+            "type": "array",
+            "description": "Tools (functions) available to the model.",
+            "items": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "function"
+                  ],
+                  "description": "The type of the tool, i.e. `function`.",
+                  "x-stainless-const": true
+                },
+                "name": {
+                  "type": "string",
+                  "description": "The name of the function."
+                },
+                "description": {
+                  "type": "string",
+                  "description": "The description of the function, including guidance on when and how \nto call it, and guidance about what to tell the user when calling \n(if anything).\n"
+                },
+                "parameters": {
+                  "type": "object",
+                  "description": "Parameters of the function in JSON Schema."
+                }
+              }
+            }
+          },
+          "tool_choice": {
+            "description": "How the model chooses tools. Provide one of the string modes or force a specific\nfunction/MCP tool.\n",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/ToolChoiceOptions"
+              },
+              {
+                "$ref": "#/components/schemas/ToolChoiceFunction"
+              },
+              {
+                "$ref": "#/components/schemas/ToolChoiceMCP"
+              }
+            ],
+            "default": "auto"
+          },
+          "temperature": {
+            "type": "number",
+            "description": "Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.\n"
+          },
+          "max_output_tokens": {
+            "oneOf": [
+              {
+                "type": "integer"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "inf"
+                ],
+                "x-stainless-const": true
+              }
+            ],
+            "description": "Maximum number of output tokens for a single assistant response,\ninclusive of tool calls. Provide an integer between 1 and 4096 to\nlimit output tokens, or `inf` for the maximum available tokens for a\ngiven model. Defaults to `inf`.\n"
+          },
+          "conversation": {
+            "description": "Controls which conversation the response is added to. Currently supports\n`auto` and `none`, with `auto` as the default value. The `auto` value\nmeans that the contents of the response will be added to the default\nconversation. Set this to `none` to create an out-of-band response which \nwill not add items to default conversation.\n",
+            "oneOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "default": "auto",
+                "enum": [
+                  "auto",
+                  "none"
+                ]
+              }
+            ]
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          },
+          "prompt": {
+            "$ref": "#/components/schemas/Prompt"
+          },
+          "input": {
+            "type": "array",
+            "description": "Input items to include in the prompt for the model. Using this field\ncreates a new context for this Response instead of using the default\nconversation. An empty array `[]` will clear the context for this Response.\nNote that this can include references to items from the default conversation.\n",
+            "items": {
+              "$ref": "#/components/schemas/RealtimeConversationItem"
+            }
+          }
+        }
+      },
+      "RealtimeBetaServerEventConversationItemCreated": {
+        "type": "object",
+        "description": "Returned when a conversation item is created. There are several scenarios that produce this event:\n  - The server is generating a Response, which if successful will produce\n    either one or two Items, which will be of type `message`\n    (role `assistant`) or type `function_call`.\n  - The input audio buffer has been committed, either by the client or the\n    server (in `server_vad` mode). The server will take the content of the\n    input audio buffer and add it to a new user message Item.\n  - The client has sent a `conversation.item.create` event to add a new Item\n    to the Conversation.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.created"
+            ],
+            "description": "The event type, must be `conversation.item.created`.",
+            "x-stainless-const": true
+          },
+          "previous_item_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the preceding item in the Conversation context, allows the\nclient to understand the order of the conversation. Can be `null` if the\nitem has no predecessor.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "item": {
+            "$ref": "#/components/schemas/RealtimeConversationItem"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.created",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_1920\",\n    \"type\": \"conversation.item.created\",\n    \"previous_item_id\": \"msg_002\",\n    \"item\": {\n        \"id\": \"msg_003\",\n        \"object\": \"realtime.item\",\n        \"type\": \"message\",\n        \"status\": \"completed\",\n        \"role\": \"user\",\n        \"content\": []\n    }\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventConversationItemDeleted": {
+        "type": "object",
+        "description": "Returned when an item in the conversation is deleted by the client with a \n`conversation.item.delete` event. This event is used to synchronize the \nserver's understanding of the conversation history with the client's view.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.deleted"
+            ],
+            "description": "The event type, must be `conversation.item.deleted`.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item that was deleted."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.deleted",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_2728\",\n    \"type\": \"conversation.item.deleted\",\n    \"item_id\": \"msg_005\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventConversationItemInputAudioTranscriptionCompleted": {
+        "type": "object",
+        "description": "This event is the output of audio transcription for user audio written to the\nuser audio buffer. Transcription begins when the input audio buffer is\ncommitted by the client or server (in `server_vad` mode). Transcription runs\nasynchronously with Response creation, so this event may come before or after\nthe Response events.\n\nRealtime API models accept audio natively, and thus input transcription is a\nseparate process run on a separate ASR (Automatic Speech Recognition) model.\nThe transcript may diverge somewhat from the model's interpretation, and\nshould be treated as a rough guide.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.input_audio_transcription.completed"
+            ],
+            "description": "The event type, must be\n`conversation.item.input_audio_transcription.completed`.\n",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the user message item containing the audio."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part containing the audio."
+          },
+          "transcript": {
+            "type": "string",
+            "description": "The transcribed text."
+          },
+          "languages": {
+            "type": "array",
+            "description": "The languages detected in the audio. Returned by `gpt-transcribe`. An empty array indicates that no language could be reliably detected.\n",
+            "items": {
+              "$ref": "#/components/schemas/TranscriptionLanguage"
+            }
+          },
+          "logprobs": {
+            "anyOf": [
+              {
+                "type": "array",
+                "description": "The log probabilities of the transcription.",
+                "items": {
+                  "$ref": "#/components/schemas/LogProbProperties"
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "usage": {
+            "type": "object",
+            "description": "Usage statistics for the transcription.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/TranscriptTextUsageTokens",
+                "title": "Token Usage"
+              },
+              {
+                "$ref": "#/components/schemas/TranscriptTextUsageDuration",
+                "title": "Duration Usage"
+              }
+            ]
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item_id",
+          "content_index",
+          "transcript",
+          "usage"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.input_audio_transcription.completed",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_2122\",\n    \"type\": \"conversation.item.input_audio_transcription.completed\",\n    \"item_id\": \"msg_003\",\n    \"content_index\": 0,\n    \"transcript\": \"Hello, how are you?\",\n    \"usage\": {\n      \"type\": \"tokens\",\n      \"total_tokens\": 48,\n      \"input_tokens\": 38,\n      \"input_token_details\": {\n        \"text_tokens\": 10,\n        \"audio_tokens\": 28,\n      },\n      \"output_tokens\": 10,\n    }\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventConversationItemInputAudioTranscriptionDelta": {
+        "type": "object",
+        "description": "Returned when the text value of an input audio transcription content part is updated.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.input_audio_transcription.delta"
+            ],
+            "description": "The event type, must be `conversation.item.input_audio_transcription.delta`.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part in the item's content array."
+          },
+          "delta": {
+            "type": "string",
+            "description": "The text delta."
+          },
+          "logprobs": {
+            "anyOf": [
+              {
+                "type": "array",
+                "description": "The log probabilities of the transcription.",
+                "items": {
+                  "$ref": "#/components/schemas/LogProbProperties"
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.input_audio_transcription.delta",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"conversation.item.input_audio_transcription.delta\",\n  \"event_id\": \"event_001\",\n  \"item_id\": \"item_001\",\n  \"content_index\": 0,\n  \"delta\": \"Hello\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventConversationItemInputAudioTranscriptionFailed": {
+        "type": "object",
+        "description": "Returned when input audio transcription is configured, and a transcription \nrequest for a user message failed. These events are separate from other \n`error` events so that the client can identify the related Item.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.input_audio_transcription.failed"
+            ],
+            "description": "The event type, must be\n`conversation.item.input_audio_transcription.failed`.\n",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the user message item."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part containing the audio."
+          },
+          "error": {
+            "type": "object",
+            "description": "Details of the transcription error.",
+            "properties": {
+              "type": {
+                "type": "string",
+                "description": "The type of error."
+              },
+              "code": {
+                "type": "string",
+                "description": "Error code, if any."
+              },
+              "message": {
+                "type": "string",
+                "description": "A human-readable error message."
+              },
+              "param": {
+                "type": "string",
+                "description": "Parameter related to the error, if any."
+              }
+            }
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item_id",
+          "content_index",
+          "error"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.input_audio_transcription.failed",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_2324\",\n    \"type\": \"conversation.item.input_audio_transcription.failed\",\n    \"item_id\": \"msg_003\",\n    \"content_index\": 0,\n    \"error\": {\n        \"type\": \"transcription_error\",\n        \"code\": \"audio_unintelligible\",\n        \"message\": \"The audio could not be transcribed.\",\n        \"param\": null\n    }\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventConversationItemInputAudioTranscriptionSegment": {
+        "type": "object",
+        "description": "Returned when an input audio transcription segment is identified for an item.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.input_audio_transcription.segment"
+            ],
+            "description": "The event type, must be `conversation.item.input_audio_transcription.segment`.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item containing the input audio content."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the input audio content part within the item."
+          },
+          "text": {
+            "type": "string",
+            "description": "The text for this segment."
+          },
+          "id": {
+            "type": "string",
+            "description": "The segment identifier."
+          },
+          "speaker": {
+            "type": "string",
+            "description": "The detected speaker label for this segment."
+          },
+          "start": {
+            "type": "number",
+            "format": "double",
+            "description": "Start time of the segment in seconds."
+          },
+          "end": {
+            "type": "number",
+            "format": "double",
+            "description": "End time of the segment in seconds."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item_id",
+          "content_index",
+          "text",
+          "id",
+          "speaker",
+          "start",
+          "end"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.input_audio_transcription.segment",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_6501\",\n    \"type\": \"conversation.item.input_audio_transcription.segment\",\n    \"item_id\": \"msg_011\",\n    \"content_index\": 0,\n    \"text\": \"hello\",\n    \"id\": \"seg_0001\",\n    \"speaker\": \"spk_1\",\n    \"start\": 0.0,\n    \"end\": 0.4\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventConversationItemRetrieved": {
+        "type": "object",
+        "description": "Returned when a conversation item is retrieved with `conversation.item.retrieve`.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.retrieved"
+            ],
+            "description": "The event type, must be `conversation.item.retrieved`.",
+            "x-stainless-const": true
+          },
+          "item": {
+            "$ref": "#/components/schemas/RealtimeConversationItem"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.retrieved",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_1920\",\n    \"type\": \"conversation.item.created\",\n    \"previous_item_id\": \"msg_002\",\n    \"item\": {\n        \"id\": \"msg_003\",\n        \"object\": \"realtime.item\",\n        \"type\": \"message\",\n        \"status\": \"completed\",\n        \"role\": \"user\",\n        \"content\": [\n            {\n                \"type\": \"input_audio\",\n                \"transcript\": \"hello how are you\",\n                \"audio\": \"base64encodedaudio==\"\n            }\n        ]\n    }\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventConversationItemTruncated": {
+        "type": "object",
+        "description": "Returned when an earlier assistant audio message item is truncated by the \nclient with a `conversation.item.truncate` event. This event is used to \nsynchronize the server's understanding of the audio with the client's playback.\n\nThis action will truncate the audio and remove the server-side text transcript \nto ensure there is no text in the context that hasn't been heard by the user.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.truncated"
+            ],
+            "description": "The event type, must be `conversation.item.truncated`.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the assistant message item that was truncated."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part that was truncated."
+          },
+          "audio_end_ms": {
+            "type": "integer",
+            "description": "The duration up to which the audio was truncated, in milliseconds.\n"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item_id",
+          "content_index",
+          "audio_end_ms"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.truncated",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_2526\",\n    \"type\": \"conversation.item.truncated\",\n    \"item_id\": \"msg_004\",\n    \"content_index\": 0,\n    \"audio_end_ms\": 1500\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventError": {
+        "type": "object",
+        "description": "Returned when an error occurs, which could be a client problem or a server\nproblem. Most errors are recoverable and the session will stay open, we\nrecommend to implementors to monitor and log error messages by default.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "error"
+            ],
+            "description": "The event type, must be `error`.",
+            "x-stainless-const": true
+          },
+          "error": {
+            "type": "object",
+            "description": "Details of the error.",
+            "required": [
+              "type",
+              "message"
+            ],
+            "properties": {
+              "type": {
+                "type": "string",
+                "description": "The type of error (e.g., \"invalid_request_error\", \"server_error\").\n"
+              },
+              "code": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "Error code, if any."
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "message": {
+                "type": "string",
+                "description": "A human-readable error message."
+              },
+              "param": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "Parameter related to the error, if any."
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "event_id": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "The event_id of the client event that caused the error, if applicable.\n"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              }
+            }
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "error"
+        ],
+        "x-oaiMeta": {
+          "name": "error",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_890\",\n    \"type\": \"error\",\n    \"error\": {\n        \"type\": \"invalid_request_error\",\n        \"code\": \"invalid_event\",\n        \"message\": \"The 'type' field is missing.\",\n        \"param\": null,\n        \"event_id\": \"event_567\"\n    }\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventInputAudioBufferCleared": {
+        "type": "object",
+        "description": "Returned when the input audio buffer is cleared by the client with a \n`input_audio_buffer.clear` event.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_audio_buffer.cleared"
+            ],
+            "description": "The event type, must be `input_audio_buffer.cleared`.",
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "event_id",
+          "type"
+        ],
+        "x-oaiMeta": {
+          "name": "input_audio_buffer.cleared",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_1314\",\n    \"type\": \"input_audio_buffer.cleared\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventInputAudioBufferCommitted": {
+        "type": "object",
+        "description": "Returned when an input audio buffer is committed, either by the client or\nautomatically in server VAD mode. The `item_id` property is the ID of the user\nmessage item that will be created, thus a `conversation.item.created` event\nwill also be sent to the client.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_audio_buffer.committed"
+            ],
+            "description": "The event type, must be `input_audio_buffer.committed`.",
+            "x-stainless-const": true
+          },
+          "previous_item_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the preceding item after which the new item will be inserted.\nCan be `null` if the item has no predecessor.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the user message item that will be created."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "input_audio_buffer.committed",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_1121\",\n    \"type\": \"input_audio_buffer.committed\",\n    \"previous_item_id\": \"msg_001\",\n    \"item_id\": \"msg_002\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventInputAudioBufferSpeechStarted": {
+        "type": "object",
+        "description": "Sent by the server when in `server_vad` mode to indicate that speech has been \ndetected in the audio buffer. This can happen any time audio is added to the \nbuffer (unless speech is already detected). The client may want to use this \nevent to interrupt audio playback or provide visual feedback to the user. \n\nThe client should expect to receive a `input_audio_buffer.speech_stopped` event \nwhen speech stops. The `item_id` property is the ID of the user message item \nthat will be created when speech stops and will also be included in the \n`input_audio_buffer.speech_stopped` event (unless the client manually commits \nthe audio buffer during VAD activation).\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_audio_buffer.speech_started"
+            ],
+            "description": "The event type, must be `input_audio_buffer.speech_started`.",
+            "x-stainless-const": true
+          },
+          "audio_start_ms": {
+            "type": "integer",
+            "description": "Milliseconds from the start of all audio written to the buffer during the \nsession when speech was first detected. This will correspond to the \nbeginning of audio sent to the model, and thus includes the \n`prefix_padding_ms` configured in the Session.\n"
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the user message item that will be created when speech stops.\n"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "audio_start_ms",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "input_audio_buffer.speech_started",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_1516\",\n    \"type\": \"input_audio_buffer.speech_started\",\n    \"audio_start_ms\": 1000,\n    \"item_id\": \"msg_003\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventInputAudioBufferSpeechStopped": {
+        "type": "object",
+        "description": "Returned in `server_vad` mode when the server detects the end of speech in \nthe audio buffer. The server will also send an `conversation.item.created` \nevent with the user message item that is created from the audio buffer.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_audio_buffer.speech_stopped"
+            ],
+            "description": "The event type, must be `input_audio_buffer.speech_stopped`.",
+            "x-stainless-const": true
+          },
+          "audio_end_ms": {
+            "type": "integer",
+            "description": "Milliseconds since the session started when speech stopped. This will \ncorrespond to the end of audio sent to the model, and thus includes the \n`min_silence_duration_ms` configured in the Session.\n"
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the user message item that will be created."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "audio_end_ms",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "input_audio_buffer.speech_stopped",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_1718\",\n    \"type\": \"input_audio_buffer.speech_stopped\",\n    \"audio_end_ms\": 2000,\n    \"item_id\": \"msg_003\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventMCPListToolsCompleted": {
+        "type": "object",
+        "description": "Returned when listing MCP tools has completed for an item.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_list_tools.completed"
+            ],
+            "description": "The event type, must be `mcp_list_tools.completed`.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP list tools item."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "mcp_list_tools.completed",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_6102\",\n    \"type\": \"mcp_list_tools.completed\",\n    \"item_id\": \"mcp_list_tools_001\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventMCPListToolsFailed": {
+        "type": "object",
+        "description": "Returned when listing MCP tools has failed for an item.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_list_tools.failed"
+            ],
+            "description": "The event type, must be `mcp_list_tools.failed`.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP list tools item."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "mcp_list_tools.failed",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_6103\",\n    \"type\": \"mcp_list_tools.failed\",\n    \"item_id\": \"mcp_list_tools_001\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventMCPListToolsInProgress": {
+        "type": "object",
+        "description": "Returned when listing MCP tools is in progress for an item.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_list_tools.in_progress"
+            ],
+            "description": "The event type, must be `mcp_list_tools.in_progress`.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP list tools item."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "mcp_list_tools.in_progress",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_6101\",\n    \"type\": \"mcp_list_tools.in_progress\",\n    \"item_id\": \"mcp_list_tools_001\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventRateLimitsUpdated": {
+        "type": "object",
+        "description": "Emitted at the beginning of a Response to indicate the updated rate limits. \nWhen a Response is created some tokens will be \"reserved\" for the output \ntokens, the rate limits shown here reflect that reservation, which is then \nadjusted accordingly once the Response is completed.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "rate_limits.updated"
+            ],
+            "description": "The event type, must be `rate_limits.updated`.",
+            "x-stainless-const": true
+          },
+          "rate_limits": {
+            "type": "array",
+            "description": "List of rate limit information.",
+            "items": {
+              "type": "object",
+              "properties": {
+                "name": {
+                  "type": "string",
+                  "enum": [
+                    "requests",
+                    "tokens"
+                  ],
+                  "description": "The name of the rate limit (`requests`, `tokens`).\n"
+                },
+                "limit": {
+                  "type": "integer",
+                  "description": "The maximum allowed value for the rate limit."
+                },
+                "remaining": {
+                  "type": "integer",
+                  "description": "The remaining value before the limit is reached."
+                },
+                "reset_seconds": {
+                  "type": "number",
+                  "description": "Seconds until the rate limit resets."
+                }
+              }
+            }
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "rate_limits"
+        ],
+        "x-oaiMeta": {
+          "name": "rate_limits.updated",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_5758\",\n    \"type\": \"rate_limits.updated\",\n    \"rate_limits\": [\n        {\n            \"name\": \"requests\",\n            \"limit\": 1000,\n            \"remaining\": 999,\n            \"reset_seconds\": 60\n        },\n        {\n            \"name\": \"tokens\",\n            \"limit\": 50000,\n            \"remaining\": 49950,\n            \"reset_seconds\": 60\n        }\n    ]\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventResponseAudioDelta": {
+        "type": "object",
+        "description": "Returned when the model-generated audio is updated.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.output_audio.delta"
+            ],
+            "description": "The event type, must be `response.output_audio.delta`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part in the item's content array."
+          },
+          "delta": {
+            "type": "string",
+            "description": "Base64-encoded audio data delta."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "delta"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_audio.delta",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_4950\",\n    \"type\": \"response.output_audio.delta\",\n    \"response_id\": \"resp_001\",\n    \"item_id\": \"msg_008\",\n    \"output_index\": 0,\n    \"content_index\": 0,\n    \"delta\": \"Base64EncodedAudioDelta\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventResponseAudioDone": {
+        "type": "object",
+        "description": "Returned when the model-generated audio is done. Also emitted when a Response\nis interrupted, incomplete, or cancelled.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.output_audio.done"
+            ],
+            "description": "The event type, must be `response.output_audio.done`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part in the item's content array."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "content_index"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_audio.done",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_5152\",\n    \"type\": \"response.output_audio.done\",\n    \"response_id\": \"resp_001\",\n    \"item_id\": \"msg_008\",\n    \"output_index\": 0,\n    \"content_index\": 0\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventResponseAudioTranscriptDelta": {
+        "type": "object",
+        "description": "Returned when the model-generated transcription of audio output is updated.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.output_audio_transcript.delta"
+            ],
+            "description": "The event type, must be `response.output_audio_transcript.delta`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part in the item's content array."
+          },
+          "delta": {
+            "type": "string",
+            "description": "The transcript delta."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "delta"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_audio_transcript.delta",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_4546\",\n    \"type\": \"response.output_audio_transcript.delta\",\n    \"response_id\": \"resp_001\",\n    \"item_id\": \"msg_008\",\n    \"output_index\": 0,\n    \"content_index\": 0,\n    \"delta\": \"Hello, how can I a\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventResponseAudioTranscriptDone": {
+        "type": "object",
+        "description": "Returned when the model-generated transcription of audio output is done\nstreaming. Also emitted when a Response is interrupted, incomplete, or\ncancelled.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.output_audio_transcript.done"
+            ],
+            "description": "The event type, must be `response.output_audio_transcript.done`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part in the item's content array."
+          },
+          "transcript": {
+            "type": "string",
+            "description": "The final transcript of the audio."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "transcript"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_audio_transcript.done",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_4748\",\n    \"type\": \"response.output_audio_transcript.done\",\n    \"response_id\": \"resp_001\",\n    \"item_id\": \"msg_008\",\n    \"output_index\": 0,\n    \"content_index\": 0,\n    \"transcript\": \"Hello, how can I assist you today?\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventResponseContentPartAdded": {
+        "type": "object",
+        "description": "Returned when a new content part is added to an assistant message item during\nresponse generation.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.content_part.added"
+            ],
+            "description": "The event type, must be `response.content_part.added`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item to which the content part was added."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part in the item's content array."
+          },
+          "part": {
+            "type": "object",
+            "description": "The content part that was added.",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "audio",
+                  "text"
+                ],
+                "description": "The content type (\"text\", \"audio\")."
+              },
+              "text": {
+                "type": "string",
+                "description": "The text content (if type is \"text\")."
+              },
+              "audio": {
+                "type": "string",
+                "description": "Base64-encoded audio data (if type is \"audio\")."
+              },
+              "transcript": {
+                "type": "string",
+                "description": "The transcript of the audio (if type is \"audio\")."
+              }
+            }
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "part"
+        ],
+        "x-oaiMeta": {
+          "name": "response.content_part.added",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_3738\",\n    \"type\": \"response.content_part.added\",\n    \"response_id\": \"resp_001\",\n    \"item_id\": \"msg_007\",\n    \"output_index\": 0,\n    \"content_index\": 0,\n    \"part\": {\n        \"type\": \"text\",\n        \"text\": \"\"\n    }\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventResponseContentPartDone": {
+        "type": "object",
+        "description": "Returned when a content part is done streaming in an assistant message item.\nAlso emitted when a Response is interrupted, incomplete, or cancelled.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.content_part.done"
+            ],
+            "description": "The event type, must be `response.content_part.done`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part in the item's content array."
+          },
+          "part": {
+            "type": "object",
+            "description": "The content part that is done.",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "audio",
+                  "text"
+                ],
+                "description": "The content type (\"text\", \"audio\")."
+              },
+              "text": {
+                "type": "string",
+                "description": "The text content (if type is \"text\")."
+              },
+              "audio": {
+                "type": "string",
+                "description": "Base64-encoded audio data (if type is \"audio\")."
+              },
+              "transcript": {
+                "type": "string",
+                "description": "The transcript of the audio (if type is \"audio\")."
+              }
+            }
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "part"
+        ],
+        "x-oaiMeta": {
+          "name": "response.content_part.done",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_3940\",\n    \"type\": \"response.content_part.done\",\n    \"response_id\": \"resp_001\",\n    \"item_id\": \"msg_007\",\n    \"output_index\": 0,\n    \"content_index\": 0,\n    \"part\": {\n        \"type\": \"text\",\n        \"text\": \"Sure, I can help with that.\"\n    }\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventResponseCreated": {
+        "type": "object",
+        "description": "Returned when a new Response is created. The first event of response creation,\nwhere the response is in an initial state of `in_progress`.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.created"
+            ],
+            "description": "The event type, must be `response.created`.",
+            "x-stainless-const": true
+          },
+          "response": {
+            "$ref": "#/components/schemas/RealtimeBetaResponse"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response"
+        ],
+        "x-oaiMeta": {
+          "name": "response.created",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"response.created\",\n  \"event_id\": \"event_C9G8pqbTEddBSIxbBN6Os\",\n  \"response\": {\n    \"object\": \"realtime.response\",\n    \"id\": \"resp_C9G8p7IH2WxLbkgPNouYL\",\n    \"status\": \"in_progress\",\n    \"status_details\": null,\n    \"output\": [],\n    \"conversation_id\": \"conv_C9G8mmBkLhQJwCon3hoJN\",\n    \"output_modalities\": [\n      \"audio\"\n    ],\n    \"max_output_tokens\": \"inf\",\n    \"audio\": {\n      \"output\": {\n        \"format\": {\n          \"type\": \"audio/pcm\",\n          \"rate\": 24000\n        },\n        \"voice\": \"marin\"\n      }\n    },\n    \"usage\": null,\n    \"metadata\": null\n  },\n  \"timestamp\": \"2:30:35 PM\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventResponseDone": {
+        "type": "object",
+        "description": "Returned when a Response is done streaming. Always emitted, no matter the \nfinal state. The Response object included in the `response.done` event will \ninclude all output Items in the Response but will omit the raw audio data.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.done"
+            ],
+            "description": "The event type, must be `response.done`.",
+            "x-stainless-const": true
+          },
+          "response": {
+            "$ref": "#/components/schemas/RealtimeBetaResponse"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response"
+        ],
+        "x-oaiMeta": {
+          "name": "response.done",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_3132\",\n    \"type\": \"response.done\",\n    \"response\": {\n        \"id\": \"resp_001\",\n        \"object\": \"realtime.response\",\n        \"status\": \"completed\",\n        \"status_details\": null,\n        \"output\": [\n            {\n                \"id\": \"msg_006\",\n                \"object\": \"realtime.item\",\n                \"type\": \"message\",\n                \"status\": \"completed\",\n                \"role\": \"assistant\",\n                \"content\": [\n                    {\n                        \"type\": \"text\",\n                        \"text\": \"Sure, how can I assist you today?\"\n                    }\n                ]\n            }\n        ],\n        \"usage\": {\n            \"total_tokens\":275,\n            \"input_tokens\":127,\n            \"output_tokens\":148,\n            \"input_token_details\": {\n                \"cached_tokens\":384,\n                \"text_tokens\":119,\n                \"audio_tokens\":8,\n                \"cached_tokens_details\": {\n                    \"text_tokens\": 128,\n                    \"audio_tokens\": 256\n                }\n            },\n            \"output_token_details\": {\n              \"text_tokens\":36,\n              \"audio_tokens\":112\n            }\n        }\n    }\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventResponseFunctionCallArgumentsDelta": {
+        "type": "object",
+        "description": "Returned when the model-generated function call arguments are updated.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.function_call_arguments.delta"
+            ],
+            "description": "The event type, must be `response.function_call_arguments.delta`.\n",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the function call item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The ID of the function call."
+          },
+          "delta": {
+            "type": "string",
+            "description": "The arguments delta as a JSON string."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "call_id",
+          "delta"
+        ],
+        "x-oaiMeta": {
+          "name": "response.function_call_arguments.delta",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_5354\",\n    \"type\": \"response.function_call_arguments.delta\",\n    \"response_id\": \"resp_002\",\n    \"item_id\": \"fc_001\",\n    \"output_index\": 0,\n    \"call_id\": \"call_001\",\n    \"delta\": \"{\\\"location\\\": \\\"San\\\"\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventResponseFunctionCallArgumentsDone": {
+        "type": "object",
+        "description": "Returned when the model-generated function call arguments are done streaming.\nAlso emitted when a Response is interrupted, incomplete, or cancelled.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.function_call_arguments.done"
+            ],
+            "description": "The event type, must be `response.function_call_arguments.done`.\n",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the function call item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The ID of the function call."
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the function that was called."
+          },
+          "arguments": {
+            "type": "string",
+            "description": "The final arguments as a JSON string."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "call_id",
+          "name",
+          "arguments"
+        ],
+        "x-oaiMeta": {
+          "name": "response.function_call_arguments.done",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_5556\",\n    \"type\": \"response.function_call_arguments.done\",\n    \"response_id\": \"resp_002\",\n    \"item_id\": \"fc_001\",\n    \"output_index\": 0,\n    \"call_id\": \"call_001\",\n    \"name\": \"get_weather\",\n    \"arguments\": \"{\\\"location\\\": \\\"San Francisco\\\"}\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventResponseMCPCallArgumentsDelta": {
+        "type": "object",
+        "description": "Returned when MCP tool call arguments are updated during response generation.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_call_arguments.delta"
+            ],
+            "description": "The event type, must be `response.mcp_call_arguments.delta`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP tool call item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "delta": {
+            "type": "string",
+            "description": "The JSON-encoded arguments delta."
+          },
+          "obfuscation": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "If present, indicates the delta text was obfuscated."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "delta"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_call_arguments.delta",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_6201\",\n    \"type\": \"response.mcp_call_arguments.delta\",\n    \"response_id\": \"resp_001\",\n    \"item_id\": \"mcp_call_001\",\n    \"output_index\": 0,\n    \"delta\": \"{\\\"partial\\\":true}\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventResponseMCPCallArgumentsDone": {
+        "type": "object",
+        "description": "Returned when MCP tool call arguments are finalized during response generation.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_call_arguments.done"
+            ],
+            "description": "The event type, must be `response.mcp_call_arguments.done`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP tool call item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "arguments": {
+            "type": "string",
+            "description": "The final JSON-encoded arguments string."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "arguments"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_call_arguments.done",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_6202\",\n    \"type\": \"response.mcp_call_arguments.done\",\n    \"response_id\": \"resp_001\",\n    \"item_id\": \"mcp_call_001\",\n    \"output_index\": 0,\n    \"arguments\": \"{\\\"q\\\":\\\"docs\\\"}\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventResponseMCPCallCompleted": {
+        "type": "object",
+        "description": "Returned when an MCP tool call has completed successfully.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_call.completed"
+            ],
+            "description": "The event type, must be `response.mcp_call.completed`.",
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP tool call item."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "output_index",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_call.completed",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_6302\",\n    \"type\": \"response.mcp_call.completed\",\n    \"output_index\": 0,\n    \"item_id\": \"mcp_call_001\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventResponseMCPCallFailed": {
+        "type": "object",
+        "description": "Returned when an MCP tool call has failed.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_call.failed"
+            ],
+            "description": "The event type, must be `response.mcp_call.failed`.",
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP tool call item."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "output_index",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_call.failed",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_6303\",\n    \"type\": \"response.mcp_call.failed\",\n    \"output_index\": 0,\n    \"item_id\": \"mcp_call_001\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventResponseMCPCallInProgress": {
+        "type": "object",
+        "description": "Returned when an MCP tool call has started and is in progress.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_call.in_progress"
+            ],
+            "description": "The event type, must be `response.mcp_call.in_progress`.",
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP tool call item."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "output_index",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_call.in_progress",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_6301\",\n    \"type\": \"response.mcp_call.in_progress\",\n    \"output_index\": 0,\n    \"item_id\": \"mcp_call_001\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventResponseOutputItemAdded": {
+        "type": "object",
+        "description": "Returned when a new Item is created during Response generation.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.output_item.added"
+            ],
+            "description": "The event type, must be `response.output_item.added`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the Response to which the item belongs."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the Response."
+          },
+          "item": {
+            "$ref": "#/components/schemas/RealtimeConversationItem"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "output_index",
+          "item"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_item.added",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_3334\",\n    \"type\": \"response.output_item.added\",\n    \"response_id\": \"resp_001\",\n    \"output_index\": 0,\n    \"item\": {\n        \"id\": \"msg_007\",\n        \"object\": \"realtime.item\",\n        \"type\": \"message\",\n        \"status\": \"in_progress\",\n        \"role\": \"assistant\",\n        \"content\": []\n    }\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventResponseOutputItemDone": {
+        "type": "object",
+        "description": "Returned when an Item is done streaming. Also emitted when a Response is \ninterrupted, incomplete, or cancelled.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.output_item.done"
+            ],
+            "description": "The event type, must be `response.output_item.done`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the Response to which the item belongs."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the Response."
+          },
+          "item": {
+            "$ref": "#/components/schemas/RealtimeConversationItem"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "output_index",
+          "item"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_item.done",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_3536\",\n    \"type\": \"response.output_item.done\",\n    \"response_id\": \"resp_001\",\n    \"output_index\": 0,\n    \"item\": {\n        \"id\": \"msg_007\",\n        \"object\": \"realtime.item\",\n        \"type\": \"message\",\n        \"status\": \"completed\",\n        \"role\": \"assistant\",\n        \"content\": [\n            {\n                \"type\": \"text\",\n                \"text\": \"Sure, I can help with that.\"\n            }\n        ]\n    }\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventResponseTextDelta": {
+        "type": "object",
+        "description": "Returned when the text value of an \"output_text\" content part is updated.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.output_text.delta"
+            ],
+            "description": "The event type, must be `response.output_text.delta`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part in the item's content array."
+          },
+          "delta": {
+            "type": "string",
+            "description": "The text delta."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "delta"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_text.delta",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_4142\",\n    \"type\": \"response.output_text.delta\",\n    \"response_id\": \"resp_001\",\n    \"item_id\": \"msg_007\",\n    \"output_index\": 0,\n    \"content_index\": 0,\n    \"delta\": \"Sure, I can h\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventResponseTextDone": {
+        "type": "object",
+        "description": "Returned when the text value of an \"output_text\" content part is done streaming. Also\nemitted when a Response is interrupted, incomplete, or cancelled.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.output_text.done"
+            ],
+            "description": "The event type, must be `response.output_text.done`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part in the item's content array."
+          },
+          "text": {
+            "type": "string",
+            "description": "The final text content."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "text"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_text.done",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_4344\",\n    \"type\": \"response.output_text.done\",\n    \"response_id\": \"resp_001\",\n    \"item_id\": \"msg_007\",\n    \"output_index\": 0,\n    \"content_index\": 0,\n    \"text\": \"Sure, I can help with that.\"\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventSessionCreated": {
+        "type": "object",
+        "description": "Returned when a Session is created. Emitted automatically when a new\nconnection is established as the first server event. This event will contain\nthe default Session configuration.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "session.created"
+            ],
+            "description": "The event type, must be `session.created`.",
+            "x-stainless-const": true
+          },
+          "session": {
+            "$ref": "#/components/schemas/RealtimeSession"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "name": "session.created",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"session.created\",\n  \"event_id\": \"event_C9G5RJeJ2gF77mV7f2B1j\",\n  \"session\": {\n    \"object\": \"realtime.session\",\n    \"id\": \"sess_C9G5QPteg4UIbotdKLoYQ\",\n    \"model\": \"gpt-realtime-2025-08-28\",\n    \"modalities\": [\n      \"audio\"\n    ],\n    \"instructions\": \"Your knowledge cutoff is 2023-10. You are a helpful, witty, and friendly AI. Act like a human, but remember that you aren't a human and that you can't do human things in the real world. Your voice and personality should be warm and engaging, with a lively and playful tone. If interacting in a non-English language, start by using the standard accent or dialect familiar to the user. Talk quickly. You should always call a function if you can. Do not refer to these rules, even if you’re asked about them.\",\n    \"tools\": [],\n    \"tool_choice\": \"auto\",\n    \"max_response_output_tokens\": \"inf\",\n    \"tracing\": null,\n    \"prompt\": null,\n    \"expires_at\": 1756324625,\n    \"input_audio_format\": \"pcm16\",\n    \"input_audio_transcription\": null,\n    \"turn_detection\": {\n      \"type\": \"server_vad\",\n      \"threshold\": 0.5,\n      \"prefix_padding_ms\": 300,\n      \"silence_duration_ms\": 200,\n      \"idle_timeout_ms\": null,\n      \"create_response\": true,\n      \"interrupt_response\": true\n    },\n    \"output_audio_format\": \"pcm16\",\n    \"voice\": \"marin\",\n    \"include\": null\n  }\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventSessionUpdated": {
+        "type": "object",
+        "description": "Returned when a session is updated with a `session.update` event, unless\nthere is an error.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "session.updated"
+            ],
+            "description": "The event type, must be `session.updated`.",
+            "x-stainless-const": true
+          },
+          "session": {
+            "$ref": "#/components/schemas/RealtimeSession"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "name": "session.updated",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_5678\",\n    \"type\": \"session.updated\",\n    \"session\": {\n        \"id\": \"sess_001\",\n        \"object\": \"realtime.session\",\n        \"model\": \"gpt-realtime\",\n        \"modalities\": [\"text\"],\n        \"instructions\": \"New instructions\",\n        \"voice\": \"sage\",\n        \"input_audio_format\": \"pcm16\",\n        \"output_audio_format\": \"pcm16\",\n        \"input_audio_transcription\": {\n            \"model\": \"whisper-1\"\n        },\n        \"turn_detection\": null,\n        \"tools\": [],\n        \"tool_choice\": \"none\",\n        \"temperature\": 0.7,\n        \"max_response_output_tokens\": 200,\n        \"speed\": 1.1,\n        \"tracing\": \"auto\"\n    }\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventTranscriptionSessionCreated": {
+        "type": "object",
+        "description": "Returned when a transcription session is created.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "transcription_session.created"
+            ],
+            "description": "The event type, must be `transcription_session.created`.",
+            "x-stainless-const": true
+          },
+          "session": {
+            "$ref": "#/components/schemas/RealtimeTranscriptionSessionCreateResponse"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "name": "transcription_session.created",
+          "group": "realtime",
+          "example": "{\n  \"event_id\": \"event_5566\",\n  \"type\": \"transcription_session.created\",\n  \"session\": {\n    \"id\": \"sess_001\",\n    \"object\": \"realtime.transcription_session\",\n    \"input_audio_format\": \"pcm16\",\n    \"input_audio_transcription\": {\n      \"model\": \"gpt-4o-transcribe\",\n      \"prompt\": \"\",\n      \"language\": \"\"\n    },\n    \"turn_detection\": {\n      \"type\": \"server_vad\",\n      \"threshold\": 0.5,\n      \"prefix_padding_ms\": 300,\n      \"silence_duration_ms\": 500\n    },\n    \"input_audio_noise_reduction\": {\n      \"type\": \"near_field\"\n    },\n    \"include\": []\n  }\n}\n"
+        }
+      },
+      "RealtimeBetaServerEventTranscriptionSessionUpdated": {
+        "type": "object",
+        "description": "Returned when a transcription session is updated with a `transcription_session.update` event, unless \nthere is an error.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "transcription_session.updated"
+            ],
+            "description": "The event type, must be `transcription_session.updated`.",
+            "x-stainless-const": true
+          },
+          "session": {
+            "$ref": "#/components/schemas/RealtimeTranscriptionSessionCreateResponse"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "name": "transcription_session.updated",
+          "group": "realtime",
+          "example": "{\n  \"event_id\": \"event_5678\",\n  \"type\": \"transcription_session.updated\",\n  \"session\": {\n    \"id\": \"sess_001\",\n    \"object\": \"realtime.transcription_session\",\n    \"input_audio_format\": \"pcm16\",\n    \"input_audio_transcription\": {\n      \"model\": \"gpt-4o-transcribe\",\n      \"prompt\": \"\",\n      \"language\": \"\"\n    },\n    \"turn_detection\": {\n      \"type\": \"server_vad\",\n      \"threshold\": 0.5,\n      \"prefix_padding_ms\": 300,\n      \"silence_duration_ms\": 500,\n      \"create_response\": true,\n      // \"interrupt_response\": false  -- this will NOT be returned\n    },\n    \"input_audio_noise_reduction\": {\n      \"type\": \"near_field\"\n    },\n    \"include\": [\n      \"item.input_audio_transcription.avg_logprob\",\n    ],\n  }\n}\n"
+        }
+      },
+      "RealtimeCallCreateRequest": {
+        "title": "Realtime call creation request",
+        "type": "object",
+        "description": "Parameters required to initiate a realtime call and receive the SDP answer\nneeded to complete a WebRTC peer connection. Provide an SDP offer generated\nby your client and optionally configure the session that will answer the call.",
+        "required": [
+          "sdp"
+        ],
+        "properties": {
+          "sdp": {
+            "type": "string",
+            "description": "WebRTC Session Description Protocol (SDP) offer generated by the caller."
+          },
+          "session": {
+            "title": "Session configuration",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/RealtimeSessionCreateRequestGA"
+              }
+            ],
+            "description": "Optional session configuration to apply before the realtime session is\ncreated. Use the same parameters you would send in a [`create client secret`](https://developers.openai.com/api/reference/resources/realtime/subresources/client_secrets/methods/create)\nrequest."
+          }
+        },
+        "additionalProperties": false
+      },
+      "RealtimeCallReferRequest": {
+        "title": "Realtime call refer request",
+        "type": "object",
+        "description": "Parameters required to transfer a SIP call to a new destination using the\nRealtime API.",
+        "required": [
+          "target_uri"
+        ],
+        "properties": {
+          "target_uri": {
+            "type": "string",
+            "description": "URI that should appear in the SIP Refer-To header. Supports values like\n`tel:+14155550123` or `sip:agent@example.com`.",
+            "example": "tel:+14155550123"
+          }
+        },
+        "additionalProperties": false
+      },
+      "RealtimeCallRejectRequest": {
+        "title": "Realtime call reject request",
+        "type": "object",
+        "description": "Parameters used to decline an incoming SIP call handled by the Realtime API.",
+        "properties": {
+          "status_code": {
+            "type": "integer",
+            "description": "SIP response code to send back to the caller. Defaults to `603` (Decline)\nwhen omitted.",
+            "example": 486
+          }
+        },
+        "additionalProperties": false
+      },
+      "RealtimeClientEvent": {
+        "discriminator": {
+          "propertyName": "type"
+        },
+        "description": "A realtime client event.\n",
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/RealtimeClientEventConversationItemCreate"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeClientEventConversationItemDelete"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeClientEventConversationItemRetrieve"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeClientEventConversationItemTruncate"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeClientEventInputAudioBufferAppend"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeClientEventInputAudioBufferClear"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeClientEventOutputAudioBufferClear"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeClientEventInputAudioBufferCommit"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeClientEventResponseCancel"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeClientEventResponseCreate"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeClientEventSessionUpdate"
+          }
+        ]
+      },
+      "RealtimeClientEventConversationItemCreate": {
+        "type": "object",
+        "description": "Add a new Item to the Conversation's context, including messages, function \ncalls, and function call responses. This event can be used both to populate a \n\"history\" of the conversation and to add new items mid-stream, but has the \ncurrent limitation that it cannot populate assistant audio messages.\n\nIf successful, the server will respond with a `conversation.item.created` \nevent, otherwise an `error` event will be sent.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "maxLength": 512,
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.create"
+            ],
+            "description": "The event type, must be `conversation.item.create`.",
+            "x-stainless-const": true
+          },
+          "previous_item_id": {
+            "type": "string",
+            "description": "The ID of the preceding item after which the new item will be inserted. If not set, the new item will be appended to the end of the conversation.\n\nIf set to `root`, the new item will be added to the beginning of the conversation.\n\nIf set to an existing ID, it allows an item to be inserted mid-conversation. If the ID cannot be found, an error will be returned and the item will not be added.\n"
+          },
+          "item": {
+            "$ref": "#/components/schemas/RealtimeConversationItem"
+          }
+        },
+        "required": [
+          "type",
+          "item"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.create",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"conversation.item.create\",\n  \"item\": {\n    \"type\": \"message\",\n    \"role\": \"user\",\n    \"content\": [\n      {\n        \"type\": \"input_text\",\n        \"text\": \"hi\"\n      }\n    ]\n  }\n}\n"
+        }
+      },
+      "RealtimeClientEventConversationItemDelete": {
+        "type": "object",
+        "description": "Send this event when you want to remove any item from the conversation \nhistory. The server will respond with a `conversation.item.deleted` event, \nunless the item does not exist in the conversation history, in which case the \nserver will respond with an error.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "maxLength": 512,
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.delete"
+            ],
+            "description": "The event type, must be `conversation.item.delete`.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item to delete."
+          }
+        },
+        "required": [
+          "type",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.delete",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_901\",\n    \"type\": \"conversation.item.delete\",\n    \"item_id\": \"item_003\"\n}\n"
+        }
+      },
+      "RealtimeClientEventConversationItemRetrieve": {
+        "type": "object",
+        "description": "Send this event when you want to retrieve the server's representation of a specific item in the conversation history. This is useful, for example, to inspect user audio after noise cancellation and VAD.\nThe server will respond with a `conversation.item.retrieved` event, \nunless the item does not exist in the conversation history, in which case the \nserver will respond with an error.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "maxLength": 512,
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.retrieve"
+            ],
+            "description": "The event type, must be `conversation.item.retrieve`.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item to retrieve."
+          }
+        },
+        "required": [
+          "type",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.retrieve",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_901\",\n    \"type\": \"conversation.item.retrieve\",\n    \"item_id\": \"item_003\"\n}\n"
+        }
+      },
+      "RealtimeClientEventConversationItemTruncate": {
+        "type": "object",
+        "description": "Send this event to truncate a previous assistant message’s audio. The server \nwill produce audio faster than realtime, so this event is useful when the user \ninterrupts to truncate audio that has already been sent to the client but not \nyet played. This will synchronize the server's understanding of the audio with \nthe client's playback.\n\nTruncating audio will delete the server-side text transcript to ensure there \nis not text in the context that hasn't been heard by the user.\n\nIf successful, the server will respond with a `conversation.item.truncated` \nevent. \n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "maxLength": 512,
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.truncate"
+            ],
+            "description": "The event type, must be `conversation.item.truncate`.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the assistant message item to truncate. Only assistant message \nitems can be truncated.\n"
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part to truncate. Set this to `0`."
+          },
+          "audio_end_ms": {
+            "type": "integer",
+            "description": "Inclusive duration up to which audio is truncated, in milliseconds. If \nthe audio_end_ms is greater than the actual audio duration, the server \nwill respond with an error.\n"
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "content_index",
+          "audio_end_ms"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.truncate",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_678\",\n    \"type\": \"conversation.item.truncate\",\n    \"item_id\": \"item_002\",\n    \"content_index\": 0,\n    \"audio_end_ms\": 1500\n}\n"
+        }
+      },
+      "RealtimeClientEventInputAudioBufferAppend": {
+        "type": "object",
+        "description": "Send this event to append audio bytes to the input audio buffer. The audio \nbuffer is temporary storage you can write to and later commit. A \"commit\" will create a new\nuser message item in the conversation history from the buffer content and clear the buffer.\nInput audio transcription (if enabled) will be generated when the buffer is committed.\n\nIf VAD is enabled the audio buffer is used to detect speech and the server will decide \nwhen to commit. When Server VAD is disabled, you must commit the audio buffer\nmanually. Input audio noise reduction operates on writes to the audio buffer.\n\nThe client may choose how much audio to place in each event up to a maximum \nof 15 MiB, for example streaming smaller chunks from the client may allow the \nVAD to be more responsive. Unlike most other client events, the server will \nnot send a confirmation response to this event.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "maxLength": 512,
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_audio_buffer.append"
+            ],
+            "description": "The event type, must be `input_audio_buffer.append`.",
+            "x-stainless-const": true
+          },
+          "audio": {
+            "type": "string",
+            "description": "Base64-encoded audio bytes. This must be in the format specified by the \n`input_audio_format` field in the session configuration.\n"
+          }
+        },
+        "required": [
+          "type",
+          "audio"
+        ],
+        "x-oaiMeta": {
+          "name": "input_audio_buffer.append",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_456\",\n    \"type\": \"input_audio_buffer.append\",\n    \"audio\": \"Base64EncodedAudioData\"\n}\n"
+        }
+      },
+      "RealtimeClientEventInputAudioBufferClear": {
+        "type": "object",
+        "description": "Send this event to clear the audio bytes in the buffer. The server will \nrespond with an `input_audio_buffer.cleared` event.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "maxLength": 512,
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_audio_buffer.clear"
+            ],
+            "description": "The event type, must be `input_audio_buffer.clear`.",
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "x-oaiMeta": {
+          "name": "input_audio_buffer.clear",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_012\",\n    \"type\": \"input_audio_buffer.clear\"\n}\n"
+        }
+      },
+      "RealtimeClientEventInputAudioBufferCommit": {
+        "type": "object",
+        "description": "Send this event to commit the user input audio buffer, which will create a  new user message item in the conversation. This event will produce an error  if the input audio buffer is empty. When in Server VAD mode, the client does  not need to send this event, the server will commit the audio buffer  automatically.\n\nCommitting the input audio buffer will trigger input audio transcription  (if enabled in session configuration), but it will not create a response  from the model. The server will respond with an `input_audio_buffer.committed` event.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "maxLength": 512,
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_audio_buffer.commit"
+            ],
+            "description": "The event type, must be `input_audio_buffer.commit`.",
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "x-oaiMeta": {
+          "name": "input_audio_buffer.commit",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_789\",\n    \"type\": \"input_audio_buffer.commit\"\n}\n"
+        }
+      },
+      "RealtimeClientEventOutputAudioBufferClear": {
+        "type": "object",
+        "description": "**WebRTC/SIP Only:** Emit to cut off the current audio response. This will trigger the server to\nstop generating audio and emit a `output_audio_buffer.cleared` event. This\nevent should be preceded by a `response.cancel` client event to stop the\ngeneration of the current response.\n[Learn more](https://developers.openai.com/api/docs/guides/realtime-conversations#client-and-server-events-for-audio-in-webrtc).\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the client event used for error handling."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "output_audio_buffer.clear"
+            ],
+            "description": "The event type, must be `output_audio_buffer.clear`.",
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "x-oaiMeta": {
+          "name": "output_audio_buffer.clear",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"optional_client_event_id\",\n    \"type\": \"output_audio_buffer.clear\"\n}\n"
+        }
+      },
+      "RealtimeClientEventResponseCancel": {
+        "type": "object",
+        "description": "Send this event to cancel an in-progress response. The server will respond \nwith a `response.done` event with a status of `response.status=cancelled`. If \nthere is no response to cancel, the server will respond with an error. It's safe\nto call `response.cancel` even if no response is in progress, an error will be\nreturned the session will remain unaffected.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "maxLength": 512,
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.cancel"
+            ],
+            "description": "The event type, must be `response.cancel`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "A specific response ID to cancel - if not provided, will cancel an \nin-progress response in the default conversation.\n"
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "x-oaiMeta": {
+          "name": "response.cancel",
+          "group": "realtime",
+          "example": "{\n    \"type\": \"response.cancel\",\n    \"response_id\": \"resp_12345\"\n}\n"
+        }
+      },
+      "RealtimeClientEventResponseCreate": {
+        "type": "object",
+        "description": "This event instructs the server to create a Response, which means triggering \nmodel inference. When in Server VAD mode, the server will create Responses \nautomatically.\n\nA Response will include at least one Item, and may have two, in which case \nthe second will be a function call. These Items will be appended to the \nconversation history by default.\n\nThe server will respond with a `response.created` event, events for Items \nand content created, and finally a `response.done` event to indicate the \nResponse is complete.\n\nThe `response.create` event includes inference configuration like \n`instructions` and `tools`. If these are set, they will override the Session's \nconfiguration for this Response only.\n\nResponses can be created out-of-band of the default Conversation, meaning that they can\nhave arbitrary input, and it's possible to disable writing the output to the Conversation.\nOnly one Response can write to the default Conversation at a time, but otherwise multiple\nResponses can be created in parallel. The `metadata` field is a good way to disambiguate\nmultiple simultaneous Responses.\n\nClients can set `conversation` to `none` to create a Response that does not write to the default\nConversation. Arbitrary input can be provided with the `input` field, which is an array accepting\nraw Items and references to existing Items.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "maxLength": 512,
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.create"
+            ],
+            "description": "The event type, must be `response.create`.",
+            "x-stainless-const": true
+          },
+          "response": {
+            "$ref": "#/components/schemas/RealtimeResponseCreateParams"
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "x-oaiMeta": {
+          "name": "response.create",
+          "group": "realtime",
+          "example": "// Trigger a response with the default Conversation and no special parameters\n{\n  \"type\": \"response.create\",\n}\n\n// Trigger an out-of-band response that does not write to the default Conversation\n{\n  \"type\": \"response.create\",\n  \"response\": {\n    \"instructions\": \"Provide a concise answer.\",\n    \"tools\": [], // clear any session tools\n    \"conversation\": \"none\",\n    \"output_modalities\": [\"text\"],\n    \"metadata\": {\n      \"response_purpose\": \"summarization\"\n    },\n    \"input\": [\n      {\n        \"type\": \"item_reference\",\n        \"id\": \"item_12345\"\n      },\n      {\n        \"type\": \"message\",\n        \"role\": \"user\",\n        \"content\": [\n          {\n            \"type\": \"input_text\",\n            \"text\": \"Summarize the above message in one sentence.\"\n          }\n        ]\n      }\n    ]\n  }\n}\n"
+        }
+      },
+      "RealtimeClientEventSessionUpdate": {
+        "type": "object",
+        "description": "Send this event to update the session’s configuration.\nThe client may send this event at any time to update any field\nexcept for `voice` and `model`. `voice` can be updated only if there have been no other audio outputs yet.\n\nWhen the server receives a `session.update`, it will respond\nwith a `session.updated` event showing the full, effective configuration.\nOnly the fields that are present in the `session.update` are updated. To clear a field like\n`instructions`, pass an empty string. To clear a field like `tools`, pass an empty array.\nTo clear a field like `turn_detection`, pass `null`.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "maxLength": 512,
+            "description": "Optional client-generated ID used to identify this event. This is an arbitrary string that a client may assign. It will be passed back if there is an error with the event, but the corresponding `session.updated` event will not include it."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "session.update"
+            ],
+            "description": "The event type, must be `session.update`.",
+            "x-stainless-const": true
+          },
+          "session": {
+            "type": "object",
+            "description": "Update the Realtime session. Choose either a realtime\nsession or a transcription session.\n",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/RealtimeSessionCreateRequestGA"
+              },
+              {
+                "$ref": "#/components/schemas/RealtimeTranscriptionSessionCreateRequestGA"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "name": "session.update",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"session.update\",\n  \"session\": {\n    \"type\": \"realtime\",\n    \"instructions\": \"You are a creative assistant that helps with design tasks.\",\n    \"tools\": [\n      {\n        \"type\": \"function\",\n        \"name\": \"display_color_palette\",\n        \"description\": \"Call this function when a user asks for a color palette.\",\n        \"parameters\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"theme\": {\n              \"type\": \"string\",\n              \"description\": \"Description of the theme for the color scheme.\"\n            },\n            \"colors\": {\n              \"type\": \"array\",\n              \"description\": \"Array of five hex color codes based on the theme.\",\n              \"items\": {\n                \"type\": \"string\",\n                \"description\": \"Hex color code\"\n              }\n            }\n          },\n          \"required\": [\n            \"theme\",\n            \"colors\"\n          ]\n        }\n      }\n    ],\n    \"tool_choice\": \"auto\"\n  }\n}\n"
+        }
+      },
+      "RealtimeClientEventTranscriptionSessionUpdate": {
+        "type": "object",
+        "description": "Send this event to update a transcription session.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "transcription_session.update"
+            ],
+            "description": "The event type, must be `transcription_session.update`.",
+            "x-stainless-const": true
+          },
+          "session": {
+            "$ref": "#/components/schemas/RealtimeTranscriptionSessionCreateRequest"
+          }
+        },
+        "required": [
+          "type",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "name": "transcription_session.update",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"transcription_session.update\",\n  \"session\": {\n    \"input_audio_format\": \"pcm16\",\n    \"input_audio_transcription\": {\n      \"model\": \"gpt-4o-transcribe\",\n      \"prompt\": \"\",\n      \"language\": \"\"\n    },\n    \"turn_detection\": {\n      \"type\": \"server_vad\",\n      \"threshold\": 0.5,\n      \"prefix_padding_ms\": 300,\n      \"silence_duration_ms\": 500,\n      \"create_response\": true,\n    },\n    \"input_audio_noise_reduction\": {\n      \"type\": \"near_field\"\n    },\n    \"include\": [\n      \"item.input_audio_transcription.logprobs\",\n    ]\n  }\n}\n"
+        }
+      },
+      "RealtimeConversationItem": {
+        "description": "A single item within a Realtime conversation.",
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/RealtimeConversationItemMessageSystem"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeConversationItemMessageUser"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeConversationItemMessageAssistant"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeConversationItemFunctionCall"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeConversationItemFunctionCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeMCPApprovalResponse"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeMCPListTools"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeMCPToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeMCPApprovalRequest"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "RealtimeConversationItemFunctionCall": {
+        "type": "object",
+        "title": "Realtime function call item",
+        "description": "A function call item in a Realtime conversation.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the item. This may be provided by the client or generated by the server."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "realtime.item"
+            ],
+            "description": "Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item.",
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "function_call"
+            ],
+            "description": "The type of the item. Always `function_call`.",
+            "x-stainless-const": true
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "completed",
+              "incomplete",
+              "in_progress"
+            ],
+            "description": "The status of the item. Has no effect on the conversation."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The ID of the function call."
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the function being called."
+          },
+          "arguments": {
+            "type": "string",
+            "description": "The arguments of the function call. This is a JSON-encoded string representing the arguments passed to the function, for example `{\"arg1\": \"value1\", \"arg2\": 42}`."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "arguments"
+        ]
+      },
+      "RealtimeConversationItemFunctionCallOutput": {
+        "type": "object",
+        "title": "Realtime function call output item",
+        "description": "A function call output item in a Realtime conversation.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the item. This may be provided by the client or generated by the server."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "realtime.item"
+            ],
+            "description": "Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item.",
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "function_call_output"
+            ],
+            "description": "The type of the item. Always `function_call_output`.",
+            "x-stainless-const": true
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "completed",
+              "incomplete",
+              "in_progress"
+            ],
+            "description": "The status of the item. Has no effect on the conversation."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The ID of the function call this output is for."
+          },
+          "output": {
+            "type": "string",
+            "description": "The output of the function call, this is free text and can contain any information or simply be empty."
+          }
+        },
+        "required": [
+          "type",
+          "call_id",
+          "output"
+        ]
+      },
+      "RealtimeConversationItemMessageAssistant": {
+        "type": "object",
+        "title": "Realtime assistant message item",
+        "description": "An assistant message item in a Realtime conversation.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the item. This may be provided by the client or generated by the server."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "realtime.item"
+            ],
+            "description": "Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item.",
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "message"
+            ],
+            "description": "The type of the item. Always `message`.",
+            "x-stainless-const": true
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "completed",
+              "incomplete",
+              "in_progress"
+            ],
+            "description": "The status of the item. Has no effect on the conversation."
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "assistant"
+            ],
+            "description": "The role of the message sender. Always `assistant`.",
+            "x-stainless-const": true
+          },
+          "content": {
+            "type": "array",
+            "description": "The content of the message.",
+            "items": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "output_text",
+                    "output_audio"
+                  ],
+                  "description": "The content type, `output_text` or `output_audio` depending on the session `output_modalities` configuration."
+                },
+                "text": {
+                  "type": "string",
+                  "description": "The text content."
+                },
+                "audio": {
+                  "type": "string",
+                  "description": "Base64-encoded audio bytes, these will be parsed as the format specified in the session output audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified."
+                },
+                "transcript": {
+                  "type": "string",
+                  "description": "The transcript of the audio content, this will always be present if the output type is `audio`."
+                }
+              }
+            }
+          }
+        },
+        "required": [
+          "type",
+          "role",
+          "content"
+        ]
+      },
+      "RealtimeConversationItemMessageSystem": {
+        "type": "object",
+        "title": "Realtime system message item",
+        "description": "A system message in a Realtime conversation can be used to provide additional context or instructions to the model. This is similar but distinct from the instruction prompt provided at the start of a conversation, as system messages can be added at any point in the conversation. For major changes to the conversation's behavior, use instructions, but for smaller updates (e.g. \"the user is now asking about a different topic\"), use system messages.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the item. This may be provided by the client or generated by the server."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "realtime.item"
+            ],
+            "description": "Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item.",
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "message"
+            ],
+            "description": "The type of the item. Always `message`.",
+            "x-stainless-const": true
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "completed",
+              "incomplete",
+              "in_progress"
+            ],
+            "description": "The status of the item. Has no effect on the conversation."
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "system"
+            ],
+            "description": "The role of the message sender. Always `system`.",
+            "x-stainless-const": true
+          },
+          "content": {
+            "type": "array",
+            "description": "The content of the message.",
+            "items": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "input_text"
+                  ],
+                  "description": "The content type. Always `input_text` for system messages.",
+                  "x-stainless-const": true
+                },
+                "text": {
+                  "type": "string",
+                  "description": "The text content."
+                }
+              }
+            }
+          }
+        },
+        "required": [
+          "type",
+          "role",
+          "content"
+        ]
+      },
+      "RealtimeConversationItemMessageUser": {
+        "type": "object",
+        "title": "Realtime user message item",
+        "description": "A user message item in a Realtime conversation.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the item. This may be provided by the client or generated by the server."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "realtime.item"
+            ],
+            "description": "Identifier for the API object being returned - always `realtime.item`. Optional when creating a new item.",
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "message"
+            ],
+            "description": "The type of the item. Always `message`.",
+            "x-stainless-const": true
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "completed",
+              "incomplete",
+              "in_progress"
+            ],
+            "description": "The status of the item. Has no effect on the conversation."
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "user"
+            ],
+            "description": "The role of the message sender. Always `user`.",
+            "x-stainless-const": true
+          },
+          "content": {
+            "type": "array",
+            "description": "The content of the message.",
+            "items": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "input_text",
+                    "input_audio",
+                    "input_image"
+                  ],
+                  "description": "The content type (`input_text`, `input_audio`, or `input_image`)."
+                },
+                "text": {
+                  "type": "string",
+                  "description": "The text content (for `input_text`)."
+                },
+                "audio": {
+                  "type": "string",
+                  "description": "Base64-encoded audio bytes (for `input_audio`), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified."
+                },
+                "image_url": {
+                  "type": "string",
+                  "format": "uri",
+                  "description": "Base64-encoded image bytes (for `input_image`) as a data URI. For example `data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...`. Supported formats are PNG and JPEG."
+                },
+                "detail": {
+                  "type": "string",
+                  "description": "The detail level of the image (for `input_image`). `auto` will default to `high`.",
+                  "default": "auto",
+                  "enum": [
+                    "auto",
+                    "low",
+                    "high"
+                  ]
+                },
+                "transcript": {
+                  "type": "string",
+                  "description": "Transcript of the audio (for `input_audio`). This is not sent to the model, but will be attached to the message item for reference."
+                }
+              }
+            }
+          }
+        },
+        "required": [
+          "type",
+          "role",
+          "content"
+        ]
+      },
+      "RealtimeConversationItemWithReference": {
+        "type": "object",
+        "description": "The item to add to the conversation.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "For an item of type (`message` | `function_call` | `function_call_output`)\nthis field allows the client to assign the unique ID of the item. It is\nnot required because the server will generate one if not provided.\n\nFor an item of type `item_reference`, this field is required and is a\nreference to any item that has previously existed in the conversation.\n"
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "message",
+              "function_call",
+              "function_call_output"
+            ],
+            "description": "The type of the item (`message`, `function_call`, `function_call_output`, `item_reference`).\n"
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "realtime.item"
+            ],
+            "description": "Identifier for the API object being returned - always `realtime.item`.\n",
+            "x-stainless-const": true
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "completed",
+              "incomplete",
+              "in_progress"
+            ],
+            "description": "The status of the item (`completed`, `incomplete`, `in_progress`). These have no effect \non the conversation, but are accepted for consistency with the \n`conversation.item.created` event.\n"
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "user",
+              "assistant",
+              "system"
+            ],
+            "description": "The role of the message sender (`user`, `assistant`, `system`), only \napplicable for `message` items.\n"
+          },
+          "content": {
+            "type": "array",
+            "description": "The content of the message, applicable for `message` items. \n- Message items of role `system` support only `input_text` content\n- Message items of role `user` support `input_text` and `input_audio` \n  content\n- Message items of role `assistant` support `text` content.\n",
+            "items": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "input_audio",
+                    "input_text",
+                    "item_reference",
+                    "text"
+                  ],
+                  "description": "The content type (`input_text`, `input_audio`, `item_reference`, `text`).\n"
+                },
+                "text": {
+                  "type": "string",
+                  "description": "The text content, used for `input_text` and `text` content types.\n"
+                },
+                "id": {
+                  "type": "string",
+                  "description": "ID of a previous conversation item to reference (for `item_reference`\ncontent types in `response.create` events). These can reference both\nclient and server created items.\n"
+                },
+                "audio": {
+                  "type": "string",
+                  "description": "Base64-encoded audio bytes, used for `input_audio` content type.\n"
+                },
+                "transcript": {
+                  "type": "string",
+                  "description": "The transcript of the audio, used for `input_audio` content type.\n"
+                }
+              }
+            }
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The ID of the function call (for `function_call` and \n`function_call_output` items). If passed on a `function_call_output` \nitem, the server will check that a `function_call` item with the same \nID exists in the conversation history.\n"
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the function being called (for `function_call` items).\n"
+          },
+          "arguments": {
+            "type": "string",
+            "description": "The arguments of the function call (for `function_call` items).\n"
+          },
+          "output": {
+            "type": "string",
+            "description": "The output of the function call (for `function_call_output` items).\n"
+          }
+        }
+      },
+      "RealtimeCreateClientSecretRequest": {
+        "type": "object",
+        "title": "Realtime client secret creation request",
+        "description": "Create a session and client secret for the Realtime API. The request can specify\neither a realtime or a transcription session configuration.\n[Learn more about the Realtime API](https://developers.openai.com/api/docs/guides/realtime).\n",
+        "properties": {
+          "expires_after": {
+            "type": "object",
+            "title": "Client secret expiration",
+            "description": "Configuration for the client secret expiration. Expiration refers to the time after which\na client secret will no longer be valid for creating sessions. The session itself may\ncontinue after that time once started. A secret can be used to create multiple sessions\nuntil it expires.\n",
+            "properties": {
+              "anchor": {
+                "type": "string",
+                "enum": [
+                  "created_at"
+                ],
+                "description": "The anchor point for the client secret expiration, meaning that `seconds` will be added to the `created_at` time of the client secret to produce an expiration timestamp. Only `created_at` is currently supported.\n",
+                "default": "created_at",
+                "x-stainless-const": true
+              },
+              "seconds": {
+                "type": "integer",
+                "format": "int64",
+                "description": "The number of seconds from the anchor point to the expiration. Select a value between `10` and `7200` (2 hours). This default to 600 seconds (10 minutes) if not specified.\n",
+                "minimum": 10,
+                "maximum": 7200,
+                "default": 600
+              }
+            }
+          },
+          "session": {
+            "title": "Session configuration",
+            "description": "Session configuration to use for the client secret. Choose either a realtime\nsession or a transcription session.\n",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/RealtimeSessionCreateRequestGA"
+              },
+              {
+                "$ref": "#/components/schemas/RealtimeTranscriptionSessionCreateRequestGA"
+              }
+            ]
+          }
+        }
+      },
+      "RealtimeCreateClientSecretResponse": {
+        "type": "object",
+        "title": "Realtime session and client secret",
+        "description": "Response from creating a session and client secret for the Realtime API.\n",
+        "properties": {
+          "value": {
+            "type": "string",
+            "description": "The generated client secret value."
+          },
+          "expires_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Expiration timestamp for the client secret, in seconds since epoch."
+          },
+          "session": {
+            "title": "Session configuration",
+            "description": "The session configuration for either a realtime or transcription session.\n",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/RealtimeSessionCreateResponseGA"
+              },
+              {
+                "$ref": "#/components/schemas/RealtimeTranscriptionSessionCreateResponseGA"
+              }
+            ],
+            "discriminator": {
+              "propertyName": "type"
+            }
+          }
+        },
+        "required": [
+          "value",
+          "expires_at",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "name": "Session response object",
+          "group": "realtime",
+          "example": "{\n  \"value\": \"ek_68af296e8e408191a1120ab6383263c2\",\n  \"expires_at\": 1756310470,\n  \"session\": {\n    \"type\": \"realtime\",\n    \"object\": \"realtime.session\",\n    \"id\": \"sess_C9CiUVUzUzYIssh3ELY1d\",\n    \"model\": \"gpt-realtime-2025-08-25\",\n    \"output_modalities\": [\n      \"audio\"\n    ],\n    \"instructions\": \"You are a friendly assistant.\",\n    \"tools\": [],\n    \"tool_choice\": \"auto\",\n    \"max_output_tokens\": \"inf\",\n    \"tracing\": null,\n    \"truncation\": \"auto\",\n    \"prompt\": null,\n    \"expires_at\": 0,\n    \"audio\": {\n      \"input\": {\n        \"format\": {\n          \"type\": \"audio/pcm\",\n          \"rate\": 24000\n        },\n        \"transcription\": null,\n        \"noise_reduction\": null,\n        \"turn_detection\": {\n          \"type\": \"server_vad\",\n          \"threshold\": 0.5,\n          \"prefix_padding_ms\": 300,\n          \"silence_duration_ms\": 200,\n          \"idle_timeout_ms\": null,\n          \"create_response\": true,\n          \"interrupt_response\": true\n        }\n      },\n      \"output\": {\n        \"format\": {\n          \"type\": \"audio/pcm\",\n          \"rate\": 24000\n        },\n        \"voice\": \"alloy\",\n        \"speed\": 1.0\n      }\n    },\n    \"include\": null\n  }\n}\n"
+        }
+      },
+      "RealtimeFunctionTool": {
+        "type": "object",
+        "title": "Function tool",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "function"
+            ],
+            "description": "The type of the tool, i.e. `function`.",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the function."
+          },
+          "description": {
+            "type": "string",
+            "description": "The description of the function, including guidance on when and how\nto call it, and guidance about what to tell the user when calling\n(if anything).\n"
+          },
+          "parameters": {
+            "type": "object",
+            "description": "Parameters of the function in JSON Schema."
+          }
+        }
+      },
+      "RealtimeMCPApprovalRequest": {
+        "type": "object",
+        "title": "Realtime MCP approval request",
+        "description": "A Realtime item requesting human approval of a tool invocation.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_approval_request"
+            ],
+            "description": "The type of the item. Always `mcp_approval_request`.",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the approval request."
+          },
+          "server_label": {
+            "type": "string",
+            "description": "The label of the MCP server making the request."
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the tool to run."
+          },
+          "arguments": {
+            "type": "string",
+            "description": "A JSON string of arguments for the tool."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "server_label",
+          "name",
+          "arguments"
+        ]
+      },
+      "RealtimeMCPApprovalResponse": {
+        "type": "object",
+        "title": "Realtime MCP approval response",
+        "description": "A Realtime item responding to an MCP approval request.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_approval_response"
+            ],
+            "description": "The type of the item. Always `mcp_approval_response`.",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the approval response."
+          },
+          "approval_request_id": {
+            "type": "string",
+            "description": "The ID of the approval request being answered."
+          },
+          "approve": {
+            "type": "boolean",
+            "description": "Whether the request was approved."
+          },
+          "reason": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Optional reason for the decision."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "approval_request_id",
+          "approve"
+        ]
+      },
+      "RealtimeMCPHTTPError": {
+        "type": "object",
+        "title": "Realtime MCP HTTP error",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "http_error"
+            ],
+            "x-stainless-const": true
+          },
+          "code": {
+            "type": "integer"
+          },
+          "message": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "type",
+          "code",
+          "message"
+        ]
+      },
+      "RealtimeMCPListTools": {
+        "type": "object",
+        "title": "Realtime MCP list tools",
+        "description": "A Realtime item listing tools available on an MCP server.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_list_tools"
+            ],
+            "description": "The type of the item. Always `mcp_list_tools`.",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the list."
+          },
+          "server_label": {
+            "type": "string",
+            "description": "The label of the MCP server."
+          },
+          "tools": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/MCPListToolsTool"
+            },
+            "description": "The tools available on the server."
+          }
+        },
+        "required": [
+          "type",
+          "server_label",
+          "tools"
+        ]
+      },
+      "RealtimeMCPProtocolError": {
+        "type": "object",
+        "title": "Realtime MCP protocol error",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "protocol_error"
+            ],
+            "x-stainless-const": true
+          },
+          "code": {
+            "type": "integer"
+          },
+          "message": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "type",
+          "code",
+          "message"
+        ]
+      },
+      "RealtimeMCPToolCall": {
+        "type": "object",
+        "title": "Realtime MCP tool call",
+        "description": "A Realtime item representing an invocation of a tool on an MCP server.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_call"
+            ],
+            "description": "The type of the item. Always `mcp_call`.",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the tool call."
+          },
+          "server_label": {
+            "type": "string",
+            "description": "The label of the MCP server running the tool."
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the tool that was run."
+          },
+          "arguments": {
+            "type": "string",
+            "description": "A JSON string of the arguments passed to the tool."
+          },
+          "approval_request_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of an associated approval request, if any."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "output": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The output from the tool call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "error": {
+            "anyOf": [
+              {
+                "description": "The error from the tool call, if any.",
+                "oneOf": [
+                  {
+                    "$ref": "#/components/schemas/RealtimeMCPProtocolError"
+                  },
+                  {
+                    "$ref": "#/components/schemas/RealtimeMCPToolExecutionError"
+                  },
+                  {
+                    "$ref": "#/components/schemas/RealtimeMCPHTTPError"
+                  }
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "server_label",
+          "name",
+          "arguments"
+        ]
+      },
+      "RealtimeMCPToolExecutionError": {
+        "type": "object",
+        "title": "Realtime MCP tool execution error",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "tool_execution_error"
+            ],
+            "x-stainless-const": true
+          },
+          "message": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "type",
+          "message"
+        ]
+      },
+      "RealtimeReasoning": {
+        "type": "object",
+        "title": "Realtime reasoning configuration",
+        "description": "Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`.\n",
+        "properties": {
+          "effort": {
+            "$ref": "#/components/schemas/RealtimeReasoningEffort"
+          }
+        }
+      },
+      "RealtimeReasoningEffort": {
+        "type": "string",
+        "description": "Constrains effort on reasoning for reasoning-capable Realtime models such as\n`gpt-realtime-2`.\n",
+        "enum": [
+          "minimal",
+          "low",
+          "medium",
+          "high",
+          "xhigh"
+        ],
+        "default": "low"
+      },
+      "RealtimeResponse": {
+        "type": "object",
+        "description": "The response resource.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the response, will look like `resp_1234`."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "realtime.response"
+            ],
+            "description": "The object type, must be `realtime.response`.",
+            "x-stainless-const": true
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "completed",
+              "cancelled",
+              "failed",
+              "incomplete",
+              "in_progress"
+            ],
+            "description": "The final status of the response (`completed`, `cancelled`, `failed`, or \n`incomplete`, `in_progress`).\n"
+          },
+          "status_details": {
+            "type": "object",
+            "description": "Additional details about the status.",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "completed",
+                  "cancelled",
+                  "failed",
+                  "incomplete"
+                ],
+                "description": "The type of error that caused the response to fail, corresponding \nwith the `status` field (`completed`, `cancelled`, `incomplete`, \n`failed`).\n"
+              },
+              "reason": {
+                "type": "string",
+                "enum": [
+                  "turn_detected",
+                  "client_cancelled",
+                  "max_output_tokens",
+                  "content_filter"
+                ],
+                "description": "The reason the Response did not complete. For a `cancelled` Response,  one of `turn_detected` (the server VAD detected a new start of speech)  or `client_cancelled` (the client sent a cancel event). For an  `incomplete` Response, one of `max_output_tokens` or `content_filter`  (the server-side safety filter activated and cut off the response).\n"
+              },
+              "error": {
+                "type": "object",
+                "description": "A description of the error that caused the response to fail, \npopulated when the `status` is `failed`.\n",
+                "properties": {
+                  "type": {
+                    "type": "string",
+                    "description": "The type of error."
+                  },
+                  "code": {
+                    "type": "string",
+                    "description": "Error code, if any."
+                  }
+                }
+              }
+            }
+          },
+          "output": {
+            "type": "array",
+            "description": "The list of output items generated by the response.",
+            "items": {
+              "$ref": "#/components/schemas/RealtimeConversationItem"
+            }
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          },
+          "audio": {
+            "type": "object",
+            "description": "Configuration for audio output.",
+            "properties": {
+              "output": {
+                "type": "object",
+                "properties": {
+                  "format": {
+                    "$ref": "#/components/schemas/RealtimeAudioFormats",
+                    "description": "The format of the output audio."
+                  },
+                  "voice": {
+                    "$ref": "#/components/schemas/VoiceIdsShared",
+                    "default": "alloy",
+                    "description": "The voice the model uses to respond. Voice cannot be changed during the\nsession once the model has responded with audio at least once. Current\nvoice options are `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`,\n`shimmer`, `verse`, `marin`, and `cedar`. We recommend `marin` and `cedar` for\nbest quality.\n"
+                  }
+                }
+              }
+            }
+          },
+          "usage": {
+            "type": "object",
+            "description": "Usage statistics for the Response, this will correspond to billing. A \nRealtime API session will maintain a conversation context and append new \nItems to the Conversation, thus output from previous turns (text and \naudio tokens) will become the input for later turns.\n",
+            "properties": {
+              "total_tokens": {
+                "type": "integer",
+                "description": "The total number of tokens in the Response including input and output \ntext and audio tokens.\n"
+              },
+              "input_tokens": {
+                "type": "integer",
+                "description": "The number of input tokens used in the Response, including text and \naudio tokens.\n"
+              },
+              "output_tokens": {
+                "type": "integer",
+                "description": "The number of output tokens sent in the Response, including text and \naudio tokens.\n"
+              },
+              "input_token_details": {
+                "type": "object",
+                "description": "Details about the input tokens used in the Response. Cached tokens are tokens from previous turns in the conversation that are included as context for the current response. Cached tokens here are counted as a subset of input tokens, meaning input tokens will include cached and uncached tokens.",
+                "properties": {
+                  "cached_tokens": {
+                    "type": "integer",
+                    "description": "The number of cached tokens used as input for the Response."
+                  },
+                  "text_tokens": {
+                    "type": "integer",
+                    "description": "The number of text tokens used as input for the Response."
+                  },
+                  "image_tokens": {
+                    "type": "integer",
+                    "description": "The number of image tokens used as input for the Response."
+                  },
+                  "audio_tokens": {
+                    "type": "integer",
+                    "description": "The number of audio tokens used as input for the Response."
+                  },
+                  "cached_tokens_details": {
+                    "type": "object",
+                    "description": "Details about the cached tokens used as input for the Response.",
+                    "properties": {
+                      "text_tokens": {
+                        "type": "integer",
+                        "description": "The number of cached text tokens used as input for the Response."
+                      },
+                      "image_tokens": {
+                        "type": "integer",
+                        "description": "The number of cached image tokens used as input for the Response."
+                      },
+                      "audio_tokens": {
+                        "type": "integer",
+                        "description": "The number of cached audio tokens used as input for the Response."
+                      }
+                    }
+                  }
+                }
+              },
+              "output_token_details": {
+                "type": "object",
+                "description": "Details about the output tokens used in the Response.",
+                "properties": {
+                  "text_tokens": {
+                    "type": "integer",
+                    "description": "The number of text tokens used in the Response."
+                  },
+                  "audio_tokens": {
+                    "type": "integer",
+                    "description": "The number of audio tokens used in the Response."
+                  }
+                }
+              }
+            }
+          },
+          "conversation_id": {
+            "description": "Which conversation the response is added to, determined by the `conversation`\nfield in the `response.create` event. If `auto`, the response will be added to\nthe default conversation and the value of `conversation_id` will be an id like\n`conv_1234`. If `none`, the response will not be added to any conversation and\nthe value of `conversation_id` will be `null`. If responses are being triggered\nautomatically by VAD the response will be added to the default conversation\n",
+            "type": "string"
+          },
+          "output_modalities": {
+            "type": "array",
+            "description": "The set of modalities the model used to respond, currently the only possible values are\n`[\\\"audio\\\"]`, `[\\\"text\\\"]`. Audio output always include a text transcript. Setting the\noutput to mode `text` will disable audio output from the model.\n",
+            "items": {
+              "type": "string",
+              "enum": [
+                "text",
+                "audio"
+              ]
+            }
+          },
+          "max_output_tokens": {
+            "oneOf": [
+              {
+                "type": "integer"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "inf"
+                ],
+                "x-stainless-const": true
+              }
+            ],
+            "description": "Maximum number of output tokens for a single assistant response,\ninclusive of tool calls, that was used in this response.\n"
+          }
+        }
+      },
+      "RealtimeResponseCreateParams": {
+        "type": "object",
+        "description": "Create a new Realtime response with these parameters",
+        "properties": {
+          "output_modalities": {
+            "type": "array",
+            "description": "The set of modalities the model used to respond, currently the only possible values are\n`[\\\"audio\\\"]`, `[\\\"text\\\"]`. Audio output always include a text transcript. Setting the\noutput to mode `text` will disable audio output from the model.\n",
+            "items": {
+              "type": "string",
+              "enum": [
+                "text",
+                "audio"
+              ]
+            }
+          },
+          "instructions": {
+            "type": "string",
+            "description": "The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. \"be extremely succinct\", \"act friendly\", \"here are examples of good responses\") and on audio behavior (e.g. \"talk quickly\", \"inject emotion into your voice\", \"laugh frequently\"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior.\nNote that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session.\n"
+          },
+          "audio": {
+            "type": "object",
+            "description": "Configuration for audio input and output.",
+            "properties": {
+              "output": {
+                "type": "object",
+                "properties": {
+                  "format": {
+                    "$ref": "#/components/schemas/RealtimeAudioFormats",
+                    "description": "The format of the output audio."
+                  },
+                  "voice": {
+                    "$ref": "#/components/schemas/VoiceIdsOrCustomVoice",
+                    "default": "alloy",
+                    "description": "The voice the model uses to respond. Supported built-in voices are\n`alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, `verse`,\n`marin`, and `cedar`. You may also provide a custom voice object with\nan `id`, for example `{ \"id\": \"voice_1234\" }`. Voice cannot be changed\nduring the session once the model has responded with audio at least once.\nWe recommend `marin` and `cedar` for best quality.\n"
+                  }
+                }
+              }
+            }
+          },
+          "tools": {
+            "type": "array",
+            "description": "Tools available to the model.",
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/RealtimeFunctionTool"
+                },
+                {
+                  "$ref": "#/components/schemas/MCPTool"
+                }
+              ]
+            }
+          },
+          "tool_choice": {
+            "description": "How the model chooses tools. Provide one of the string modes or force a specific\nfunction/MCP tool.\n",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/ToolChoiceOptions"
+              },
+              {
+                "$ref": "#/components/schemas/ToolChoiceFunction"
+              },
+              {
+                "$ref": "#/components/schemas/ToolChoiceMCP"
+              }
+            ],
+            "default": "auto"
+          },
+          "parallel_tool_calls": {
+            "type": "boolean",
+            "description": "Whether the model may call multiple tools in parallel. Only supported by\nreasoning Realtime models such as `gpt-realtime-2`.\n"
+          },
+          "reasoning": {
+            "$ref": "#/components/schemas/RealtimeReasoning"
+          },
+          "max_output_tokens": {
+            "oneOf": [
+              {
+                "type": "integer"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "inf"
+                ],
+                "x-stainless-const": true
+              }
+            ],
+            "description": "Maximum number of output tokens for a single assistant response,\ninclusive of tool calls. Provide an integer between 1 and 4096 to\nlimit output tokens, or `inf` for the maximum available tokens for a\ngiven model. Defaults to `inf`.\n"
+          },
+          "conversation": {
+            "description": "Controls which conversation the response is added to. Currently supports\n`auto` and `none`, with `auto` as the default value. The `auto` value\nmeans that the contents of the response will be added to the default\nconversation. Set this to `none` to create an out-of-band response which\nwill not add items to default conversation.\n",
+            "oneOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "default": "auto",
+                "enum": [
+                  "auto",
+                  "none"
+                ]
+              }
+            ]
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          },
+          "prompt": {
+            "$ref": "#/components/schemas/Prompt"
+          },
+          "input": {
+            "type": "array",
+            "description": "Input items to include in the prompt for the model. Using this field\ncreates a new context for this Response instead of using the default\nconversation. An empty array `[]` will clear the context for this Response.\nNote that this can include references to items that previously appeared in the session\nusing their id.\n",
+            "items": {
+              "$ref": "#/components/schemas/RealtimeConversationItem"
+            }
+          }
+        }
+      },
+      "RealtimeServerEvent": {
+        "discriminator": {
+          "propertyName": "type"
+        },
+        "description": "A realtime server event.\n",
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventConversationCreated"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventConversationItemCreated"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventConversationItemDeleted"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventConversationItemInputAudioTranscriptionCompleted"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventConversationItemInputAudioTranscriptionDelta"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventConversationItemInputAudioTranscriptionFailed"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventConversationItemRetrieved"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventConversationItemTruncated"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventError"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventInputAudioBufferCleared"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventInputAudioBufferCommitted"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventInputAudioBufferDtmfEventReceived"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventInputAudioBufferSpeechStarted"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventInputAudioBufferSpeechStopped"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventRateLimitsUpdated"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventResponseAudioDelta"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventResponseAudioDone"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventResponseAudioTranscriptDelta"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventResponseAudioTranscriptDone"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventResponseContentPartAdded"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventResponseContentPartDone"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventResponseCreated"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventResponseDone"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventResponseFunctionCallArgumentsDelta"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventResponseFunctionCallArgumentsDone"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventResponseOutputItemAdded"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventResponseOutputItemDone"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventResponseTextDelta"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventResponseTextDone"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventSessionCreated"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventSessionUpdated"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventOutputAudioBufferStarted"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventOutputAudioBufferStopped"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventOutputAudioBufferCleared"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventConversationItemAdded"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventConversationItemDone"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventInputAudioBufferTimeoutTriggered"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventConversationItemInputAudioTranscriptionSegment"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventMCPListToolsInProgress"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventMCPListToolsCompleted"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventMCPListToolsFailed"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventResponseMCPCallArgumentsDelta"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventResponseMCPCallArgumentsDone"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventResponseMCPCallInProgress"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventResponseMCPCallCompleted"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventResponseMCPCallFailed"
+          }
+        ]
+      },
+      "RealtimeServerEventConversationCreated": {
+        "type": "object",
+        "description": "Returned when a conversation is created. Emitted right after session creation.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.created"
+            ],
+            "description": "The event type, must be `conversation.created`.",
+            "x-stainless-const": true
+          },
+          "conversation": {
+            "type": "object",
+            "description": "The conversation resource.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the conversation."
+              },
+              "object": {
+                "type": "string",
+                "description": "The object type, must be `realtime.conversation`."
+              }
+            }
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "conversation"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.created",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_9101\",\n    \"type\": \"conversation.created\",\n    \"conversation\": {\n        \"id\": \"conv_001\",\n        \"object\": \"realtime.conversation\"\n    }\n}\n"
+        }
+      },
+      "RealtimeServerEventConversationItemAdded": {
+        "type": "object",
+        "description": "Sent by the server when an Item is added to the default Conversation. This can happen in several cases:\n- When the client sends a `conversation.item.create` event.\n- When the input audio buffer is committed. In this case the item will be a user message containing the audio from the buffer.\n- When the model is generating a Response. In this case the `conversation.item.added` event will be sent when the model starts generating a specific Item, and thus it will not yet have any content (and `status` will be `in_progress`).\n\nThe event will include the full content of the Item (except when model is generating a Response) except for audio data, which can be retrieved separately with a `conversation.item.retrieve` event if necessary.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.added"
+            ],
+            "description": "The event type, must be `conversation.item.added`.",
+            "x-stainless-const": true
+          },
+          "previous_item_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the item that precedes this one, if any. This is used to\nmaintain ordering when items are inserted.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "item": {
+            "$ref": "#/components/schemas/RealtimeConversationItem"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.added",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"conversation.item.added\",\n  \"event_id\": \"event_C9G8pjSJCfRNEhMEnYAVy\",\n  \"previous_item_id\": null,\n  \"item\": {\n    \"id\": \"item_C9G8pGVKYnaZu8PH5YQ9O\",\n    \"type\": \"message\",\n    \"status\": \"completed\",\n    \"role\": \"user\",\n    \"content\": [\n      {\n        \"type\": \"input_text\",\n        \"text\": \"hi\"\n      }\n    ]\n  }\n}\n"
+        }
+      },
+      "RealtimeServerEventConversationItemCreated": {
+        "type": "object",
+        "description": "Returned when a conversation item is created. There are several scenarios that produce this event:\n  - The server is generating a Response, which if successful will produce\n    either one or two Items, which will be of type `message`\n    (role `assistant`) or type `function_call`.\n  - The input audio buffer has been committed, either by the client or the\n    server (in `server_vad` mode). The server will take the content of the\n    input audio buffer and add it to a new user message Item.\n  - The client has sent a `conversation.item.create` event to add a new Item\n    to the Conversation.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.created"
+            ],
+            "description": "The event type, must be `conversation.item.created`.",
+            "x-stainless-const": true
+          },
+          "previous_item_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the preceding item in the Conversation context, allows the\nclient to understand the order of the conversation. Can be `null` if the\nitem has no predecessor.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "item": {
+            "$ref": "#/components/schemas/RealtimeConversationItem"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.created",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_1920\",\n    \"type\": \"conversation.item.created\",\n    \"previous_item_id\": \"msg_002\",\n    \"item\": {\n        \"id\": \"msg_003\",\n        \"object\": \"realtime.item\",\n        \"type\": \"message\",\n        \"status\": \"completed\",\n        \"role\": \"user\",\n        \"content\": []\n    }\n}\n"
+        }
+      },
+      "RealtimeServerEventConversationItemDeleted": {
+        "type": "object",
+        "description": "Returned when an item in the conversation is deleted by the client with a \n`conversation.item.delete` event. This event is used to synchronize the \nserver's understanding of the conversation history with the client's view.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.deleted"
+            ],
+            "description": "The event type, must be `conversation.item.deleted`.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item that was deleted."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.deleted",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_2728\",\n    \"type\": \"conversation.item.deleted\",\n    \"item_id\": \"msg_005\"\n}\n"
+        }
+      },
+      "RealtimeServerEventConversationItemDone": {
+        "type": "object",
+        "description": "Returned when a conversation item is finalized.\n\nThe event will include the full content of the Item except for audio data, which can be retrieved separately with a `conversation.item.retrieve` event if needed.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.done"
+            ],
+            "description": "The event type, must be `conversation.item.done`.",
+            "x-stainless-const": true
+          },
+          "previous_item_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the item that precedes this one, if any. This is used to\nmaintain ordering when items are inserted.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "item": {
+            "$ref": "#/components/schemas/RealtimeConversationItem"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.done",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"conversation.item.done\",\n  \"event_id\": \"event_CCXLgMZPo3qioWCeQa4WH\",\n  \"previous_item_id\": \"item_CCXLecNJVIVR2HUy3ABLj\",\n  \"item\": {\n    \"id\": \"item_CCXLfxmM5sXVJVz4mCa2S\",\n    \"type\": \"message\",\n    \"status\": \"completed\",\n    \"role\": \"assistant\",\n    \"content\": [\n      {\n        \"type\": \"output_audio\",\n        \"transcript\": \"Oh, I can hear you loud and clear! Sounds like we're connected just fine. What can I help you with today?\"\n      }\n    ]\n  }\n}\n"
+        }
+      },
+      "RealtimeServerEventConversationItemInputAudioTranscriptionCompleted": {
+        "type": "object",
+        "description": "This event is the output of audio transcription for user audio written to the\nuser audio buffer. Transcription begins when the input audio buffer is\ncommitted by the client or server (when VAD is enabled). Transcription runs\nasynchronously with Response creation, so this event may come before or after\nthe Response events.\n\nRealtime API models accept audio natively, and thus input transcription is a\nseparate process run on a separate ASR (Automatic Speech Recognition) model.\nThe transcript may diverge somewhat from the model's interpretation, and\nshould be treated as a rough guide.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.input_audio_transcription.completed"
+            ],
+            "description": "The event type, must be\n`conversation.item.input_audio_transcription.completed`.\n",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item containing the audio that is being transcribed."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part containing the audio."
+          },
+          "transcript": {
+            "type": "string",
+            "description": "The transcribed text."
+          },
+          "languages": {
+            "type": "array",
+            "description": "The languages detected in the audio. Returned by `gpt-transcribe`. An empty array indicates that no language could be reliably detected.\n",
+            "items": {
+              "$ref": "#/components/schemas/TranscriptionLanguage"
+            }
+          },
+          "logprobs": {
+            "anyOf": [
+              {
+                "type": "array",
+                "description": "The log probabilities of the transcription.",
+                "items": {
+                  "$ref": "#/components/schemas/LogProbProperties"
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "usage": {
+            "type": "object",
+            "description": "Usage statistics for the transcription, this is billed according to the ASR model's pricing rather than the realtime model's pricing.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/TranscriptTextUsageTokens",
+                "title": "Token Usage"
+              },
+              {
+                "$ref": "#/components/schemas/TranscriptTextUsageDuration",
+                "title": "Duration Usage"
+              }
+            ]
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item_id",
+          "content_index",
+          "transcript",
+          "usage"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.input_audio_transcription.completed",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"conversation.item.input_audio_transcription.completed\",\n  \"event_id\": \"event_CCXGRvtUVrax5SJAnNOWZ\",\n  \"item_id\": \"item_CCXGQ4e1ht4cOraEYcuR2\",\n  \"content_index\": 0,\n  \"transcript\": \"Hey, can you hear me?\",\n  \"usage\": {\n    \"type\": \"tokens\",\n    \"total_tokens\": 22,\n    \"input_tokens\": 13,\n    \"input_token_details\": {\n      \"text_tokens\": 0,\n      \"audio_tokens\": 13\n    },\n    \"output_tokens\": 9\n  }\n}\n"
+        }
+      },
+      "RealtimeServerEventConversationItemInputAudioTranscriptionDelta": {
+        "type": "object",
+        "description": "Returned when the text value of an input audio transcription content part is updated with incremental transcription results.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.input_audio_transcription.delta"
+            ],
+            "description": "The event type, must be `conversation.item.input_audio_transcription.delta`.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item containing the audio that is being transcribed."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part in the item's content array."
+          },
+          "delta": {
+            "type": "string",
+            "description": "The text delta."
+          },
+          "logprobs": {
+            "anyOf": [
+              {
+                "type": "array",
+                "description": "The log probabilities of the transcription. These can be enabled by configurating the session with `\"include\": [\"item.input_audio_transcription.logprobs\"]`. Each entry in the array corresponds a log probability of which token would be selected for this chunk of transcription. This can help to identify if it was possible there were multiple valid options for a given chunk of transcription.",
+                "items": {
+                  "$ref": "#/components/schemas/LogProbProperties"
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.input_audio_transcription.delta",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"conversation.item.input_audio_transcription.delta\",\n  \"event_id\": \"event_CCXGRxsAimPAs8kS2Wc7Z\",\n  \"item_id\": \"item_CCXGQ4e1ht4cOraEYcuR2\",\n  \"content_index\": 0,\n  \"delta\": \"Hey\",\n  \"obfuscation\": \"aLxx0jTEciOGe\"\n}\n"
+        }
+      },
+      "RealtimeServerEventConversationItemInputAudioTranscriptionFailed": {
+        "type": "object",
+        "description": "Returned when input audio transcription is configured, and a transcription \nrequest for a user message failed. These events are separate from other \n`error` events so that the client can identify the related Item.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.input_audio_transcription.failed"
+            ],
+            "description": "The event type, must be\n`conversation.item.input_audio_transcription.failed`.\n",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the user message item."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part containing the audio."
+          },
+          "error": {
+            "type": "object",
+            "description": "Details of the transcription error.",
+            "properties": {
+              "type": {
+                "type": "string",
+                "description": "The type of error."
+              },
+              "code": {
+                "type": "string",
+                "description": "Error code, if any."
+              },
+              "message": {
+                "type": "string",
+                "description": "A human-readable error message."
+              },
+              "param": {
+                "type": "string",
+                "description": "Parameter related to the error, if any."
+              }
+            }
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item_id",
+          "content_index",
+          "error"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.input_audio_transcription.failed",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_2324\",\n    \"type\": \"conversation.item.input_audio_transcription.failed\",\n    \"item_id\": \"msg_003\",\n    \"content_index\": 0,\n    \"error\": {\n        \"type\": \"transcription_error\",\n        \"code\": \"audio_unintelligible\",\n        \"message\": \"The audio could not be transcribed.\",\n        \"param\": null\n    }\n}\n"
+        }
+      },
+      "RealtimeServerEventConversationItemInputAudioTranscriptionSegment": {
+        "type": "object",
+        "description": "Returned when an input audio transcription segment is identified for an item.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.input_audio_transcription.segment"
+            ],
+            "description": "The event type, must be `conversation.item.input_audio_transcription.segment`.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item containing the input audio content."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the input audio content part within the item."
+          },
+          "text": {
+            "type": "string",
+            "description": "The text for this segment."
+          },
+          "id": {
+            "type": "string",
+            "description": "The segment identifier."
+          },
+          "speaker": {
+            "type": "string",
+            "description": "The detected speaker label for this segment."
+          },
+          "start": {
+            "type": "number",
+            "format": "double",
+            "description": "Start time of the segment in seconds."
+          },
+          "end": {
+            "type": "number",
+            "format": "double",
+            "description": "End time of the segment in seconds."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item_id",
+          "content_index",
+          "text",
+          "id",
+          "speaker",
+          "start",
+          "end"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.input_audio_transcription.segment",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_6501\",\n    \"type\": \"conversation.item.input_audio_transcription.segment\",\n    \"item_id\": \"msg_011\",\n    \"content_index\": 0,\n    \"text\": \"hello\",\n    \"id\": \"seg_0001\",\n    \"speaker\": \"spk_1\",\n    \"start\": 0.0,\n    \"end\": 0.4\n}\n"
+        }
+      },
+      "RealtimeServerEventConversationItemRetrieved": {
+        "type": "object",
+        "description": "Returned when a conversation item is retrieved with `conversation.item.retrieve`. This is provided as a way to fetch the server's representation of an item, for example to get access to the post-processed audio data after noise cancellation and VAD. It includes the full content of the Item, including audio data.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.retrieved"
+            ],
+            "description": "The event type, must be `conversation.item.retrieved`.",
+            "x-stainless-const": true
+          },
+          "item": {
+            "$ref": "#/components/schemas/RealtimeConversationItem"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.retrieved",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"conversation.item.retrieved\",\n  \"event_id\": \"event_CCXGSizgEppa2d4XbKA7K\",\n  \"item\": {\n    \"id\": \"item_CCXGRxbY0n6WE4EszhF5w\",\n    \"object\": \"realtime.item\",\n    \"type\": \"message\",\n    \"status\": \"completed\",\n    \"role\": \"assistant\",\n    \"content\": [\n      {\n        \"type\": \"audio\",\n        \"transcript\": \"Yes, I can hear you loud and clear. How can I help you today?\",\n        \"audio\": \"8//2//v/9//q/+//+P/s...\",\n        \"format\": \"pcm16\"\n      }\n    ]\n  }\n}\n"
+        }
+      },
+      "RealtimeServerEventConversationItemTruncated": {
+        "type": "object",
+        "description": "Returned when an earlier assistant audio message item is truncated by the \nclient with a `conversation.item.truncate` event. This event is used to \nsynchronize the server's understanding of the audio with the client's playback.\n\nThis action will truncate the audio and remove the server-side text transcript \nto ensure there is no text in the context that hasn't been heard by the user.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "conversation.item.truncated"
+            ],
+            "description": "The event type, must be `conversation.item.truncated`.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the assistant message item that was truncated."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part that was truncated."
+          },
+          "audio_end_ms": {
+            "type": "integer",
+            "description": "The duration up to which the audio was truncated, in milliseconds.\n"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item_id",
+          "content_index",
+          "audio_end_ms"
+        ],
+        "x-oaiMeta": {
+          "name": "conversation.item.truncated",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_2526\",\n    \"type\": \"conversation.item.truncated\",\n    \"item_id\": \"msg_004\",\n    \"content_index\": 0,\n    \"audio_end_ms\": 1500\n}\n"
+        }
+      },
+      "RealtimeServerEventError": {
+        "type": "object",
+        "description": "Returned when an error occurs, which could be a client problem or a server\nproblem. Most errors are recoverable and the session will stay open, we\nrecommend to implementors to monitor and log error messages by default.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "error"
+            ],
+            "description": "The event type, must be `error`.",
+            "x-stainless-const": true
+          },
+          "error": {
+            "type": "object",
+            "description": "Details of the error.",
+            "required": [
+              "type",
+              "message"
+            ],
+            "properties": {
+              "type": {
+                "type": "string",
+                "description": "The type of error (e.g., \"invalid_request_error\", \"server_error\").\n"
+              },
+              "code": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "Error code, if any."
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "message": {
+                "type": "string",
+                "description": "A human-readable error message."
+              },
+              "param": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "Parameter related to the error, if any."
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "event_id": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "The event_id of the client event that caused the error, if applicable.\n"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              }
+            }
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "error"
+        ],
+        "x-oaiMeta": {
+          "name": "error",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_890\",\n    \"type\": \"error\",\n    \"error\": {\n        \"type\": \"invalid_request_error\",\n        \"code\": \"invalid_event\",\n        \"message\": \"The 'type' field is missing.\",\n        \"param\": null,\n        \"event_id\": \"event_567\"\n    }\n}\n"
+        }
+      },
+      "RealtimeServerEventInputAudioBufferCleared": {
+        "type": "object",
+        "description": "Returned when the input audio buffer is cleared by the client with a \n`input_audio_buffer.clear` event.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_audio_buffer.cleared"
+            ],
+            "description": "The event type, must be `input_audio_buffer.cleared`.",
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "event_id",
+          "type"
+        ],
+        "x-oaiMeta": {
+          "name": "input_audio_buffer.cleared",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_1314\",\n    \"type\": \"input_audio_buffer.cleared\"\n}\n"
+        }
+      },
+      "RealtimeServerEventInputAudioBufferCommitted": {
+        "type": "object",
+        "description": "Returned when an input audio buffer is committed, either by the client or\nautomatically in server VAD mode. The `item_id` property is the ID of the user\nmessage item that will be created, thus a `conversation.item.created` event\nwill also be sent to the client.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_audio_buffer.committed"
+            ],
+            "description": "The event type, must be `input_audio_buffer.committed`.",
+            "x-stainless-const": true
+          },
+          "previous_item_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the preceding item after which the new item will be inserted.\nCan be `null` if the item has no predecessor.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the user message item that will be created."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "input_audio_buffer.committed",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_1121\",\n    \"type\": \"input_audio_buffer.committed\",\n    \"previous_item_id\": \"msg_001\",\n    \"item_id\": \"msg_002\"\n}\n"
+        }
+      },
+      "RealtimeServerEventInputAudioBufferDtmfEventReceived": {
+        "type": "object",
+        "description": "**SIP Only:** Returned when an DTMF event is received. A DTMF event is a message that\nrepresents a telephone keypad press (0–9, *, #, A–D). The `event` property\nis the keypad that the user press. The `received_at` is the UTC Unix Timestamp\nthat the server received the event.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_audio_buffer.dtmf_event_received"
+            ],
+            "description": "The event type, must be `input_audio_buffer.dtmf_event_received`.",
+            "x-stainless-const": true
+          },
+          "event": {
+            "type": "string",
+            "description": "The telephone keypad that was pressed by the user."
+          },
+          "received_at": {
+            "type": "integer",
+            "description": "UTC Unix Timestamp when DTMF Event was received by server.\n"
+          }
+        },
+        "required": [
+          "type",
+          "event",
+          "received_at"
+        ],
+        "x-oaiMeta": {
+          "name": "input_audio_buffer.dtmf_event_received",
+          "group": "realtime",
+          "example": "{\n    \"type\":\" input_audio_buffer.dtmf_event_received\",\n    \"event\": \"9\",\n    \"received_at\": 1763605109,\n}\n"
+        }
+      },
+      "RealtimeServerEventInputAudioBufferSpeechStarted": {
+        "type": "object",
+        "description": "Sent by the server when in `server_vad` mode to indicate that speech has been \ndetected in the audio buffer. This can happen any time audio is added to the \nbuffer (unless speech is already detected). The client may want to use this \nevent to interrupt audio playback or provide visual feedback to the user. \n\nThe client should expect to receive a `input_audio_buffer.speech_stopped` event \nwhen speech stops. The `item_id` property is the ID of the user message item \nthat will be created when speech stops and will also be included in the \n`input_audio_buffer.speech_stopped` event (unless the client manually commits \nthe audio buffer during VAD activation).\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_audio_buffer.speech_started"
+            ],
+            "description": "The event type, must be `input_audio_buffer.speech_started`.",
+            "x-stainless-const": true
+          },
+          "audio_start_ms": {
+            "type": "integer",
+            "description": "Milliseconds from the start of all audio written to the buffer during the \nsession when speech was first detected. This will correspond to the \nbeginning of audio sent to the model, and thus includes the \n`prefix_padding_ms` configured in the Session.\n"
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the user message item that will be created when speech stops.\n"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "audio_start_ms",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "input_audio_buffer.speech_started",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_1516\",\n    \"type\": \"input_audio_buffer.speech_started\",\n    \"audio_start_ms\": 1000,\n    \"item_id\": \"msg_003\"\n}\n"
+        }
+      },
+      "RealtimeServerEventInputAudioBufferSpeechStopped": {
+        "type": "object",
+        "description": "Returned in `server_vad` mode when the server detects the end of speech in \nthe audio buffer. The server will also send an `conversation.item.created` \nevent with the user message item that is created from the audio buffer.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_audio_buffer.speech_stopped"
+            ],
+            "description": "The event type, must be `input_audio_buffer.speech_stopped`.",
+            "x-stainless-const": true
+          },
+          "audio_end_ms": {
+            "type": "integer",
+            "description": "Milliseconds since the session started when speech stopped. This will \ncorrespond to the end of audio sent to the model, and thus includes the \n`min_silence_duration_ms` configured in the Session.\n"
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the user message item that will be created."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "audio_end_ms",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "input_audio_buffer.speech_stopped",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_1718\",\n    \"type\": \"input_audio_buffer.speech_stopped\",\n    \"audio_end_ms\": 2000,\n    \"item_id\": \"msg_003\"\n}\n"
+        }
+      },
+      "RealtimeServerEventInputAudioBufferTimeoutTriggered": {
+        "type": "object",
+        "description": "Returned when the Server VAD timeout is triggered for the input audio buffer. This is configured\nwith `idle_timeout_ms` in the `turn_detection` settings of the session, and it indicates that\nthere hasn't been any speech detected for the configured duration.\n\nThe `audio_start_ms` and `audio_end_ms` fields indicate the segment of audio after the last\nmodel response up to the triggering time, as an offset from the beginning of audio written\nto the input audio buffer. This means it demarcates the segment of audio that was silent and\nthe difference between the start and end values will roughly match the configured timeout.\n\nThe empty audio will be committed to the conversation as an `input_audio` item (there will be a\n`input_audio_buffer.committed` event) and a model response will be generated. There may be speech\nthat didn't trigger VAD but is still detected by the model, so the model may respond with\nsomething relevant to the conversation or a prompt to continue speaking.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_audio_buffer.timeout_triggered"
+            ],
+            "description": "The event type, must be `input_audio_buffer.timeout_triggered`.",
+            "x-stainless-const": true
+          },
+          "audio_start_ms": {
+            "type": "integer",
+            "description": "Millisecond offset of audio written to the input audio buffer that was after the playback time of the last model response."
+          },
+          "audio_end_ms": {
+            "type": "integer",
+            "description": "Millisecond offset of audio written to the input audio buffer at the time the timeout was triggered."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item associated with this segment."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "audio_start_ms",
+          "audio_end_ms",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "input_audio_buffer.timeout_triggered",
+          "group": "realtime",
+          "example": "{\n    \"type\":\"input_audio_buffer.timeout_triggered\",\n    \"event_id\":\"event_CEKKrf1KTGvemCPyiJTJ2\",\n    \"audio_start_ms\":13216,\n    \"audio_end_ms\":19232,\n    \"item_id\":\"item_CEKKrWH0GiwN0ET97NUZc\"\n}\n"
+        }
+      },
+      "RealtimeServerEventMCPListToolsCompleted": {
+        "type": "object",
+        "description": "Returned when listing MCP tools has completed for an item.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_list_tools.completed"
+            ],
+            "description": "The event type, must be `mcp_list_tools.completed`.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP list tools item."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "mcp_list_tools.completed",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_6102\",\n    \"type\": \"mcp_list_tools.completed\",\n    \"item_id\": \"mcp_list_tools_001\"\n}\n"
+        }
+      },
+      "RealtimeServerEventMCPListToolsFailed": {
+        "type": "object",
+        "description": "Returned when listing MCP tools has failed for an item.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_list_tools.failed"
+            ],
+            "description": "The event type, must be `mcp_list_tools.failed`.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP list tools item."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "mcp_list_tools.failed",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_6103\",\n    \"type\": \"mcp_list_tools.failed\",\n    \"item_id\": \"mcp_list_tools_001\"\n}\n"
+        }
+      },
+      "RealtimeServerEventMCPListToolsInProgress": {
+        "type": "object",
+        "description": "Returned when listing MCP tools is in progress for an item.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_list_tools.in_progress"
+            ],
+            "description": "The event type, must be `mcp_list_tools.in_progress`.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP list tools item."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "mcp_list_tools.in_progress",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_6101\",\n    \"type\": \"mcp_list_tools.in_progress\",\n    \"item_id\": \"mcp_list_tools_001\"\n}\n"
+        }
+      },
+      "RealtimeServerEventOutputAudioBufferCleared": {
+        "type": "object",
+        "description": "**WebRTC/SIP Only:** Emitted when the output audio buffer is cleared. This happens either in VAD\nmode when the user has interrupted (`input_audio_buffer.speech_started`),\nor when the client has emitted the `output_audio_buffer.clear` event to manually\ncut off the current audio response.\n[Learn more](https://developers.openai.com/api/docs/guides/realtime-conversations#client-and-server-events-for-audio-in-webrtc).\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "output_audio_buffer.cleared"
+            ],
+            "description": "The event type, must be `output_audio_buffer.cleared`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The unique ID of the response that produced the audio."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id"
+        ],
+        "x-oaiMeta": {
+          "name": "output_audio_buffer.cleared",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_abc123\",\n    \"type\": \"output_audio_buffer.cleared\",\n    \"response_id\": \"resp_abc123\"\n}\n"
+        }
+      },
+      "RealtimeServerEventOutputAudioBufferStarted": {
+        "type": "object",
+        "description": "**WebRTC/SIP Only:** Emitted when the server begins streaming audio to the client. This event is\nemitted after an audio content part has been added (`response.content_part.added`)\nto the response.\n[Learn more](https://developers.openai.com/api/docs/guides/realtime-conversations#client-and-server-events-for-audio-in-webrtc).\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "output_audio_buffer.started"
+            ],
+            "description": "The event type, must be `output_audio_buffer.started`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The unique ID of the response that produced the audio."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id"
+        ],
+        "x-oaiMeta": {
+          "name": "output_audio_buffer.started",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_abc123\",\n    \"type\": \"output_audio_buffer.started\",\n    \"response_id\": \"resp_abc123\"\n}\n"
+        }
+      },
+      "RealtimeServerEventOutputAudioBufferStopped": {
+        "type": "object",
+        "description": "**WebRTC/SIP Only:** Emitted when the output audio buffer has been completely drained on the server,\nand no more audio is forthcoming. This event is emitted after the full response\ndata has been sent to the client (`response.done`).\n[Learn more](https://developers.openai.com/api/docs/guides/realtime-conversations#client-and-server-events-for-audio-in-webrtc).\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "output_audio_buffer.stopped"
+            ],
+            "description": "The event type, must be `output_audio_buffer.stopped`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The unique ID of the response that produced the audio."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id"
+        ],
+        "x-oaiMeta": {
+          "name": "output_audio_buffer.stopped",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_abc123\",\n    \"type\": \"output_audio_buffer.stopped\",\n    \"response_id\": \"resp_abc123\"\n}\n"
+        }
+      },
+      "RealtimeServerEventRateLimitsUpdated": {
+        "type": "object",
+        "description": "Emitted at the beginning of a Response to indicate the updated rate limits. \nWhen a Response is created some tokens will be \"reserved\" for the output \ntokens, the rate limits shown here reflect that reservation, which is then \nadjusted accordingly once the Response is completed.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "rate_limits.updated"
+            ],
+            "description": "The event type, must be `rate_limits.updated`.",
+            "x-stainless-const": true
+          },
+          "rate_limits": {
+            "type": "array",
+            "description": "List of rate limit information.",
+            "items": {
+              "type": "object",
+              "properties": {
+                "name": {
+                  "type": "string",
+                  "enum": [
+                    "requests",
+                    "tokens"
+                  ],
+                  "description": "The name of the rate limit (`requests`, `tokens`).\n"
+                },
+                "limit": {
+                  "type": "integer",
+                  "description": "The maximum allowed value for the rate limit."
+                },
+                "remaining": {
+                  "type": "integer",
+                  "description": "The remaining value before the limit is reached."
+                },
+                "reset_seconds": {
+                  "type": "number",
+                  "description": "Seconds until the rate limit resets."
+                }
+              }
+            }
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "rate_limits"
+        ],
+        "x-oaiMeta": {
+          "name": "rate_limits.updated",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_5758\",\n    \"type\": \"rate_limits.updated\",\n    \"rate_limits\": [\n        {\n            \"name\": \"requests\",\n            \"limit\": 1000,\n            \"remaining\": 999,\n            \"reset_seconds\": 60\n        },\n        {\n            \"name\": \"tokens\",\n            \"limit\": 50000,\n            \"remaining\": 49950,\n            \"reset_seconds\": 60\n        }\n    ]\n}\n"
+        }
+      },
+      "RealtimeServerEventResponseAudioDelta": {
+        "type": "object",
+        "description": "Returned when the model-generated audio is updated.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.output_audio.delta"
+            ],
+            "description": "The event type, must be `response.output_audio.delta`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part in the item's content array."
+          },
+          "delta": {
+            "type": "string",
+            "description": "Base64-encoded audio data delta."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "delta"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_audio.delta",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_4950\",\n    \"type\": \"response.output_audio.delta\",\n    \"response_id\": \"resp_001\",\n    \"item_id\": \"msg_008\",\n    \"output_index\": 0,\n    \"content_index\": 0,\n    \"delta\": \"Base64EncodedAudioDelta\"\n}\n"
+        }
+      },
+      "RealtimeServerEventResponseAudioDone": {
+        "type": "object",
+        "description": "Returned when the model-generated audio is done. Also emitted when a Response\nis interrupted, incomplete, or cancelled.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.output_audio.done"
+            ],
+            "description": "The event type, must be `response.output_audio.done`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part in the item's content array."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "content_index"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_audio.done",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_5152\",\n    \"type\": \"response.output_audio.done\",\n    \"response_id\": \"resp_001\",\n    \"item_id\": \"msg_008\",\n    \"output_index\": 0,\n    \"content_index\": 0\n}\n"
+        }
+      },
+      "RealtimeServerEventResponseAudioTranscriptDelta": {
+        "type": "object",
+        "description": "Returned when the model-generated transcription of audio output is updated.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.output_audio_transcript.delta"
+            ],
+            "description": "The event type, must be `response.output_audio_transcript.delta`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part in the item's content array."
+          },
+          "delta": {
+            "type": "string",
+            "description": "The transcript delta."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "delta"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_audio_transcript.delta",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_4546\",\n    \"type\": \"response.output_audio_transcript.delta\",\n    \"response_id\": \"resp_001\",\n    \"item_id\": \"msg_008\",\n    \"output_index\": 0,\n    \"content_index\": 0,\n    \"delta\": \"Hello, how can I a\"\n}\n"
+        }
+      },
+      "RealtimeServerEventResponseAudioTranscriptDone": {
+        "type": "object",
+        "description": "Returned when the model-generated transcription of audio output is done\nstreaming. Also emitted when a Response is interrupted, incomplete, or\ncancelled.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.output_audio_transcript.done"
+            ],
+            "description": "The event type, must be `response.output_audio_transcript.done`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part in the item's content array."
+          },
+          "transcript": {
+            "type": "string",
+            "description": "The final transcript of the audio."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "transcript"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_audio_transcript.done",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_4748\",\n    \"type\": \"response.output_audio_transcript.done\",\n    \"response_id\": \"resp_001\",\n    \"item_id\": \"msg_008\",\n    \"output_index\": 0,\n    \"content_index\": 0,\n    \"transcript\": \"Hello, how can I assist you today?\"\n}\n"
+        }
+      },
+      "RealtimeServerEventResponseContentPartAdded": {
+        "type": "object",
+        "description": "Returned when a new content part is added to an assistant message item during\nresponse generation.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.content_part.added"
+            ],
+            "description": "The event type, must be `response.content_part.added`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item to which the content part was added."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part in the item's content array."
+          },
+          "part": {
+            "type": "object",
+            "description": "The content part that was added.",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "audio",
+                  "text"
+                ],
+                "description": "The content type (\"text\", \"audio\")."
+              },
+              "text": {
+                "type": "string",
+                "description": "The text content (if type is \"text\")."
+              },
+              "audio": {
+                "type": "string",
+                "description": "Base64-encoded audio data (if type is \"audio\")."
+              },
+              "transcript": {
+                "type": "string",
+                "description": "The transcript of the audio (if type is \"audio\")."
+              }
+            }
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "part"
+        ],
+        "x-oaiMeta": {
+          "name": "response.content_part.added",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_3738\",\n    \"type\": \"response.content_part.added\",\n    \"response_id\": \"resp_001\",\n    \"item_id\": \"msg_007\",\n    \"output_index\": 0,\n    \"content_index\": 0,\n    \"part\": {\n        \"type\": \"text\",\n        \"text\": \"\"\n    }\n}\n"
+        }
+      },
+      "RealtimeServerEventResponseContentPartDone": {
+        "type": "object",
+        "description": "Returned when a content part is done streaming in an assistant message item.\nAlso emitted when a Response is interrupted, incomplete, or cancelled.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.content_part.done"
+            ],
+            "description": "The event type, must be `response.content_part.done`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part in the item's content array."
+          },
+          "part": {
+            "type": "object",
+            "description": "The content part that is done.",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "audio",
+                  "text"
+                ],
+                "description": "The content type (\"text\", \"audio\")."
+              },
+              "text": {
+                "type": "string",
+                "description": "The text content (if type is \"text\")."
+              },
+              "audio": {
+                "type": "string",
+                "description": "Base64-encoded audio data (if type is \"audio\")."
+              },
+              "transcript": {
+                "type": "string",
+                "description": "The transcript of the audio (if type is \"audio\")."
+              }
+            }
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "part"
+        ],
+        "x-oaiMeta": {
+          "name": "response.content_part.done",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_3940\",\n    \"type\": \"response.content_part.done\",\n    \"response_id\": \"resp_001\",\n    \"item_id\": \"msg_007\",\n    \"output_index\": 0,\n    \"content_index\": 0,\n    \"part\": {\n        \"type\": \"text\",\n        \"text\": \"Sure, I can help with that.\"\n    }\n}\n"
+        }
+      },
+      "RealtimeServerEventResponseCreated": {
+        "type": "object",
+        "description": "Returned when a new Response is created. The first event of response creation,\nwhere the response is in an initial state of `in_progress`.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.created"
+            ],
+            "description": "The event type, must be `response.created`.",
+            "x-stainless-const": true
+          },
+          "response": {
+            "$ref": "#/components/schemas/RealtimeResponse"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response"
+        ],
+        "x-oaiMeta": {
+          "name": "response.created",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"response.created\",\n  \"event_id\": \"event_C9G8pqbTEddBSIxbBN6Os\",\n  \"response\": {\n    \"object\": \"realtime.response\",\n    \"id\": \"resp_C9G8p7IH2WxLbkgPNouYL\",\n    \"status\": \"in_progress\",\n    \"status_details\": null,\n    \"output\": [],\n    \"conversation_id\": \"conv_C9G8mmBkLhQJwCon3hoJN\",\n    \"output_modalities\": [\n      \"audio\"\n    ],\n    \"max_output_tokens\": \"inf\",\n    \"audio\": {\n      \"output\": {\n        \"format\": {\n          \"type\": \"audio/pcm\",\n          \"rate\": 24000\n        },\n        \"voice\": \"marin\"\n      }\n    },\n    \"usage\": null,\n    \"metadata\": null\n  },\n}\n"
+        }
+      },
+      "RealtimeServerEventResponseDone": {
+        "type": "object",
+        "description": "Returned when a Response is done streaming. Always emitted, no matter the \nfinal state. The Response object included in the `response.done` event will \ninclude all output Items in the Response but will omit the raw audio data.\n\nClients should check the `status` field of the Response to determine if it was successful\n(`completed`) or if there was another outcome: `cancelled`, `failed`, or `incomplete`.\n\nA response will contain all output items that were generated during the response, excluding\nany audio content.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.done"
+            ],
+            "description": "The event type, must be `response.done`.",
+            "x-stainless-const": true
+          },
+          "response": {
+            "$ref": "#/components/schemas/RealtimeResponse"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response"
+        ],
+        "x-oaiMeta": {
+          "name": "response.done",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"response.done\",\n  \"event_id\": \"event_CCXHxcMy86rrKhBLDdqCh\",\n  \"response\": {\n    \"object\": \"realtime.response\",\n    \"id\": \"resp_CCXHw0UJld10EzIUXQCNh\",\n    \"status\": \"completed\",\n    \"status_details\": null,\n    \"output\": [\n      {\n        \"id\": \"item_CCXHwGjjDUfOXbiySlK7i\",\n        \"type\": \"message\",\n        \"status\": \"completed\",\n        \"role\": \"assistant\",\n        \"content\": [\n          {\n            \"type\": \"output_audio\",\n            \"transcript\": \"Loud and clear! I can hear you perfectly. How can I help you today?\"\n          }\n        ]\n      }\n    ],\n    \"conversation_id\": \"conv_CCXHsurMKcaVxIZvaCI5m\",\n    \"output_modalities\": [\n      \"audio\"\n    ],\n    \"max_output_tokens\": \"inf\",\n    \"audio\": {\n      \"output\": {\n        \"format\": {\n          \"type\": \"audio/pcm\",\n          \"rate\": 24000\n        },\n        \"voice\": \"alloy\"\n      }\n    },\n    \"usage\": {\n      \"total_tokens\": 253,\n      \"input_tokens\": 132,\n      \"output_tokens\": 121,\n      \"input_token_details\": {\n        \"text_tokens\": 119,\n        \"audio_tokens\": 13,\n        \"image_tokens\": 0,\n        \"cached_tokens\": 64,\n        \"cached_tokens_details\": {\n          \"text_tokens\": 64,\n          \"audio_tokens\": 0,\n          \"image_tokens\": 0\n        }\n      },\n      \"output_token_details\": {\n        \"text_tokens\": 30,\n        \"audio_tokens\": 91\n      }\n    },\n    \"metadata\": null\n  }\n}\n"
+        }
+      },
+      "RealtimeServerEventResponseFunctionCallArgumentsDelta": {
+        "type": "object",
+        "description": "Returned when the model-generated function call arguments are updated.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.function_call_arguments.delta"
+            ],
+            "description": "The event type, must be `response.function_call_arguments.delta`.\n",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the function call item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The ID of the function call."
+          },
+          "delta": {
+            "type": "string",
+            "description": "The arguments delta as a JSON string."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "call_id",
+          "delta"
+        ],
+        "x-oaiMeta": {
+          "name": "response.function_call_arguments.delta",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_5354\",\n    \"type\": \"response.function_call_arguments.delta\",\n    \"response_id\": \"resp_002\",\n    \"item_id\": \"fc_001\",\n    \"output_index\": 0,\n    \"call_id\": \"call_001\",\n    \"delta\": \"{\\\"location\\\": \\\"San\\\"\"\n}\n"
+        }
+      },
+      "RealtimeServerEventResponseFunctionCallArgumentsDone": {
+        "type": "object",
+        "description": "Returned when the model-generated function call arguments are done streaming.\nAlso emitted when a Response is interrupted, incomplete, or cancelled.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.function_call_arguments.done"
+            ],
+            "description": "The event type, must be `response.function_call_arguments.done`.\n",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the function call item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The ID of the function call."
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the function that was called."
+          },
+          "arguments": {
+            "type": "string",
+            "description": "The final arguments as a JSON string."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "call_id",
+          "name",
+          "arguments"
+        ],
+        "x-oaiMeta": {
+          "name": "response.function_call_arguments.done",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_5556\",\n    \"type\": \"response.function_call_arguments.done\",\n    \"response_id\": \"resp_002\",\n    \"item_id\": \"fc_001\",\n    \"output_index\": 0,\n    \"call_id\": \"call_001\",\n    \"name\": \"get_weather\",\n    \"arguments\": \"{\\\"location\\\": \\\"San Francisco\\\"}\"\n}\n"
+        }
+      },
+      "RealtimeServerEventResponseMCPCallArgumentsDelta": {
+        "type": "object",
+        "description": "Returned when MCP tool call arguments are updated during response generation.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_call_arguments.delta"
+            ],
+            "description": "The event type, must be `response.mcp_call_arguments.delta`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP tool call item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "delta": {
+            "type": "string",
+            "description": "The JSON-encoded arguments delta."
+          },
+          "obfuscation": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "If present, indicates the delta text was obfuscated."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "delta"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_call_arguments.delta",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_6201\",\n    \"type\": \"response.mcp_call_arguments.delta\",\n    \"response_id\": \"resp_001\",\n    \"item_id\": \"mcp_call_001\",\n    \"output_index\": 0,\n    \"delta\": \"{\\\"partial\\\":true}\"\n}\n"
+        }
+      },
+      "RealtimeServerEventResponseMCPCallArgumentsDone": {
+        "type": "object",
+        "description": "Returned when MCP tool call arguments are finalized during response generation.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_call_arguments.done"
+            ],
+            "description": "The event type, must be `response.mcp_call_arguments.done`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP tool call item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "arguments": {
+            "type": "string",
+            "description": "The final JSON-encoded arguments string."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "arguments"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_call_arguments.done",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_6202\",\n    \"type\": \"response.mcp_call_arguments.done\",\n    \"response_id\": \"resp_001\",\n    \"item_id\": \"mcp_call_001\",\n    \"output_index\": 0,\n    \"arguments\": \"{\\\"q\\\":\\\"docs\\\"}\"\n}\n"
+        }
+      },
+      "RealtimeServerEventResponseMCPCallCompleted": {
+        "type": "object",
+        "description": "Returned when an MCP tool call has completed successfully.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_call.completed"
+            ],
+            "description": "The event type, must be `response.mcp_call.completed`.",
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP tool call item."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "output_index",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_call.completed",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_6302\",\n    \"type\": \"response.mcp_call.completed\",\n    \"output_index\": 0,\n    \"item_id\": \"mcp_call_001\"\n}\n"
+        }
+      },
+      "RealtimeServerEventResponseMCPCallFailed": {
+        "type": "object",
+        "description": "Returned when an MCP tool call has failed.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_call.failed"
+            ],
+            "description": "The event type, must be `response.mcp_call.failed`.",
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP tool call item."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "output_index",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_call.failed",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_6303\",\n    \"type\": \"response.mcp_call.failed\",\n    \"output_index\": 0,\n    \"item_id\": \"mcp_call_001\"\n}\n"
+        }
+      },
+      "RealtimeServerEventResponseMCPCallInProgress": {
+        "type": "object",
+        "description": "Returned when an MCP tool call has started and is in progress.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_call.in_progress"
+            ],
+            "description": "The event type, must be `response.mcp_call.in_progress`.",
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP tool call item."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "output_index",
+          "item_id"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_call.in_progress",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_6301\",\n    \"type\": \"response.mcp_call.in_progress\",\n    \"output_index\": 0,\n    \"item_id\": \"mcp_call_001\"\n}\n"
+        }
+      },
+      "RealtimeServerEventResponseOutputItemAdded": {
+        "type": "object",
+        "description": "Returned when a new Item is created during Response generation.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.output_item.added"
+            ],
+            "description": "The event type, must be `response.output_item.added`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the Response to which the item belongs."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the Response."
+          },
+          "item": {
+            "$ref": "#/components/schemas/RealtimeConversationItem"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "output_index",
+          "item"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_item.added",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_3334\",\n    \"type\": \"response.output_item.added\",\n    \"response_id\": \"resp_001\",\n    \"output_index\": 0,\n    \"item\": {\n        \"id\": \"msg_007\",\n        \"object\": \"realtime.item\",\n        \"type\": \"message\",\n        \"status\": \"in_progress\",\n        \"role\": \"assistant\",\n        \"content\": []\n    }\n}\n"
+        }
+      },
+      "RealtimeServerEventResponseOutputItemDone": {
+        "type": "object",
+        "description": "Returned when an Item is done streaming. Also emitted when a Response is \ninterrupted, incomplete, or cancelled.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.output_item.done"
+            ],
+            "description": "The event type, must be `response.output_item.done`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the Response to which the item belongs."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the Response."
+          },
+          "item": {
+            "$ref": "#/components/schemas/RealtimeConversationItem"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "output_index",
+          "item"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_item.done",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_3536\",\n    \"type\": \"response.output_item.done\",\n    \"response_id\": \"resp_001\",\n    \"output_index\": 0,\n    \"item\": {\n        \"id\": \"msg_007\",\n        \"object\": \"realtime.item\",\n        \"type\": \"message\",\n        \"status\": \"completed\",\n        \"role\": \"assistant\",\n        \"content\": [\n            {\n                \"type\": \"text\",\n                \"text\": \"Sure, I can help with that.\"\n            }\n        ]\n    }\n}\n"
+        }
+      },
+      "RealtimeServerEventResponseTextDelta": {
+        "type": "object",
+        "description": "Returned when the text value of an \"output_text\" content part is updated.",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.output_text.delta"
+            ],
+            "description": "The event type, must be `response.output_text.delta`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part in the item's content array."
+          },
+          "delta": {
+            "type": "string",
+            "description": "The text delta."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "delta"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_text.delta",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_4142\",\n    \"type\": \"response.output_text.delta\",\n    \"response_id\": \"resp_001\",\n    \"item_id\": \"msg_007\",\n    \"output_index\": 0,\n    \"content_index\": 0,\n    \"delta\": \"Sure, I can h\"\n}\n"
+        }
+      },
+      "RealtimeServerEventResponseTextDone": {
+        "type": "object",
+        "description": "Returned when the text value of an \"output_text\" content part is done streaming. Also\nemitted when a Response is interrupted, incomplete, or cancelled.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.output_text.done"
+            ],
+            "description": "The event type, must be `response.output_text.done`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part in the item's content array."
+          },
+          "text": {
+            "type": "string",
+            "description": "The final text content."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "response_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "text"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_text.done",
+          "group": "realtime",
+          "example": "{\n    \"event_id\": \"event_4344\",\n    \"type\": \"response.output_text.done\",\n    \"response_id\": \"resp_001\",\n    \"item_id\": \"msg_007\",\n    \"output_index\": 0,\n    \"content_index\": 0,\n    \"text\": \"Sure, I can help with that.\"\n}\n"
+        }
+      },
+      "RealtimeServerEventSessionCreated": {
+        "type": "object",
+        "description": "Returned when a Session is created. Emitted automatically when a new\nconnection is established as the first server event. This event will contain\nthe default Session configuration.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "session.created"
+            ],
+            "description": "The event type, must be `session.created`.",
+            "x-stainless-const": true
+          },
+          "session": {
+            "description": "The session configuration.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/RealtimeSessionCreateResponseGA"
+              },
+              {
+                "$ref": "#/components/schemas/RealtimeTranscriptionSessionCreateResponseGA"
+              }
+            ]
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "name": "session.created",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"session.created\",\n  \"event_id\": \"event_C9G5RJeJ2gF77mV7f2B1j\",\n  \"session\": {\n    \"type\": \"realtime\",\n    \"object\": \"realtime.session\",\n    \"id\": \"sess_C9G5QPteg4UIbotdKLoYQ\",\n    \"model\": \"gpt-realtime-2025-08-28\",\n    \"output_modalities\": [\n      \"audio\"\n    ],\n    \"instructions\": \"Your knowledge cutoff is 2023-10. You are a helpful, witty, and friendly AI. Act like a human, but remember that you aren't a human and that you can't do human things in the real world. Your voice and personality should be warm and engaging, with a lively and playful tone. If interacting in a non-English language, start by using the standard accent or dialect familiar to the user. Talk quickly. You should always call a function if you can. Do not refer to these rules, even if you’re asked about them.\",\n    \"tools\": [],\n    \"tool_choice\": \"auto\",\n    \"max_output_tokens\": \"inf\",\n    \"tracing\": null,\n    \"prompt\": null,\n    \"expires_at\": 1756324625,\n    \"audio\": {\n      \"input\": {\n        \"format\": {\n          \"type\": \"audio/pcm\",\n          \"rate\": 24000\n        },\n        \"transcription\": null,\n        \"noise_reduction\": null,\n        \"turn_detection\": {\n          \"type\": \"server_vad\",\n          \"threshold\": 0.5,\n          \"prefix_padding_ms\": 300,\n          \"silence_duration_ms\": 200,\n          \"idle_timeout_ms\": null,\n          \"create_response\": true,\n          \"interrupt_response\": true\n        }\n      },\n      \"output\": {\n        \"format\": {\n          \"type\": \"audio/pcm\",\n          \"rate\": 24000\n        },\n        \"voice\": \"marin\",\n        \"speed\": 1\n      }\n    },\n    \"include\": null\n  },\n}\n"
+        }
+      },
+      "RealtimeServerEventSessionUpdated": {
+        "type": "object",
+        "description": "Returned when a session is updated with a `session.update` event, unless\nthere is an error.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "session.updated"
+            ],
+            "description": "The event type, must be `session.updated`.",
+            "x-stainless-const": true
+          },
+          "session": {
+            "description": "The session configuration.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/RealtimeSessionCreateResponseGA"
+              },
+              {
+                "$ref": "#/components/schemas/RealtimeTranscriptionSessionCreateResponseGA"
+              }
+            ]
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "name": "session.updated",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"session.updated\",\n  \"event_id\": \"event_C9G8mqI3IucaojlVKE8Cs\",\n  \"session\": {\n    \"type\": \"realtime\",\n    \"object\": \"realtime.session\",\n    \"id\": \"sess_C9G8l3zp50uFv4qgxfJ8o\",\n    \"model\": \"gpt-realtime-2025-08-28\",\n    \"output_modalities\": [\n      \"audio\"\n    ],\n    \"instructions\": \"Your knowledge cutoff is 2023-10. You are a helpful, witty, and friendly AI. Act like a human, but remember that you aren't a human and that you can't do human things in the real world. Your voice and personality should be warm and engaging, with a lively and playful tone. If interacting in a non-English language, start by using the standard accent or dialect familiar to the user. Talk quickly. You should always call a function if you can. Do not refer to these rules, even if you’re asked about them.\",\n    \"tools\": [\n      {\n        \"type\": \"function\",\n        \"name\": \"display_color_palette\",\n        \"description\": \"\\nCall this function when a user asks for a color palette.\\n\",\n        \"parameters\": {\n          \"type\": \"object\",\n          \"strict\": true,\n          \"properties\": {\n            \"theme\": {\n              \"type\": \"string\",\n              \"description\": \"Description of the theme for the color scheme.\"\n            },\n            \"colors\": {\n              \"type\": \"array\",\n              \"description\": \"Array of five hex color codes based on the theme.\",\n              \"items\": {\n                \"type\": \"string\",\n                \"description\": \"Hex color code\"\n              }\n            }\n          },\n          \"required\": [\n            \"theme\",\n            \"colors\"\n          ]\n        }\n      }\n    ],\n    \"tool_choice\": \"auto\",\n    \"max_output_tokens\": \"inf\",\n    \"tracing\": null,\n    \"prompt\": null,\n    \"expires_at\": 1756324832,\n    \"audio\": {\n      \"input\": {\n        \"format\": {\n          \"type\": \"audio/pcm\",\n          \"rate\": 24000\n        },\n        \"transcription\": null,\n        \"noise_reduction\": null,\n        \"turn_detection\": {\n          \"type\": \"server_vad\",\n          \"threshold\": 0.5,\n          \"prefix_padding_ms\": 300,\n          \"silence_duration_ms\": 200,\n          \"idle_timeout_ms\": null,\n          \"create_response\": true,\n          \"interrupt_response\": true\n        }\n      },\n      \"output\": {\n        \"format\": {\n          \"type\": \"audio/pcm\",\n          \"rate\": 24000\n        },\n        \"voice\": \"marin\",\n        \"speed\": 1\n      }\n    },\n    \"include\": null\n  },\n}\n"
+        }
+      },
+      "RealtimeServerEventTranscriptionSessionUpdated": {
+        "type": "object",
+        "description": "Returned when a transcription session is updated with a `transcription_session.update` event, unless \nthere is an error.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "transcription_session.updated"
+            ],
+            "description": "The event type, must be `transcription_session.updated`.",
+            "x-stainless-const": true
+          },
+          "session": {
+            "$ref": "#/components/schemas/RealtimeTranscriptionSessionCreateResponse"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "name": "transcription_session.updated",
+          "group": "realtime",
+          "example": "{\n  \"event_id\": \"event_5678\",\n  \"type\": \"transcription_session.updated\",\n  \"session\": {\n    \"id\": \"sess_001\",\n    \"object\": \"realtime.transcription_session\",\n    \"input_audio_format\": \"pcm16\",\n    \"input_audio_transcription\": {\n      \"model\": \"gpt-4o-transcribe\",\n      \"prompt\": \"\",\n      \"language\": \"\"\n    },\n    \"turn_detection\": {\n      \"type\": \"server_vad\",\n      \"threshold\": 0.5,\n      \"prefix_padding_ms\": 300,\n      \"silence_duration_ms\": 500,\n      \"create_response\": true,\n      // \"interrupt_response\": false  -- this will NOT be returned\n    },\n    \"input_audio_noise_reduction\": {\n      \"type\": \"near_field\"\n    },\n    \"include\": [\n      \"item.input_audio_transcription.avg_logprob\",\n    ],\n  }\n}\n"
+        }
+      },
+      "RealtimeSession": {
+        "type": "object",
+        "description": "Realtime session object for the beta interface.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Unique identifier for the session that looks like `sess_1234567890abcdef`.\n"
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "realtime.session"
+            ],
+            "description": "The object type. Always `realtime.session`."
+          },
+          "modalities": {
+            "description": "The set of modalities the model can respond with. To disable audio,\nset this to [\"text\"].\n",
+            "items": {
+              "type": "string",
+              "default": [
+                "text",
+                "audio"
+              ],
+              "enum": [
+                "text",
+                "audio"
+              ]
+            }
+          },
+          "model": {
+            "description": "The Realtime model used for this session.\n",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "gpt-realtime",
+                  "gpt-realtime-1.5",
+                  "gpt-realtime-2025-08-28",
+                  "gpt-4o-realtime-preview",
+                  "gpt-4o-realtime-preview-2024-10-01",
+                  "gpt-4o-realtime-preview-2024-12-17",
+                  "gpt-4o-realtime-preview-2025-06-03",
+                  "gpt-4o-mini-realtime-preview",
+                  "gpt-4o-mini-realtime-preview-2024-12-17",
+                  "gpt-realtime-mini",
+                  "gpt-realtime-mini-2025-10-06",
+                  "gpt-realtime-mini-2025-12-15",
+                  "gpt-audio-1.5",
+                  "gpt-audio-mini",
+                  "gpt-audio-mini-2025-10-06",
+                  "gpt-audio-mini-2025-12-15"
+                ]
+              }
+            ]
+          },
+          "instructions": {
+            "type": "string",
+            "description": "The default system instructions (i.e. system message) prepended to model\ncalls. This field allows the client to guide the model on desired\nresponses. The model can be instructed on response content and format,\n(e.g. \"be extremely succinct\", \"act friendly\", \"here are examples of good\nresponses\") and on audio behavior (e.g. \"talk quickly\", \"inject emotion\ninto your voice\", \"laugh frequently\"). The instructions are not\nguaranteed to be followed by the model, but they provide guidance to the\nmodel on the desired behavior.\n\n\nNote that the server sets default instructions which will be used if this\nfield is not set and are visible in the `session.created` event at the\nstart of the session.\n"
+          },
+          "voice": {
+            "$ref": "#/components/schemas/VoiceIdsShared",
+            "description": "The voice the model uses to respond. Voice cannot be changed during the\nsession once the model has responded with audio at least once. Current\nvoice options are `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`,\n`shimmer`, and `verse`.\n"
+          },
+          "input_audio_format": {
+            "type": "string",
+            "default": "pcm16",
+            "enum": [
+              "pcm16",
+              "g711_ulaw",
+              "g711_alaw"
+            ],
+            "description": "The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.\nFor `pcm16`, input audio must be 16-bit PCM at a 24kHz sample rate,\nsingle channel (mono), and little-endian byte order.\n"
+          },
+          "output_audio_format": {
+            "type": "string",
+            "default": "pcm16",
+            "enum": [
+              "pcm16",
+              "g711_ulaw",
+              "g711_alaw"
+            ],
+            "description": "The format of output audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.\nFor `pcm16`, output audio is sampled at a rate of 24kHz.\n"
+          },
+          "input_audio_transcription": {
+            "anyOf": [
+              {
+                "allOf": [
+                  {
+                    "$ref": "#/components/schemas/AudioTranscriptionResponse"
+                  }
+                ],
+                "description": "Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://developers.openai.com/api/reference/resources/audio/subresources/transcriptions/methods/create) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "turn_detection": {
+            "$ref": "#/components/schemas/RealtimeTurnDetection"
+          },
+          "input_audio_noise_reduction": {
+            "type": "object",
+            "default": null,
+            "description": "Configuration for input audio noise reduction. This can be set to `null` to turn off.\nNoise reduction filters audio added to the input audio buffer before it is sent to VAD and the model.\nFiltering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.\n",
+            "properties": {
+              "type": {
+                "$ref": "#/components/schemas/NoiseReductionType"
+              }
+            }
+          },
+          "speed": {
+            "type": "number",
+            "default": 1,
+            "maximum": 1.5,
+            "minimum": 0.25,
+            "description": "The speed of the model's spoken response. 1.0 is the default speed. 0.25 is\nthe minimum speed. 1.5 is the maximum speed. This value can only be changed\nin between model turns, not while a response is in progress.\n"
+          },
+          "tracing": {
+            "anyOf": [
+              {
+                "title": "Tracing Configuration",
+                "description": "Configuration options for tracing. Set to null to disable tracing. Once\ntracing is enabled for a session, the configuration cannot be modified.\n\n`auto` will create a trace for the session with default values for the\nworkflow name, group id, and metadata.\n",
+                "oneOf": [
+                  {
+                    "type": "string",
+                    "default": "auto",
+                    "description": "Default tracing mode for the session.\n",
+                    "enum": [
+                      "auto"
+                    ],
+                    "x-stainless-const": true
+                  },
+                  {
+                    "type": "object",
+                    "title": "Tracing Configuration",
+                    "description": "Granular configuration for tracing.\n",
+                    "properties": {
+                      "workflow_name": {
+                        "type": "string",
+                        "description": "The name of the workflow to attach to this trace. This is used to\nname the trace in the traces dashboard.\n"
+                      },
+                      "group_id": {
+                        "type": "string",
+                        "description": "The group id to attach to this trace to enable filtering and\ngrouping in the traces dashboard.\n"
+                      },
+                      "metadata": {
+                        "type": "object",
+                        "description": "The arbitrary metadata to attach to this trace to enable\nfiltering in the traces dashboard.\n"
+                      }
+                    }
+                  }
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "tools": {
+            "type": "array",
+            "description": "Tools (functions) available to the model.",
+            "items": {
+              "$ref": "#/components/schemas/RealtimeFunctionTool"
+            }
+          },
+          "tool_choice": {
+            "type": "string",
+            "default": "auto",
+            "description": "How the model chooses tools. Options are `auto`, `none`, `required`, or\nspecify a function.\n"
+          },
+          "temperature": {
+            "type": "number",
+            "default": 0.8,
+            "description": "Sampling temperature for the model, limited to [0.6, 1.2]. For audio models a temperature of 0.8 is highly recommended for best performance.\n"
+          },
+          "max_response_output_tokens": {
+            "oneOf": [
+              {
+                "type": "integer"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "inf"
+                ],
+                "x-stainless-const": true
+              }
+            ],
+            "description": "Maximum number of output tokens for a single assistant response,\ninclusive of tool calls. Provide an integer between 1 and 4096 to\nlimit output tokens, or `inf` for the maximum available tokens for a\ngiven model. Defaults to `inf`.\n"
+          },
+          "expires_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Expiration timestamp for the session, in seconds since epoch."
+          },
+          "prompt": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Prompt"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "include": {
+            "anyOf": [
+              {
+                "type": "array",
+                "items": {
+                  "type": "string",
+                  "enum": [
+                    "item.input_audio_transcription.logprobs"
+                  ]
+                },
+                "description": "Additional fields to include in server outputs.\n- `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        }
+      },
+      "RealtimeSessionCreateRequest": {
+        "type": "object",
+        "description": "A new Realtime session configuration, with an ephemeral key. Default TTL\nfor keys is one minute.\n",
+        "properties": {
+          "client_secret": {
+            "type": "object",
+            "description": "Ephemeral key returned by the API.",
+            "properties": {
+              "value": {
+                "type": "string",
+                "description": "Ephemeral key usable in client environments to authenticate connections\nto the Realtime API. Use this in client-side environments rather than\na standard API token, which should only be used server-side.\n"
+              },
+              "expires_at": {
+                "type": "integer",
+                "format": "unixtime",
+                "description": "Timestamp for when the token expires. Currently, all tokens expire\nafter one minute.\n"
+              }
+            },
+            "required": [
+              "value",
+              "expires_at"
+            ]
+          },
+          "modalities": {
+            "description": "The set of modalities the model can respond with. To disable audio,\nset this to [\"text\"].\n",
+            "items": {
+              "type": "string",
+              "enum": [
+                "text",
+                "audio"
+              ]
+            }
+          },
+          "instructions": {
+            "type": "string",
+            "description": "The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. \"be extremely succinct\", \"act friendly\", \"here are examples of good responses\") and on audio behavior (e.g. \"talk quickly\", \"inject emotion into your voice\", \"laugh frequently\"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior.\nNote that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session.\n"
+          },
+          "voice": {
+            "$ref": "#/components/schemas/VoiceIdsOrCustomVoice",
+            "description": "The voice the model uses to respond. Supported built-in voices are\n`alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, `verse`,\n`marin`, and `cedar`. You may also provide a custom voice object with an\n`id`, for example `{ \"id\": \"voice_1234\" }`. Voice cannot be changed during\nthe session once the model has responded with audio at least once.\n"
+          },
+          "input_audio_format": {
+            "type": "string",
+            "description": "The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.\n"
+          },
+          "output_audio_format": {
+            "type": "string",
+            "description": "The format of output audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.\n"
+          },
+          "input_audio_transcription": {
+            "type": "object",
+            "description": "Configuration for input audio transcription, defaults to off and can be\nset to `null` to turn off once on. Input audio transcription is not native\nto the model, since the model consumes audio directly. Transcription runs\nasynchronously and should be treated as rough guidance\nrather than the representation understood by the model.\n",
+            "properties": {
+              "model": {
+                "type": "string",
+                "description": "The model to use for transcription.\n"
+              }
+            }
+          },
+          "speed": {
+            "type": "number",
+            "default": 1,
+            "maximum": 1.5,
+            "minimum": 0.25,
+            "description": "The speed of the model's spoken response. 1.0 is the default speed. 0.25 is\nthe minimum speed. 1.5 is the maximum speed. This value can only be changed\nin between model turns, not while a response is in progress.\n"
+          },
+          "tracing": {
+            "title": "Tracing Configuration",
+            "description": "Configuration options for tracing. Set to null to disable tracing. Once\ntracing is enabled for a session, the configuration cannot be modified.\n\n`auto` will create a trace for the session with default values for the\nworkflow name, group id, and metadata.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "default": "auto",
+                "description": "Default tracing mode for the session.\n",
+                "enum": [
+                  "auto"
+                ],
+                "x-stainless-const": true
+              },
+              {
+                "type": "object",
+                "title": "Tracing Configuration",
+                "description": "Granular configuration for tracing.\n",
+                "properties": {
+                  "workflow_name": {
+                    "type": "string",
+                    "description": "The name of the workflow to attach to this trace. This is used to\nname the trace in the traces dashboard.\n"
+                  },
+                  "group_id": {
+                    "type": "string",
+                    "description": "The group id to attach to this trace to enable filtering and\ngrouping in the traces dashboard.\n"
+                  },
+                  "metadata": {
+                    "type": "object",
+                    "description": "The arbitrary metadata to attach to this trace to enable\nfiltering in the traces dashboard.\n"
+                  }
+                }
+              }
+            ]
+          },
+          "turn_detection": {
+            "type": "object",
+            "description": "Configuration for turn detection. Can be set to `null` to turn off. Server\nVAD means that the model will detect the start and end of speech based on\naudio volume and respond at the end of user speech.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "description": "Type of turn detection, only `server_vad` is currently supported.\n"
+              },
+              "threshold": {
+                "type": "number",
+                "description": "Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A\nhigher threshold will require louder audio to activate the model, and\nthus might perform better in noisy environments.\n"
+              },
+              "prefix_padding_ms": {
+                "type": "integer",
+                "description": "Amount of audio to include before the VAD detected speech (in\nmilliseconds). Defaults to 300ms.\n"
+              },
+              "silence_duration_ms": {
+                "type": "integer",
+                "description": "Duration of silence to detect speech stop (in milliseconds). Defaults\nto 500ms. With shorter values the model will respond more quickly,\nbut may jump in on short pauses from the user.\n"
+              }
+            }
+          },
+          "tools": {
+            "type": "array",
+            "description": "Tools (functions) available to the model.",
+            "items": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "function"
+                  ],
+                  "description": "The type of the tool, i.e. `function`.",
+                  "x-stainless-const": true
+                },
+                "name": {
+                  "type": "string",
+                  "description": "The name of the function."
+                },
+                "description": {
+                  "type": "string",
+                  "description": "The description of the function, including guidance on when and how\nto call it, and guidance about what to tell the user when calling\n(if anything).\n"
+                },
+                "parameters": {
+                  "type": "object",
+                  "description": "Parameters of the function in JSON Schema."
+                }
+              }
+            }
+          },
+          "tool_choice": {
+            "type": "string",
+            "description": "How the model chooses tools. Options are `auto`, `none`, `required`, or\nspecify a function.\n"
+          },
+          "temperature": {
+            "type": "number",
+            "description": "Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.\n"
+          },
+          "max_response_output_tokens": {
+            "oneOf": [
+              {
+                "type": "integer"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "inf"
+                ],
+                "x-stainless-const": true
+              }
+            ],
+            "description": "Maximum number of output tokens for a single assistant response,\ninclusive of tool calls. Provide an integer between 1 and 4096 to\nlimit output tokens, or `inf` for the maximum available tokens for a\ngiven model. Defaults to `inf`.\n"
+          },
+          "truncation": {
+            "$ref": "#/components/schemas/RealtimeTruncation"
+          },
+          "prompt": {
+            "$ref": "#/components/schemas/Prompt"
+          }
+        },
+        "required": [
+          "client_secret"
+        ],
+        "x-oaiMeta": {
+          "name": "The session object",
+          "group": "realtime",
+          "example": "{\n  \"id\": \"sess_001\",\n  \"object\": \"realtime.session\",\n  \"model\": \"gpt-realtime-2025-08-25\",\n  \"modalities\": [\"audio\", \"text\"],\n  \"instructions\": \"You are a friendly assistant.\",\n  \"voice\": \"alloy\",\n  \"input_audio_format\": \"pcm16\",\n  \"output_audio_format\": \"pcm16\",\n  \"input_audio_transcription\": {\n      \"model\": \"whisper-1\"\n  },\n  \"turn_detection\": null,\n  \"tools\": [],\n  \"tool_choice\": \"none\",\n  \"temperature\": 0.7,\n  \"speed\": 1.1,\n  \"tracing\": \"auto\",\n  \"max_response_output_tokens\": 200,\n  \"truncation\": \"auto\",\n  \"prompt\": null,\n  \"client_secret\": {\n    \"value\": \"ek_abc123\",\n    \"expires_at\": 1234567890\n  }\n}\n"
+        }
+      },
+      "RealtimeSessionCreateRequestGA": {
+        "type": "object",
+        "title": "Realtime session configuration",
+        "description": "Realtime session object configuration.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of session to create. Always `realtime` for the Realtime API.\n",
+            "enum": [
+              "realtime"
+            ],
+            "x-stainless-const": true
+          },
+          "output_modalities": {
+            "type": "array",
+            "description": "The set of modalities the model can respond with. It defaults to `[\"audio\"]`, indicating\nthat the model will respond with audio plus a transcript. `[\"text\"]` can be used to make\nthe model respond with text only. It is not possible to request both `text` and `audio` at the same time.\n",
+            "default": [
+              "audio"
+            ],
+            "items": {
+              "type": "string",
+              "enum": [
+                "text",
+                "audio"
+              ]
+            }
+          },
+          "model": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "gpt-realtime",
+                  "gpt-realtime-1.5",
+                  "gpt-realtime-2",
+                  "gpt-realtime-2.1",
+                  "gpt-realtime-2.1-mini",
+                  "gpt-realtime-2025-08-28",
+                  "gpt-4o-realtime-preview",
+                  "gpt-4o-realtime-preview-2024-10-01",
+                  "gpt-4o-realtime-preview-2024-12-17",
+                  "gpt-4o-realtime-preview-2025-06-03",
+                  "gpt-4o-mini-realtime-preview",
+                  "gpt-4o-mini-realtime-preview-2024-12-17",
+                  "gpt-realtime-mini",
+                  "gpt-realtime-mini-2025-10-06",
+                  "gpt-realtime-mini-2025-12-15",
+                  "gpt-audio-1.5",
+                  "gpt-audio-mini",
+                  "gpt-audio-mini-2025-10-06",
+                  "gpt-audio-mini-2025-12-15"
+                ]
+              }
+            ],
+            "description": "The Realtime model used for this session.\n"
+          },
+          "instructions": {
+            "type": "string",
+            "description": "The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. \"be extremely succinct\", \"act friendly\", \"here are examples of good responses\") and on audio behavior (e.g. \"talk quickly\", \"inject emotion into your voice\", \"laugh frequently\"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior.\n\nNote that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session.\n"
+          },
+          "audio": {
+            "type": "object",
+            "description": "Configuration for input and output audio.\n",
+            "properties": {
+              "input": {
+                "type": "object",
+                "properties": {
+                  "format": {
+                    "$ref": "#/components/schemas/RealtimeAudioFormats",
+                    "description": "The format of the input audio."
+                  },
+                  "transcription": {
+                    "description": "Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://developers.openai.com/api/reference/resources/audio/subresources/transcriptions/methods/create) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service.\n",
+                    "$ref": "#/components/schemas/AudioTranscription"
+                  },
+                  "noise_reduction": {
+                    "type": "object",
+                    "default": null,
+                    "description": "Configuration for input audio noise reduction. This can be set to `null` to turn off.\nNoise reduction filters audio added to the input audio buffer before it is sent to VAD and the model.\nFiltering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.\n",
+                    "properties": {
+                      "type": {
+                        "$ref": "#/components/schemas/NoiseReductionType"
+                      }
+                    }
+                  },
+                  "turn_detection": {
+                    "$ref": "#/components/schemas/RealtimeTurnDetection"
+                  }
+                }
+              },
+              "output": {
+                "type": "object",
+                "properties": {
+                  "format": {
+                    "$ref": "#/components/schemas/RealtimeAudioFormats",
+                    "description": "The format of the output audio."
+                  },
+                  "voice": {
+                    "$ref": "#/components/schemas/VoiceIdsOrCustomVoice",
+                    "default": "alloy",
+                    "description": "The voice the model uses to respond. Supported built-in voices are\n`alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, `verse`,\n`marin`, and `cedar`. You may also provide a custom voice object with\nan `id`, for example `{ \"id\": \"voice_1234\" }`. Voice cannot be changed\nduring the session once the model has responded with audio at least once.\nWe recommend `marin` and `cedar` for best quality.\n"
+                  },
+                  "speed": {
+                    "type": "number",
+                    "default": 1,
+                    "maximum": 1.5,
+                    "minimum": 0.25,
+                    "description": "The speed of the model's spoken response as a multiple of the original speed.\n1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress.\n\nThis parameter is a post-processing adjustment to the audio after it is generated, it's\nalso possible to prompt the model to speak faster or slower.\n"
+                  }
+                }
+              }
+            }
+          },
+          "include": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "enum": [
+                "item.input_audio_transcription.logprobs"
+              ]
+            },
+            "description": "Additional fields to include in server outputs.\n\n`item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription.\n"
+          },
+          "tracing": {
+            "title": "Tracing Configuration",
+            "default": null,
+            "description": "Realtime API can write session traces to the [Traces Dashboard](https://platform.openai.com/logs?api=traces). Set to null to disable tracing. Once\ntracing is enabled for a session, the configuration cannot be modified.\n\n`auto` will create a trace for the session with default values for the\nworkflow name, group id, and metadata.\n",
+            "nullable": true,
+            "oneOf": [
+              {
+                "type": "string",
+                "title": "auto",
+                "default": "auto",
+                "description": "Enables tracing and sets default values for tracing configuration options. Always `auto`.\n",
+                "enum": [
+                  "auto"
+                ],
+                "x-stainless-const": true
+              },
+              {
+                "type": "object",
+                "title": "Tracing Configuration",
+                "description": "Granular configuration for tracing.\n",
+                "properties": {
+                  "workflow_name": {
+                    "type": "string",
+                    "description": "The name of the workflow to attach to this trace. This is used to\nname the trace in the Traces Dashboard.\n"
+                  },
+                  "group_id": {
+                    "type": "string",
+                    "description": "The group id to attach to this trace to enable filtering and\ngrouping in the Traces Dashboard.\n"
+                  },
+                  "metadata": {
+                    "type": "object",
+                    "description": "The arbitrary metadata to attach to this trace to enable\nfiltering in the Traces Dashboard.\n"
+                  }
+                }
+              }
+            ]
+          },
+          "tools": {
+            "type": "array",
+            "description": "Tools available to the model.",
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/RealtimeFunctionTool"
+                },
+                {
+                  "$ref": "#/components/schemas/MCPTool"
+                }
+              ]
+            }
+          },
+          "tool_choice": {
+            "description": "How the model chooses tools. Provide one of the string modes or force a specific\nfunction/MCP tool.\n",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/ToolChoiceOptions"
+              },
+              {
+                "$ref": "#/components/schemas/ToolChoiceFunction"
+              },
+              {
+                "$ref": "#/components/schemas/ToolChoiceMCP"
+              }
+            ],
+            "default": "auto"
+          },
+          "parallel_tool_calls": {
+            "type": "boolean",
+            "description": "Whether the model may call multiple tools in parallel. Only supported by\nreasoning Realtime models such as `gpt-realtime-2`.\n"
+          },
+          "reasoning": {
+            "$ref": "#/components/schemas/RealtimeReasoning"
+          },
+          "max_output_tokens": {
+            "oneOf": [
+              {
+                "type": "integer"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "inf"
+                ],
+                "x-stainless-const": true
+              }
+            ],
+            "description": "Maximum number of output tokens for a single assistant response,\ninclusive of tool calls. Provide an integer between 1 and 4096 to\nlimit output tokens, or `inf` for the maximum available tokens for a\ngiven model. Defaults to `inf`.\n"
+          },
+          "truncation": {
+            "$ref": "#/components/schemas/RealtimeTruncation"
+          },
+          "prompt": {
+            "$ref": "#/components/schemas/Prompt"
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "RealtimeSessionCreateResponse": {
+        "type": "object",
+        "title": "Realtime session configuration object",
+        "description": "A Realtime session configuration object.\n",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Unique identifier for the session that looks like `sess_1234567890abcdef`.\n"
+          },
+          "object": {
+            "type": "string",
+            "description": "The object type. Always `realtime.session`."
+          },
+          "expires_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Expiration timestamp for the session, in seconds since epoch."
+          },
+          "include": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "enum": [
+                "item.input_audio_transcription.logprobs"
+              ]
+            },
+            "description": "Additional fields to include in server outputs.\n- `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription.\n"
+          },
+          "model": {
+            "type": "string",
+            "description": "The Realtime model used for this session."
+          },
+          "output_modalities": {
+            "description": "The set of modalities the model can respond with. To disable audio,\nset this to [\"text\"].\n",
+            "items": {
+              "type": "string",
+              "enum": [
+                "text",
+                "audio"
+              ]
+            }
+          },
+          "instructions": {
+            "type": "string",
+            "description": "The default system instructions (i.e. system message) prepended to model\ncalls. This field allows the client to guide the model on desired\nresponses. The model can be instructed on response content and format,\n(e.g. \"be extremely succinct\", \"act friendly\", \"here are examples of good\nresponses\") and on audio behavior (e.g. \"talk quickly\", \"inject emotion\ninto your voice\", \"laugh frequently\"). The instructions are not guaranteed\nto be followed by the model, but they provide guidance to the model on the\ndesired behavior.\n\nNote that the server sets default instructions which will be used if this\nfield is not set and are visible in the `session.created` event at the\nstart of the session.\n"
+          },
+          "audio": {
+            "type": "object",
+            "description": "Configuration for input and output audio for the session.\n",
+            "properties": {
+              "input": {
+                "type": "object",
+                "properties": {
+                  "format": {
+                    "$ref": "#/components/schemas/RealtimeAudioFormats"
+                  },
+                  "transcription": {
+                    "description": "Configuration for input audio transcription.\n",
+                    "$ref": "#/components/schemas/AudioTranscriptionResponse"
+                  },
+                  "noise_reduction": {
+                    "type": "object",
+                    "description": "Configuration for input audio noise reduction.\n",
+                    "properties": {
+                      "type": {
+                        "$ref": "#/components/schemas/NoiseReductionType"
+                      }
+                    }
+                  },
+                  "turn_detection": {
+                    "type": "object",
+                    "description": "Configuration for turn detection.\n",
+                    "properties": {
+                      "type": {
+                        "type": "string",
+                        "description": "Type of turn detection, only `server_vad` is currently supported.\n"
+                      },
+                      "threshold": {
+                        "type": "number"
+                      },
+                      "prefix_padding_ms": {
+                        "type": "integer"
+                      },
+                      "silence_duration_ms": {
+                        "type": "integer"
+                      }
+                    }
+                  }
+                }
+              },
+              "output": {
+                "type": "object",
+                "properties": {
+                  "format": {
+                    "$ref": "#/components/schemas/RealtimeAudioFormats"
+                  },
+                  "voice": {
+                    "$ref": "#/components/schemas/VoiceIdsShared"
+                  },
+                  "speed": {
+                    "type": "number"
+                  }
+                }
+              }
+            }
+          },
+          "tracing": {
+            "title": "Tracing Configuration",
+            "description": "Configuration options for tracing. Set to null to disable tracing. Once\ntracing is enabled for a session, the configuration cannot be modified.\n\n`auto` will create a trace for the session with default values for the\nworkflow name, group id, and metadata.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "default": "auto",
+                "description": "Default tracing mode for the session.\n",
+                "enum": [
+                  "auto"
+                ],
+                "x-stainless-const": true
+              },
+              {
+                "type": "object",
+                "title": "Tracing Configuration",
+                "description": "Granular configuration for tracing.\n",
+                "properties": {
+                  "workflow_name": {
+                    "type": "string",
+                    "description": "The name of the workflow to attach to this trace. This is used to\nname the trace in the traces dashboard.\n"
+                  },
+                  "group_id": {
+                    "type": "string",
+                    "description": "The group id to attach to this trace to enable filtering and\ngrouping in the traces dashboard.\n"
+                  },
+                  "metadata": {
+                    "type": "object",
+                    "description": "The arbitrary metadata to attach to this trace to enable\nfiltering in the traces dashboard.\n"
+                  }
+                }
+              }
+            ]
+          },
+          "turn_detection": {
+            "type": "object",
+            "description": "Configuration for turn detection. Can be set to `null` to turn off. Server\nVAD means that the model will detect the start and end of speech based on\naudio volume and respond at the end of user speech.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "description": "Type of turn detection, only `server_vad` is currently supported.\n"
+              },
+              "threshold": {
+                "type": "number",
+                "description": "Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A\nhigher threshold will require louder audio to activate the model, and\nthus might perform better in noisy environments.\n"
+              },
+              "prefix_padding_ms": {
+                "type": "integer",
+                "description": "Amount of audio to include before the VAD detected speech (in\nmilliseconds). Defaults to 300ms.\n"
+              },
+              "silence_duration_ms": {
+                "type": "integer",
+                "description": "Duration of silence to detect speech stop (in milliseconds). Defaults\nto 500ms. With shorter values the model will respond more quickly,\nbut may jump in on short pauses from the user.\n"
+              }
+            }
+          },
+          "tools": {
+            "type": "array",
+            "description": "Tools (functions) available to the model.",
+            "items": {
+              "$ref": "#/components/schemas/RealtimeFunctionTool"
+            }
+          },
+          "tool_choice": {
+            "type": "string",
+            "description": "How the model chooses tools. Options are `auto`, `none`, `required`, or\nspecify a function.\n"
+          },
+          "max_output_tokens": {
+            "oneOf": [
+              {
+                "type": "integer"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "inf"
+                ],
+                "x-stainless-const": true
+              }
+            ],
+            "description": "Maximum number of output tokens for a single assistant response,\ninclusive of tool calls. Provide an integer between 1 and 4096 to\nlimit output tokens, or `inf` for the maximum available tokens for a\ngiven model. Defaults to `inf`.\n"
+          }
+        },
+        "x-oaiMeta": {
+          "name": "The session object",
+          "group": "realtime",
+          "example": "{\n  \"id\": \"sess_001\",\n  \"object\": \"realtime.session\",\n  \"expires_at\": 1742188264,\n  \"model\": \"gpt-realtime\",\n  \"output_modalities\": [\"audio\"],\n  \"instructions\": \"You are a friendly assistant.\",\n  \"tools\": [],\n  \"tool_choice\": \"none\",\n  \"max_output_tokens\": \"inf\",\n  \"tracing\": \"auto\",\n  \"truncation\": \"auto\",\n  \"prompt\": null,\n  \"audio\": {\n    \"input\": {\n      \"format\": {\n        \"type\": \"audio/pcm\",\n        \"rate\": 24000\n      },\n      \"transcription\": { \"model\": \"whisper-1\" },\n      \"noise_reduction\": null,\n      \"turn_detection\": null\n    },\n    \"output\": {\n      \"format\": {\n        \"type\": \"audio/pcm\",\n        \"rate\": 24000\n      },\n      \"voice\": \"alloy\",\n      \"speed\": 1.0\n    }\n  }\n}\n"
+        }
+      },
+      "RealtimeSessionCreateResponseGA": {
+        "type": "object",
+        "title": "Realtime session configuration object",
+        "description": "A Realtime session configuration object.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of session to create. Always `realtime` for the Realtime API.\n",
+            "enum": [
+              "realtime"
+            ],
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "Unique identifier for the session that looks like `sess_1234567890abcdef`.\n"
+          },
+          "object": {
+            "type": "string",
+            "description": "The object type. Always `realtime.session`.",
+            "enum": [
+              "realtime.session"
+            ],
+            "x-stainless-const": true
+          },
+          "expires_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Expiration timestamp for the session, in seconds since epoch."
+          },
+          "output_modalities": {
+            "type": "array",
+            "description": "The set of modalities the model can respond with. It defaults to `[\"audio\"]`, indicating\nthat the model will respond with audio plus a transcript. `[\"text\"]` can be used to make\nthe model respond with text only. It is not possible to request both `text` and `audio` at the same time.\n",
+            "default": [
+              "audio"
+            ],
+            "items": {
+              "type": "string",
+              "enum": [
+                "text",
+                "audio"
+              ]
+            }
+          },
+          "model": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "gpt-realtime",
+                  "gpt-realtime-1.5",
+                  "gpt-realtime-2",
+                  "gpt-realtime-2.1",
+                  "gpt-realtime-2.1-mini",
+                  "gpt-realtime-2025-08-28",
+                  "gpt-4o-realtime-preview",
+                  "gpt-4o-realtime-preview-2024-10-01",
+                  "gpt-4o-realtime-preview-2024-12-17",
+                  "gpt-4o-realtime-preview-2025-06-03",
+                  "gpt-4o-mini-realtime-preview",
+                  "gpt-4o-mini-realtime-preview-2024-12-17",
+                  "gpt-realtime-mini",
+                  "gpt-realtime-mini-2025-10-06",
+                  "gpt-realtime-mini-2025-12-15",
+                  "gpt-audio-1.5",
+                  "gpt-audio-mini",
+                  "gpt-audio-mini-2025-10-06",
+                  "gpt-audio-mini-2025-12-15"
+                ]
+              }
+            ],
+            "description": "The Realtime model used for this session.\n"
+          },
+          "instructions": {
+            "type": "string",
+            "description": "The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. \"be extremely succinct\", \"act friendly\", \"here are examples of good responses\") and on audio behavior (e.g. \"talk quickly\", \"inject emotion into your voice\", \"laugh frequently\"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior.\n\nNote that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session.\n"
+          },
+          "audio": {
+            "type": "object",
+            "description": "Configuration for input and output audio.\n",
+            "properties": {
+              "input": {
+                "type": "object",
+                "properties": {
+                  "format": {
+                    "$ref": "#/components/schemas/RealtimeAudioFormats",
+                    "description": "The format of the input audio."
+                  },
+                  "transcription": {
+                    "description": "Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://developers.openai.com/api/reference/resources/audio/subresources/transcriptions/methods/create) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service.\n",
+                    "$ref": "#/components/schemas/AudioTranscriptionResponse"
+                  },
+                  "noise_reduction": {
+                    "type": "object",
+                    "default": null,
+                    "description": "Configuration for input audio noise reduction. This can be set to `null` to turn off.\nNoise reduction filters audio added to the input audio buffer before it is sent to VAD and the model.\nFiltering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.\n",
+                    "properties": {
+                      "type": {
+                        "$ref": "#/components/schemas/NoiseReductionType"
+                      }
+                    }
+                  },
+                  "turn_detection": {
+                    "$ref": "#/components/schemas/RealtimeTurnDetection"
+                  }
+                }
+              },
+              "output": {
+                "type": "object",
+                "properties": {
+                  "format": {
+                    "$ref": "#/components/schemas/RealtimeAudioFormats",
+                    "description": "The format of the output audio."
+                  },
+                  "voice": {
+                    "$ref": "#/components/schemas/VoiceIdsShared",
+                    "default": "alloy",
+                    "description": "The voice the model uses to respond. Voice cannot be changed during the\nsession once the model has responded with audio at least once. Current\nvoice options are `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`,\n`shimmer`, `verse`, `marin`, and `cedar`. We recommend `marin` and `cedar` for\nbest quality.\n"
+                  },
+                  "speed": {
+                    "type": "number",
+                    "default": 1,
+                    "maximum": 1.5,
+                    "minimum": 0.25,
+                    "description": "The speed of the model's spoken response as a multiple of the original speed.\n1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress.\n\nThis parameter is a post-processing adjustment to the audio after it is generated, it's\nalso possible to prompt the model to speak faster or slower.\n"
+                  }
+                }
+              }
+            }
+          },
+          "include": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "enum": [
+                "item.input_audio_transcription.logprobs"
+              ]
+            },
+            "description": "Additional fields to include in server outputs.\n\n`item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription.\n"
+          },
+          "tracing": {
+            "anyOf": [
+              {
+                "title": "Tracing Configuration",
+                "default": null,
+                "description": "Realtime API can write session traces to the [Traces Dashboard](https://platform.openai.com/logs?api=traces). Set to null to disable tracing. Once\ntracing is enabled for a session, the configuration cannot be modified.\n\n`auto` will create a trace for the session with default values for the\nworkflow name, group id, and metadata.\n",
+                "oneOf": [
+                  {
+                    "type": "string",
+                    "title": "auto",
+                    "default": "auto",
+                    "description": "Enables tracing and sets default values for tracing configuration options. Always `auto`.\n",
+                    "enum": [
+                      "auto"
+                    ],
+                    "x-stainless-const": true
+                  },
+                  {
+                    "type": "object",
+                    "title": "Tracing Configuration",
+                    "description": "Granular configuration for tracing.\n",
+                    "properties": {
+                      "workflow_name": {
+                        "type": "string",
+                        "description": "The name of the workflow to attach to this trace. This is used to\nname the trace in the Traces Dashboard.\n"
+                      },
+                      "group_id": {
+                        "type": "string",
+                        "description": "The group id to attach to this trace to enable filtering and\ngrouping in the Traces Dashboard.\n"
+                      },
+                      "metadata": {
+                        "type": "object",
+                        "description": "The arbitrary metadata to attach to this trace to enable\nfiltering in the Traces Dashboard.\n"
+                      }
+                    }
+                  }
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "tools": {
+            "type": "array",
+            "description": "Tools available to the model.",
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/RealtimeFunctionTool"
+                },
+                {
+                  "$ref": "#/components/schemas/MCPTool"
+                }
+              ]
+            }
+          },
+          "tool_choice": {
+            "description": "How the model chooses tools. Provide one of the string modes or force a specific\nfunction/MCP tool.\n",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/ToolChoiceOptions"
+              },
+              {
+                "$ref": "#/components/schemas/ToolChoiceFunction"
+              },
+              {
+                "$ref": "#/components/schemas/ToolChoiceMCP"
+              }
+            ],
+            "default": "auto"
+          },
+          "reasoning": {
+            "$ref": "#/components/schemas/RealtimeReasoning"
+          },
+          "max_output_tokens": {
+            "oneOf": [
+              {
+                "type": "integer"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "inf"
+                ],
+                "x-stainless-const": true
+              }
+            ],
+            "description": "Maximum number of output tokens for a single assistant response,\ninclusive of tool calls. Provide an integer between 1 and 4096 to\nlimit output tokens, or `inf` for the maximum available tokens for a\ngiven model. Defaults to `inf`.\n"
+          },
+          "truncation": {
+            "$ref": "#/components/schemas/RealtimeTruncation"
+          },
+          "prompt": {
+            "$ref": "#/components/schemas/Prompt"
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "object"
+        ],
+        "x-oaiMeta": {
+          "name": "The session object",
+          "group": "realtime"
+        }
+      },
+      "RealtimeTranscriptionSessionCreateRequest": {
+        "type": "object",
+        "title": "Realtime transcription session configuration",
+        "description": "Realtime transcription session object configuration.",
+        "properties": {
+          "turn_detection": {
+            "type": "object",
+            "description": "Configuration for turn detection. Can be set to `null` to turn off. Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "description": "Type of turn detection. Only `server_vad` is currently supported for transcription sessions.\n",
+                "enum": [
+                  "server_vad"
+                ]
+              },
+              "threshold": {
+                "type": "number",
+                "description": "Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A\nhigher threshold will require louder audio to activate the model, and\nthus might perform better in noisy environments.\n"
+              },
+              "prefix_padding_ms": {
+                "type": "integer",
+                "description": "Amount of audio to include before the VAD detected speech (in\nmilliseconds). Defaults to 300ms.\n"
+              },
+              "silence_duration_ms": {
+                "type": "integer",
+                "description": "Duration of silence to detect speech stop (in milliseconds). Defaults\nto 500ms. With shorter values the model will respond more quickly,\nbut may jump in on short pauses from the user.\n"
+              }
+            }
+          },
+          "input_audio_noise_reduction": {
+            "type": "object",
+            "default": null,
+            "description": "Configuration for input audio noise reduction. This can be set to `null` to turn off.\nNoise reduction filters audio added to the input audio buffer before it is sent to VAD and the model.\nFiltering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.\n",
+            "properties": {
+              "type": {
+                "$ref": "#/components/schemas/NoiseReductionType"
+              }
+            }
+          },
+          "input_audio_format": {
+            "type": "string",
+            "default": "pcm16",
+            "enum": [
+              "pcm16",
+              "g711_ulaw",
+              "g711_alaw"
+            ],
+            "description": "The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.\nFor `pcm16`, input audio must be 16-bit PCM at a 24kHz sample rate,\nsingle channel (mono), and little-endian byte order.\n"
+          },
+          "input_audio_transcription": {
+            "description": "Configuration for input audio transcription. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service.\n",
+            "$ref": "#/components/schemas/AudioTranscription"
+          },
+          "include": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "enum": [
+                "item.input_audio_transcription.logprobs"
+              ]
+            },
+            "description": "The set of items to include in the transcription. Current available items are:\n`item.input_audio_transcription.logprobs`\n"
+          }
+        }
+      },
+      "RealtimeTranscriptionSessionCreateRequestGA": {
+        "type": "object",
+        "title": "Realtime transcription session configuration",
+        "description": "Realtime transcription session object configuration.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of session to create. Always `transcription` for transcription sessions.\n",
+            "enum": [
+              "transcription"
+            ],
+            "x-stainless-const": true
+          },
+          "audio": {
+            "type": "object",
+            "description": "Configuration for input and output audio.\n",
+            "properties": {
+              "input": {
+                "type": "object",
+                "properties": {
+                  "format": {
+                    "$ref": "#/components/schemas/RealtimeAudioFormats"
+                  },
+                  "transcription": {
+                    "description": "Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://developers.openai.com/api/reference/resources/audio/subresources/transcriptions/methods/create) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service.\n",
+                    "$ref": "#/components/schemas/AudioTranscription"
+                  },
+                  "noise_reduction": {
+                    "type": "object",
+                    "default": null,
+                    "description": "Configuration for input audio noise reduction. This can be set to `null` to turn off.\nNoise reduction filters audio added to the input audio buffer before it is sent to VAD and the model.\nFiltering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.\n",
+                    "properties": {
+                      "type": {
+                        "$ref": "#/components/schemas/NoiseReductionType"
+                      }
+                    }
+                  },
+                  "turn_detection": {
+                    "$ref": "#/components/schemas/RealtimeTurnDetection"
+                  }
+                }
+              }
+            }
+          },
+          "include": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "enum": [
+                "item.input_audio_transcription.logprobs"
+              ]
+            },
+            "description": "Additional fields to include in server outputs.\n\n`item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription.\n"
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "RealtimeTranscriptionSessionCreateResponse": {
+        "type": "object",
+        "description": "A new Realtime transcription session configuration.\n\nWhen a session is created on the server via REST API, the session object\nalso contains an ephemeral key. Default TTL for keys is 10 minutes. This\nproperty is not present when a session is updated via the WebSocket API.\n",
+        "properties": {
+          "client_secret": {
+            "type": "object",
+            "description": "Ephemeral key returned by the API. Only present when the session is\ncreated on the server via REST API.\n",
+            "properties": {
+              "value": {
+                "type": "string",
+                "description": "Ephemeral key usable in client environments to authenticate connections\nto the Realtime API. Use this in client-side environments rather than\na standard API token, which should only be used server-side.\n"
+              },
+              "expires_at": {
+                "type": "integer",
+                "format": "unixtime",
+                "description": "Timestamp for when the token expires. Currently, all tokens expire\nafter one minute.\n"
+              }
+            },
+            "required": [
+              "value",
+              "expires_at"
+            ]
+          },
+          "modalities": {
+            "description": "The set of modalities the model can respond with. To disable audio,\nset this to [\"text\"].\n",
+            "items": {
+              "type": "string",
+              "enum": [
+                "text",
+                "audio"
+              ]
+            }
+          },
+          "input_audio_format": {
+            "type": "string",
+            "description": "The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.\n"
+          },
+          "input_audio_transcription": {
+            "description": "Configuration of the transcription model.\n",
+            "$ref": "#/components/schemas/AudioTranscriptionResponse"
+          },
+          "turn_detection": {
+            "type": "object",
+            "description": "Configuration for turn detection. Can be set to `null` to turn off. Server\nVAD means that the model will detect the start and end of speech based on\naudio volume and respond at the end of user speech.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "description": "Type of turn detection, only `server_vad` is currently supported.\n"
+              },
+              "threshold": {
+                "type": "number",
+                "description": "Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A\nhigher threshold will require louder audio to activate the model, and\nthus might perform better in noisy environments.\n"
+              },
+              "prefix_padding_ms": {
+                "type": "integer",
+                "description": "Amount of audio to include before the VAD detected speech (in\nmilliseconds). Defaults to 300ms.\n"
+              },
+              "silence_duration_ms": {
+                "type": "integer",
+                "description": "Duration of silence to detect speech stop (in milliseconds). Defaults\nto 500ms. With shorter values the model will respond more quickly,\nbut may jump in on short pauses from the user.\n"
+              }
+            }
+          }
+        },
+        "required": [
+          "client_secret"
+        ],
+        "x-oaiMeta": {
+          "name": "The transcription session object",
+          "group": "realtime",
+          "example": "{\n  \"id\": \"sess_BBwZc7cFV3XizEyKGDCGL\",\n  \"object\": \"realtime.transcription_session\",\n  \"expires_at\": 1742188264,\n  \"modalities\": [\"audio\", \"text\"],\n  \"turn_detection\": {\n    \"type\": \"server_vad\",\n    \"threshold\": 0.5,\n    \"prefix_padding_ms\": 300,\n    \"silence_duration_ms\": 200\n  },\n  \"input_audio_format\": \"pcm16\",\n  \"input_audio_transcription\": {\n    \"model\": \"gpt-4o-transcribe\",\n    \"language\": null,\n    \"prompt\": \"\"\n  },\n  \"client_secret\": null\n}\n"
+        }
+      },
+      "RealtimeTranscriptionSessionCreateResponseGA": {
+        "type": "object",
+        "title": "Realtime transcription session configuration object",
+        "description": "A Realtime transcription session configuration object.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of session. Always `transcription` for transcription sessions.\n",
+            "enum": [
+              "transcription"
+            ],
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "Unique identifier for the session that looks like `sess_1234567890abcdef`.\n"
+          },
+          "object": {
+            "type": "string",
+            "description": "The object type. Always `realtime.transcription_session`."
+          },
+          "expires_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Expiration timestamp for the session, in seconds since epoch."
+          },
+          "include": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "enum": [
+                "item.input_audio_transcription.logprobs"
+              ]
+            },
+            "description": "Additional fields to include in server outputs.\n- `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription.\n"
+          },
+          "audio": {
+            "type": "object",
+            "description": "Configuration for input audio for the session.\n",
+            "properties": {
+              "input": {
+                "type": "object",
+                "properties": {
+                  "format": {
+                    "$ref": "#/components/schemas/RealtimeAudioFormats"
+                  },
+                  "transcription": {
+                    "description": "Configuration of the transcription model.\n",
+                    "$ref": "#/components/schemas/AudioTranscriptionResponse"
+                  },
+                  "noise_reduction": {
+                    "type": "object",
+                    "description": "Configuration for input audio noise reduction.\n",
+                    "properties": {
+                      "type": {
+                        "$ref": "#/components/schemas/NoiseReductionType"
+                      }
+                    }
+                  },
+                  "turn_detection": {
+                    "description": "Configuration for turn detection. For `gpt-realtime-whisper`, this must be `null`; VAD is not supported.\n",
+                    "anyOf": [
+                      {
+                        "type": "object",
+                        "description": "Configuration for turn detection. Can be set to `null` to turn off. Server\nVAD means that the model will detect the start and end of speech based on\naudio volume and respond at the end of user speech. For `gpt-realtime-whisper`, this must be `null`; VAD is not supported.\n",
+                        "properties": {
+                          "type": {
+                            "type": "string",
+                            "description": "Type of turn detection, only `server_vad` is currently supported.\n"
+                          },
+                          "threshold": {
+                            "type": "number",
+                            "description": "Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A\nhigher threshold will require louder audio to activate the model, and\nthus might perform better in noisy environments.\n"
+                          },
+                          "prefix_padding_ms": {
+                            "type": "integer",
+                            "description": "Amount of audio to include before the VAD detected speech (in\nmilliseconds). Defaults to 300ms.\n"
+                          },
+                          "silence_duration_ms": {
+                            "type": "integer",
+                            "description": "Duration of silence to detect speech stop (in milliseconds). Defaults\nto 500ms. With shorter values the model will respond more quickly,\nbut may jump in on short pauses from the user.\n"
+                          }
+                        }
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ]
+                  }
+                }
+              }
+            }
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "object"
+        ],
+        "x-oaiMeta": {
+          "name": "The transcription session object",
+          "group": "realtime",
+          "example": "{\n  \"id\": \"sess_BBwZc7cFV3XizEyKGDCGL\",\n  \"type\": \"transcription\",\n  \"object\": \"realtime.transcription_session\",\n  \"expires_at\": 1742188264,\n  \"include\": [\"item.input_audio_transcription.logprobs\"],\n  \"audio\": {\n    \"input\": {\n      \"format\": \"pcm16\",\n      \"transcription\": {\n        \"model\": \"gpt-4o-transcribe\",\n        \"language\": null,\n        \"prompt\": \"\"\n      },\n      \"noise_reduction\": null,\n      \"turn_detection\": {\n        \"type\": \"server_vad\",\n        \"threshold\": 0.5,\n        \"prefix_padding_ms\": 300,\n        \"silence_duration_ms\": 200\n      }\n    }\n  }\n}\n"
+        }
+      },
+      "RealtimeTranslationClientEvent": {
+        "discriminator": {
+          "propertyName": "type"
+        },
+        "description": "A Realtime translation client event.\n",
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/RealtimeTranslationClientEventSessionUpdate"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeTranslationClientEventInputAudioBufferAppend"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeTranslationClientEventSessionClose"
+          }
+        ]
+      },
+      "RealtimeTranslationClientEventInputAudioBufferAppend": {
+        "type": "object",
+        "description": "Send this event to append audio bytes to the translation session input audio buffer.\n\nWebSocket translation sessions accept base64-encoded 24 kHz PCM16 mono\nlittle-endian raw audio bytes. Unsupported websocket audio formats return a\nvalidation error because lower-quality audio materially degrades translation\nquality.\n\nTranslation consumes 200 ms engine frames. For best realtime behavior, append\naudio in 200 ms chunks. If a chunk is shorter, the server buffers it until it\nhas enough audio for one frame. If a chunk is longer, the server splits it into\n200 ms frames and enqueues them back-to-back.\n\nKeep appending silence while the session is active. If a client stops sending\naudio and later resumes, model time treats the resumed audio as contiguous with\nthe previous audio rather than as a real-world pause.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "maxLength": 512,
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "session.input_audio_buffer.append"
+            ],
+            "description": "The event type, must be `session.input_audio_buffer.append`.",
+            "x-stainless-const": true
+          },
+          "audio": {
+            "type": "string",
+            "description": "Base64-encoded 24 kHz PCM16 mono audio bytes."
+          }
+        },
+        "required": [
+          "type",
+          "audio"
+        ],
+        "x-oaiMeta": {
+          "name": "session.input_audio_buffer.append",
+          "group": "realtime",
+          "example": "{\n  \"event_id\": \"event_456\",\n  \"type\": \"session.input_audio_buffer.append\",\n  \"audio\": \"Base64EncodedAudioData\"\n}\n"
+        }
+      },
+      "RealtimeTranslationClientEventSessionClose": {
+        "type": "object",
+        "description": "Gracefully close the realtime translation session. The server flushes pending\ninput audio and emits any remaining translated output before closing the\nsession.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "maxLength": 512,
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "session.close"
+            ],
+            "description": "The event type, must be `session.close`.",
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "x-oaiMeta": {
+          "name": "session.close",
+          "group": "realtime",
+          "example": "{\n  \"event_id\": \"event_789\",\n  \"type\": \"session.close\"\n}\n"
+        }
+      },
+      "RealtimeTranslationClientEventSessionUpdate": {
+        "type": "object",
+        "description": "Send this event to update the translation session configuration. Translation\nsessions support updates to `audio.output.language`, `audio.input.transcription`,\nand `audio.input.noise_reduction`.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "maxLength": 512,
+            "description": "Optional client-generated ID used to identify this event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "session.update"
+            ],
+            "description": "The event type, must be `session.update`.",
+            "x-stainless-const": true
+          },
+          "session": {
+            "$ref": "#/components/schemas/RealtimeTranslationSessionUpdateRequest",
+            "description": "Translation session fields to update. The session `type` and `model` are set\nat creation and cannot be changed with `session.update`.\n"
+          }
+        },
+        "required": [
+          "type",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "name": "session.update",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"session.update\",\n  \"session\": {\n    \"audio\": {\n      \"input\": {\n        \"transcription\": {\n          \"model\": \"gpt-realtime-whisper\"\n        },\n        \"noise_reduction\": null\n      },\n      \"output\": {\n        \"language\": \"es\"\n      }\n    }\n  }\n}\n"
+        }
+      },
+      "RealtimeTranslationClientSecretCreateRequest": {
+        "type": "object",
+        "title": "Realtime translation client secret creation request",
+        "description": "Create a translation session and client secret for the Realtime API.\n",
+        "properties": {
+          "expires_after": {
+            "type": "object",
+            "title": "Client secret expiration",
+            "description": "Configuration for the client secret expiration. Expiration refers to the time after which\na client secret will no longer be valid for creating sessions. The session itself may\ncontinue after that time once started. A secret can be used to create multiple sessions\nuntil it expires.\n",
+            "properties": {
+              "anchor": {
+                "type": "string",
+                "enum": [
+                  "created_at"
+                ],
+                "description": "The anchor point for the client secret expiration, meaning that `seconds` will be added to the `created_at` time of the client secret to produce an expiration timestamp. Only `created_at` is currently supported.\n",
+                "default": "created_at",
+                "x-stainless-const": true
+              },
+              "seconds": {
+                "type": "integer",
+                "format": "int64",
+                "description": "The number of seconds from the anchor point to the expiration. Select a value between `10` and `7200` (2 hours). This default to 600 seconds (10 minutes) if not specified.\n",
+                "minimum": 10,
+                "maximum": 7200,
+                "default": 600
+              }
+            }
+          },
+          "session": {
+            "$ref": "#/components/schemas/RealtimeTranslationSessionCreateRequest"
+          }
+        },
+        "required": [
+          "session"
+        ]
+      },
+      "RealtimeTranslationClientSecretCreateResponse": {
+        "type": "object",
+        "title": "Realtime translation session and client secret",
+        "description": "Response from creating a translation session and client secret for the Realtime API.\n",
+        "properties": {
+          "value": {
+            "type": "string",
+            "description": "The generated client secret value."
+          },
+          "expires_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Expiration timestamp for the client secret, in seconds since epoch."
+          },
+          "session": {
+            "$ref": "#/components/schemas/RealtimeTranslationSession"
+          }
+        },
+        "required": [
+          "value",
+          "expires_at",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "name": "Translation session response object",
+          "group": "realtime",
+          "example": "{\n  \"value\": \"ek_68af296e8e408191a1120ab6383263c2\",\n  \"expires_at\": 1756310470,\n  \"session\": {\n    \"id\": \"sess_C9CiUVUzUzYIssh3ELY1d\",\n    \"type\": \"translation\",\n    \"expires_at\": 1756310470,\n    \"model\": \"gpt-realtime-translate\",\n    \"audio\": {\n      \"input\": {\n        \"transcription\": null,\n        \"noise_reduction\": null\n      },\n      \"output\": {\n        \"language\": \"es\"\n      }\n    }\n  }\n}\n"
+        }
+      },
+      "RealtimeTranslationServerEvent": {
+        "discriminator": {
+          "propertyName": "type"
+        },
+        "description": "A Realtime translation server event.\n",
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/RealtimeServerEventError"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeTranslationServerEventSessionCreated"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeTranslationServerEventSessionUpdated"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeTranslationServerEventSessionClosed"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeTranslationServerEventSessionInputTranscriptDelta"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeTranslationServerEventSessionOutputTranscriptDelta"
+          },
+          {
+            "$ref": "#/components/schemas/RealtimeTranslationServerEventSessionOutputAudioDelta"
+          }
+        ]
+      },
+      "RealtimeTranslationServerEventSessionClosed": {
+        "type": "object",
+        "description": "Returned when a realtime translation session is closed.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "session.closed"
+            ],
+            "description": "The event type, must be `session.closed`.",
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "event_id",
+          "type"
+        ],
+        "x-oaiMeta": {
+          "name": "session.closed",
+          "group": "realtime",
+          "example": "{\n  \"event_id\": \"event_987\",\n  \"type\": \"session.closed\"\n}\n"
+        }
+      },
+      "RealtimeTranslationServerEventSessionCreated": {
+        "type": "object",
+        "description": "Returned when a translation session is created. Emitted automatically when a\nnew connection is established as the first server event. This event contains\nthe default translation session configuration.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "session.created"
+            ],
+            "description": "The event type, must be `session.created`.",
+            "x-stainless-const": true
+          },
+          "session": {
+            "$ref": "#/components/schemas/RealtimeTranslationSession",
+            "description": "The translation session configuration."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "name": "session.created",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"session.created\",\n  \"event_id\": \"event_123\",\n  \"session\": {\n    \"id\": \"sess_123\",\n    \"type\": \"translation\",\n    \"model\": \"gpt-realtime-translate\",\n    \"expires_at\": 1714857600,\n    \"audio\": {\n      \"input\": {\n        \"transcription\": {\n          \"model\": \"gpt-realtime-whisper\",\n          \"language\": \"en\"\n        },\n        \"noise_reduction\": {\n          \"type\": \"near_field\"\n        }\n      },\n      \"output\": {\n        \"language\": \"fr\"\n      }\n    }\n  }\n}\n"
+        }
+      },
+      "RealtimeTranslationServerEventSessionInputTranscriptDelta": {
+        "type": "object",
+        "description": "Returned when optional source-language transcript text is available. This event\nis emitted only when `audio.input.transcription` is configured.\n\nTranscript deltas are append-only text fragments. Clients should not insert\nunconditional spaces between deltas.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "session.input_transcript.delta"
+            ],
+            "description": "The event type, must be `session.input_transcript.delta`.",
+            "x-stainless-const": true
+          },
+          "delta": {
+            "type": "string",
+            "description": "Append-only source-language transcript text."
+          },
+          "elapsed_ms": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "Timing metadata for stream alignment, derived from the translation frame\nwhen available. It advances in 200 ms increments, but multiple transcript\ndeltas may share the same `elapsed_ms`. Treat it as alignment metadata,\nnot a unique transcript-delta identifier.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "delta"
+        ],
+        "x-oaiMeta": {
+          "name": "session.input_transcript.delta",
+          "group": "realtime",
+          "example": "{\n  \"event_id\": \"event_125\",\n  \"type\": \"session.input_transcript.delta\",\n  \"delta\": \" hear\",\n  \"elapsed_ms\": 1200\n}\n"
+        }
+      },
+      "RealtimeTranslationServerEventSessionOutputAudioDelta": {
+        "type": "object",
+        "description": "Returned when translated output audio is available. The `delta` contains a\nPCM16 audio chunk whose length can vary. Clients should decode and queue the\ncomplete delta instead of assuming a fixed byte or sample count.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "session.output_audio.delta"
+            ],
+            "description": "The event type, must be `session.output_audio.delta`.",
+            "x-stainless-const": true
+          },
+          "delta": {
+            "type": "string",
+            "description": "Base64-encoded translated audio data."
+          },
+          "sample_rate": {
+            "type": "integer",
+            "description": "Sample rate of the audio delta.",
+            "default": 24000
+          },
+          "channels": {
+            "type": "integer",
+            "description": "Number of audio channels.",
+            "default": 1
+          },
+          "format": {
+            "type": "string",
+            "enum": [
+              "pcm16"
+            ],
+            "description": "Audio encoding for `delta`.",
+            "x-stainless-const": true
+          },
+          "elapsed_ms": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "Timing metadata for stream alignment, derived from the translation frame\nwhen available. Treat `elapsed_ms` as alignment metadata, not a unique\nevent identifier.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "delta"
+        ],
+        "x-oaiMeta": {
+          "name": "session.output_audio.delta",
+          "group": "realtime",
+          "example": "{\n  \"event_id\": \"event_123\",\n  \"type\": \"session.output_audio.delta\",\n  \"delta\": \"Base64EncodedAudioDelta\",\n  \"sample_rate\": 24000,\n  \"channels\": 1,\n  \"format\": \"pcm16\",\n  \"elapsed_ms\": 1200\n}\n"
+        }
+      },
+      "RealtimeTranslationServerEventSessionOutputTranscriptDelta": {
+        "type": "object",
+        "description": "Returned when translated transcript text is available.\n\nTranscript deltas are append-only text fragments. Clients should not insert\nunconditional spaces between deltas.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "session.output_transcript.delta"
+            ],
+            "description": "The event type, must be `session.output_transcript.delta`.",
+            "x-stainless-const": true
+          },
+          "delta": {
+            "type": "string",
+            "description": "Append-only transcript text for the translated output audio."
+          },
+          "elapsed_ms": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "Timing metadata for stream alignment, derived from the translation frame\nwhen available. It advances in 200 ms increments, but multiple transcript\ndeltas may share the same `elapsed_ms`. Treat it as alignment metadata,\nnot a unique transcript-delta identifier.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "delta"
+        ],
+        "x-oaiMeta": {
+          "name": "session.output_transcript.delta",
+          "group": "realtime",
+          "example": "{\n  \"event_id\": \"event_124\",\n  \"type\": \"session.output_transcript.delta\",\n  \"delta\": \" escuch\",\n  \"elapsed_ms\": 1200\n}\n"
+        }
+      },
+      "RealtimeTranslationServerEventSessionUpdated": {
+        "type": "object",
+        "description": "Returned when a translation session is updated with a `session.update` event,\nunless there is an error.\n",
+        "properties": {
+          "event_id": {
+            "type": "string",
+            "description": "The unique ID of the server event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "session.updated"
+            ],
+            "description": "The event type, must be `session.updated`.",
+            "x-stainless-const": true
+          },
+          "session": {
+            "$ref": "#/components/schemas/RealtimeTranslationSession",
+            "description": "The translation session configuration."
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "name": "session.updated",
+          "group": "realtime",
+          "example": "{\n  \"type\": \"session.updated\",\n  \"event_id\": \"event_124\",\n  \"session\": {\n    \"id\": \"sess_123\",\n    \"type\": \"translation\",\n    \"model\": \"gpt-realtime-translate\",\n    \"expires_at\": 1714857600,\n    \"audio\": {\n      \"input\": {\n        \"transcription\": {\n          \"model\": \"gpt-realtime-whisper\",\n          \"language\": \"en\"\n        },\n        \"noise_reduction\": {\n          \"type\": \"near_field\"\n        }\n      },\n      \"output\": {\n        \"language\": \"es\"\n      }\n    }\n  }\n}\n"
+        }
+      },
+      "RealtimeTranslationSession": {
+        "type": "object",
+        "title": "Realtime translation session",
+        "description": "A Realtime translation session. Translation sessions continuously translate input\naudio into the configured output language.\n",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Unique identifier for the session that looks like `sess_1234567890abcdef`.\n"
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "translation"
+            ],
+            "description": "The session type. Always `translation` for Realtime translation sessions.\n",
+            "x-stainless-const": true
+          },
+          "expires_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Expiration timestamp for the session, in seconds since epoch."
+          },
+          "model": {
+            "type": "string",
+            "description": "The Realtime translation model used for this session. This field is set at\nsession creation and cannot be changed with `session.update`.\n"
+          },
+          "audio": {
+            "type": "object",
+            "description": "Configuration for translation input and output audio.\n",
+            "properties": {
+              "input": {
+                "type": "object",
+                "properties": {
+                  "transcription": {
+                    "anyOf": [
+                      {
+                        "type": "object",
+                        "description": "Optional source-language transcription. When configured, the server emits\n`session.input_transcript.delta` events. Translation itself still runs from\nthe input audio stream.\n",
+                        "properties": {
+                          "model": {
+                            "type": "string",
+                            "description": "The transcription model used for source transcript deltas."
+                          }
+                        },
+                        "required": [
+                          "model"
+                        ]
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ]
+                  },
+                  "noise_reduction": {
+                    "anyOf": [
+                      {
+                        "type": "object",
+                        "description": "Optional input noise reduction.\n",
+                        "properties": {
+                          "type": {
+                            "$ref": "#/components/schemas/NoiseReductionType"
+                          }
+                        },
+                        "required": [
+                          "type"
+                        ]
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ]
+                  }
+                }
+              },
+              "output": {
+                "type": "object",
+                "properties": {
+                  "language": {
+                    "type": "string",
+                    "description": "Target language for translated output audio and transcript deltas.\n"
+                  }
+                }
+              }
+            }
+          }
+        },
+        "required": [
+          "id",
+          "type",
+          "expires_at",
+          "model",
+          "audio"
+        ],
+        "x-oaiMeta": {
+          "name": "The translation session object",
+          "group": "realtime",
+          "example": "{\n  \"id\": \"sess_C9G5QPteg4UIbotdKLoYQ\",\n  \"type\": \"translation\",\n  \"expires_at\": 1756324625,\n  \"model\": \"gpt-realtime-translate\",\n  \"audio\": {\n    \"input\": {\n      \"transcription\": {\n        \"model\": \"gpt-realtime-whisper\"\n      },\n      \"noise_reduction\": null\n    },\n    \"output\": {\n      \"language\": \"es\"\n    }\n  }\n}\n"
+        }
+      },
+      "RealtimeTranslationSessionCreateRequest": {
+        "type": "object",
+        "title": "Realtime translation session configuration",
+        "description": "Realtime translation session configuration. Translation sessions stream source\naudio in and translated audio plus transcript deltas out continuously.\n",
+        "properties": {
+          "model": {
+            "type": "string",
+            "description": "The Realtime translation model used for this session.\n"
+          },
+          "audio": {
+            "type": "object",
+            "description": "Configuration for translation input and output audio.\n",
+            "properties": {
+              "input": {
+                "type": "object",
+                "properties": {
+                  "transcription": {
+                    "anyOf": [
+                      {
+                        "type": "object",
+                        "description": "Optional source-language transcription. When configured, the server emits\n`session.input_transcript.delta` events. Translation itself still runs from\nthe input audio stream.\n",
+                        "properties": {
+                          "model": {
+                            "type": "string",
+                            "description": "The transcription model to use for source transcript deltas."
+                          }
+                        },
+                        "required": [
+                          "model"
+                        ]
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ]
+                  },
+                  "noise_reduction": {
+                    "anyOf": [
+                      {
+                        "type": "object",
+                        "description": "Optional input noise reduction. Set to `null` to disable it.\n",
+                        "properties": {
+                          "type": {
+                            "$ref": "#/components/schemas/NoiseReductionType"
+                          }
+                        },
+                        "required": [
+                          "type"
+                        ]
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ]
+                  }
+                }
+              },
+              "output": {
+                "type": "object",
+                "properties": {
+                  "language": {
+                    "type": "string",
+                    "description": "Target language for translated output audio and transcript deltas.\n"
+                  }
+                }
+              }
+            }
+          }
+        },
+        "required": [
+          "model"
+        ]
+      },
+      "RealtimeTranslationSessionUpdateRequest": {
+        "type": "object",
+        "title": "Realtime translation session update",
+        "description": "Realtime translation session fields that can be updated with `session.update`.\n",
+        "properties": {
+          "audio": {
+            "type": "object",
+            "description": "Configuration for translation input and output audio.\n",
+            "properties": {
+              "input": {
+                "type": "object",
+                "properties": {
+                  "transcription": {
+                    "anyOf": [
+                      {
+                        "type": "object",
+                        "description": "Optional source-language transcription. When configured, the server emits\n`session.input_transcript.delta` events. Translation itself still runs from\nthe input audio stream.\n",
+                        "properties": {
+                          "model": {
+                            "type": "string",
+                            "description": "The transcription model to use for source transcript deltas."
+                          }
+                        },
+                        "required": [
+                          "model"
+                        ]
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ]
+                  },
+                  "noise_reduction": {
+                    "anyOf": [
+                      {
+                        "type": "object",
+                        "description": "Optional input noise reduction. Set to `null` to disable it.\n",
+                        "properties": {
+                          "type": {
+                            "$ref": "#/components/schemas/NoiseReductionType"
+                          }
+                        },
+                        "required": [
+                          "type"
+                        ]
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ]
+                  }
+                }
+              },
+              "output": {
+                "type": "object",
+                "properties": {
+                  "language": {
+                    "type": "string",
+                    "description": "Target language for translated output audio and transcript deltas.\n"
+                  }
+                }
+              }
+            }
+          }
+        }
+      },
+      "RealtimeTruncation": {
+        "title": "Realtime Truncation Controls",
+        "description": "When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs.\n\nClients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost.\n\nTruncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate.\n\nTruncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit.\n",
+        "oneOf": [
+          {
+            "type": "string",
+            "description": "The truncation strategy to use for the session. `auto` is the default truncation strategy. `disabled` will disable truncation and emit errors when the conversation exceeds the input token limit.",
+            "enum": [
+              "auto",
+              "disabled"
+            ]
+          },
+          {
+            "type": "object",
+            "title": "Retention ratio truncation",
+            "description": "Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage.",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "retention_ratio"
+                ],
+                "description": "Use retention ratio truncation.",
+                "x-stainless-const": true
+              },
+              "retention_ratio": {
+                "type": "number",
+                "description": "Fraction of post-instruction conversation tokens to retain (`0.0` - `1.0`) when the conversation exceeds the input token limit. Setting this to `0.8` means that messages will be dropped until 80% of the maximum allowed tokens are used. This helps reduce the frequency of truncations and improve cache rates.\n",
+                "minimum": 0,
+                "maximum": 1
+              },
+              "token_limits": {
+                "type": "object",
+                "description": "Optional custom token limits for this truncation strategy. If not provided, the model's default token limits will be used.",
+                "properties": {
+                  "post_instructions": {
+                    "type": "integer",
+                    "description": "Maximum tokens allowed in the conversation after instructions (which including tool definitions). For example, setting this to 5,000 would mean that truncation would occur when the conversation exceeds 5,000 tokens after instructions. This cannot be higher than the model's context window size minus the maximum output tokens.",
+                    "minimum": 0
+                  }
+                }
+              }
+            },
+            "required": [
+              "type",
+              "retention_ratio"
+            ]
+          }
+        ]
+      },
+      "RealtimeTurnDetection": {
+        "anyOf": [
+          {
+            "title": "Realtime Turn Detection",
+            "description": "Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response.\n\nServer VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech.\n\nSemantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with \"uhhm\", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency.\n\nFor `gpt-realtime-whisper` transcription sessions, turn detection must be\nset to `null`; VAD is not supported.\n",
+            "oneOf": [
+              {
+                "type": "object",
+                "title": "Server VAD",
+                "description": "Server-side voice activity detection (VAD) which flips on when user speech is detected and off after a period of silence.",
+                "required": [
+                  "type"
+                ],
+                "properties": {
+                  "type": {
+                    "type": "string",
+                    "default": "server_vad",
+                    "const": "server_vad",
+                    "description": "Type of turn detection, `server_vad` to turn on simple Server VAD.\n"
+                  },
+                  "threshold": {
+                    "type": "number",
+                    "description": "Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A\nhigher threshold will require louder audio to activate the model, and\nthus might perform better in noisy environments.\n"
+                  },
+                  "prefix_padding_ms": {
+                    "type": "integer",
+                    "description": "Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in\nmilliseconds). Defaults to 300ms.\n"
+                  },
+                  "silence_duration_ms": {
+                    "type": "integer",
+                    "description": "Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults\nto 500ms. With shorter values the model will respond more quickly,\nbut may jump in on short pauses from the user.\n"
+                  },
+                  "create_response": {
+                    "type": "boolean",
+                    "default": true,
+                    "description": "Whether or not to automatically generate a response when a VAD stop event occurs. If `interrupt_response` is set to `false` this may fail to create a response if the model is already responding.\n\nIf both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted.\n"
+                  },
+                  "interrupt_response": {
+                    "type": "boolean",
+                    "default": true,
+                    "description": "Whether or not to automatically interrupt (cancel) any ongoing response with output to the default\nconversation (i.e. `conversation` of `auto`) when a VAD start event occurs. If `true` then the response will be cancelled, otherwise it will continue until complete.\n\nIf both `create_response` and `interrupt_response` are set to `false`, the model will never respond automatically but VAD events will still be emitted.\n"
+                  },
+                  "idle_timeout_ms": {
+                    "anyOf": [
+                      {
+                        "type": "integer",
+                        "minimum": 5000,
+                        "maximum": 30000,
+                        "description": "Optional timeout after which a model response will be triggered automatically. This is\nuseful for situations in which a long pause from the user is unexpected, such as a phone\ncall. The model will effectively prompt the user to continue the conversation based\non the current context.\n\nThe timeout value will be applied after the last model response's audio has finished playing,\ni.e. it's set to the `response.done` time plus audio playback duration.\n\nAn `input_audio_buffer.timeout_triggered` event (plus events\nassociated with the Response) will be emitted when the timeout is reached.\nIdle timeout is currently only supported for `server_vad` mode.\n"
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ]
+                  }
+                }
+              },
+              {
+                "type": "object",
+                "title": "Semantic VAD",
+                "description": "Server-side semantic turn detection which uses a model to determine when the user has finished speaking.",
+                "required": [
+                  "type"
+                ],
+                "properties": {
+                  "type": {
+                    "type": "string",
+                    "const": "semantic_vad",
+                    "description": "Type of turn detection, `semantic_vad` to turn on Semantic VAD.\n"
+                  },
+                  "eagerness": {
+                    "type": "string",
+                    "default": "auto",
+                    "enum": [
+                      "low",
+                      "medium",
+                      "high",
+                      "auto"
+                    ],
+                    "description": "Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`, and `high` have max timeouts of 8s, 4s, and 2s respectively.\n"
+                  },
+                  "create_response": {
+                    "type": "boolean",
+                    "default": true,
+                    "description": "Whether or not to automatically generate a response when a VAD stop event occurs.\n"
+                  },
+                  "interrupt_response": {
+                    "type": "boolean",
+                    "default": true,
+                    "description": "Whether or not to automatically interrupt any ongoing response with output to the default\nconversation (i.e. `conversation` of `auto`) when a VAD start event occurs.\n"
+                  }
+                }
+              }
+            ],
+            "discriminator": {
+              "propertyName": "type"
+            }
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "Reasoning": {
+        "type": "object",
+        "description": "Configuration options for\n[reasoning models](https://developers.openai.com/api/docs/guides/reasoning).\n",
+        "title": "Reasoning",
+        "properties": {
+          "mode": {
+            "$ref": "#/components/schemas/ReasoningModeEnum",
+            "description": "Controls the reasoning execution mode for the request.\n\nWhen returned on a response, this is the effective execution mode.\n"
+          },
+          "effort": {
+            "$ref": "#/components/schemas/ReasoningEffort"
+          },
+          "summary": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "A summary of the reasoning performed by the model. This can be\nuseful for debugging and understanding the model's reasoning process.\nOne of `auto`, `concise`, or `detailed`.\n\n`concise` is supported for `computer-use-preview` models and all reasoning models after `gpt-5`.\n",
+                "enum": [
+                  "auto",
+                  "concise",
+                  "detailed"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "context": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Controls which reasoning items are rendered back to the model on later turns.\nIf omitted or set to `auto`, the model determines the context mode. The\n`gpt-5.6` model family defaults to `all_turns`; earlier models default to\n`current_turn`.\n\nWhen returned on a response, this is the effective reasoning context mode\nused for the response.\n",
+                "enum": [
+                  "auto",
+                  "current_turn",
+                  "all_turns"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "generate_summary": {
+            "anyOf": [
+              {
+                "type": "string",
+                "deprecated": true,
+                "description": "**Deprecated:** use `summary` instead.\n\nA summary of the reasoning performed by the model. This can be\nuseful for debugging and understanding the model's reasoning process.\nOne of `auto`, `concise`, or `detailed`.\n",
+                "enum": [
+                  "auto",
+                  "concise",
+                  "detailed"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        }
+      },
+      "ReasoningEffort": {
+        "anyOf": [
+          {
+            "type": "string",
+            "enum": [
+              "none",
+              "minimal",
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max"
+            ],
+            "default": "medium",
+            "description": "Constrains effort on reasoning for reasoning models. Currently supported\nvalues are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`.\nReducing reasoning effort can result in faster responses and fewer tokens\nused on reasoning in a response. Not all reasoning models support every\nvalue. See the\n[reasoning guide](https://developers.openai.com/api/docs/guides/reasoning)\nfor model-specific support.\n"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "ReasoningItem": {
+        "type": "object",
+        "description": "A description of the chain of thought used by a reasoning model while generating\na response. Be sure to include these items in your `input` to the Responses API\nfor subsequent turns of a conversation if you are manually\n[managing context](https://developers.openai.com/api/docs/guides/conversation-state).\n",
+        "title": "Reasoning",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the object. Always `reasoning`.\n",
+            "enum": [
+              "reasoning"
+            ],
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique identifier of the reasoning content.\n"
+          },
+          "encrypted_content": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The encrypted content of the reasoning item. This is populated by default\nfor reasoning items returned by `POST /v1/responses` and WebSocket\n`response.create` requests.\n\nWhen streaming, use the completed reasoning item and its\n`encrypted_content` from the `response.output_item.done` event in\nsubsequent requests. The `encrypted_content` in\n`response.output_item.added` may be incomplete. This is especially\nimportant when `store` is `false` or when using Zero Data Retention.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "summary": {
+            "type": "array",
+            "description": "Reasoning summary content.\n",
+            "items": {
+              "$ref": "#/components/schemas/SummaryTextContent"
+            }
+          },
+          "content": {
+            "type": "array",
+            "description": "Reasoning text content.\n",
+            "items": {
+              "$ref": "#/components/schemas/ReasoningTextContent"
+            }
+          },
+          "status": {
+            "type": "string",
+            "description": "The status of the item. One of `in_progress`, `completed`, or\n`incomplete`. Populated when items are returned via API.\n",
+            "enum": [
+              "in_progress",
+              "completed",
+              "incomplete"
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "summary",
+          "type"
+        ]
+      },
+      "Response": {
+        "title": "The response object",
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/ModelResponseProperties"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseProperties"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "service_tier": {
+                "$ref": "#/components/schemas/ServiceTierResponses"
+              },
+              "truncation": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "The truncation strategy to use for the model response.\n- `auto`: If the input to this Response exceeds\n  the model's context window size, the model will truncate the\n  response to fit the context window by dropping items from the beginning of the conversation.\n- `disabled` (default): If the input size will exceed the context window\n  size for a model, the request will fail with a 400 error.\n",
+                    "enum": [
+                      "auto",
+                      "disabled"
+                    ],
+                    "default": "disabled"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "id": {
+                "type": "string",
+                "description": "Unique identifier for this Response.\n"
+              },
+              "object": {
+                "type": "string",
+                "description": "The object type of this resource - always set to `response`.\n",
+                "enum": [
+                  "response"
+                ],
+                "x-stainless-const": true
+              },
+              "status": {
+                "type": "string",
+                "description": "The status of the response generation. One of `completed`, `failed`,\n`in_progress`, `cancelled`, `queued`, or `incomplete`.\n",
+                "enum": [
+                  "completed",
+                  "failed",
+                  "in_progress",
+                  "cancelled",
+                  "queued",
+                  "incomplete"
+                ]
+              },
+              "created_at": {
+                "type": "number",
+                "format": "unixtime",
+                "description": "Unix timestamp (in seconds) of when this Response was created.\n"
+              },
+              "completed_at": {
+                "anyOf": [
+                  {
+                    "type": "number",
+                    "format": "unixtime",
+                    "description": "Unix timestamp (in seconds) of when this Response was completed.\nOnly present when the status is `completed`.\n"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "error": {
+                "$ref": "#/components/schemas/ResponseError"
+              },
+              "incomplete_details": {
+                "anyOf": [
+                  {
+                    "type": "object",
+                    "description": "Details about why the response is incomplete.\n",
+                    "properties": {
+                      "reason": {
+                        "type": "string",
+                        "description": "The reason why the response is incomplete. `steered` means\nthe response stopped at a safe output boundary after a\nWebSocket `response.steer` event. The server can then create\na successor response automatically with the queued input.\n",
+                        "enum": [
+                          "max_output_tokens",
+                          "max_messages",
+                          "content_filter",
+                          "steered"
+                        ]
+                      }
+                    }
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "output": {
+                "type": "array",
+                "description": "An array of content items generated by the model.\n\n- The length and order of items in the `output` array is dependent\n  on the model's response.\n- Rather than accessing the first item in the `output` array and\n  assuming it's an `assistant` message with the content generated by\n  the model, you might consider using the `output_text` property where\n  supported in SDKs.\n",
+                "items": {
+                  "$ref": "#/components/schemas/OutputItem"
+                }
+              },
+              "reasoning": {
+                "anyOf": [
+                  {
+                    "$ref": "#/components/schemas/Reasoning"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "instructions": {
+                "anyOf": [
+                  {
+                    "description": "A system (or developer) message inserted into the model's context.\n\nWhen using along with `previous_response_id`, the instructions from a previous\nresponse will not be carried over to the next response. This makes it simple\nto swap out system (or developer) messages in new responses.\n",
+                    "oneOf": [
+                      {
+                        "type": "string",
+                        "description": "A text input to the model, equivalent to a text input with the\n`developer` role.\n"
+                      },
+                      {
+                        "type": "array",
+                        "title": "Input item list",
+                        "description": "A list of one or many input items to the model, containing\ndifferent content types.\n",
+                        "items": {
+                          "$ref": "#/components/schemas/InputItem"
+                        }
+                      }
+                    ]
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "output_text": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "SDK-only convenience property that contains the aggregated text output\nfrom all `output_text` items in the `output` array, if any are present.\nSupported in the Python and JavaScript SDKs.\n",
+                    "x-oaiSupportedSDKs": [
+                      "python",
+                      "javascript"
+                    ]
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "usage": {
+                "$ref": "#/components/schemas/ResponseUsage"
+              },
+              "prompt_cache_options": {
+                "$ref": "#/components/schemas/PromptCacheOptions"
+              },
+              "prompt_cache_diagnostics": {
+                "$ref": "#/components/schemas/PromptCacheDiagnostics"
+              },
+              "moderation": {
+                "anyOf": [
+                  {
+                    "$ref": "#/components/schemas/Moderation",
+                    "description": "Moderation results for the response input and output, if moderated completions were requested.\n"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "parallel_tool_calls": {
+                "type": "boolean",
+                "description": "Whether to allow the model to run tool calls in parallel.\n",
+                "default": true
+              },
+              "conversation": {
+                "anyOf": [
+                  {
+                    "default": null,
+                    "$ref": "#/components/schemas/ResponseConversation"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "max_output_tokens": {
+                "anyOf": [
+                  {
+                    "description": "An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](https://developers.openai.com/api/docs/guides/reasoning).\n",
+                    "type": "integer"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              }
+            },
+            "required": [
+              "id",
+              "object",
+              "created_at",
+              "error",
+              "incomplete_details",
+              "instructions",
+              "model",
+              "tools",
+              "output",
+              "parallel_tool_calls",
+              "metadata",
+              "tool_choice",
+              "temperature",
+              "top_p"
+            ]
+          }
+        ],
+        "example": {
+          "id": "resp_67ccd3a9da748190baa7f1570fe91ac604becb25c45c1d41",
+          "object": "response",
+          "created_at": 1741476777,
+          "status": "completed",
+          "completed_at": 1741476778,
+          "error": null,
+          "incomplete_details": null,
+          "instructions": null,
+          "max_output_tokens": null,
+          "model": "gpt-6-astra",
+          "output": [
+            {
+              "type": "message",
+              "id": "msg_67ccd3acc8d48190a77525dc6de64b4104becb25c45c1d41",
+              "status": "completed",
+              "role": "assistant",
+              "content": [
+                {
+                  "type": "output_text",
+                  "text": "The image depicts a scenic landscape with a wooden boardwalk or pathway leading through lush, green grass under a blue sky with some clouds. The setting suggests a peaceful natural area, possibly a park or nature reserve. There are trees and shrubs in the background.",
+                  "annotations": []
+                }
+              ]
+            }
+          ],
+          "parallel_tool_calls": true,
+          "previous_response_id": null,
+          "reasoning": {
+            "effort": null,
+            "summary": null,
+            "context": null
+          },
+          "store": true,
+          "temperature": 1,
+          "text": {
+            "format": {
+              "type": "text"
+            }
+          },
+          "tool_choice": "auto",
+          "tools": [],
+          "top_p": 1,
+          "truncation": "disabled",
+          "usage": {
+            "input_tokens": 328,
+            "input_tokens_details": {
+              "cached_tokens": 0,
+              "cache_write_tokens": 0
+            },
+            "output_tokens": 52,
+            "output_tokens_details": {
+              "reasoning_tokens": 0
+            },
+            "total_tokens": 380
+          },
+          "user": null,
+          "metadata": {}
+        }
+      },
+      "ResponseAudioDeltaEvent": {
+        "type": "object",
+        "description": "Emitted when there is a partial audio response.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.audio.delta`.\n",
+            "enum": [
+              "response.audio.delta"
+            ],
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "A sequence number for this chunk of the stream response.\n"
+          },
+          "delta": {
+            "type": "string",
+            "description": "A chunk of Base64 encoded response audio bytes.\n"
+          }
+        },
+        "required": [
+          "type",
+          "delta",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.audio.delta",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.audio.delta\",\n  \"response_id\": \"resp_123\",\n  \"delta\": \"base64encoded...\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseAudioDoneEvent": {
+        "type": "object",
+        "description": "Emitted when the audio response is complete.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.audio.done`.\n",
+            "enum": [
+              "response.audio.done"
+            ],
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the delta.\n"
+          }
+        },
+        "required": [
+          "type",
+          "sequence_number",
+          "response_id"
+        ],
+        "x-oaiMeta": {
+          "name": "response.audio.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.audio.done\",\n  \"response_id\": \"resp-123\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseAudioTranscriptDeltaEvent": {
+        "type": "object",
+        "description": "Emitted when there is a partial transcript of audio.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.audio.transcript.delta`.\n",
+            "enum": [
+              "response.audio.transcript.delta"
+            ],
+            "x-stainless-const": true
+          },
+          "delta": {
+            "type": "string",
+            "description": "The partial transcript of the audio response.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "response_id",
+          "delta",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.audio.transcript.delta",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.audio.transcript.delta\",\n  \"response_id\": \"resp_123\",\n  \"delta\": \" ... partial transcript ... \",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseAudioTranscriptDoneEvent": {
+        "type": "object",
+        "description": "Emitted when the full audio transcript is completed.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.audio.transcript.done`.\n",
+            "enum": [
+              "response.audio.transcript.done"
+            ],
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "response_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.audio.transcript.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.audio.transcript.done\",\n  \"response_id\": \"resp_123\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseCodeInterpreterCallCodeDeltaEvent": {
+        "type": "object",
+        "description": "Emitted when a partial code snippet is streamed by the code interpreter.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.code_interpreter_call_code.delta`.",
+            "enum": [
+              "response.code_interpreter_call_code.delta"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response for which the code is being streamed."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the code interpreter tool call item."
+          },
+          "delta": {
+            "type": "string",
+            "description": "The partial code snippet being streamed by the code interpreter."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event, used to order streaming events."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "delta",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.code_interpreter_call_code.delta",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.code_interpreter_call_code.delta\",\n  \"output_index\": 0,\n  \"item_id\": \"ci_12345\",\n  \"delta\": \"print('Hello, world')\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseCodeInterpreterCallCodeDoneEvent": {
+        "type": "object",
+        "description": "Emitted when the code snippet is finalized by the code interpreter.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.code_interpreter_call_code.done`.",
+            "enum": [
+              "response.code_interpreter_call_code.done"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response for which the code is finalized."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the code interpreter tool call item."
+          },
+          "code": {
+            "type": "string",
+            "description": "The final code snippet output by the code interpreter."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event, used to order streaming events."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "code",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.code_interpreter_call_code.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.code_interpreter_call_code.done\",\n  \"output_index\": 3,\n  \"item_id\": \"ci_12345\",\n  \"code\": \"print('done')\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseCodeInterpreterCallCompletedEvent": {
+        "type": "object",
+        "description": "Emitted when the code interpreter call is completed.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.code_interpreter_call.completed`.",
+            "enum": [
+              "response.code_interpreter_call.completed"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response for which the code interpreter call is completed."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the code interpreter tool call item."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event, used to order streaming events."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.code_interpreter_call.completed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.code_interpreter_call.completed\",\n  \"output_index\": 5,\n  \"item_id\": \"ci_12345\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseCodeInterpreterCallInProgressEvent": {
+        "type": "object",
+        "description": "Emitted when a code interpreter call is in progress.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.code_interpreter_call.in_progress`.",
+            "enum": [
+              "response.code_interpreter_call.in_progress"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response for which the code interpreter call is in progress."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the code interpreter tool call item."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event, used to order streaming events."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.code_interpreter_call.in_progress",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.code_interpreter_call.in_progress\",\n  \"output_index\": 0,\n  \"item_id\": \"ci_12345\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseCodeInterpreterCallInterpretingEvent": {
+        "type": "object",
+        "description": "Emitted when the code interpreter is actively interpreting the code snippet.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.code_interpreter_call.interpreting`.",
+            "enum": [
+              "response.code_interpreter_call.interpreting"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response for which the code interpreter is interpreting code."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the code interpreter tool call item."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event, used to order streaming events."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.code_interpreter_call.interpreting",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.code_interpreter_call.interpreting\",\n  \"output_index\": 4,\n  \"item_id\": \"ci_12345\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseCompletedEvent": {
+        "type": "object",
+        "description": "Emitted when the model response is complete.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.completed`.\n",
+            "enum": [
+              "response.completed"
+            ],
+            "x-stainless-const": true
+          },
+          "response": {
+            "$ref": "#/components/schemas/Response",
+            "description": "Properties of the completed response.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number for this event."
+          }
+        },
+        "required": [
+          "type",
+          "response",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.completed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.completed\",\n  \"response\": {\n    \"id\": \"resp_123\",\n    \"object\": \"response\",\n    \"created_at\": 1740855869,\n    \"status\": \"completed\",\n    \"completed_at\": 1740855870,\n    \"error\": null,\n    \"incomplete_details\": null,\n    \"input\": [],\n    \"instructions\": null,\n    \"max_output_tokens\": null,\n    \"model\": \"gpt-6-astra\",\n    \"output\": [\n      {\n        \"id\": \"msg_123\",\n        \"type\": \"message\",\n        \"role\": \"assistant\",\n        \"content\": [\n          {\n            \"type\": \"output_text\",\n            \"text\": \"In a shimmering forest under a sky full of stars, a lonely unicorn named Lila discovered a hidden pond that glowed with moonlight. Every night, she would leave sparkling, magical flowers by the water's edge, hoping to share her beauty with others. One enchanting evening, she woke to find a group of friendly animals gathered around, eager to be friends and share in her magic.\",\n            \"annotations\": []\n          }\n        ]\n      }\n    ],\n    \"previous_response_id\": null,\n    \"reasoning_effort\": null,\n    \"store\": false,\n    \"temperature\": 1,\n    \"text\": {\n      \"format\": {\n        \"type\": \"text\"\n      }\n    },\n    \"tool_choice\": \"auto\",\n    \"tools\": [],\n    \"top_p\": 1,\n    \"truncation\": \"disabled\",\n    \"usage\": {\n      \"input_tokens\": 0,\n      \"output_tokens\": 0,\n      \"output_tokens_details\": {\n        \"reasoning_tokens\": 0\n      },\n      \"total_tokens\": 0\n    },\n    \"user\": null,\n    \"metadata\": {}\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseConfigurationUpdate": {
+        "type": "object",
+        "description": "A configuration update that applies to subsequent responses until it is\nreplaced by another configuration update.\n",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the configuration update item.",
+            "example": "cnfu_123"
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "configuration_update"
+            ],
+            "description": "The item type. Always `configuration_update`.",
+            "default": "configuration_update",
+            "x-stainless-const": true
+          },
+          "reasoning": {
+            "type": "object",
+            "description": "The reasoning configuration applied by this update.",
+            "properties": {
+              "effort": {
+                "$ref": "#/components/schemas/ReasoningEffort",
+                "description": "The reasoning effort used for subsequent responses until another\nconfiguration update replaces it.\n"
+              }
+            }
+          }
+        },
+        "required": [
+          "id",
+          "type"
+        ]
+      },
+      "ResponseConfigurationUpdateItemParam": {
+        "type": "object",
+        "description": "An update to the conversation's response configuration. The configuration\nremains in effect for subsequent responses until it is replaced by another\nconfiguration update.\n",
+        "properties": {
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the configuration update item.",
+                "example": "cnfu_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "configuration_update"
+            ],
+            "description": "The item type. Always `configuration_update`.",
+            "default": "configuration_update",
+            "x-stainless-const": true
+          },
+          "reasoning": {
+            "type": "object",
+            "description": "Updates to reasoning configuration. Only effort is supported.",
+            "properties": {
+              "effort": {
+                "$ref": "#/components/schemas/ReasoningEffort",
+                "description": "The reasoning effort to use for subsequent responses until another\nconfiguration update replaces it.\n"
+              }
+            }
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "ResponseContentPartAddedEvent": {
+        "type": "object",
+        "description": "Emitted when a new content part is added.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.content_part.added`.\n",
+            "enum": [
+              "response.content_part.added"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that the content part was added to.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the content part was added to.\n"
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part that was added.\n"
+          },
+          "part": {
+            "$ref": "#/components/schemas/OutputContent",
+            "description": "The content part that was added.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "content_index",
+          "part",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.content_part.added",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.content_part.added\",\n  \"item_id\": \"msg_123\",\n  \"output_index\": 0,\n  \"content_index\": 0,\n  \"part\": {\n    \"type\": \"output_text\",\n    \"text\": \"\",\n    \"annotations\": []\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseContentPartDoneEvent": {
+        "type": "object",
+        "description": "Emitted when a content part is done.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.content_part.done`.\n",
+            "enum": [
+              "response.content_part.done"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that the content part was added to.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the content part was added to.\n"
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part that is done.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          },
+          "part": {
+            "$ref": "#/components/schemas/OutputContent",
+            "description": "The content part that is done.\n"
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "content_index",
+          "part",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.content_part.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.content_part.done\",\n  \"item_id\": \"msg_123\",\n  \"output_index\": 0,\n  \"content_index\": 0,\n  \"sequence_number\": 1,\n  \"part\": {\n    \"type\": \"output_text\",\n    \"text\": \"In a shimmering forest under a sky full of stars, a lonely unicorn named Lila discovered a hidden pond that glowed with moonlight. Every night, she would leave sparkling, magical flowers by the water's edge, hoping to share her beauty with others. One enchanting evening, she woke to find a group of friendly animals gathered around, eager to be friends and share in her magic.\",\n    \"annotations\": []\n  }\n}\n"
+        }
+      },
+      "ResponseCreatedEvent": {
+        "type": "object",
+        "description": "An event that is emitted when a response is created.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.created`.\n",
+            "enum": [
+              "response.created"
+            ],
+            "x-stainless-const": true
+          },
+          "response": {
+            "$ref": "#/components/schemas/Response",
+            "description": "The response that was created.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number for this event."
+          }
+        },
+        "required": [
+          "type",
+          "response",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.created",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.created\",\n  \"response\": {\n    \"id\": \"resp_67ccfcdd16748190a91872c75d38539e09e4d4aac714747c\",\n    \"object\": \"response\",\n    \"created_at\": 1741487325,\n    \"status\": \"in_progress\",\n    \"completed_at\": null,\n    \"error\": null,\n    \"incomplete_details\": null,\n    \"instructions\": null,\n    \"max_output_tokens\": null,\n    \"model\": \"gpt-6-astra\",\n    \"output\": [],\n    \"parallel_tool_calls\": true,\n    \"previous_response_id\": null,\n    \"reasoning\": {\n      \"effort\": null,\n      \"summary\": null\n    },\n    \"store\": true,\n    \"temperature\": 1,\n    \"text\": {\n      \"format\": {\n        \"type\": \"text\"\n      }\n    },\n    \"tool_choice\": \"auto\",\n    \"tools\": [],\n    \"top_p\": 1,\n    \"truncation\": \"disabled\",\n    \"usage\": null,\n    \"user\": null,\n    \"metadata\": {}\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseCustomToolCallInputDeltaEvent": {
+        "title": "ResponseCustomToolCallInputDelta",
+        "type": "object",
+        "description": "Event representing a delta (partial update) to the input of a custom tool call.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.custom_tool_call_input.delta"
+            ],
+            "description": "The event type identifier.",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output this delta applies to."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "Unique identifier for the API item associated with this event."
+          },
+          "delta": {
+            "type": "string",
+            "description": "The incremental input data (delta) for the custom tool call."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "delta",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.custom_tool_call_input.delta",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.custom_tool_call_input.delta\",\n  \"output_index\": 0,\n  \"item_id\": \"ctc_1234567890abcdef\",\n  \"delta\": \"partial input text\"\n}\n"
+        }
+      },
+      "ResponseCustomToolCallInputDoneEvent": {
+        "title": "ResponseCustomToolCallInputDone",
+        "type": "object",
+        "description": "Event indicating that input for a custom tool call is complete.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.custom_tool_call_input.done"
+            ],
+            "description": "The event type identifier.",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output this event applies to."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "Unique identifier for the API item associated with this event."
+          },
+          "input": {
+            "type": "string",
+            "description": "The complete input data for the custom tool call."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "input",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.custom_tool_call_input.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.custom_tool_call_input.done\",\n  \"output_index\": 0,\n  \"item_id\": \"ctc_1234567890abcdef\",\n  \"input\": \"final complete input text\"\n}\n"
+        }
+      },
+      "ResponseError": {
+        "anyOf": [
+          {
+            "type": "object",
+            "description": "An error object returned when the model fails to generate a Response.\n",
+            "properties": {
+              "code": {
+                "$ref": "#/components/schemas/ResponseErrorCode"
+              },
+              "message": {
+                "type": "string",
+                "description": "A human-readable description of the error.\n"
+              },
+              "misalignment": {
+                "$ref": "#/components/schemas/MisalignmentErrorDetailsResource"
+              }
+            },
+            "required": [
+              "code",
+              "message"
+            ]
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "ResponseErrorCode": {
+        "type": "string",
+        "description": "The error code for the response.\n",
+        "enum": [
+          "server_error",
+          "rate_limit_exceeded",
+          "invalid_prompt",
+          "data_residency_mismatch",
+          "bio_policy",
+          "misalignment_policy_violation",
+          "vector_store_timeout",
+          "invalid_image",
+          "invalid_image_format",
+          "invalid_base64_image",
+          "invalid_image_url",
+          "image_too_large",
+          "image_too_small",
+          "image_parse_error",
+          "image_content_policy_violation",
+          "invalid_image_mode",
+          "image_file_too_large",
+          "unsupported_image_media_type",
+          "empty_image_file",
+          "failed_to_download_image",
+          "image_file_not_found"
+        ]
+      },
+      "ResponseErrorEvent": {
+        "type": "object",
+        "description": "Emitted when an error occurs.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `error`.\n",
+            "enum": [
+              "error"
+            ],
+            "x-stainless-const": true
+          },
+          "code": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The error code.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "message": {
+            "type": "string",
+            "description": "The error message.\n"
+          },
+          "param": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The error parameter.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "code",
+          "message",
+          "param",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "error",
+          "group": "responses",
+          "example": "{\n  \"type\": \"error\",\n  \"code\": \"ERR_SOMETHING\",\n  \"message\": \"Something went wrong\",\n  \"param\": null,\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseFailedEvent": {
+        "type": "object",
+        "description": "An event that is emitted when a response fails.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.failed`.\n",
+            "enum": [
+              "response.failed"
+            ],
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          },
+          "response": {
+            "$ref": "#/components/schemas/Response",
+            "description": "The response that failed.\n"
+          }
+        },
+        "required": [
+          "type",
+          "response",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.failed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.failed\",\n  \"response\": {\n    \"id\": \"resp_123\",\n    \"object\": \"response\",\n    \"created_at\": 1740855869,\n    \"status\": \"failed\",\n    \"completed_at\": null,\n    \"error\": {\n      \"code\": \"server_error\",\n      \"message\": \"The model failed to generate a response.\"\n    },\n    \"incomplete_details\": null,\n    \"instructions\": null,\n    \"max_output_tokens\": null,\n    \"model\": \"gpt-6-astra\",\n    \"output\": [],\n    \"previous_response_id\": null,\n    \"reasoning_effort\": null,\n    \"store\": false,\n    \"temperature\": 1,\n    \"text\": {\n      \"format\": {\n        \"type\": \"text\"\n      }\n    },\n    \"tool_choice\": \"auto\",\n    \"tools\": [],\n    \"top_p\": 1,\n    \"truncation\": \"disabled\",\n    \"usage\": null,\n    \"user\": null,\n    \"metadata\": {}\n  }\n}\n"
+        }
+      },
+      "ResponseFileSearchCallCompletedEvent": {
+        "type": "object",
+        "description": "Emitted when a file search call is completed (results found).",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.file_search_call.completed`.\n",
+            "enum": [
+              "response.file_search_call.completed"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the file search call is initiated.\n"
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that the file search call is initiated.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.file_search_call.completed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.file_search_call.completed\",\n  \"output_index\": 0,\n  \"item_id\": \"fs_123\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseFileSearchCallInProgressEvent": {
+        "type": "object",
+        "description": "Emitted when a file search call is initiated.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.file_search_call.in_progress`.\n",
+            "enum": [
+              "response.file_search_call.in_progress"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the file search call is initiated.\n"
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that the file search call is initiated.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.file_search_call.in_progress",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.file_search_call.in_progress\",\n  \"output_index\": 0,\n  \"item_id\": \"fs_123\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseFileSearchCallSearchingEvent": {
+        "type": "object",
+        "description": "Emitted when a file search is currently searching.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.file_search_call.searching`.\n",
+            "enum": [
+              "response.file_search_call.searching"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the file search call is searching.\n"
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that the file search call is initiated.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.file_search_call.searching",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.file_search_call.searching\",\n  \"output_index\": 0,\n  \"item_id\": \"fs_123\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseFormatJsonObject": {
+        "type": "object",
+        "title": "JSON object",
+        "description": "JSON object response format. An older method of generating JSON responses.\nUsing `json_schema` is recommended for models that support it. Note that the\nmodel will not generate JSON without a system or user message instructing it\nto do so.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of response format being defined. Always `json_object`.",
+            "enum": [
+              "json_object"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "ResponseFormatJsonSchema": {
+        "type": "object",
+        "title": "JSON schema",
+        "description": "JSON Schema response format. Used to generate structured JSON responses.\nLearn more about [Structured Outputs](https://developers.openai.com/api/docs/guides/structured-outputs).\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of response format being defined. Always `json_schema`.",
+            "enum": [
+              "json_schema"
+            ],
+            "x-stainless-const": true
+          },
+          "json_schema": {
+            "type": "object",
+            "title": "JSON schema",
+            "description": "Structured Outputs configuration options, including a JSON Schema.\n",
+            "properties": {
+              "description": {
+                "type": "string",
+                "description": "A description of what the response format is for, used by the model to\ndetermine how to respond in the format.\n"
+              },
+              "name": {
+                "type": "string",
+                "description": "The name of the response format. Must be a-z, A-Z, 0-9, or contain\nunderscores and dashes, with a maximum length of 64.\n"
+              },
+              "schema": {
+                "$ref": "#/components/schemas/ResponseFormatJsonSchemaSchema"
+              },
+              "strict": {
+                "anyOf": [
+                  {
+                    "type": "boolean",
+                    "default": false,
+                    "description": "Whether to enable strict schema adherence when generating the output.\nIf set to true, the model will always follow the exact schema defined\nin the `schema` field. Only a subset of JSON Schema is supported when\n`strict` is `true`. To learn more, read the [Structured Outputs\nguide](https://developers.openai.com/api/docs/guides/structured-outputs).\n"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              }
+            },
+            "required": [
+              "name"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "json_schema"
+        ]
+      },
+      "ResponseFormatJsonSchemaSchema": {
+        "type": "object",
+        "title": "JSON schema",
+        "description": "The schema for the response format, described as a JSON Schema object.\nLearn how to build JSON schemas [here](https://json-schema.org/).\n",
+        "additionalProperties": true
+      },
+      "ResponseFormatText": {
+        "type": "object",
+        "title": "Text",
+        "description": "Default response format. Used to generate text responses.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of response format being defined. Always `text`.",
+            "enum": [
+              "text"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "ResponseFormatTextGrammar": {
+        "type": "object",
+        "title": "Text grammar",
+        "description": "A custom grammar for the model to follow when generating text.\nLearn more in the [custom grammars guide](https://developers.openai.com/api/docs/guides/function-calling#context-free-grammars).\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of response format being defined. Always `grammar`.",
+            "enum": [
+              "grammar"
+            ],
+            "x-stainless-const": true
+          },
+          "grammar": {
+            "type": "string",
+            "description": "The custom grammar for the model to follow."
+          }
+        },
+        "required": [
+          "type",
+          "grammar"
+        ]
+      },
+      "ResponseFormatTextPython": {
+        "type": "object",
+        "title": "Python grammar",
+        "description": "Configure the model to generate valid Python code. See the\n[custom grammars guide](https://developers.openai.com/api/docs/guides/function-calling#context-free-grammars) for more details.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of response format being defined. Always `python`.",
+            "enum": [
+              "python"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "ResponseFunctionCallArgumentsDeltaEvent": {
+        "type": "object",
+        "description": "Emitted when there is a partial function-call arguments delta.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.function_call_arguments.delta`.\n",
+            "enum": [
+              "response.function_call_arguments.delta"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that the function-call arguments delta is added to.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the function-call arguments delta is added to.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          },
+          "delta": {
+            "type": "string",
+            "description": "The function-call arguments delta that is added.\n"
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "delta",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.function_call_arguments.delta",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.function_call_arguments.delta\",\n  \"item_id\": \"item-abc\",\n  \"output_index\": 0,\n  \"delta\": \"{ \\\"arg\\\":\"\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseFunctionCallArgumentsDoneEvent": {
+        "type": "object",
+        "description": "Emitted when function-call arguments are finalized.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.function_call_arguments.done"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          },
+          "arguments": {
+            "type": "string",
+            "description": "The function-call arguments."
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "arguments",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.function_call_arguments.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.function_call_arguments.done\",\n  \"item_id\": \"item-abc\",\n  \"output_index\": 1,\n  \"arguments\": \"{ \\\"arg\\\": 123 }\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseImageGenCallCompletedEvent": {
+        "type": "object",
+        "title": "ResponseImageGenCallCompletedEvent",
+        "description": "Emitted when an image generation tool call has completed and the final image is available.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.image_generation_call.completed"
+            ],
+            "description": "The type of the event. Always 'response.image_generation_call.completed'.",
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response's output array."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the image generation item being processed."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.image_generation_call.completed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.image_generation_call.completed\",\n  \"output_index\": 0,\n  \"item_id\": \"item-123\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseImageGenCallGeneratingEvent": {
+        "type": "object",
+        "title": "ResponseImageGenCallGeneratingEvent",
+        "description": "Emitted when an image generation tool call is actively generating an image (intermediate state).\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.image_generation_call.generating"
+            ],
+            "description": "The type of the event. Always 'response.image_generation_call.generating'.",
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response's output array."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the image generation item being processed."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the image generation item being processed."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.image_generation_call.generating",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.image_generation_call.generating\",\n  \"output_index\": 0,\n  \"item_id\": \"item-123\",\n  \"sequence_number\": 0\n}\n"
+        }
+      },
+      "ResponseImageGenCallInProgressEvent": {
+        "type": "object",
+        "title": "ResponseImageGenCallInProgressEvent",
+        "description": "Emitted when an image generation tool call is in progress.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.image_generation_call.in_progress"
+            ],
+            "description": "The type of the event. Always 'response.image_generation_call.in_progress'.",
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response's output array."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the image generation item being processed."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the image generation item being processed."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.image_generation_call.in_progress",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.image_generation_call.in_progress\",\n  \"output_index\": 0,\n  \"item_id\": \"item-123\",\n  \"sequence_number\": 0\n}\n"
+        }
+      },
+      "ResponseImageGenCallPartialImageEvent": {
+        "type": "object",
+        "title": "ResponseImageGenCallPartialImageEvent",
+        "description": "Emitted when a partial image is available during image generation streaming.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.image_generation_call.partial_image"
+            ],
+            "description": "The type of the event. Always 'response.image_generation_call.partial_image'.",
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response's output array."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the image generation item being processed."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the image generation item being processed."
+          },
+          "partial_image_index": {
+            "type": "integer",
+            "description": "0-based index for the partial image (backend is 1-based, but this is 0-based for the user)."
+          },
+          "partial_image_b64": {
+            "type": "string",
+            "description": "Base64-encoded partial image data, suitable for rendering as an image."
+          },
+          "size": {
+            "type": "string",
+            "description": "The image size that was used."
+          },
+          "quality": {
+            "type": "string",
+            "description": "The image quality that was used."
+          },
+          "background": {
+            "type": "string",
+            "description": "The background setting that was used."
+          },
+          "output_format": {
+            "type": "string",
+            "description": "The output format that was used."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number",
+          "partial_image_index",
+          "partial_image_b64"
+        ],
+        "x-oaiMeta": {
+          "name": "response.image_generation_call.partial_image",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.image_generation_call.partial_image\",\n  \"output_index\": 0,\n  \"item_id\": \"item-123\",\n  \"sequence_number\": 0,\n  \"partial_image_index\": 0,\n  \"partial_image_b64\": \"...\"\n}\n"
+        }
+      },
+      "ResponseInProgressEvent": {
+        "type": "object",
+        "description": "Emitted when the response is in progress.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.in_progress`.\n",
+            "enum": [
+              "response.in_progress"
+            ],
+            "x-stainless-const": true
+          },
+          "response": {
+            "$ref": "#/components/schemas/Response",
+            "description": "The response that is in progress.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "response",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.in_progress",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.in_progress\",\n  \"response\": {\n    \"id\": \"resp_67ccfcdd16748190a91872c75d38539e09e4d4aac714747c\",\n    \"object\": \"response\",\n    \"created_at\": 1741487325,\n    \"status\": \"in_progress\",\n    \"completed_at\": null,\n    \"error\": null,\n    \"incomplete_details\": null,\n    \"instructions\": null,\n    \"max_output_tokens\": null,\n    \"model\": \"gpt-6-astra\",\n    \"output\": [],\n    \"parallel_tool_calls\": true,\n    \"previous_response_id\": null,\n    \"reasoning\": {\n      \"effort\": null,\n      \"summary\": null\n    },\n    \"store\": true,\n    \"temperature\": 1,\n    \"text\": {\n      \"format\": {\n        \"type\": \"text\"\n      }\n    },\n    \"tool_choice\": \"auto\",\n    \"tools\": [],\n    \"top_p\": 1,\n    \"truncation\": \"disabled\",\n    \"usage\": null,\n    \"user\": null,\n    \"metadata\": {}\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseIncompleteEvent": {
+        "type": "object",
+        "description": "An event that is emitted when a response finishes as incomplete.\n\nOver WebSocket, steering can finish a response with\n`response.incomplete_details.reason` set to `steered`, followed automatically\nby a successor `response.created` that commits the queued steering input.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.incomplete`.\n",
+            "enum": [
+              "response.incomplete"
+            ],
+            "x-stainless-const": true
+          },
+          "response": {
+            "$ref": "#/components/schemas/Response",
+            "description": "The response that was incomplete.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "response",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.incomplete",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.incomplete\",\n  \"response\": {\n    \"id\": \"resp_123\",\n    \"object\": \"response\",\n    \"created_at\": 1740855869,\n    \"status\": \"incomplete\",\n    \"completed_at\": null,\n    \"error\": null,\n    \"incomplete_details\": {\n      \"reason\": \"max_tokens\"\n    },\n    \"instructions\": null,\n    \"max_output_tokens\": null,\n    \"model\": \"gpt-6-astra\",\n    \"output\": [],\n    \"previous_response_id\": null,\n    \"reasoning_effort\": null,\n    \"store\": false,\n    \"temperature\": 1,\n    \"text\": {\n      \"format\": {\n        \"type\": \"text\"\n      }\n    },\n    \"tool_choice\": \"auto\",\n    \"tools\": [],\n    \"top_p\": 1,\n    \"truncation\": \"disabled\",\n    \"usage\": null,\n    \"user\": null,\n    \"metadata\": {}\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseItemList": {
+        "type": "object",
+        "description": "A list of Response items.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "description": "The type of object returned, must be `list`.",
+            "enum": [
+              "list"
+            ],
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "description": "A list of items used to generate this response.",
+            "items": {
+              "$ref": "#/components/schemas/ItemResource"
+            }
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more items available."
+          },
+          "first_id": {
+            "type": "string",
+            "description": "The ID of the first item in the list."
+          },
+          "last_id": {
+            "type": "string",
+            "description": "The ID of the last item in the list."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more",
+          "first_id",
+          "last_id"
+        ],
+        "x-oaiMeta": {
+          "name": "The input item list",
+          "group": "responses",
+          "example": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"id\": \"msg_abc123\",\n      \"type\": \"message\",\n      \"role\": \"user\",\n      \"content\": [\n        {\n          \"type\": \"input_text\",\n          \"text\": \"Tell me a three sentence bedtime story about a unicorn.\"\n        }\n      ]\n    }\n  ],\n  \"first_id\": \"msg_abc123\",\n  \"last_id\": \"msg_abc123\",\n  \"has_more\": false\n}\n"
+        }
+      },
+      "ResponseLogProb": {
+        "type": "object",
+        "description": "A logprob is the logarithmic probability that the model assigns to producing \na particular token at a given position in the sequence. Less-negative (higher) \nlogprob values indicate greater model confidence in that token choice.\n",
+        "properties": {
+          "token": {
+            "description": "A possible text token.",
+            "type": "string"
+          },
+          "logprob": {
+            "description": "The log probability of this token.\n",
+            "type": "number"
+          },
+          "top_logprobs": {
+            "description": "The log probabilities of up to 20 of the most likely tokens.\n",
+            "type": "array",
+            "items": {
+              "type": "object",
+              "properties": {
+                "token": {
+                  "description": "A possible text token.",
+                  "type": "string"
+                },
+                "logprob": {
+                  "description": "The log probability of this token.",
+                  "type": "number"
+                }
+              }
+            }
+          }
+        },
+        "required": [
+          "token",
+          "logprob"
+        ]
+      },
+      "ResponseMCPCallArgumentsDeltaEvent": {
+        "type": "object",
+        "title": "ResponseMCPCallArgumentsDeltaEvent",
+        "description": "Emitted when there is a delta (partial update) to the arguments of an MCP tool call.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_call_arguments.delta"
+            ],
+            "description": "The type of the event. Always 'response.mcp_call_arguments.delta'.",
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response's output array."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the MCP tool call item being processed."
+          },
+          "delta": {
+            "type": "string",
+            "description": "A JSON string containing the partial update to the arguments for the MCP tool call.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "delta",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_call_arguments.delta",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.mcp_call_arguments.delta\",\n  \"output_index\": 0,\n  \"item_id\": \"item-abc\",\n  \"delta\": \"{\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseMCPCallArgumentsDoneEvent": {
+        "type": "object",
+        "title": "ResponseMCPCallArgumentsDoneEvent",
+        "description": "Emitted when the arguments for an MCP tool call are finalized.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_call_arguments.done"
+            ],
+            "description": "The type of the event. Always 'response.mcp_call_arguments.done'.",
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response's output array."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the MCP tool call item being processed."
+          },
+          "arguments": {
+            "type": "string",
+            "description": "A JSON string containing the finalized arguments for the MCP tool call.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "arguments",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_call_arguments.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.mcp_call_arguments.done\",\n  \"output_index\": 0,\n  \"item_id\": \"item-abc\",\n  \"arguments\": \"{\\\"arg1\\\": \\\"value1\\\", \\\"arg2\\\": \\\"value2\\\"}\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseMCPCallCompletedEvent": {
+        "type": "object",
+        "title": "ResponseMCPCallCompletedEvent",
+        "description": "Emitted when an MCP  tool call has completed successfully.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_call.completed"
+            ],
+            "description": "The type of the event. Always 'response.mcp_call.completed'.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP tool call item that completed."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that completed."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_call.completed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.mcp_call.completed\",\n  \"sequence_number\": 1,\n  \"item_id\": \"mcp_682d437d90a88191bf88cd03aae0c3e503937d5f622d7a90\",\n  \"output_index\": 0\n}\n"
+        }
+      },
+      "ResponseMCPCallFailedEvent": {
+        "type": "object",
+        "title": "ResponseMCPCallFailedEvent",
+        "description": "Emitted when an MCP  tool call has failed.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_call.failed"
+            ],
+            "description": "The type of the event. Always 'response.mcp_call.failed'.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP tool call item that failed."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that failed."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_call.failed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.mcp_call.failed\",\n  \"sequence_number\": 1,\n  \"item_id\": \"mcp_682d437d90a88191bf88cd03aae0c3e503937d5f622d7a90\",\n  \"output_index\": 0\n}\n"
+        }
+      },
+      "ResponseMCPCallInProgressEvent": {
+        "type": "object",
+        "title": "ResponseMCPCallInProgressEvent",
+        "description": "Emitted when an MCP  tool call is in progress.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_call.in_progress"
+            ],
+            "description": "The type of the event. Always 'response.mcp_call.in_progress'.",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response's output array."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the MCP tool call item being processed."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_call.in_progress",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.mcp_call.in_progress\",\n  \"sequence_number\": 1,\n  \"output_index\": 0,\n  \"item_id\": \"mcp_682d437d90a88191bf88cd03aae0c3e503937d5f622d7a90\"\n}\n"
+        }
+      },
+      "ResponseMCPListToolsCompletedEvent": {
+        "type": "object",
+        "title": "ResponseMCPListToolsCompletedEvent",
+        "description": "Emitted when the list of available MCP tools has been successfully retrieved.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_list_tools.completed"
+            ],
+            "description": "The type of the event. Always 'response.mcp_list_tools.completed'.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP tool call item that produced this output."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that was processed."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_list_tools.completed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.mcp_list_tools.completed\",\n  \"sequence_number\": 1,\n  \"output_index\": 0,\n  \"item_id\": \"mcpl_682d4379df088191886b70f4ec39f90403937d5f622d7a90\"\n}\n"
+        }
+      },
+      "ResponseMCPListToolsFailedEvent": {
+        "type": "object",
+        "title": "ResponseMCPListToolsFailedEvent",
+        "description": "Emitted when the attempt to list available MCP tools has failed.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_list_tools.failed"
+            ],
+            "description": "The type of the event. Always 'response.mcp_list_tools.failed'.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP tool call item that failed."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that failed."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_list_tools.failed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.mcp_list_tools.failed\",\n  \"sequence_number\": 1,\n  \"output_index\": 0,\n  \"item_id\": \"mcpl_682d4379df088191886b70f4ec39f90403937d5f622d7a90\"\n}\n"
+        }
+      },
+      "ResponseMCPListToolsInProgressEvent": {
+        "type": "object",
+        "title": "ResponseMCPListToolsInProgressEvent",
+        "description": "Emitted when the system is in the process of retrieving the list of available MCP tools.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_list_tools.in_progress"
+            ],
+            "description": "The type of the event. Always 'response.mcp_list_tools.in_progress'.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP tool call item that is being processed."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that is being processed."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_list_tools.in_progress",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.mcp_list_tools.in_progress\",\n  \"sequence_number\": 1,\n  \"output_index\": 0,\n  \"item_id\": \"mcpl_682d4379df088191886b70f4ec39f90403937d5f622d7a90\"\n}\n"
+        }
+      },
+      "ResponseModalities": {
+        "anyOf": [
+          {
+            "type": "array",
+            "description": "Output types that you would like the model to generate.\nMost models are capable of generating text, which is the default:\n\n`[\"text\"]`\n\nThe `gpt-4o-audio-preview` model can also be used to\n[generate audio](https://developers.openai.com/api/docs/guides/audio). To request that this model generate\nboth text and audio responses, you can use:\n\n`[\"text\", \"audio\"]`\n",
+            "items": {
+              "type": "string",
+              "enum": [
+                "text",
+                "audio"
+              ]
+            }
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "ResponseOutputItemAddedEvent": {
+        "type": "object",
+        "description": "Emitted when a new output item is added.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.output_item.added`.\n",
+            "enum": [
+              "response.output_item.added"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that was added.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event.\n"
+          },
+          "item": {
+            "$ref": "#/components/schemas/OutputItem",
+            "description": "The output item that was added. For reasoning items, `encrypted_content`\nmay be incomplete while the item is in progress. Use the reasoning item\nfrom the corresponding `response.output_item.done` event when passing it\nas input to a subsequent request.\n"
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_item.added",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.output_item.added\",\n  \"output_index\": 0,\n  \"item\": {\n    \"id\": \"msg_123\",\n    \"status\": \"in_progress\",\n    \"type\": \"message\",\n    \"role\": \"assistant\",\n    \"content\": []\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseOutputItemDoneEvent": {
+        "type": "object",
+        "description": "Emitted when an output item is marked done.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.output_item.done`.\n",
+            "enum": [
+              "response.output_item.done"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that was marked done.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event.\n"
+          },
+          "item": {
+            "$ref": "#/components/schemas/OutputItem",
+            "description": "The output item that was marked done.\n"
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_item.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.output_item.done\",\n  \"output_index\": 0,\n  \"item\": {\n    \"id\": \"msg_123\",\n    \"status\": \"completed\",\n    \"type\": \"message\",\n    \"role\": \"assistant\",\n    \"content\": [\n      {\n        \"type\": \"output_text\",\n        \"text\": \"In a shimmering forest under a sky full of stars, a lonely unicorn named Lila discovered a hidden pond that glowed with moonlight. Every night, she would leave sparkling, magical flowers by the water's edge, hoping to share her beauty with others. One enchanting evening, she woke to find a group of friendly animals gathered around, eager to be friends and share in her magic.\",\n        \"annotations\": []\n      }\n    ]\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseOutputTextAnnotationAddedEvent": {
+        "type": "object",
+        "title": "ResponseOutputTextAnnotationAddedEvent",
+        "description": "Emitted when an annotation is added to output text content.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.output_text.annotation.added"
+            ],
+            "description": "The type of the event. Always 'response.output_text.annotation.added'.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the item to which the annotation is being added."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response's output array."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part within the output item."
+          },
+          "annotation_index": {
+            "type": "integer",
+            "description": "The index of the annotation within the content part."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          },
+          "annotation": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Annotation"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The annotation object being added. (See annotation schema for details.)"
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "content_index",
+          "annotation_index",
+          "annotation",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_text.annotation.added",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.output_text.annotation.added\",\n  \"item_id\": \"item-abc\",\n  \"output_index\": 0,\n  \"content_index\": 0,\n  \"annotation_index\": 0,\n  \"annotation\": {\n    \"type\": \"file_citation\",\n    \"file_id\": \"file-abc\",\n    \"index\": 0,\n    \"filename\": \"example.txt\"\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponsePromptVariables": {
+        "anyOf": [
+          {
+            "type": "object",
+            "title": "Prompt Variables",
+            "description": "Optional map of values to substitute in for variables in your\nprompt. The substitution values can either be strings, or other\nResponse input types like images or files.\n",
+            "x-oaiExpandable": true,
+            "x-oaiTypeLabel": "map",
+            "additionalProperties": {
+              "x-oaiExpandable": true,
+              "x-oaiTypeLabel": "map",
+              "oneOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "$ref": "#/components/schemas/InputTextContent"
+                },
+                {
+                  "$ref": "#/components/schemas/InputImageContent"
+                },
+                {
+                  "$ref": "#/components/schemas/InputFileContent"
+                }
+              ]
+            }
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "ResponseProperties": {
+        "type": "object",
+        "properties": {
+          "previous_response_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the previous response to the model. Use this to\ncreate multi-turn conversations. Learn more about\n[conversation state](https://developers.openai.com/api/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "model": {
+            "description": "Model ID used to generate the response, like `gpt-6-astra`. OpenAI\noffers a wide range of models with different capabilities, performance\ncharacteristics, and price points. Refer to the [model guide](https://developers.openai.com/api/docs/models)\nto browse and compare available models.\n",
+            "$ref": "#/components/schemas/ModelIdsResponses"
+          },
+          "background": {
+            "anyOf": [
+              {
+                "type": "boolean",
+                "description": "Whether to run the model response in the background.\n[Learn more](https://developers.openai.com/api/docs/guides/background).\n",
+                "default": false
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "max_tool_calls": {
+            "anyOf": [
+              {
+                "description": "The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.\n",
+                "type": "integer"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "text": {
+            "$ref": "#/components/schemas/ResponseTextParam"
+          },
+          "tools": {
+            "$ref": "#/components/schemas/ToolsArray"
+          },
+          "tool_choice": {
+            "$ref": "#/components/schemas/ToolChoiceParam"
+          },
+          "prompt": {
+            "$ref": "#/components/schemas/Prompt"
+          }
+        }
+      },
+      "ResponseQueuedEvent": {
+        "type": "object",
+        "title": "ResponseQueuedEvent",
+        "description": "Emitted when a response is queued and waiting to be processed.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.queued"
+            ],
+            "description": "The type of the event. Always 'response.queued'.",
+            "x-stainless-const": true
+          },
+          "response": {
+            "$ref": "#/components/schemas/Response",
+            "description": "The full response object that is queued."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number for this event."
+          }
+        },
+        "required": [
+          "type",
+          "response",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.queued",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.queued\",\n  \"response\": {\n    \"id\": \"res_123\",\n    \"status\": \"queued\",\n    \"created_at\": \"2021-01-01T00:00:00Z\",\n    \"updated_at\": \"2021-01-01T00:00:00Z\"\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseReasoningSummaryPartAddedEvent": {
+        "type": "object",
+        "description": "Emitted when a new reasoning summary part is added.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.reasoning_summary_part.added`.\n",
+            "enum": [
+              "response.reasoning_summary_part.added"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item this summary part is associated with.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item this summary part is associated with.\n"
+          },
+          "summary_index": {
+            "type": "integer",
+            "description": "The index of the summary part within the reasoning summary.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event.\n"
+          },
+          "part": {
+            "type": "object",
+            "description": "The summary part that was added.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "description": "The type of the summary part. Always `summary_text`.",
+                "enum": [
+                  "summary_text"
+                ],
+                "x-stainless-const": true
+              },
+              "text": {
+                "type": "string",
+                "description": "The text of the summary part."
+              }
+            },
+            "required": [
+              "type",
+              "text"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "summary_index",
+          "part",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.reasoning_summary_part.added",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.reasoning_summary_part.added\",\n  \"item_id\": \"rs_6806bfca0b2481918a5748308061a2600d3ce51bdffd5476\",\n  \"output_index\": 0,\n  \"summary_index\": 0,\n  \"part\": {\n    \"type\": \"summary_text\",\n    \"text\": \"\"\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseReasoningSummaryPartDoneEvent": {
+        "type": "object",
+        "description": "Emitted when a reasoning summary part is completed.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.reasoning_summary_part.done`.\n",
+            "enum": [
+              "response.reasoning_summary_part.done"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item this summary part is associated with.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item this summary part is associated with.\n"
+          },
+          "summary_index": {
+            "type": "integer",
+            "description": "The index of the summary part within the reasoning summary.\n"
+          },
+          "status": {
+            "type": "string",
+            "description": "The completion status of the summary part. Omitted when the part completed\nnormally and set to `incomplete` when generation was interrupted.\n",
+            "enum": [
+              "incomplete"
+            ]
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event.\n"
+          },
+          "part": {
+            "type": "object",
+            "description": "The completed summary part.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "description": "The type of the summary part. Always `summary_text`.",
+                "enum": [
+                  "summary_text"
+                ],
+                "x-stainless-const": true
+              },
+              "text": {
+                "type": "string",
+                "description": "The text of the summary part."
+              }
+            },
+            "required": [
+              "type",
+              "text"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "summary_index",
+          "part",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.reasoning_summary_part.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.reasoning_summary_part.done\",\n  \"item_id\": \"rs_6806bfca0b2481918a5748308061a2600d3ce51bdffd5476\",\n  \"output_index\": 0,\n  \"summary_index\": 0,\n  \"part\": {\n    \"type\": \"summary_text\",\n    \"text\": \"**Responding to a greeting**\\n\\nThe user just said, \\\"Hello!\\\" So, it seems I need to engage. I'll greet them back and offer help since they're looking to chat. I could say something like, \\\"Hello! How can I assist you today?\\\" That feels friendly and open. They didn't ask a specific question, so this approach will work well for starting a conversation. Let's see where it goes from there!\"\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseReasoningSummaryTextDeltaEvent": {
+        "type": "object",
+        "description": "Emitted when a delta is added to a reasoning summary text.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.reasoning_summary_text.delta`.\n",
+            "enum": [
+              "response.reasoning_summary_text.delta"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item this summary text delta is associated with.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item this summary text delta is associated with.\n"
+          },
+          "summary_index": {
+            "type": "integer",
+            "description": "The index of the summary part within the reasoning summary.\n"
+          },
+          "delta": {
+            "type": "string",
+            "description": "The text delta that was added to the summary.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event.\n"
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "summary_index",
+          "delta",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.reasoning_summary_text.delta",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.reasoning_summary_text.delta\",\n  \"item_id\": \"rs_6806bfca0b2481918a5748308061a2600d3ce51bdffd5476\",\n  \"output_index\": 0,\n  \"summary_index\": 0,\n  \"delta\": \"**Responding to a greeting**\\n\\nThe user just said, \\\"Hello!\\\" So, it seems I need to engage. I'll greet them back and offer help since they're looking to chat. I could say something like, \\\"Hello! How can I assist you today?\\\" That feels friendly and open. They didn't ask a specific question, so this approach will work well for starting a conversation. Let's see where it goes from there!\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseReasoningSummaryTextDoneEvent": {
+        "type": "object",
+        "description": "Emitted when a reasoning summary text is completed.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.reasoning_summary_text.done`.\n",
+            "enum": [
+              "response.reasoning_summary_text.done"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item this summary text is associated with.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item this summary text is associated with.\n"
+          },
+          "summary_index": {
+            "type": "integer",
+            "description": "The index of the summary part within the reasoning summary.\n"
+          },
+          "text": {
+            "type": "string",
+            "description": "The full text of the completed reasoning summary.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event.\n"
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "summary_index",
+          "text",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.reasoning_summary_text.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.reasoning_summary_text.done\",\n  \"item_id\": \"rs_6806bfca0b2481918a5748308061a2600d3ce51bdffd5476\",\n  \"output_index\": 0,\n  \"summary_index\": 0,\n  \"text\": \"**Responding to a greeting**\\n\\nThe user just said, \\\"Hello!\\\" So, it seems I need to engage. I'll greet them back and offer help since they're looking to chat. I could say something like, \\\"Hello! How can I assist you today?\\\" That feels friendly and open. They didn't ask a specific question, so this approach will work well for starting a conversation. Let's see where it goes from there!\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseReasoningTextDeltaEvent": {
+        "type": "object",
+        "description": "Emitted when a delta is added to a reasoning text.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.reasoning_text.delta`.\n",
+            "enum": [
+              "response.reasoning_text.delta"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item this reasoning text delta is associated with.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item this reasoning text delta is associated with.\n"
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the reasoning content part this delta is associated with.\n"
+          },
+          "delta": {
+            "type": "string",
+            "description": "The text delta that was added to the reasoning content.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event.\n"
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "content_index",
+          "delta",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.reasoning_text.delta",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.reasoning_text.delta\",\n  \"item_id\": \"rs_123\",\n  \"output_index\": 0,\n  \"content_index\": 0,\n  \"delta\": \"The\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseReasoningTextDoneEvent": {
+        "type": "object",
+        "description": "Emitted when a reasoning text is completed.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.reasoning_text.done`.\n",
+            "enum": [
+              "response.reasoning_text.done"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item this reasoning text is associated with.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item this reasoning text is associated with.\n"
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the reasoning content part.\n"
+          },
+          "text": {
+            "type": "string",
+            "description": "The full text of the completed reasoning content.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event.\n"
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "content_index",
+          "text",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.reasoning_text.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.reasoning_text.done\",\n  \"item_id\": \"rs_123\",\n  \"output_index\": 0,\n  \"content_index\": 0,\n  \"text\": \"The user is asking...\",\n  \"sequence_number\": 4\n}\n"
+        }
+      },
+      "ResponseRefusalDeltaEvent": {
+        "type": "object",
+        "description": "Emitted when there is a partial refusal text.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.refusal.delta`.\n",
+            "enum": [
+              "response.refusal.delta"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that the refusal text is added to.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the refusal text is added to.\n"
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part that the refusal text is added to.\n"
+          },
+          "delta": {
+            "type": "string",
+            "description": "The refusal text that is added.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event.\n"
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "content_index",
+          "delta",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.refusal.delta",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.refusal.delta\",\n  \"item_id\": \"msg_123\",\n  \"output_index\": 0,\n  \"content_index\": 0,\n  \"delta\": \"refusal text so far\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseRefusalDoneEvent": {
+        "type": "object",
+        "description": "Emitted when refusal text is finalized.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.refusal.done`.\n",
+            "enum": [
+              "response.refusal.done"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that the refusal text is finalized.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the refusal text is finalized.\n"
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part that the refusal text is finalized.\n"
+          },
+          "refusal": {
+            "type": "string",
+            "description": "The refusal text that is finalized.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event.\n"
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "content_index",
+          "refusal",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.refusal.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.refusal.done\",\n  \"item_id\": \"item-abc\",\n  \"output_index\": 1,\n  \"content_index\": 2,\n  \"refusal\": \"final refusal text\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseSteerAcceptedEvent": {
+        "type": "object",
+        "title": "ResponseSteerAcceptedEvent",
+        "description": "Emitted when steering input has been validated and queued. Acceptance means\nthe server owns the input, not that it has been applied. The successor's\n`response.created` event is the commit point. If accepted input cannot be\ncommitted, `response.steer.failed` returns it with the same steering ID.\n\nWhen the response stops for client-owned tool output or approval, the input\nremains queued and `response.steer.pending` is emitted after\n`response.completed`. Fill the pending event's `required_input` stubs with\nsaved results and send one matching explicit `response.create` per parent.\nDo not resend accepted input while it is still queued.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.steer.accepted"
+            ],
+            "description": "The event discriminator. Always `response.steer.accepted`.",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number for this event."
+          },
+          "steer": {
+            "type": "object",
+            "description": "The accepted steering submission.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID assigned to the steering submission."
+              },
+              "previous_response_id": {
+                "type": "string",
+                "description": "The ID of the response being steered."
+              }
+            },
+            "required": [
+              "id",
+              "previous_response_id"
+            ]
+          },
+          "stream_id": {
+            "type": "string",
+            "description": "The WebSocket lane that emitted this event. This field is present when\nthe target response's `response.create` event supplied a `stream_id`.\n"
+          }
+        },
+        "required": [
+          "type",
+          "sequence_number",
+          "steer"
+        ],
+        "x-oaiMeta": {
+          "name": "response.steer.accepted",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.steer.accepted\",\n  \"sequence_number\": 2,\n  \"steer\": {\n    \"id\": \"steer_456\",\n    \"previous_response_id\": \"resp_123\"\n  }\n}\n"
+        }
+      },
+      "ResponseSteerErrorCode": {
+        "title": "ResponseSteerErrorCode",
+        "description": "A machine-readable steering error code. Clients should handle unknown\nvalues because additional codes may be introduced. Known values include:\n- `response_not_found`: The target response is not available on this connection.\n- `invalid_input`: The event or input failed validation.\n- `steering_not_supported`: The model or response execution mode does not support steering.\n- `too_many_pending_steers`: Too much steering input is pending for the response.\n- `response_already_completed`: The response completed and is no longer accepting steering input.\n- `response_not_active`: The response is no longer accepting steering input.\n- `successor_creation_failed`: The successor response could not be created.\n",
+        "anyOf": [
+          {
+            "type": "string",
+            "enum": [
+              "response_not_found",
+              "invalid_input",
+              "steering_not_supported",
+              "too_many_pending_steers",
+              "response_already_completed",
+              "response_not_active",
+              "successor_creation_failed"
+            ]
+          },
+          {
+            "type": "string"
+          }
+        ]
+      },
+      "ResponseSteerEvent": {
+        "type": "object",
+        "title": "ResponseSteerEvent",
+        "additionalProperties": false,
+        "description": "Queues user input to steer a response on this WebSocket connection. Input\ncan contain text, images, and files. Steering is supported only for\nsingle-agent responses on models and execution modes that support steering.\nResponses bound to a conversation or using automatic compaction do not\nsupport steering.\n\nA `response.steer.accepted` event acknowledges that the server owns the\nqueued input, not that it has been applied. The successor's `response.created`\nevent is the commit point. Input that cannot be committed is returned in\n`response.steer.failed`.\n\nSteering may cause the active response to finish at a safe output boundary\nwith `response.incomplete` and `incomplete_details.reason` set to `steered`,\nfollowed automatically by a successor `response.created`. Normal completion\ncan also be followed by an automatic successor. Automatic successors inherit\nthe previous response's settings and continue from it with the queued input.\n\nIf the response stops for client-owned tool output or approval, accepted\nsteering input remains queued and `response.steer.pending` is emitted after\n`response.completed`. Fill the `required_input` stubs from that event with\nsaved tool results or approval decisions, and send one explicit\n`response.create` per parent with the same `previous_response_id` and\nWebSocket lane. Do not rerun tools or resend accepted steering input. The\nqueued input is prepended in submission order to that request's input, and\nthe explicit request retains its own settings.\n\nThis event accepts only `type`, `previous_response_id`, and `input`. Do not\nsend `stream_id`; the target response determines the WebSocket lane.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.steer"
+            ],
+            "description": "The event discriminator. Always `response.steer`.",
+            "x-stainless-const": true
+          },
+          "previous_response_id": {
+            "type": "string",
+            "description": "The ID of the response to steer on this WebSocket connection."
+          },
+          "input": {
+            "$ref": "#/components/schemas/ResponseSteerInput"
+          }
+        },
+        "required": [
+          "type",
+          "previous_response_id",
+          "input"
+        ],
+        "x-oaiMeta": {
+          "name": "response.steer",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.steer\",\n  \"previous_response_id\": \"resp_123\",\n  \"input\": [\n    {\n      \"type\": \"message\",\n      \"role\": \"user\",\n      \"content\": [\n        {\n          \"type\": \"input_text\",\n          \"text\": \"Prioritize the database rollout.\"\n        }\n      ]\n    }\n  ]\n}\n"
+        }
+      },
+      "ResponseSteerFailedEvent": {
+        "type": "object",
+        "title": "ResponseSteerFailedEvent",
+        "description": "Emitted when steering input is rejected or cannot be committed to a\nsuccessor response. Returns the original, uncommitted input so the client\ncan carry it into `response.create` when appropriate. Invalid input must\nbe corrected before retrying.\n\nFailures after acceptance include the same steering ID. Failures before an\nID is allocated omit `steer.id`. A lost connection or missing acknowledgement\nleaves the outcome unknown; it is not proof that the input was rejected.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.steer.failed"
+            ],
+            "description": "The event discriminator. Always `response.steer.failed`.",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number for this event."
+          },
+          "steer": {
+            "type": "object",
+            "description": "The steering submission that could not be committed.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID assigned to the steering submission, if one was allocated.\n"
+              },
+              "previous_response_id": {
+                "type": "string",
+                "description": "The ID of the response that was targeted for steering."
+              },
+              "input": {
+                "$ref": "#/components/schemas/ResponseSteerInput"
+              }
+            },
+            "required": [
+              "previous_response_id",
+              "input"
+            ]
+          },
+          "error": {
+            "type": "object",
+            "description": "Information about why the input could not be committed.",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "invalid_request_error"
+                ],
+                "description": "The error type. Always `invalid_request_error`.",
+                "x-stainless-const": true
+              },
+              "code": {
+                "$ref": "#/components/schemas/ResponseSteerErrorCode"
+              },
+              "message": {
+                "type": "string",
+                "description": "A human-readable description of the error."
+              }
+            },
+            "required": [
+              "type",
+              "code",
+              "message"
+            ]
+          },
+          "stream_id": {
+            "type": "string",
+            "description": "The WebSocket lane that emitted this event, when the target response is\navailable and its `response.create` event supplied a `stream_id`.\n"
+          }
+        },
+        "required": [
+          "type",
+          "sequence_number",
+          "steer",
+          "error"
+        ],
+        "x-oaiMeta": {
+          "name": "response.steer.failed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.steer.failed\",\n  \"sequence_number\": 5,\n  \"steer\": {\n    \"id\": \"steer_456\",\n    \"previous_response_id\": \"resp_123\",\n    \"input\": [\n      {\n        \"type\": \"message\",\n        \"role\": \"user\",\n        \"content\": [\n          {\n            \"type\": \"input_text\",\n            \"text\": \"Prioritize the database rollout.\"\n          }\n        ]\n      }\n    ]\n  },\n  \"error\": {\n    \"type\": \"invalid_request_error\",\n    \"code\": \"successor_creation_failed\",\n    \"message\": \"We couldn't start the next response. Send this steering input again with response.create.\"\n  }\n}\n"
+        }
+      },
+      "ResponseSteerInput": {
+        "title": "ResponseSteerInput",
+        "description": "Input to queue for a continuation of the response. Uses the same string or\ninput-item shape as `response.create.input`, with a non-empty array when\nsupplying input items.\n\nSteering accepts only messages with the `user` role. Each message may\ncontain only `type`, `role`, and `content`, with `content` as a string or an\narray of `input_text`, `input_image`, and `input_file` parts. The optional\n`type` must be `message`. Other roles, tool outputs, and item types are not\nsupported for steering.\n",
+        "oneOf": [
+          {
+            "type": "string",
+            "title": "Text input",
+            "description": "A text input, equivalent to a message with the `user` role."
+          },
+          {
+            "$ref": "#/components/schemas/ResponseSteerInputItemList"
+          }
+        ]
+      },
+      "ResponseSteerInputItem": {
+        "title": "Response steer input item",
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/UserMessageItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionCallOutputItemParam"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "ResponseSteerInputItemList": {
+        "type": "array",
+        "title": "Response steer input item list",
+        "description": "A non-empty list of message inputs to queue for the response.",
+        "minItems": 1,
+        "items": {
+          "$ref": "#/components/schemas/ResponseSteerInputItem"
+        }
+      },
+      "ResponseSteerPendingEvent": {
+        "type": "object",
+        "title": "ResponseSteerPendingEvent",
+        "description": "Emitted when accepted steering input remains queued after the target\nresponse completes. The server still owns the input. Do not resend it.\nThe successor's `response.created` event is the commit point.\n\nWhen `reason` is `waiting_for_required_input`, this event follows\n`response.completed` while the response waits for the tool results or\napproval decisions identified by `required_input`. Copy those stubs, fill\ntheir result fields using the ordinary `response.create` input schemas,\nand submit one continuation per parent with the same `previous_response_id`\nand WebSocket lane. Use saved results without rerunning tools. The queued\nsteering input is prepended in submission order to the continuation's\ninput. That explicit request retains its own settings.\n\nThis notification is emitted at most once per steering submission. Multiple\nsubmissions for the same parent can report the same required inputs; they\ndo not each require a separate continuation.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.steer.pending"
+            ],
+            "description": "The event discriminator. Always `response.steer.pending`.",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number for this event."
+          },
+          "steer": {
+            "type": "object",
+            "description": "The steering submission that remains queued.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID assigned to the steering submission."
+              },
+              "previous_response_id": {
+                "type": "string",
+                "description": "The ID of the response being steered."
+              }
+            },
+            "required": [
+              "id",
+              "previous_response_id"
+            ]
+          },
+          "reason": {
+            "$ref": "#/components/schemas/ResponseSteerPendingReason"
+          },
+          "required_input": {
+            "type": "array",
+            "minItems": 1,
+            "description": "Input stubs identifying outstanding client-owned tool results or\napproval decisions. Each stub contains identifying fields only; the\nclient supplies the result before including it in `response.create`.\n",
+            "items": {
+              "$ref": "#/components/schemas/ResponseSteerRequiredInput"
+            }
+          },
+          "stream_id": {
+            "type": "string",
+            "description": "The WebSocket lane that emitted this event. This field is present when\nthe target response's `response.create` event supplied a `stream_id`.\n"
+          }
+        },
+        "required": [
+          "type",
+          "sequence_number",
+          "steer",
+          "reason",
+          "required_input"
+        ],
+        "x-oaiMeta": {
+          "name": "response.steer.pending",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.steer.pending\",\n  \"sequence_number\": 10,\n  \"steer\": {\n    \"id\": \"steer_456\",\n    \"previous_response_id\": \"resp_123\"\n  },\n  \"reason\": \"waiting_for_required_input\",\n  \"required_input\": [\n    {\n      \"type\": \"function_call_output\",\n      \"call_id\": \"call_789\",\n      \"name\": \"lookup\"\n    }\n  ]\n}\n"
+        }
+      },
+      "ResponseSteerPendingReason": {
+        "title": "ResponseSteerPendingReason",
+        "description": "An extensible enum describing why accepted steering input is still queued.\nClients should handle unknown values because additional reasons may be\nintroduced. Known values include:\n- `waiting_for_required_input`: The response is waiting for the tool results or approval decisions identified by `required_input`.\n",
+        "anyOf": [
+          {
+            "type": "string",
+            "enum": [
+              "waiting_for_required_input"
+            ]
+          },
+          {
+            "type": "string"
+          }
+        ]
+      },
+      "ResponseSteerRequiredInput": {
+        "title": "ResponseSteerRequiredInput",
+        "description": "An input stub identifying an outstanding client-owned tool result or\napproval decision. Copy the stub and fill the result fields using the\ncorresponding `response.create` input schema. Use saved results without\nrerunning the tool. The server does not supply results, approval decisions,\nor safety acknowledgements in these stubs.\n",
+        "oneOf": [
+          {
+            "type": "object",
+            "title": "Required function tool call output",
+            "additionalProperties": false,
+            "description": "Supply `output` using the function tool call output input schema.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "function_call_output"
+                ],
+                "x-stainless-const": true
+              },
+              "call_id": {
+                "type": "string"
+              },
+              "name": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "type",
+              "call_id",
+              "name"
+            ]
+          },
+          {
+            "type": "object",
+            "title": "Required custom tool call output",
+            "additionalProperties": false,
+            "description": "Supply `output` using the custom tool call output input schema. The\noriginal custom tool call supplies the tool's name.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "custom_tool_call_output"
+                ],
+                "x-stainless-const": true
+              },
+              "call_id": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "type",
+              "call_id"
+            ]
+          },
+          {
+            "type": "object",
+            "title": "Required computer tool call output",
+            "additionalProperties": false,
+            "description": "Supply `output` using the computer tool call output input schema,\nincluding any required `acknowledged_safety_checks`.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "computer_call_output"
+                ],
+                "x-stainless-const": true
+              },
+              "call_id": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "type",
+              "call_id"
+            ]
+          },
+          {
+            "type": "object",
+            "title": "Required shell tool call output",
+            "additionalProperties": false,
+            "description": "Supply `output` using the shell tool call output input schema. Each\noutput entry includes `stdout`, `stderr`, and `outcome`.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "shell_call_output"
+                ],
+                "x-stainless-const": true
+              },
+              "call_id": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "type",
+              "call_id"
+            ]
+          },
+          {
+            "type": "object",
+            "title": "Required apply patch tool call output",
+            "additionalProperties": false,
+            "description": "Supply `status` and optional `output` using the apply patch tool call\noutput input schema.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "apply_patch_call_output"
+                ],
+                "x-stainless-const": true
+              },
+              "call_id": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "type",
+              "call_id"
+            ]
+          },
+          {
+            "type": "object",
+            "title": "Required tool search output",
+            "additionalProperties": false,
+            "description": "Supply `tools` using the tool search output input schema, retaining\n`execution: \"client\"`.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "tool_search_output"
+                ],
+                "x-stainless-const": true
+              },
+              "call_id": {
+                "type": "string"
+              },
+              "execution": {
+                "type": "string",
+                "enum": [
+                  "client"
+                ],
+                "x-stainless-const": true
+              }
+            },
+            "required": [
+              "type",
+              "call_id",
+              "execution"
+            ]
+          },
+          {
+            "type": "object",
+            "title": "Required MCP approval response",
+            "additionalProperties": false,
+            "description": "Supply `approve` using the MCP approval response input schema. An\noptional `reason` can be supplied when denying the request. The original\napproval request identifies the tool and server.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "mcp_approval_response"
+                ],
+                "x-stainless-const": true
+              },
+              "approval_request_id": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "type",
+              "approval_request_id"
+            ]
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "ResponseStreamEvent": {
+        "description": "Event emitted while a response is streamed.",
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/ResponseAudioDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseAudioDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseAudioTranscriptDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseAudioTranscriptDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseCodeInterpreterCallCodeDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseCodeInterpreterCallCodeDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseCodeInterpreterCallCompletedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseCodeInterpreterCallInProgressEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseCodeInterpreterCallInterpretingEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseCompletedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseContentPartAddedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseContentPartDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseCreatedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseErrorEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseFileSearchCallCompletedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseFileSearchCallInProgressEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseFileSearchCallSearchingEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseFunctionCallArgumentsDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseFunctionCallArgumentsDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseShellCallCommandAddedStreamingEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseShellCallCommandDeltaStreamingEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseShellCallCommandDoneStreamingEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseShellCallOutputContentDeltaStreamingEvent",
+            "x-stainless-skip": [
+              "go"
+            ]
+          },
+          {
+            "$ref": "#/components/schemas/ResponseShellCallOutputContentDoneStreamingEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseInProgressEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseFailedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseIncompleteEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseOutputItemAddedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseOutputItemDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseReasoningSummaryPartAddedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseReasoningSummaryPartDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseReasoningSummaryTextDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseReasoningSummaryTextDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseReasoningTextDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseReasoningTextDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseRefusalDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseRefusalDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseTextDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseTextDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseWebSearchCallCompletedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseWebSearchCallInProgressEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseWebSearchCallSearchingEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseImageGenCallCompletedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseImageGenCallGeneratingEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseImageGenCallInProgressEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseImageGenCallPartialImageEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseMCPCallArgumentsDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseMCPCallArgumentsDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseMCPCallCompletedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseMCPCallFailedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseMCPCallInProgressEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseMCPListToolsCompletedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseMCPListToolsFailedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseMCPListToolsInProgressEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseOutputTextAnnotationAddedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseQueuedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseCustomToolCallInputDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseCustomToolCallInputDoneEvent"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "ResponseStreamOptions": {
+        "anyOf": [
+          {
+            "description": "Options for streaming responses. Only set this when you set `stream: true`.\n",
+            "type": "object",
+            "default": null,
+            "properties": {
+              "include_obfuscation": {
+                "type": "boolean",
+                "description": "When true, stream obfuscation will be enabled. Stream obfuscation adds\nrandom characters to an `obfuscation` field on streaming delta events to\nnormalize payload sizes as a mitigation to certain side-channel attacks.\nThese obfuscation fields are included by default, but add a small amount\nof overhead to the data stream. You can set `include_obfuscation` to\nfalse to optimize for bandwidth if you trust the network links between\nyour application and the OpenAI API.\n"
+              }
+            }
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "ResponseTextDeltaEvent": {
+        "type": "object",
+        "description": "Emitted when there is an additional text delta.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.output_text.delta`.\n",
+            "enum": [
+              "response.output_text.delta"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that the text delta was added to.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the text delta was added to.\n"
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part that the text delta was added to.\n"
+          },
+          "delta": {
+            "type": "string",
+            "description": "The text delta that was added.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number for this event."
+          },
+          "logprobs": {
+            "type": "array",
+            "description": "The log probabilities of the tokens in the delta.\n",
+            "items": {
+              "$ref": "#/components/schemas/ResponseLogProb"
+            }
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "content_index",
+          "delta",
+          "sequence_number",
+          "logprobs"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_text.delta",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.output_text.delta\",\n  \"item_id\": \"msg_123\",\n  \"output_index\": 0,\n  \"content_index\": 0,\n  \"delta\": \"In\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseTextDoneEvent": {
+        "type": "object",
+        "description": "Emitted when text content is finalized.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.output_text.done`.\n",
+            "enum": [
+              "response.output_text.done"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that the text content is finalized.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the text content is finalized.\n"
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part that the text content is finalized.\n"
+          },
+          "text": {
+            "type": "string",
+            "description": "The text content that is finalized.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number for this event."
+          },
+          "logprobs": {
+            "type": "array",
+            "description": "The log probabilities of the tokens in the delta.\n",
+            "items": {
+              "$ref": "#/components/schemas/ResponseLogProb"
+            }
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "content_index",
+          "text",
+          "sequence_number",
+          "logprobs"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_text.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.output_text.done\",\n  \"item_id\": \"msg_123\",\n  \"output_index\": 0,\n  \"content_index\": 0,\n  \"text\": \"In a shimmering forest under a sky full of stars, a lonely unicorn named Lila discovered a hidden pond that glowed with moonlight. Every night, she would leave sparkling, magical flowers by the water's edge, hoping to share her beauty with others. One enchanting evening, she woke to find a group of friendly animals gathered around, eager to be friends and share in her magic.\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "ResponseTextParam": {
+        "type": "object",
+        "description": "Configuration options for a text response from the model. Can be plain\ntext or structured JSON data. Learn more:\n- [Text inputs and outputs](https://developers.openai.com/api/docs/guides/text)\n- [Structured Outputs](https://developers.openai.com/api/docs/guides/structured-outputs)\n",
+        "properties": {
+          "format": {
+            "$ref": "#/components/schemas/TextResponseFormatConfiguration"
+          },
+          "verbosity": {
+            "$ref": "#/components/schemas/Verbosity"
+          }
+        }
+      },
+      "ResponseUsage": {
+        "type": "object",
+        "description": "Represents token usage details including input tokens, output tokens,\na breakdown of output tokens, and the total tokens used.\n",
+        "properties": {
+          "input_tokens": {
+            "type": "integer",
+            "description": "The number of input tokens."
+          },
+          "input_tokens_details": {
+            "type": "object",
+            "description": "A detailed breakdown of the input tokens.",
+            "properties": {
+              "cached_tokens": {
+                "type": "integer",
+                "description": "The number of tokens that were retrieved from the cache.\n[More on prompt caching](https://developers.openai.com/api/docs/guides/prompt-caching).\n"
+              },
+              "cache_write_tokens": {
+                "type": "integer",
+                "description": "The number of input tokens that were written to the cache."
+              }
+            },
+            "required": [
+              "cached_tokens",
+              "cache_write_tokens"
+            ]
+          },
+          "output_tokens": {
+            "type": "integer",
+            "description": "The number of output tokens."
+          },
+          "output_tokens_details": {
+            "type": "object",
+            "description": "A detailed breakdown of the output tokens.",
+            "properties": {
+              "reasoning_tokens": {
+                "type": "integer",
+                "description": "The number of reasoning tokens."
+              }
+            },
+            "required": [
+              "reasoning_tokens"
+            ]
+          },
+          "total_tokens": {
+            "type": "integer",
+            "description": "The total number of tokens used."
+          }
+        },
+        "required": [
+          "input_tokens",
+          "input_tokens_details",
+          "output_tokens",
+          "output_tokens_details",
+          "total_tokens"
+        ]
+      },
+      "ResponseWebSearchCallCompletedEvent": {
+        "type": "object",
+        "description": "Emitted when a web search call is completed.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.web_search_call.completed`.\n",
+            "enum": [
+              "response.web_search_call.completed"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the web search call is associated with.\n"
+          },
+          "item_id": {
+            "type": "string",
+            "description": "Unique ID for the output item associated with the web search call.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the web search call being processed."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.web_search_call.completed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.web_search_call.completed\",\n  \"output_index\": 0,\n  \"item_id\": \"ws_123\",\n  \"sequence_number\": 0\n}\n"
+        }
+      },
+      "ResponseWebSearchCallInProgressEvent": {
+        "type": "object",
+        "description": "Emitted when a web search call is initiated.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.web_search_call.in_progress`.\n",
+            "enum": [
+              "response.web_search_call.in_progress"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the web search call is associated with.\n"
+          },
+          "item_id": {
+            "type": "string",
+            "description": "Unique ID for the output item associated with the web search call.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the web search call being processed."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.web_search_call.in_progress",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.web_search_call.in_progress\",\n  \"output_index\": 0,\n  \"item_id\": \"ws_123\",\n  \"sequence_number\": 0\n}\n"
+        }
+      },
+      "ResponseWebSearchCallSearchingEvent": {
+        "type": "object",
+        "description": "Emitted when a web search call is executing.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.web_search_call.searching`.\n",
+            "enum": [
+              "response.web_search_call.searching"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the web search call is associated with.\n"
+          },
+          "item_id": {
+            "type": "string",
+            "description": "Unique ID for the output item associated with the web search call.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the web search call being processed."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.web_search_call.searching",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.web_search_call.searching\",\n  \"output_index\": 0,\n  \"item_id\": \"ws_123\",\n  \"sequence_number\": 0\n}\n"
+        }
+      },
+      "ResponseWsError": {
+        "type": "object",
+        "title": "ResponseWsError",
+        "description": "Emitted when an error occurs while processing a Responses WebSocket request.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `error`.",
+            "enum": [
+              "error"
+            ],
+            "x-stainless-const": true
+          },
+          "status": {
+            "type": "integer",
+            "description": "The HTTP status code associated with a WebSocket protocol error."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of an error emitted by the response stream."
+          },
+          "error": {
+            "$ref": "#/components/schemas/ErrorPayload",
+            "description": "Details about the error."
+          },
+          "stream_id": {
+            "type": "string",
+            "description": "The WebSocket lane that emitted this event. This field is present when the\noriginating `response.create` event supplied a `stream_id`.\n"
+          }
+        },
+        "required": [
+          "type",
+          "error"
+        ],
+        "x-oaiMeta": {
+          "name": "error",
+          "group": "responses",
+          "example": "{\n  \"type\": \"error\",\n  \"status\": 400,\n  \"stream_id\": \"agent_1\",\n  \"error\": {\n    \"type\": \"invalid_request_error\",\n    \"code\": \"websocket_stream_limit_reached\",\n    \"message\": \"This WebSocket connection has reached its stream limit.\",\n    \"param\": \"stream_id\"\n  }\n}\n"
+        }
+      },
+      "ResponsesClientEvent": {
+        "discriminator": {
+          "propertyName": "type"
+        },
+        "description": "Client events accepted by the Responses WebSocket server.\n",
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/ResponsesClientEventResponseCreate"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseSteerEvent"
+          }
+        ]
+      },
+      "ResponsesClientEventResponseCreate": {
+        "allOf": [
+          {
+            "type": "object",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "response.create"
+                ],
+                "description": "The type of the client event. Always `response.create`.\n",
+                "x-stainless-const": true
+              },
+              "stream_id": {
+                "type": "string",
+                "minLength": 1,
+                "maxLength": 256,
+                "pattern": "^[A-Za-z0-9_.-]+$",
+                "description": "The WebSocket lane for this response. Requests with the same\n`stream_id` are processed FIFO, and events for the response echo the\nsame `stream_id`.\n\n`stream_id` controls routing; `previous_response_id` controls\nconversation lineage, so a new lane can fork from a response created\non another lane.\n"
+              }
+            },
+            "required": [
+              "type"
+            ]
+          },
+          {
+            "$ref": "#/components/schemas/CreateResponse"
+          }
+        ],
+        "description": "Client event for creating a response over a persistent WebSocket connection.\nThis payload uses the same top-level fields as `POST /v1/responses`, plus\nWebSocket-only envelope metadata.\n\nNotes:\n- `stream` is implicit over WebSocket and should not be sent.\n- `background` is not supported over WebSocket.\n- `stream_id` is WebSocket-only and is not part of `POST /v1/responses`.\n",
+        "x-oaiMeta": {
+          "example": "{\n  \"type\": \"response.create\",\n  \"stream_id\": \"agent_1\",\n  \"model\": \"gpt-6-astra\",\n  \"input\": \"Say hello.\"\n}\n"
+        }
+      },
+      "ResponsesServerEvent": {
+        "discriminator": {
+          "propertyName": "type"
+        },
+        "description": "Server events emitted by the Responses WebSocket server.\n",
+        "anyOf": [
+          {
+            "title": "ResponseAudioWsDelta",
+            "description": "Emitted when there is a partial audio response.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseAudioDeltaEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseAudioWsDone",
+            "description": "Emitted when the audio response is complete.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseAudioDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseAudioTranscriptWsDelta",
+            "description": "Emitted when there is a partial transcript of audio.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseAudioTranscriptDeltaEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseAudioTranscriptWsDone",
+            "description": "Emitted when the full audio transcript is completed.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseAudioTranscriptDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseCodeInterpreterCallCodeWsDelta",
+            "description": "Emitted when a partial code snippet is streamed by the code interpreter.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseCodeInterpreterCallCodeDeltaEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseCodeInterpreterCallCodeWsDone",
+            "description": "Emitted when the code snippet is finalized by the code interpreter.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseCodeInterpreterCallCodeDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseCodeInterpreterCallWsCompleted",
+            "description": "Emitted when the code interpreter call is completed.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseCodeInterpreterCallCompletedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseCodeInterpreterCallInWsProgress",
+            "description": "Emitted when a code interpreter call is in progress.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseCodeInterpreterCallInProgressEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseCodeInterpreterCallWsInterpreting",
+            "description": "Emitted when the code interpreter is actively interpreting the code snippet.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseCodeInterpreterCallInterpretingEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseWsCompleted",
+            "description": "Emitted when the model response is complete.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseCompletedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseContentPartWsAdded",
+            "description": "Emitted when a new content part is added.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseContentPartAddedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseContentPartWsDone",
+            "description": "Emitted when a content part is done.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseContentPartDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseWsCreated",
+            "description": "An event that is emitted when a response is created.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseCreatedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseFileSearchCallWsCompleted",
+            "description": "Emitted when a file search call is completed (results found).",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseFileSearchCallCompletedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseFileSearchCallInWsProgress",
+            "description": "Emitted when a file search call is initiated.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseFileSearchCallInProgressEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseFileSearchCallWsSearching",
+            "description": "Emitted when a file search is currently searching.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseFileSearchCallSearchingEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseFunctionCallArgumentsWsDelta",
+            "description": "Emitted when there is a partial function-call arguments delta.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseFunctionCallArgumentsDeltaEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseFunctionCallArgumentsWsDone",
+            "description": "Emitted when function-call arguments are finalized.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseFunctionCallArgumentsDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseShellCallCommandWsAdded",
+            "description": "A streaming event that indicated a shell command was added to a tool call.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseShellCallCommandAddedStreamingEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseShellCallCommandWsDelta",
+            "description": "A streaming event that indicated a shell command was incrementally updated.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseShellCallCommandDeltaStreamingEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseShellCallCommandWsDone",
+            "description": "A streaming event that indicated a shell command was completed.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseShellCallCommandDoneStreamingEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseShellCallOutputContentWsDelta",
+            "description": "A streaming event that indicated shell call output was incrementally added.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseShellCallOutputContentDeltaStreamingEvent",
+                "x-stainless-skip": [
+                  "go"
+                ]
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseShellCallOutputContentWsDone",
+            "description": "A streaming event that indicated shell call output was completed.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseShellCallOutputContentDoneStreamingEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseInWsProgress",
+            "description": "Emitted when the response is in progress.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseInProgressEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseWsFailed",
+            "description": "An event that is emitted when a response fails.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseFailedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseWsIncomplete",
+            "description": "An event that is emitted when a response finishes as incomplete.\n\nOver WebSocket, steering can finish a response with\n`response.incomplete_details.reason` set to `steered`, followed automatically\nby a successor `response.created` that commits the queued steering input.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseIncompleteEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseOutputItemWsAdded",
+            "description": "Emitted when a new output item is added.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseOutputItemAddedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseOutputItemWsDone",
+            "description": "Emitted when an output item is marked done.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseOutputItemDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseReasoningSummaryPartWsAdded",
+            "description": "Emitted when a new reasoning summary part is added.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseReasoningSummaryPartAddedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseReasoningSummaryPartWsDone",
+            "description": "Emitted when a reasoning summary part is completed.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseReasoningSummaryPartDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseReasoningSummaryTextWsDelta",
+            "description": "Emitted when a delta is added to a reasoning summary text.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseReasoningSummaryTextDeltaEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseReasoningSummaryTextWsDone",
+            "description": "Emitted when a reasoning summary text is completed.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseReasoningSummaryTextDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseReasoningTextWsDelta",
+            "description": "Emitted when a delta is added to a reasoning text.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseReasoningTextDeltaEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseReasoningTextWsDone",
+            "description": "Emitted when a reasoning text is completed.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseReasoningTextDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseRefusalWsDelta",
+            "description": "Emitted when there is a partial refusal text.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseRefusalDeltaEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseRefusalWsDone",
+            "description": "Emitted when refusal text is finalized.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseRefusalDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseTextWsDelta",
+            "description": "Emitted when there is an additional text delta.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseTextDeltaEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseTextWsDone",
+            "description": "Emitted when text content is finalized.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseTextDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseWebSearchCallWsCompleted",
+            "description": "Emitted when a web search call is completed.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseWebSearchCallCompletedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseWebSearchCallInWsProgress",
+            "description": "Emitted when a web search call is initiated.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseWebSearchCallInProgressEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseWebSearchCallWsSearching",
+            "description": "Emitted when a web search call is executing.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseWebSearchCallSearchingEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseImageGenCallWsCompleted",
+            "description": "Emitted when an image generation tool call has completed and the final image is available.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseImageGenCallCompletedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseImageGenCallWsGenerating",
+            "description": "Emitted when an image generation tool call is actively generating an image (intermediate state).\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseImageGenCallGeneratingEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseImageGenCallInWsProgress",
+            "description": "Emitted when an image generation tool call is in progress.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseImageGenCallInProgressEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseImageGenCallPartialWsImage",
+            "description": "Emitted when a partial image is available during image generation streaming.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseImageGenCallPartialImageEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseMcpCallArgumentsWsDelta",
+            "description": "Emitted when there is a delta (partial update) to the arguments of an MCP tool call.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseMCPCallArgumentsDeltaEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseMcpCallArgumentsWsDone",
+            "description": "Emitted when the arguments for an MCP tool call are finalized.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseMCPCallArgumentsDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseMcpCallWsCompleted",
+            "description": "Emitted when an MCP  tool call has completed successfully.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseMCPCallCompletedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseMcpCallWsFailed",
+            "description": "Emitted when an MCP  tool call has failed.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseMCPCallFailedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseMcpCallInWsProgress",
+            "description": "Emitted when an MCP  tool call is in progress.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseMCPCallInProgressEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseMcpListToolsWsCompleted",
+            "description": "Emitted when the list of available MCP tools has been successfully retrieved.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseMCPListToolsCompletedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseMcpListToolsWsFailed",
+            "description": "Emitted when the attempt to list available MCP tools has failed.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseMCPListToolsFailedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseMcpListToolsInWsProgress",
+            "description": "Emitted when the system is in the process of retrieving the list of available MCP tools.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseMCPListToolsInProgressEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseOutputTextAnnotationWsAdded",
+            "description": "Emitted when an annotation is added to output text content.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseOutputTextAnnotationAddedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseWsQueued",
+            "description": "Emitted when a response is queued and waiting to be processed.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseQueuedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseCustomToolCallInputWsDelta",
+            "description": "Event representing a delta (partial update) to the input of a custom tool call.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseCustomToolCallInputDeltaEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "ResponseCustomToolCallInputWsDone",
+            "description": "Event indicating that input for a custom tool call is complete.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/ResponseCustomToolCallInputDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "$ref": "#/components/schemas/ResponseWsError"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseSteerAcceptedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseSteerPendingEvent"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseSteerFailedEvent"
+          }
+        ]
+      },
+      "ResponsesWebSocketStreamEvent": {
+        "allOf": [
+          {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ResponseAudioDeltaEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseAudioDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseAudioTranscriptDeltaEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseAudioTranscriptDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseCodeInterpreterCallCodeDeltaEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseCodeInterpreterCallCodeDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseCodeInterpreterCallCompletedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseCodeInterpreterCallInProgressEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseCodeInterpreterCallInterpretingEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseCompletedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseContentPartAddedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseContentPartDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseCreatedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseFileSearchCallCompletedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseFileSearchCallInProgressEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseFileSearchCallSearchingEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseFunctionCallArgumentsDeltaEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseFunctionCallArgumentsDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseShellCallCommandAddedStreamingEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseShellCallCommandDeltaStreamingEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseShellCallCommandDoneStreamingEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseShellCallOutputContentDeltaStreamingEvent",
+                "x-stainless-skip": [
+                  "go"
+                ]
+              },
+              {
+                "$ref": "#/components/schemas/ResponseShellCallOutputContentDoneStreamingEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseInProgressEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseFailedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseIncompleteEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseOutputItemAddedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseOutputItemDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseReasoningSummaryPartAddedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseReasoningSummaryPartDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseReasoningSummaryTextDeltaEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseReasoningSummaryTextDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseReasoningTextDeltaEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseReasoningTextDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseRefusalDeltaEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseRefusalDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseTextDeltaEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseTextDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseWebSearchCallCompletedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseWebSearchCallInProgressEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseWebSearchCallSearchingEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseImageGenCallCompletedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseImageGenCallGeneratingEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseImageGenCallInProgressEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseImageGenCallPartialImageEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseMCPCallArgumentsDeltaEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseMCPCallArgumentsDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseMCPCallCompletedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseMCPCallFailedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseMCPCallInProgressEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseMCPListToolsCompletedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseMCPListToolsFailedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseMCPListToolsInProgressEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseOutputTextAnnotationAddedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseQueuedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseCustomToolCallInputDeltaEvent"
+              },
+              {
+                "$ref": "#/components/schemas/ResponseCustomToolCallInputDoneEvent"
+              }
+            ]
+          },
+          {
+            "type": "object",
+            "properties": {
+              "stream_id": {
+                "type": "string",
+                "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+              }
+            }
+          }
+        ]
+      },
+      "Role": {
+        "type": "object",
+        "description": "Details about a role that can be assigned through the public Roles API.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "role"
+            ],
+            "description": "Always `role`.",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "Identifier for the role."
+          },
+          "name": {
+            "type": "string",
+            "description": "Unique name for the role."
+          },
+          "description": {
+            "description": "Optional description of the role.",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "permissions": {
+            "type": "array",
+            "description": "Permissions granted by the role.",
+            "items": {
+              "type": "string"
+            }
+          },
+          "resource_type": {
+            "type": "string",
+            "description": "Resource type the role is bound to (for example `api.organization` or `api.project`)."
+          },
+          "predefined_role": {
+            "type": "boolean",
+            "description": "Whether the role is predefined and managed by OpenAI."
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "name",
+          "description",
+          "permissions",
+          "resource_type",
+          "predefined_role"
+        ],
+        "x-oaiMeta": {
+          "name": "The role object",
+          "example": "{\n    \"object\": \"role\",\n    \"id\": \"role_01J1F8ROLE01\",\n    \"name\": \"API Group Manager\",\n    \"description\": \"Allows managing organization groups\",\n    \"permissions\": [\n        \"api.groups.read\",\n        \"api.groups.write\"\n    ],\n    \"resource_type\": \"api.organization\",\n    \"predefined_role\": false\n}\n"
+        }
+      },
+      "RoleDeletedResource": {
+        "type": "object",
+        "description": "Confirmation payload returned after deleting a role.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "role.deleted"
+            ],
+            "description": "Always `role.deleted`.",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "Identifier of the deleted role."
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the role was deleted."
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "deleted"
+        ],
+        "x-oaiMeta": {
+          "name": "Role deletion confirmation",
+          "example": "{\n    \"object\": \"role.deleted\",\n    \"id\": \"role_01J1F8ROLE01\",\n    \"deleted\": true\n}\n"
+        }
+      },
+      "RoleListResource": {
+        "type": "object",
+        "description": "Paginated list of roles assigned to a principal.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "description": "Always `list`.",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "description": "Role assignments returned in the current page.",
+            "items": {
+              "$ref": "#/components/schemas/AssignedRoleDetails"
+            }
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether additional assignments are available when paginating."
+          },
+          "next": {
+            "description": "Cursor to fetch the next page of results, or `null` when there are no more assignments.",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more",
+          "next"
+        ],
+        "x-oaiMeta": {
+          "name": "Assigned role list",
+          "example": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"id\": \"role_01J1F8ROLE01\",\n            \"name\": \"API Group Manager\",\n            \"permissions\": [\n                \"api.groups.read\",\n                \"api.groups.write\"\n            ],\n            \"resource_type\": \"api.organization\",\n            \"predefined_role\": false,\n            \"description\": \"Allows managing organization groups\",\n            \"created_at\": 1711471533,\n            \"updated_at\": 1711472599,\n            \"created_by\": \"user_abc123\",\n            \"created_by_user_obj\": {\n                \"id\": \"user_abc123\",\n                \"name\": \"Ada Lovelace\",\n                \"email\": \"ada@example.com\"\n            },\n            \"metadata\": {},\n            \"assignment_sources\": null\n        }\n    ],\n    \"has_more\": false,\n    \"next\": null\n}\n"
+        }
+      },
+      "RunCompletionUsage": {
+        "anyOf": [
+          {
+            "type": "object",
+            "description": "Usage statistics related to the run. This value will be `null` if the run is not in a terminal state (i.e. `in_progress`, `queued`, etc.).",
+            "properties": {
+              "completion_tokens": {
+                "type": "integer",
+                "description": "Number of completion tokens used over the course of the run."
+              },
+              "prompt_tokens": {
+                "type": "integer",
+                "description": "Number of prompt tokens used over the course of the run."
+              },
+              "total_tokens": {
+                "type": "integer",
+                "description": "Total number of tokens used (prompt + completion)."
+              }
+            },
+            "required": [
+              "prompt_tokens",
+              "completion_tokens",
+              "total_tokens"
+            ]
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "RunGraderRequest": {
+        "type": "object",
+        "title": "RunGraderRequest",
+        "properties": {
+          "grader": {
+            "type": "object",
+            "description": "The grader used for the fine-tuning job.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/GraderStringCheck"
+              },
+              {
+                "$ref": "#/components/schemas/GraderTextSimilarity"
+              },
+              {
+                "$ref": "#/components/schemas/GraderPython"
+              },
+              {
+                "$ref": "#/components/schemas/GraderScoreModel"
+              },
+              {
+                "$ref": "#/components/schemas/GraderMulti"
+              }
+            ]
+          },
+          "item": {
+            "type": "object",
+            "description": "The dataset item provided to the grader. This will be used to populate\nthe `item` namespace. See [the guide](https://developers.openai.com/api/docs/guides/graders) for more details.\n"
+          },
+          "model_sample": {
+            "type": "string",
+            "description": "The model sample to be evaluated. This value will be used to populate\nthe `sample` namespace. See [the guide](https://developers.openai.com/api/docs/guides/graders) for more details.\nThe `output_json` variable will be populated if the model sample is a\nvalid JSON string.\n"
+          }
+        },
+        "required": [
+          "grader",
+          "model_sample"
+        ]
+      },
+      "RunGraderResponse": {
+        "type": "object",
+        "properties": {
+          "reward": {
+            "type": "number"
+          },
+          "metadata": {
+            "type": "object",
+            "properties": {
+              "name": {
+                "type": "string"
+              },
+              "type": {
+                "type": "string"
+              },
+              "errors": {
+                "type": "object",
+                "properties": {
+                  "formula_parse_error": {
+                    "type": "boolean"
+                  },
+                  "sample_parse_error": {
+                    "type": "boolean"
+                  },
+                  "truncated_observation_error": {
+                    "type": "boolean"
+                  },
+                  "unresponsive_reward_error": {
+                    "type": "boolean"
+                  },
+                  "invalid_variable_error": {
+                    "type": "boolean"
+                  },
+                  "other_error": {
+                    "type": "boolean"
+                  },
+                  "python_grader_server_error": {
+                    "type": "boolean"
+                  },
+                  "python_grader_server_error_type": {
+                    "anyOf": [
+                      {
+                        "type": "string"
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ]
+                  },
+                  "python_grader_runtime_error": {
+                    "type": "boolean"
+                  },
+                  "python_grader_runtime_error_details": {
+                    "anyOf": [
+                      {
+                        "type": "string"
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ]
+                  },
+                  "model_grader_server_error": {
+                    "type": "boolean"
+                  },
+                  "model_grader_refusal_error": {
+                    "type": "boolean"
+                  },
+                  "model_grader_parse_error": {
+                    "type": "boolean"
+                  },
+                  "model_grader_server_error_details": {
+                    "anyOf": [
+                      {
+                        "type": "string"
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ]
+                  }
+                },
+                "required": [
+                  "formula_parse_error",
+                  "sample_parse_error",
+                  "truncated_observation_error",
+                  "unresponsive_reward_error",
+                  "invalid_variable_error",
+                  "other_error",
+                  "python_grader_server_error",
+                  "python_grader_server_error_type",
+                  "python_grader_runtime_error",
+                  "python_grader_runtime_error_details",
+                  "model_grader_server_error",
+                  "model_grader_refusal_error",
+                  "model_grader_parse_error",
+                  "model_grader_server_error_details"
+                ]
+              },
+              "execution_time": {
+                "type": "number"
+              },
+              "scores": {
+                "type": "object",
+                "additionalProperties": {}
+              },
+              "token_usage": {
+                "anyOf": [
+                  {
+                    "type": "integer"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "sampled_model_name": {
+                "anyOf": [
+                  {
+                    "type": "string"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              }
+            },
+            "required": [
+              "name",
+              "type",
+              "errors",
+              "execution_time",
+              "scores",
+              "token_usage",
+              "sampled_model_name"
+            ]
+          },
+          "sub_rewards": {
+            "type": "object",
+            "additionalProperties": {}
+          },
+          "model_grader_token_usage_per_model": {
+            "type": "object",
+            "additionalProperties": {}
+          }
+        },
+        "required": [
+          "reward",
+          "metadata",
+          "sub_rewards",
+          "model_grader_token_usage_per_model"
+        ]
+      },
+      "RunObject": {
+        "type": "object",
+        "title": "A run on a thread",
+        "description": "Represents an execution run on a [thread](https://developers.openai.com/api/docs/assistants/migration).",
+        "properties": {
+          "id": {
+            "description": "The identifier, which can be referenced in API endpoints.",
+            "type": "string"
+          },
+          "object": {
+            "description": "The object type, which is always `thread.run`.",
+            "type": "string",
+            "enum": [
+              "thread.run"
+            ],
+            "x-stainless-const": true
+          },
+          "created_at": {
+            "description": "The Unix timestamp (in seconds) for when the run was created.",
+            "type": "integer",
+            "format": "unixtime"
+          },
+          "thread_id": {
+            "description": "The ID of the [thread](https://developers.openai.com/api/docs/assistants/migration) that was executed on as a part of this run.",
+            "type": "string"
+          },
+          "assistant_id": {
+            "description": "The ID of the [assistant](https://developers.openai.com/api/docs/assistants/migration) used for execution of this run.",
+            "type": "string"
+          },
+          "status": {
+            "description": "The status of the run, which can be either `queued`, `in_progress`, `requires_action`, `cancelling`, `cancelled`, `failed`, `completed`, `incomplete`, or `expired`.",
+            "type": "string",
+            "enum": [
+              "queued",
+              "in_progress",
+              "requires_action",
+              "cancelling",
+              "cancelled",
+              "failed",
+              "completed",
+              "incomplete",
+              "expired"
+            ]
+          },
+          "required_action": {
+            "type": "object",
+            "description": "Details on the action required to continue the run. Will be `null` if no action is required.",
+            "nullable": true,
+            "properties": {
+              "type": {
+                "description": "For now, this is always `submit_tool_outputs`.",
+                "type": "string",
+                "enum": [
+                  "submit_tool_outputs"
+                ],
+                "x-stainless-const": true
+              },
+              "submit_tool_outputs": {
+                "type": "object",
+                "description": "Details on the tool outputs needed for this run to continue.",
+                "properties": {
+                  "tool_calls": {
+                    "type": "array",
+                    "description": "A list of the relevant tool calls.",
+                    "items": {
+                      "$ref": "#/components/schemas/RunToolCallObject"
+                    }
+                  }
+                },
+                "required": [
+                  "tool_calls"
+                ]
+              }
+            },
+            "required": [
+              "type",
+              "submit_tool_outputs"
+            ]
+          },
+          "last_error": {
+            "type": "object",
+            "description": "The last error associated with this run. Will be `null` if there are no errors.",
+            "nullable": true,
+            "properties": {
+              "code": {
+                "type": "string",
+                "description": "One of `server_error`, `rate_limit_exceeded`, or `invalid_prompt`.",
+                "enum": [
+                  "server_error",
+                  "rate_limit_exceeded",
+                  "invalid_prompt"
+                ]
+              },
+              "message": {
+                "type": "string",
+                "description": "A human-readable description of the error."
+              }
+            },
+            "required": [
+              "code",
+              "message"
+            ]
+          },
+          "expires_at": {
+            "description": "The Unix timestamp (in seconds) for when the run will expire.",
+            "type": "integer",
+            "format": "unixtime",
+            "nullable": true
+          },
+          "started_at": {
+            "description": "The Unix timestamp (in seconds) for when the run was started.",
+            "type": "integer",
+            "format": "unixtime",
+            "nullable": true
+          },
+          "cancelled_at": {
+            "description": "The Unix timestamp (in seconds) for when the run was cancelled.",
+            "type": "integer",
+            "format": "unixtime",
+            "nullable": true
+          },
+          "failed_at": {
+            "description": "The Unix timestamp (in seconds) for when the run failed.",
+            "type": "integer",
+            "format": "unixtime",
+            "nullable": true
+          },
+          "completed_at": {
+            "description": "The Unix timestamp (in seconds) for when the run was completed.",
+            "type": "integer",
+            "format": "unixtime",
+            "nullable": true
+          },
+          "incomplete_details": {
+            "description": "Details on why the run is incomplete. Will be `null` if the run is not incomplete.",
+            "type": "object",
+            "nullable": true,
+            "properties": {
+              "reason": {
+                "description": "The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.",
+                "type": "string",
+                "enum": [
+                  "max_completion_tokens",
+                  "max_prompt_tokens"
+                ]
+              }
+            }
+          },
+          "model": {
+            "description": "The model that the [assistant](https://developers.openai.com/api/docs/assistants/migration) used for this run.",
+            "type": "string"
+          },
+          "instructions": {
+            "description": "The instructions that the [assistant](https://developers.openai.com/api/docs/assistants/migration) used for this run.",
+            "type": "string"
+          },
+          "tools": {
+            "description": "The list of tools that the [assistant](https://developers.openai.com/api/docs/assistants/migration) used for this run.",
+            "default": [],
+            "type": "array",
+            "maxItems": 20,
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/AssistantToolsCode"
+                },
+                {
+                  "$ref": "#/components/schemas/AssistantToolsFileSearch"
+                },
+                {
+                  "$ref": "#/components/schemas/AssistantToolsFunction"
+                }
+              ]
+            }
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          },
+          "usage": {
+            "$ref": "#/components/schemas/RunCompletionUsage"
+          },
+          "temperature": {
+            "description": "The sampling temperature used for this run. If not set, defaults to 1.",
+            "type": "number",
+            "nullable": true
+          },
+          "top_p": {
+            "description": "The nucleus sampling value used for this run. If not set, defaults to 1.",
+            "type": "number",
+            "nullable": true
+          },
+          "max_prompt_tokens": {
+            "type": "integer",
+            "nullable": true,
+            "description": "The maximum number of prompt tokens specified to have been used over the course of the run.\n",
+            "minimum": 256
+          },
+          "max_completion_tokens": {
+            "type": "integer",
+            "nullable": true,
+            "description": "The maximum number of completion tokens specified to have been used over the course of the run.\n",
+            "minimum": 256
+          },
+          "truncation_strategy": {
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/TruncationObject"
+              },
+              {
+                "nullable": true
+              }
+            ]
+          },
+          "tool_choice": {
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/AssistantsApiToolChoiceOption"
+              },
+              {
+                "nullable": true
+              }
+            ]
+          },
+          "parallel_tool_calls": {
+            "$ref": "#/components/schemas/ParallelToolCalls"
+          },
+          "response_format": {
+            "$ref": "#/components/schemas/AssistantsApiResponseFormatOption",
+            "nullable": true
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "created_at",
+          "thread_id",
+          "assistant_id",
+          "status",
+          "required_action",
+          "last_error",
+          "expires_at",
+          "started_at",
+          "cancelled_at",
+          "failed_at",
+          "completed_at",
+          "model",
+          "instructions",
+          "tools",
+          "metadata",
+          "usage",
+          "incomplete_details",
+          "max_prompt_tokens",
+          "max_completion_tokens",
+          "truncation_strategy",
+          "tool_choice",
+          "parallel_tool_calls",
+          "response_format"
+        ],
+        "x-oaiMeta": {
+          "name": "The run object",
+          "beta": true,
+          "example": "{\n  \"id\": \"run_abc123\",\n  \"object\": \"thread.run\",\n  \"created_at\": 1698107661,\n  \"assistant_id\": \"asst_abc123\",\n  \"thread_id\": \"thread_abc123\",\n  \"status\": \"completed\",\n  \"started_at\": 1699073476,\n  \"expires_at\": null,\n  \"cancelled_at\": null,\n  \"failed_at\": null,\n  \"completed_at\": 1699073498,\n  \"last_error\": null,\n  \"model\": \"gpt-5\",\n  \"instructions\": null,\n  \"tools\": [{\"type\": \"file_search\"}, {\"type\": \"code_interpreter\"}],\n  \"metadata\": {},\n  \"incomplete_details\": null,\n  \"usage\": {\n    \"prompt_tokens\": 123,\n    \"completion_tokens\": 456,\n    \"total_tokens\": 579\n  },\n  \"temperature\": 1.0,\n  \"top_p\": 1.0,\n  \"max_prompt_tokens\": 1000,\n  \"max_completion_tokens\": 1000,\n  \"truncation_strategy\": {\n    \"type\": \"auto\",\n    \"last_messages\": null\n  },\n  \"response_format\": \"auto\",\n  \"tool_choice\": \"auto\",\n  \"parallel_tool_calls\": true\n}\n"
+        }
+      },
+      "RunStepCompletionUsage": {
+        "anyOf": [
+          {
+            "type": "object",
+            "description": "Usage statistics related to the run step. This value will be `null` while the run step's status is `in_progress`.",
+            "properties": {
+              "completion_tokens": {
+                "type": "integer",
+                "description": "Number of completion tokens used over the course of the run step."
+              },
+              "prompt_tokens": {
+                "type": "integer",
+                "description": "Number of prompt tokens used over the course of the run step."
+              },
+              "total_tokens": {
+                "type": "integer",
+                "description": "Total number of tokens used (prompt + completion)."
+              }
+            },
+            "required": [
+              "prompt_tokens",
+              "completion_tokens",
+              "total_tokens"
+            ]
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "RunStepDeltaObject": {
+        "type": "object",
+        "title": "Run step delta object",
+        "description": "Represents a run step delta i.e. any changed fields on a run step during streaming.\n",
+        "properties": {
+          "id": {
+            "description": "The identifier of the run step, which can be referenced in API endpoints.",
+            "type": "string"
+          },
+          "object": {
+            "description": "The object type, which is always `thread.run.step.delta`.",
+            "type": "string",
+            "enum": [
+              "thread.run.step.delta"
+            ],
+            "x-stainless-const": true
+          },
+          "delta": {
+            "description": "The delta containing the fields that have changed on the run step.",
+            "type": "object",
+            "properties": {
+              "step_details": {
+                "type": "object",
+                "description": "The details of the run step.",
+                "oneOf": [
+                  {
+                    "$ref": "#/components/schemas/RunStepDeltaStepDetailsMessageCreationObject"
+                  },
+                  {
+                    "$ref": "#/components/schemas/RunStepDeltaStepDetailsToolCallsObject"
+                  }
+                ]
+              }
+            }
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "delta"
+        ],
+        "x-oaiMeta": {
+          "name": "The run step delta object",
+          "beta": true,
+          "example": "{\n  \"id\": \"step_123\",\n  \"object\": \"thread.run.step.delta\",\n  \"delta\": {\n    \"step_details\": {\n      \"type\": \"tool_calls\",\n      \"tool_calls\": [\n        {\n          \"index\": 0,\n          \"id\": \"call_123\",\n          \"type\": \"code_interpreter\",\n          \"code_interpreter\": { \"input\": \"\", \"outputs\": [] }\n        }\n      ]\n    }\n  }\n}\n"
+        }
+      },
+      "RunStepDeltaStepDetailsMessageCreationObject": {
+        "title": "Message creation",
+        "type": "object",
+        "description": "Details of the message creation by the run step.",
+        "properties": {
+          "type": {
+            "description": "Always `message_creation`.",
+            "type": "string",
+            "enum": [
+              "message_creation"
+            ],
+            "x-stainless-const": true
+          },
+          "message_creation": {
+            "type": "object",
+            "properties": {
+              "message_id": {
+                "type": "string",
+                "description": "The ID of the message that was created by this run step."
+              }
+            }
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "RunStepDeltaStepDetailsToolCallsCodeObject": {
+        "title": "Code interpreter tool call",
+        "type": "object",
+        "description": "Details of the Code Interpreter tool call the run step was involved in.",
+        "properties": {
+          "index": {
+            "type": "integer",
+            "description": "The index of the tool call in the tool calls array."
+          },
+          "id": {
+            "type": "string",
+            "description": "The ID of the tool call."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of tool call. This is always going to be `code_interpreter` for this type of tool call.",
+            "enum": [
+              "code_interpreter"
+            ],
+            "x-stainless-const": true
+          },
+          "code_interpreter": {
+            "type": "object",
+            "description": "The Code Interpreter tool call definition.",
+            "properties": {
+              "input": {
+                "type": "string",
+                "description": "The input to the Code Interpreter tool call."
+              },
+              "outputs": {
+                "type": "array",
+                "description": "The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (`logs`) or images (`image`). Each of these are represented by a different object type.",
+                "items": {
+                  "type": "object",
+                  "oneOf": [
+                    {
+                      "$ref": "#/components/schemas/RunStepDeltaStepDetailsToolCallsCodeOutputLogsObject"
+                    },
+                    {
+                      "$ref": "#/components/schemas/RunStepDeltaStepDetailsToolCallsCodeOutputImageObject"
+                    }
+                  ]
+                }
+              }
+            }
+          }
+        },
+        "required": [
+          "index",
+          "type"
+        ]
+      },
+      "RunStepDeltaStepDetailsToolCallsCodeOutputImageObject": {
+        "title": "Code interpreter image output",
+        "type": "object",
+        "properties": {
+          "index": {
+            "type": "integer",
+            "description": "The index of the output in the outputs array."
+          },
+          "type": {
+            "description": "Always `image`.",
+            "type": "string",
+            "enum": [
+              "image"
+            ],
+            "x-stainless-const": true
+          },
+          "image": {
+            "type": "object",
+            "properties": {
+              "file_id": {
+                "description": "The [file](https://developers.openai.com/api/reference/resources/files) ID of the image.",
+                "type": "string"
+              }
+            }
+          }
+        },
+        "required": [
+          "index",
+          "type"
+        ]
+      },
+      "RunStepDeltaStepDetailsToolCallsCodeOutputLogsObject": {
+        "title": "Code interpreter log output",
+        "type": "object",
+        "description": "Text output from the Code Interpreter tool call as part of a run step.",
+        "properties": {
+          "index": {
+            "type": "integer",
+            "description": "The index of the output in the outputs array."
+          },
+          "type": {
+            "description": "Always `logs`.",
+            "type": "string",
+            "enum": [
+              "logs"
+            ],
+            "x-stainless-const": true
+          },
+          "logs": {
+            "type": "string",
+            "description": "The text output from the Code Interpreter tool call."
+          }
+        },
+        "required": [
+          "index",
+          "type"
+        ]
+      },
+      "RunStepDeltaStepDetailsToolCallsFileSearchObject": {
+        "title": "File search tool call",
+        "type": "object",
+        "properties": {
+          "index": {
+            "type": "integer",
+            "description": "The index of the tool call in the tool calls array."
+          },
+          "id": {
+            "type": "string",
+            "description": "The ID of the tool call object."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of tool call. This is always going to be `file_search` for this type of tool call.",
+            "enum": [
+              "file_search"
+            ],
+            "x-stainless-const": true
+          },
+          "file_search": {
+            "type": "object",
+            "description": "For now, this is always going to be an empty object.",
+            "x-oaiTypeLabel": "map"
+          }
+        },
+        "required": [
+          "index",
+          "type",
+          "file_search"
+        ]
+      },
+      "RunStepDeltaStepDetailsToolCallsFunctionObject": {
+        "type": "object",
+        "title": "Function tool call",
+        "properties": {
+          "index": {
+            "type": "integer",
+            "description": "The index of the tool call in the tool calls array."
+          },
+          "id": {
+            "type": "string",
+            "description": "The ID of the tool call object."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of tool call. This is always going to be `function` for this type of tool call.",
+            "enum": [
+              "function"
+            ],
+            "x-stainless-const": true
+          },
+          "function": {
+            "type": "object",
+            "description": "The definition of the function that was called.",
+            "properties": {
+              "name": {
+                "type": "string",
+                "description": "The name of the function."
+              },
+              "arguments": {
+                "type": "string",
+                "description": "The arguments passed to the function."
+              },
+              "output": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "The output of the function. This will be `null` if the outputs have not been [submitted](https://developers.openai.com/api/docs/assistants/migration) yet."
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              }
+            }
+          }
+        },
+        "required": [
+          "index",
+          "type"
+        ]
+      },
+      "RunStepDeltaStepDetailsToolCallsObject": {
+        "title": "Tool calls",
+        "type": "object",
+        "description": "Details of the tool call.",
+        "properties": {
+          "type": {
+            "description": "Always `tool_calls`.",
+            "type": "string",
+            "enum": [
+              "tool_calls"
+            ],
+            "x-stainless-const": true
+          },
+          "tool_calls": {
+            "type": "array",
+            "description": "An array of tool calls the run step was involved in. These can be associated with one of three types of tools: `code_interpreter`, `file_search`, or `function`.\n",
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/RunStepDeltaStepDetailsToolCallsCodeObject"
+                },
+                {
+                  "$ref": "#/components/schemas/RunStepDeltaStepDetailsToolCallsFileSearchObject"
+                },
+                {
+                  "$ref": "#/components/schemas/RunStepDeltaStepDetailsToolCallsFunctionObject"
+                }
+              ]
+            }
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "RunStepDetailsMessageCreationObject": {
+        "title": "Message creation",
+        "type": "object",
+        "description": "Details of the message creation by the run step.",
+        "properties": {
+          "type": {
+            "description": "Always `message_creation`.",
+            "type": "string",
+            "enum": [
+              "message_creation"
+            ],
+            "x-stainless-const": true
+          },
+          "message_creation": {
+            "type": "object",
+            "properties": {
+              "message_id": {
+                "type": "string",
+                "description": "The ID of the message that was created by this run step."
+              }
+            },
+            "required": [
+              "message_id"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "message_creation"
+        ]
+      },
+      "RunStepDetailsToolCallsCodeObject": {
+        "title": "Code Interpreter tool call",
+        "type": "object",
+        "description": "Details of the Code Interpreter tool call the run step was involved in.",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The ID of the tool call."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of tool call. This is always going to be `code_interpreter` for this type of tool call.",
+            "enum": [
+              "code_interpreter"
+            ],
+            "x-stainless-const": true
+          },
+          "code_interpreter": {
+            "type": "object",
+            "description": "The Code Interpreter tool call definition.",
+            "required": [
+              "input",
+              "outputs"
+            ],
+            "properties": {
+              "input": {
+                "type": "string",
+                "description": "The input to the Code Interpreter tool call."
+              },
+              "outputs": {
+                "type": "array",
+                "description": "The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (`logs`) or images (`image`). Each of these are represented by a different object type.",
+                "items": {
+                  "type": "object",
+                  "oneOf": [
+                    {
+                      "$ref": "#/components/schemas/RunStepDetailsToolCallsCodeOutputLogsObject"
+                    },
+                    {
+                      "$ref": "#/components/schemas/RunStepDetailsToolCallsCodeOutputImageObject"
+                    }
+                  ]
+                }
+              }
+            }
+          }
+        },
+        "required": [
+          "id",
+          "type",
+          "code_interpreter"
+        ]
+      },
+      "RunStepDetailsToolCallsCodeOutputImageObject": {
+        "title": "Code Interpreter image output",
+        "type": "object",
+        "properties": {
+          "type": {
+            "description": "Always `image`.",
+            "type": "string",
+            "enum": [
+              "image"
+            ],
+            "x-stainless-const": true
+          },
+          "image": {
+            "type": "object",
+            "properties": {
+              "file_id": {
+                "description": "The [file](https://developers.openai.com/api/reference/resources/files) ID of the image.",
+                "type": "string"
+              }
+            },
+            "required": [
+              "file_id"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "image"
+        ]
+      },
+      "RunStepDetailsToolCallsCodeOutputLogsObject": {
+        "title": "Code Interpreter log output",
+        "type": "object",
+        "description": "Text output from the Code Interpreter tool call as part of a run step.",
+        "properties": {
+          "type": {
+            "description": "Always `logs`.",
+            "type": "string",
+            "enum": [
+              "logs"
+            ],
+            "x-stainless-const": true
+          },
+          "logs": {
+            "type": "string",
+            "description": "The text output from the Code Interpreter tool call."
+          }
+        },
+        "required": [
+          "type",
+          "logs"
+        ]
+      },
+      "RunStepDetailsToolCallsFileSearchObject": {
+        "title": "File search tool call",
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The ID of the tool call object."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of tool call. This is always going to be `file_search` for this type of tool call.",
+            "enum": [
+              "file_search"
+            ],
+            "x-stainless-const": true
+          },
+          "file_search": {
+            "type": "object",
+            "description": "For now, this is always going to be an empty object.",
+            "x-oaiTypeLabel": "map",
+            "properties": {
+              "ranking_options": {
+                "$ref": "#/components/schemas/RunStepDetailsToolCallsFileSearchRankingOptionsObject"
+              },
+              "results": {
+                "type": "array",
+                "description": "The results of the file search.",
+                "items": {
+                  "$ref": "#/components/schemas/RunStepDetailsToolCallsFileSearchResultObject"
+                }
+              }
+            }
+          }
+        },
+        "required": [
+          "id",
+          "type",
+          "file_search"
+        ]
+      },
+      "RunStepDetailsToolCallsFileSearchRankingOptionsObject": {
+        "title": "File search tool call ranking options",
+        "type": "object",
+        "description": "The ranking options for the file search.",
+        "properties": {
+          "ranker": {
+            "$ref": "#/components/schemas/FileSearchRanker"
+          },
+          "score_threshold": {
+            "type": "number",
+            "description": "The score threshold for the file search. All values must be a floating point number between 0 and 1.",
+            "minimum": 0,
+            "maximum": 1
+          }
+        },
+        "required": [
+          "ranker",
+          "score_threshold"
+        ]
+      },
+      "RunStepDetailsToolCallsFileSearchResultObject": {
+        "title": "File search tool call result",
+        "type": "object",
+        "description": "A result instance of the file search.",
+        "x-oaiTypeLabel": "map",
+        "properties": {
+          "file_id": {
+            "type": "string",
+            "description": "The ID of the file that result was found in."
+          },
+          "file_name": {
+            "type": "string",
+            "description": "The name of the file that result was found in."
+          },
+          "score": {
+            "type": "number",
+            "description": "The score of the result. All values must be a floating point number between 0 and 1.",
+            "minimum": 0,
+            "maximum": 1
+          },
+          "content": {
+            "type": "array",
+            "description": "The content of the result that was found. The content is only included if requested via the include query parameter.",
+            "items": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "description": "The type of the content.",
+                  "enum": [
+                    "text"
+                  ],
+                  "x-stainless-const": true
+                },
+                "text": {
+                  "type": "string",
+                  "description": "The text content of the file."
+                }
+              }
+            }
+          }
+        },
+        "required": [
+          "file_id",
+          "file_name",
+          "score"
+        ]
+      },
+      "RunStepDetailsToolCallsFunctionObject": {
+        "type": "object",
+        "title": "Function tool call",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The ID of the tool call object."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of tool call. This is always going to be `function` for this type of tool call.",
+            "enum": [
+              "function"
+            ],
+            "x-stainless-const": true
+          },
+          "function": {
+            "type": "object",
+            "description": "The definition of the function that was called.",
+            "properties": {
+              "name": {
+                "type": "string",
+                "description": "The name of the function."
+              },
+              "arguments": {
+                "type": "string",
+                "description": "The arguments passed to the function."
+              },
+              "output": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "The output of the function. This will be `null` if the outputs have not been [submitted](https://developers.openai.com/api/docs/assistants/migration) yet."
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              }
+            },
+            "required": [
+              "name",
+              "arguments",
+              "output"
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "type",
+          "function"
+        ]
+      },
+      "RunStepDetailsToolCallsObject": {
+        "title": "Tool calls",
+        "type": "object",
+        "description": "Details of the tool call.",
+        "properties": {
+          "type": {
+            "description": "Always `tool_calls`.",
+            "type": "string",
+            "enum": [
+              "tool_calls"
+            ],
+            "x-stainless-const": true
+          },
+          "tool_calls": {
+            "type": "array",
+            "description": "An array of tool calls the run step was involved in. These can be associated with one of three types of tools: `code_interpreter`, `file_search`, or `function`.\n",
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/RunStepDetailsToolCallsCodeObject"
+                },
+                {
+                  "$ref": "#/components/schemas/RunStepDetailsToolCallsFileSearchObject"
+                },
+                {
+                  "$ref": "#/components/schemas/RunStepDetailsToolCallsFunctionObject"
+                }
+              ]
+            }
+          }
+        },
+        "required": [
+          "type",
+          "tool_calls"
+        ]
+      },
+      "RunStepObject": {
+        "type": "object",
+        "title": "Run steps",
+        "description": "Represents a step in execution of a run.\n",
+        "properties": {
+          "id": {
+            "description": "The identifier of the run step, which can be referenced in API endpoints.",
+            "type": "string"
+          },
+          "object": {
+            "description": "The object type, which is always `thread.run.step`.",
+            "type": "string",
+            "enum": [
+              "thread.run.step"
+            ],
+            "x-stainless-const": true
+          },
+          "created_at": {
+            "description": "The Unix timestamp (in seconds) for when the run step was created.",
+            "type": "integer",
+            "format": "unixtime"
+          },
+          "assistant_id": {
+            "description": "The ID of the [assistant](https://developers.openai.com/api/docs/assistants/migration) associated with the run step.",
+            "type": "string"
+          },
+          "thread_id": {
+            "description": "The ID of the [thread](https://developers.openai.com/api/docs/assistants/migration) that was run.",
+            "type": "string"
+          },
+          "run_id": {
+            "description": "The ID of the [run](https://developers.openai.com/api/docs/assistants/migration) that this run step is a part of.",
+            "type": "string"
+          },
+          "type": {
+            "description": "The type of run step, which can be either `message_creation` or `tool_calls`.",
+            "type": "string",
+            "enum": [
+              "message_creation",
+              "tool_calls"
+            ]
+          },
+          "status": {
+            "description": "The status of the run step, which can be either `in_progress`, `cancelled`, `failed`, `completed`, or `expired`.",
+            "type": "string",
+            "enum": [
+              "in_progress",
+              "cancelled",
+              "failed",
+              "completed",
+              "expired"
+            ]
+          },
+          "step_details": {
+            "type": "object",
+            "description": "The details of the run step.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/RunStepDetailsMessageCreationObject"
+              },
+              {
+                "$ref": "#/components/schemas/RunStepDetailsToolCallsObject"
+              }
+            ]
+          },
+          "last_error": {
+            "anyOf": [
+              {
+                "type": "object",
+                "description": "The last error associated with this run step. Will be `null` if there are no errors.",
+                "properties": {
+                  "code": {
+                    "type": "string",
+                    "description": "One of `server_error` or `rate_limit_exceeded`.",
+                    "enum": [
+                      "server_error",
+                      "rate_limit_exceeded"
+                    ]
+                  },
+                  "message": {
+                    "type": "string",
+                    "description": "A human-readable description of the error."
+                  }
+                },
+                "required": [
+                  "code",
+                  "message"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "expired_at": {
+            "anyOf": [
+              {
+                "description": "The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired.",
+                "type": "integer",
+                "format": "unixtime"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "cancelled_at": {
+            "anyOf": [
+              {
+                "description": "The Unix timestamp (in seconds) for when the run step was cancelled.",
+                "type": "integer",
+                "format": "unixtime"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "failed_at": {
+            "anyOf": [
+              {
+                "description": "The Unix timestamp (in seconds) for when the run step failed.",
+                "type": "integer",
+                "format": "unixtime"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "completed_at": {
+            "anyOf": [
+              {
+                "description": "The Unix timestamp (in seconds) for when the run step completed.",
+                "type": "integer",
+                "format": "unixtime"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          },
+          "usage": {
+            "$ref": "#/components/schemas/RunStepCompletionUsage"
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "created_at",
+          "assistant_id",
+          "thread_id",
+          "run_id",
+          "type",
+          "status",
+          "step_details",
+          "last_error",
+          "expired_at",
+          "cancelled_at",
+          "failed_at",
+          "completed_at",
+          "metadata",
+          "usage"
+        ],
+        "x-oaiMeta": {
+          "name": "The run step object",
+          "beta": true,
+          "example": "{\n  \"id\": \"step_abc123\",\n  \"object\": \"thread.run.step\",\n  \"created_at\": 1699063291,\n  \"run_id\": \"run_abc123\",\n  \"assistant_id\": \"asst_abc123\",\n  \"thread_id\": \"thread_abc123\",\n  \"type\": \"message_creation\",\n  \"status\": \"completed\",\n  \"cancelled_at\": null,\n  \"completed_at\": 1699063291,\n  \"expired_at\": null,\n  \"failed_at\": null,\n  \"last_error\": null,\n  \"step_details\": {\n    \"type\": \"message_creation\",\n    \"message_creation\": {\n      \"message_id\": \"msg_abc123\"\n    }\n  },\n  \"usage\": {\n    \"prompt_tokens\": 123,\n    \"completion_tokens\": 456,\n    \"total_tokens\": 579\n  }\n}\n"
+        }
+      },
+      "RunStepStreamEvent": {
+        "oneOf": [
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.run.step.created"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/RunStepObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a [run step](https://developers.openai.com/api/docs/assistants/migration) is created.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [run step](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          },
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.run.step.in_progress"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/RunStepObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a [run step](https://developers.openai.com/api/docs/assistants/migration) moves to an `in_progress` state.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [run step](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          },
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.run.step.delta"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/RunStepDeltaObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when parts of a [run step](https://developers.openai.com/api/docs/assistants/migration) are being streamed.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [run step delta](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          },
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.run.step.completed"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/RunStepObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a [run step](https://developers.openai.com/api/docs/assistants/migration) is completed.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [run step](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          },
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.run.step.failed"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/RunStepObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a [run step](https://developers.openai.com/api/docs/assistants/migration) fails.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [run step](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          },
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.run.step.cancelled"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/RunStepObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a [run step](https://developers.openai.com/api/docs/assistants/migration) is cancelled.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [run step](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          },
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.run.step.expired"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/RunStepObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a [run step](https://developers.openai.com/api/docs/assistants/migration) expires.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [run step](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          }
+        ]
+      },
+      "RunStreamEvent": {
+        "oneOf": [
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.run.created"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/RunObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a new [run](https://developers.openai.com/api/docs/assistants/migration) is created.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [run](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          },
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.run.queued"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/RunObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a [run](https://developers.openai.com/api/docs/assistants/migration) moves to a `queued` status.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [run](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          },
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.run.in_progress"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/RunObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a [run](https://developers.openai.com/api/docs/assistants/migration) moves to an `in_progress` status.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [run](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          },
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.run.requires_action"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/RunObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a [run](https://developers.openai.com/api/docs/assistants/migration) moves to a `requires_action` status.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [run](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          },
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.run.completed"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/RunObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a [run](https://developers.openai.com/api/docs/assistants/migration) is completed.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [run](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          },
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.run.incomplete"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/RunObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a [run](https://developers.openai.com/api/docs/assistants/migration) ends with status `incomplete`.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [run](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          },
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.run.failed"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/RunObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a [run](https://developers.openai.com/api/docs/assistants/migration) fails.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [run](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          },
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.run.cancelling"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/RunObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a [run](https://developers.openai.com/api/docs/assistants/migration) moves to a `cancelling` status.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [run](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          },
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.run.cancelled"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/RunObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a [run](https://developers.openai.com/api/docs/assistants/migration) is cancelled.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [run](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          },
+          {
+            "type": "object",
+            "properties": {
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.run.expired"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/RunObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a [run](https://developers.openai.com/api/docs/assistants/migration) expires.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [run](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          }
+        ]
+      },
+      "RunToolCallObject": {
+        "type": "object",
+        "description": "Tool call objects",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the [Submit tool outputs to run](https://developers.openai.com/api/docs/assistants/migration) endpoint."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of tool call the output is required for. For now, this is always `function`.",
+            "enum": [
+              "function"
+            ],
+            "x-stainless-const": true
+          },
+          "function": {
+            "type": "object",
+            "description": "The function definition.",
+            "properties": {
+              "name": {
+                "type": "string",
+                "description": "The name of the function."
+              },
+              "arguments": {
+                "type": "string",
+                "description": "The arguments that the model expects you to pass to the function."
+              }
+            },
+            "required": [
+              "name",
+              "arguments"
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "type",
+          "function"
+        ]
+      },
+      "ServiceTier": {
+        "anyOf": [
+          {
+            "type": "string",
+            "description": "Specifies the processing type used for serving the request.\n  - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.\n  - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.\n  - If set to '[flex](https://developers.openai.com/api/docs/guides/flex-processing)', then the request will be processed with the Flex Processing service tier.\n  - To opt-in to [Fast mode](https://developers.openai.com/api/docs/guides/fast-mode) at the request level, include the `service_tier=fast` or `service_tier=priority` parameter for Responses or Chat Completions. The response will show `service_tier=priority` regardless of if you specify `service_tier=fast` or `priority` in your request.\n  - When not set, the default behavior is 'auto'.\n\n  When the `service_tier` parameter is set, the response body will include the `service_tier` value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.\n",
+            "enum": [
+              "auto",
+              "default",
+              "flex",
+              "scale",
+              "priority",
+              "fast"
+            ],
+            "default": "auto"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "ServiceTierResponses": {
+        "anyOf": [
+          {
+            "type": "string",
+            "description": "Specifies the processing type used for serving the request.\n  - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.\n  - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.\n  - If set to '[flex](https://developers.openai.com/api/docs/guides/flex-processing)', then the request will be processed with the Flex Processing service tier.\n  - To opt-in to [Fast mode](https://developers.openai.com/api/docs/guides/fast-mode) at the request level, include the `service_tier=fast` or `service_tier=priority` parameter for Responses or Chat Completions. The response will show `service_tier=priority` regardless of if you specify `service_tier=fast` or `priority` in your request.\n  - If set to 'ultrafast', then the request will be processed with the access-controlled Ultrafast Processing service tier. This tier is currently available for `gpt-5.6-sol`; a response served through it will show `service_tier=ultrafast`.\n  - When not set, the default behavior is 'auto'.\n\n  When the `service_tier` parameter is set, the response body will include the `service_tier` value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.\n",
+            "enum": [
+              "auto",
+              "default",
+              "flex",
+              "scale",
+              "priority",
+              "fast",
+              "ultrafast"
+            ],
+            "default": "auto"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "SpeechAudioDeltaEvent": {
+        "type": "object",
+        "description": "Emitted for each chunk of audio data generated during speech synthesis.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `speech.audio.delta`.\n",
+            "enum": [
+              "speech.audio.delta"
+            ],
+            "x-stainless-const": true
+          },
+          "audio": {
+            "type": "string",
+            "description": "A chunk of Base64-encoded audio data.\n"
+          }
+        },
+        "required": [
+          "type",
+          "audio"
+        ],
+        "x-oaiMeta": {
+          "name": "Stream Event (speech.audio.delta)",
+          "group": "speech",
+          "example": "{\n  \"type\": \"speech.audio.delta\",\n  \"audio\": \"base64-encoded-audio-data\"\n}\n"
+        }
+      },
+      "SpeechAudioDoneEvent": {
+        "type": "object",
+        "description": "Emitted when the speech synthesis is complete and all audio has been streamed.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `speech.audio.done`.\n",
+            "enum": [
+              "speech.audio.done"
+            ],
+            "x-stainless-const": true
+          },
+          "usage": {
+            "type": "object",
+            "description": "Token usage statistics for the request.\n",
+            "properties": {
+              "input_tokens": {
+                "type": "integer",
+                "description": "Number of input tokens in the prompt."
+              },
+              "output_tokens": {
+                "type": "integer",
+                "description": "Number of output tokens generated."
+              },
+              "total_tokens": {
+                "type": "integer",
+                "description": "Total number of tokens used (input + output)."
+              }
+            },
+            "required": [
+              "input_tokens",
+              "output_tokens",
+              "total_tokens"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "usage"
+        ],
+        "x-oaiMeta": {
+          "name": "Stream Event (speech.audio.done)",
+          "group": "speech",
+          "example": "{\n  \"type\": \"speech.audio.done\",\n  \"usage\": {\n    \"input_tokens\": 14,\n    \"output_tokens\": 101,\n    \"total_tokens\": 115\n  }\n}\n"
+        }
+      },
+      "SpendAlertNotificationChannel": {
+        "type": "object",
+        "description": "Email notification settings for a spend alert.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "email"
+            ],
+            "description": "The notification channel type. Currently only `email` is supported.",
+            "x-stainless-const": true
+          },
+          "recipients": {
+            "type": "array",
+            "description": "Email addresses that receive the spend alert notification.",
+            "items": {
+              "type": "string"
+            }
+          },
+          "subject_prefix": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Optional subject prefix for alert emails."
+          }
+        },
+        "required": [
+          "type",
+          "recipients"
+        ]
+      },
+      "StaticChunkingStrategy": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "max_chunk_size_tokens": {
+            "type": "integer",
+            "minimum": 100,
+            "maximum": 4096,
+            "description": "The maximum number of tokens in each chunk. The default value is `800`. The minimum value is `100` and the maximum value is `4096`."
+          },
+          "chunk_overlap_tokens": {
+            "type": "integer",
+            "description": "The number of tokens that overlap between chunks. The default value is `400`.\n\nNote that the overlap must not exceed half of `max_chunk_size_tokens`.\n"
+          }
+        },
+        "required": [
+          "max_chunk_size_tokens",
+          "chunk_overlap_tokens"
+        ]
+      },
+      "StaticChunkingStrategyRequestParam": {
+        "type": "object",
+        "title": "Static Chunking Strategy",
+        "description": "Customize your own chunking strategy by setting chunk size and chunk overlap.",
+        "additionalProperties": false,
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "Always `static`.",
+            "enum": [
+              "static"
+            ],
+            "x-stainless-const": true
+          },
+          "static": {
+            "$ref": "#/components/schemas/StaticChunkingStrategy"
+          }
+        },
+        "required": [
+          "type",
+          "static"
+        ]
+      },
+      "StaticChunkingStrategyResponseParam": {
+        "type": "object",
+        "title": "Static Chunking Strategy",
+        "additionalProperties": false,
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "Always `static`.",
+            "enum": [
+              "static"
+            ],
+            "x-stainless-const": true
+          },
+          "static": {
+            "$ref": "#/components/schemas/StaticChunkingStrategy"
+          }
+        },
+        "required": [
+          "type",
+          "static"
+        ]
+      },
+      "StopConfiguration": {
+        "description": "Not supported with latest reasoning models `o3` and `o4-mini`.\n\nUp to 4 sequences where the API will stop generating further tokens. The\nreturned text will not contain the stop sequence.\n",
+        "default": null,
+        "nullable": true,
+        "oneOf": [
+          {
+            "type": "string",
+            "default": "<|endoftext|>",
+            "example": "\n",
+            "nullable": true
+          },
+          {
+            "type": "array",
+            "minItems": 1,
+            "maxItems": 4,
+            "items": {
+              "type": "string",
+              "example": "[\"\\n\"]"
+            }
+          }
+        ]
+      },
+      "SubmitToolOutputsRunRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "tool_outputs": {
+            "description": "A list of tools for which the outputs are being submitted.",
+            "type": "array",
+            "items": {
+              "type": "object",
+              "properties": {
+                "tool_call_id": {
+                  "type": "string",
+                  "description": "The ID of the tool call in the `required_action` object within the run object the output is being submitted for."
+                },
+                "output": {
+                  "type": "string",
+                  "description": "The output of the tool call to be submitted to continue the run."
+                }
+              }
+            }
+          },
+          "stream": {
+            "anyOf": [
+              {
+                "type": "boolean",
+                "description": "If `true`, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a `data: [DONE]` message.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "tool_outputs"
+        ]
+      },
+      "TextResponseFormatConfiguration": {
+        "description": "An object specifying the format that the model must output.\n\nConfiguring `{ \"type\": \"json_schema\" }` enables Structured Outputs,\nwhich ensures the model will match your supplied JSON schema. Learn more in the\n[Structured Outputs guide](https://developers.openai.com/api/docs/guides/structured-outputs).\n\nThe default format is `{ \"type\": \"text\" }` with no additional options.\n\n**Not recommended for gpt-4o and newer models:**\n\nSetting to `{ \"type\": \"json_object\" }` enables the older JSON mode, which\nensures the message the model generates is valid JSON. Using `json_schema`\nis preferred for models that support it.\n",
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/ResponseFormatText"
+          },
+          {
+            "$ref": "#/components/schemas/TextResponseFormatJsonSchema"
+          },
+          {
+            "$ref": "#/components/schemas/ResponseFormatJsonObject"
+          }
+        ]
+      },
+      "TextResponseFormatJsonSchema": {
+        "type": "object",
+        "title": "JSON schema",
+        "description": "JSON Schema response format. Used to generate structured JSON responses.\nLearn more about [Structured Outputs](https://developers.openai.com/api/docs/guides/structured-outputs).\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of response format being defined. Always `json_schema`.",
+            "enum": [
+              "json_schema"
+            ],
+            "x-stainless-const": true
+          },
+          "description": {
+            "type": "string",
+            "description": "A description of what the response format is for, used by the model to\ndetermine how to respond in the format.\n"
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the response format. Must be a-z, A-Z, 0-9, or contain\nunderscores and dashes, with a maximum length of 64.\n"
+          },
+          "schema": {
+            "$ref": "#/components/schemas/ResponseFormatJsonSchemaSchema"
+          },
+          "strict": {
+            "anyOf": [
+              {
+                "type": "boolean",
+                "default": false,
+                "description": "Whether to enable strict schema adherence when generating the output.\nIf set to true, the model will always follow the exact schema defined\nin the `schema` field. Only a subset of JSON Schema is supported when\n`strict` is `true`. To learn more, read the [Structured Outputs\nguide](https://developers.openai.com/api/docs/guides/structured-outputs).\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "schema",
+          "name"
+        ]
+      },
+      "ThreadObject": {
+        "type": "object",
+        "title": "Thread",
+        "description": "Represents a thread that contains [messages](https://developers.openai.com/api/docs/assistants/migration).",
+        "properties": {
+          "id": {
+            "description": "The identifier, which can be referenced in API endpoints.",
+            "type": "string"
+          },
+          "object": {
+            "description": "The object type, which is always `thread`.",
+            "type": "string",
+            "enum": [
+              "thread"
+            ],
+            "x-stainless-const": true
+          },
+          "created_at": {
+            "description": "The Unix timestamp (in seconds) for when the thread was created.",
+            "type": "integer",
+            "format": "unixtime"
+          },
+          "tool_resources": {
+            "anyOf": [
+              {
+                "type": "object",
+                "description": "A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs.\n",
+                "properties": {
+                  "code_interpreter": {
+                    "type": "object",
+                    "properties": {
+                      "file_ids": {
+                        "type": "array",
+                        "description": "A list of [file](https://developers.openai.com/api/reference/resources/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool.\n",
+                        "default": [],
+                        "maxItems": 20,
+                        "items": {
+                          "type": "string"
+                        }
+                      }
+                    }
+                  },
+                  "file_search": {
+                    "type": "object",
+                    "properties": {
+                      "vector_store_ids": {
+                        "type": "array",
+                        "description": "The [vector store](https://developers.openai.com/api/reference/resources/vector_stores) attached to this thread. There can be a maximum of 1 vector store attached to the thread.\n",
+                        "maxItems": 1,
+                        "items": {
+                          "type": "string"
+                        }
+                      }
+                    }
+                  }
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "created_at",
+          "tool_resources",
+          "metadata"
+        ],
+        "x-oaiMeta": {
+          "name": "The thread object",
+          "beta": true,
+          "example": "{\n  \"id\": \"thread_abc123\",\n  \"object\": \"thread\",\n  \"created_at\": 1698107661,\n  \"metadata\": {}\n}\n"
+        }
+      },
+      "ThreadStreamEvent": {
+        "oneOf": [
+          {
+            "type": "object",
+            "properties": {
+              "enabled": {
+                "type": "boolean",
+                "description": "Whether to enable input audio transcription."
+              },
+              "event": {
+                "type": "string",
+                "enum": [
+                  "thread.created"
+                ],
+                "x-stainless-const": true
+              },
+              "data": {
+                "$ref": "#/components/schemas/ThreadObject"
+              }
+            },
+            "required": [
+              "event",
+              "data"
+            ],
+            "description": "Occurs when a new [thread](https://developers.openai.com/api/docs/assistants/migration) is created.",
+            "x-oaiMeta": {
+              "dataDescription": "`data` is a [thread](https://developers.openai.com/api/docs/assistants/migration)"
+            }
+          }
+        ]
+      },
+      "ToggleCertificatesRequest": {
+        "type": "object",
+        "properties": {
+          "certificate_ids": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "example": "cert_abc"
+            },
+            "minItems": 1,
+            "maxItems": 10
+          }
+        },
+        "required": [
+          "certificate_ids"
+        ]
+      },
+      "Tool": {
+        "description": "A tool that can be used to generate a response.\n",
+        "discriminator": {
+          "propertyName": "type"
+        },
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/FunctionTool"
+          },
+          {
+            "$ref": "#/components/schemas/FileSearchTool"
+          },
+          {
+            "$ref": "#/components/schemas/ComputerTool"
+          },
+          {
+            "$ref": "#/components/schemas/ComputerUsePreviewTool"
+          },
+          {
+            "$ref": "#/components/schemas/WebSearchTool"
+          },
+          {
+            "$ref": "#/components/schemas/MCPTool"
+          },
+          {
+            "$ref": "#/components/schemas/CodeInterpreterTool"
+          },
+          {
+            "$ref": "#/components/schemas/ProgrammaticToolCallingParam"
+          },
+          {
+            "$ref": "#/components/schemas/ImageGenTool"
+          },
+          {
+            "$ref": "#/components/schemas/LocalShellToolParam"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionShellToolParam"
+          },
+          {
+            "$ref": "#/components/schemas/CustomToolParam"
+          },
+          {
+            "$ref": "#/components/schemas/NamespaceToolParam"
+          },
+          {
+            "$ref": "#/components/schemas/ToolSearchToolParam"
+          },
+          {
+            "$ref": "#/components/schemas/WebSearchPreviewTool"
+          },
+          {
+            "$ref": "#/components/schemas/ApplyPatchToolParam"
+          }
+        ]
+      },
+      "ToolChoiceAllowed": {
+        "type": "object",
+        "title": "Allowed tools",
+        "description": "Constrains the tools available to the model to a pre-defined set.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "allowed_tools"
+            ],
+            "description": "Allowed tool configuration type. Always `allowed_tools`.",
+            "x-stainless-const": true
+          },
+          "mode": {
+            "type": "string",
+            "enum": [
+              "auto",
+              "required"
+            ],
+            "description": "Constrains the tools available to the model to a pre-defined set.\n\n`auto` allows the model to pick from among the allowed tools and generate a\nmessage.\n\n`required` requires the model to call one or more of the allowed tools.\n"
+          },
+          "tools": {
+            "type": "array",
+            "description": "A list of tool definitions that the model should be allowed to call.\n\nFor the Responses API, the list of tool definitions might look like:\n```json\n[\n  { \"type\": \"function\", \"name\": \"get_weather\" },\n  { \"type\": \"mcp\", \"server_label\": \"deepwiki\" },\n  { \"type\": \"image_generation\" }\n]\n```\n",
+            "items": {
+              "type": "object",
+              "description": "A tool definition that the model should be allowed to call.\n",
+              "additionalProperties": true,
+              "x-oaiExpandable": false
+            }
+          }
+        },
+        "required": [
+          "type",
+          "mode",
+          "tools"
+        ]
+      },
+      "ToolChoiceCustom": {
+        "type": "object",
+        "title": "Custom tool",
+        "description": "Use this option to force the model to call a specific custom tool.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "custom"
+            ],
+            "description": "For custom tool calling, the type is always `custom`.",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the custom tool to call."
+          }
+        },
+        "required": [
+          "type",
+          "name"
+        ]
+      },
+      "ToolChoiceFunction": {
+        "type": "object",
+        "title": "Function tool",
+        "description": "Use this option to force the model to call a specific function.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "function"
+            ],
+            "description": "For function calling, the type is always `function`.",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the function to call."
+          }
+        },
+        "required": [
+          "type",
+          "name"
+        ]
+      },
+      "ToolChoiceMCP": {
+        "type": "object",
+        "title": "MCP tool",
+        "description": "Use this option to force the model to call a specific tool on a remote MCP server.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp"
+            ],
+            "description": "For MCP tools, the type is always `mcp`.",
+            "x-stainless-const": true
+          },
+          "server_label": {
+            "type": "string",
+            "description": "The label of the MCP server to use.\n"
+          },
+          "name": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The name of the tool to call on the server.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "server_label"
+        ]
+      },
+      "ToolChoiceOptions": {
+        "type": "string",
+        "title": "Tool choice mode",
+        "description": "Controls which (if any) tool is called by the model.\n\n`none` means the model will not call any tool and instead generates a message.\n\n`auto` means the model can pick between generating a message or calling one or\nmore tools.\n\n`required` means the model must call one or more tools.\n",
+        "enum": [
+          "none",
+          "auto",
+          "required"
+        ]
+      },
+      "ToolChoiceParam": {
+        "description": "How the model should select which tool (or tools) to use when generating\na response. See the `tools` parameter to see how to specify which tools\nthe model can call.\n",
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/ToolChoiceOptions"
+          },
+          {
+            "$ref": "#/components/schemas/ToolChoiceAllowed"
+          },
+          {
+            "$ref": "#/components/schemas/ToolChoiceTypes"
+          },
+          {
+            "$ref": "#/components/schemas/ToolChoiceFunction"
+          },
+          {
+            "$ref": "#/components/schemas/ToolChoiceMCP"
+          },
+          {
+            "$ref": "#/components/schemas/ToolChoiceCustom"
+          },
+          {
+            "$ref": "#/components/schemas/SpecificProgrammaticToolCallingParam"
+          },
+          {
+            "$ref": "#/components/schemas/SpecificApplyPatchParam"
+          },
+          {
+            "$ref": "#/components/schemas/SpecificFunctionShellParam"
+          }
+        ]
+      },
+      "ToolChoiceTypes": {
+        "type": "object",
+        "title": "Hosted tool",
+        "description": "Indicates that the model should use a built-in tool to generate a response.\n[Learn more about built-in tools](https://developers.openai.com/api/docs/guides/tools).\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of hosted tool the model should to use. Learn more about\n[built-in tools](https://developers.openai.com/api/docs/guides/tools).\n\nAllowed values are:\n- `file_search`\n- `web_search_preview`\n- `computer`\n- `computer_use_preview`\n- `computer_use`\n- `code_interpreter`\n- `image_generation`\n",
+            "enum": [
+              "file_search",
+              "web_search_preview",
+              "computer",
+              "computer_use_preview",
+              "computer_use",
+              "web_search_preview_2025_03_11",
+              "image_generation",
+              "code_interpreter"
+            ]
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "ToolsArray": {
+        "type": "array",
+        "description": "An array of tools the model may call while generating a response. You\ncan specify which tool to use by setting the `tool_choice` parameter.\n\nWe support the following categories of tools:\n- **Built-in tools**: Tools that are provided by OpenAI that extend the\n  model's capabilities, like [web search](https://developers.openai.com/api/docs/guides/tools-web-search)\n  or [file search](https://developers.openai.com/api/docs/guides/tools-file-search). Learn more about\n  [built-in tools](https://developers.openai.com/api/docs/guides/tools).\n- **MCP Tools**: Integrations with third-party systems via custom MCP servers\n  or predefined connectors such as Google Drive and SharePoint. Learn more about\n  [MCP Tools](https://developers.openai.com/api/docs/guides/tools-connectors-mcp).\n- **Function calls (custom tools)**: Functions that are defined by you,\n  enabling the model to call your own code with strongly typed arguments\n  and outputs. Learn more about\n  [function calling](https://developers.openai.com/api/docs/guides/function-calling). You can also use\n  custom tools to call your own code.\n",
+        "items": {
+          "$ref": "#/components/schemas/Tool"
+        }
+      },
+      "TranscriptTextDeltaEvent": {
+        "type": "object",
+        "description": "Emitted when there is an additional text delta. This is also the first event emitted when the transcription starts. Only emitted when you [create a transcription](https://developers.openai.com/api/reference/resources/audio/subresources/transcriptions/methods/create) with the `Stream` parameter set to `true`.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `transcript.text.delta`.\n",
+            "enum": [
+              "transcript.text.delta"
+            ],
+            "x-stainless-const": true
+          },
+          "delta": {
+            "type": "string",
+            "description": "The text delta that was additionally transcribed.\n"
+          },
+          "logprobs": {
+            "type": "array",
+            "description": "The log probabilities of the delta. Only included if you [create a transcription](https://developers.openai.com/api/reference/resources/audio/subresources/transcriptions/methods/create) with the `include[]` parameter set to `logprobs`.\n",
+            "items": {
+              "type": "object",
+              "properties": {
+                "token": {
+                  "type": "string",
+                  "description": "The token that was used to generate the log probability.\n"
+                },
+                "logprob": {
+                  "type": "number",
+                  "description": "The log probability of the token.\n"
+                },
+                "bytes": {
+                  "type": "array",
+                  "items": {
+                    "type": "integer"
+                  },
+                  "description": "The bytes that were used to generate the log probability.\n"
+                }
+              }
+            }
+          },
+          "segment_id": {
+            "type": "string",
+            "description": "Identifier of the diarized segment that this delta belongs to. Only present when using `gpt-4o-transcribe-diarize`.\n"
+          }
+        },
+        "required": [
+          "type",
+          "delta"
+        ],
+        "x-oaiMeta": {
+          "name": "Stream Event (transcript.text.delta)",
+          "group": "transcript",
+          "example": "{\n  \"type\": \"transcript.text.delta\",\n  \"delta\": \" wonderful\"\n}\n"
+        }
+      },
+      "TranscriptTextDoneEvent": {
+        "type": "object",
+        "description": "Emitted when the transcription is complete. Contains the complete transcription text. Only emitted when you [create a transcription](https://developers.openai.com/api/reference/resources/audio/subresources/transcriptions/methods/create) with the `Stream` parameter set to `true`.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `transcript.text.done`.\n",
+            "enum": [
+              "transcript.text.done"
+            ],
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string",
+            "description": "The text that was transcribed.\n"
+          },
+          "languages": {
+            "type": "array",
+            "description": "The languages detected in the audio. Returned by `gpt-transcribe`. An empty array indicates that no language could be reliably detected.\n",
+            "items": {
+              "$ref": "#/components/schemas/TranscriptionLanguage"
+            }
+          },
+          "logprobs": {
+            "type": "array",
+            "description": "The log probabilities of the individual tokens in the transcription. Only included if you [create a transcription](https://developers.openai.com/api/reference/resources/audio/subresources/transcriptions/methods/create) with the `include[]` parameter set to `logprobs`.\n",
+            "items": {
+              "type": "object",
+              "properties": {
+                "token": {
+                  "type": "string",
+                  "description": "The token that was used to generate the log probability.\n"
+                },
+                "logprob": {
+                  "type": "number",
+                  "description": "The log probability of the token.\n"
+                },
+                "bytes": {
+                  "type": "array",
+                  "items": {
+                    "type": "integer"
+                  },
+                  "description": "The bytes that were used to generate the log probability.\n"
+                }
+              }
+            }
+          },
+          "usage": {
+            "$ref": "#/components/schemas/TranscriptTextUsageTokens"
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ],
+        "x-oaiMeta": {
+          "name": "Stream Event (transcript.text.done)",
+          "group": "transcript",
+          "example": "{\n  \"type\": \"transcript.text.done\",\n  \"text\": \"I see skies of blue and clouds of white, the bright blessed days, the dark sacred nights, and I think to myself, what a wonderful world.\",\n  \"usage\": {\n    \"type\": \"tokens\",\n    \"input_tokens\": 14,\n    \"input_token_details\": {\n      \"text_tokens\": 10,\n      \"audio_tokens\": 4\n    },\n    \"output_tokens\": 31,\n    \"total_tokens\": 45\n  }\n}\n"
+        }
+      },
+      "TranscriptTextSegmentEvent": {
+        "type": "object",
+        "description": "Emitted when a diarized transcription returns a completed segment with speaker information. Only emitted when you [create a transcription](https://developers.openai.com/api/reference/resources/audio/subresources/transcriptions/methods/create) with `stream` set to `true` and `response_format` set to `diarized_json`.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `transcript.text.segment`.",
+            "enum": [
+              "transcript.text.segment"
+            ],
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "Unique identifier for the segment."
+          },
+          "start": {
+            "type": "number",
+            "format": "double",
+            "description": "Start timestamp of the segment in seconds."
+          },
+          "end": {
+            "type": "number",
+            "format": "double",
+            "description": "End timestamp of the segment in seconds."
+          },
+          "text": {
+            "type": "string",
+            "description": "Transcript text for this segment."
+          },
+          "speaker": {
+            "type": "string",
+            "description": "Speaker label for this segment."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "start",
+          "end",
+          "text",
+          "speaker"
+        ],
+        "x-oaiMeta": {
+          "name": "Stream Event (transcript.text.segment)",
+          "group": "transcript",
+          "example": "{\n  \"type\": \"transcript.text.segment\",\n  \"id\": \"seg_002\",\n  \"start\": 5.2,\n  \"end\": 12.8,\n  \"text\": \"Hi, I need help with diarization.\",\n  \"speaker\": \"A\"\n}\n"
+        }
+      },
+      "TranscriptTextUsageDuration": {
+        "type": "object",
+        "title": "Duration Usage",
+        "description": "Usage statistics for models billed by audio input duration.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "duration"
+            ],
+            "description": "The type of the usage object. Always `duration` for this variant.",
+            "x-stainless-const": true
+          },
+          "seconds": {
+            "type": "number",
+            "format": "double",
+            "description": "Duration of the input audio in seconds."
+          }
+        },
+        "required": [
+          "type",
+          "seconds"
+        ]
+      },
+      "TranscriptTextUsageTokens": {
+        "type": "object",
+        "title": "Token Usage",
+        "description": "Usage statistics for models billed by token usage.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "tokens"
+            ],
+            "description": "The type of the usage object. Always `tokens` for this variant.",
+            "x-stainless-const": true
+          },
+          "input_tokens": {
+            "type": "integer",
+            "description": "Number of input tokens billed for this request."
+          },
+          "input_token_details": {
+            "type": "object",
+            "description": "Details about the input tokens billed for this request.",
+            "properties": {
+              "text_tokens": {
+                "type": "integer",
+                "description": "Number of text tokens billed for this request."
+              },
+              "audio_tokens": {
+                "type": "integer",
+                "description": "Number of audio tokens billed for this request."
+              }
+            }
+          },
+          "output_tokens": {
+            "type": "integer",
+            "description": "Number of output tokens generated."
+          },
+          "total_tokens": {
+            "type": "integer",
+            "description": "Total number of tokens used (input + output)."
+          }
+        },
+        "required": [
+          "type",
+          "input_tokens",
+          "output_tokens",
+          "total_tokens"
+        ]
+      },
+      "TranscriptionChunkingStrategy": {
+        "type": "object",
+        "description": "Controls how the audio is cut into chunks. When set to `\"auto\"`, the\nserver first normalizes loudness and then uses voice activity detection (VAD) to\nchoose boundaries. `server_vad` object can be provided to tweak VAD detection\nparameters manually. If unset, the audio is transcribed as a single block. ",
+        "oneOf": [
+          {
+            "type": "string",
+            "enum": [
+              "auto"
+            ],
+            "default": [
+              "auto"
+            ],
+            "description": "Automatically set chunking parameters based on the audio. Must be set to `\"auto\"`.\n",
+            "x-stainless-const": true
+          },
+          {
+            "$ref": "#/components/schemas/VadConfig"
+          }
+        ]
+      },
+      "TranscriptionDiarizedSegment": {
+        "type": "object",
+        "description": "A segment of diarized transcript text with speaker metadata.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the segment. Always `transcript.text.segment`.\n",
+            "enum": [
+              "transcript.text.segment"
+            ],
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "Unique identifier for the segment."
+          },
+          "start": {
+            "type": "number",
+            "format": "double",
+            "description": "Start timestamp of the segment in seconds."
+          },
+          "end": {
+            "type": "number",
+            "format": "double",
+            "description": "End timestamp of the segment in seconds."
+          },
+          "text": {
+            "type": "string",
+            "description": "Transcript text for this segment."
+          },
+          "speaker": {
+            "type": "string",
+            "description": "Speaker label for this segment. When known speakers are provided, the label matches `known_speaker_names[]`. Otherwise speakers are labeled sequentially using capital letters (`A`, `B`, ...).\n"
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "start",
+          "end",
+          "text",
+          "speaker"
+        ]
+      },
+      "TranscriptionInclude": {
+        "type": "string",
+        "enum": [
+          "logprobs"
+        ],
+        "default": []
+      },
+      "TranscriptionLanguage": {
+        "type": "object",
+        "description": "A language detected in transcribed audio.",
+        "properties": {
+          "code": {
+            "type": "string",
+            "description": "The code of a language detected in the audio."
+          }
+        },
+        "required": [
+          "code"
+        ]
+      },
+      "TranscriptionSegment": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "integer",
+            "description": "Unique identifier of the segment."
+          },
+          "seek": {
+            "type": "integer",
+            "description": "Seek offset of the segment."
+          },
+          "start": {
+            "type": "number",
+            "format": "double",
+            "description": "Start time of the segment in seconds."
+          },
+          "end": {
+            "type": "number",
+            "format": "double",
+            "description": "End time of the segment in seconds."
+          },
+          "text": {
+            "type": "string",
+            "description": "Text content of the segment."
+          },
+          "tokens": {
+            "type": "array",
+            "items": {
+              "type": "integer"
+            },
+            "description": "Array of token IDs for the text content."
+          },
+          "temperature": {
+            "type": "number",
+            "format": "float",
+            "description": "Temperature parameter used for generating the segment."
+          },
+          "avg_logprob": {
+            "type": "number",
+            "format": "float",
+            "description": "Average logprob of the segment. If the value is lower than -1, consider the logprobs failed."
+          },
+          "compression_ratio": {
+            "type": "number",
+            "format": "float",
+            "description": "Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed."
+          },
+          "no_speech_prob": {
+            "type": "number",
+            "format": "float",
+            "description": "Probability of no speech in the segment. If the value is higher than 1.0 and the `avg_logprob` is below -1, consider this segment silent."
+          }
+        },
+        "required": [
+          "id",
+          "seek",
+          "start",
+          "end",
+          "text",
+          "tokens",
+          "temperature",
+          "avg_logprob",
+          "compression_ratio",
+          "no_speech_prob"
+        ]
+      },
+      "TranscriptionWord": {
+        "type": "object",
+        "properties": {
+          "word": {
+            "type": "string",
+            "description": "The text content of the word."
+          },
+          "start": {
+            "type": "number",
+            "format": "double",
+            "description": "Start time of the word in seconds."
+          },
+          "end": {
+            "type": "number",
+            "format": "double",
+            "description": "End time of the word in seconds."
+          }
+        },
+        "required": [
+          "word",
+          "start",
+          "end"
+        ]
+      },
+      "TruncationObject": {
+        "type": "object",
+        "title": "Thread Truncation Controls",
+        "description": "Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The truncation strategy to use for the thread. The default is `auto`. If set to `last_messages`, the thread will be truncated to the n most recent messages in the thread. When set to `auto`, messages in the middle of the thread will be dropped to fit the context length of the model, `max_prompt_tokens`.",
+            "enum": [
+              "auto",
+              "last_messages"
+            ]
+          },
+          "last_messages": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "The number of most recent messages from the thread when constructing the context for the run.",
+                "minimum": 1
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "UpdateGroupBody": {
+        "type": "object",
+        "description": "Request payload for updating the details of an existing group.",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "New display name for the group.",
+            "minLength": 1,
+            "maxLength": 255
+          }
+        },
+        "required": [
+          "name"
+        ],
+        "x-oaiMeta": {
+          "example": "{\n    \"name\": \"Escalations\"\n}\n"
+        }
+      },
+      "UpdateOrganizationDataRetentionBody": {
+        "type": "object",
+        "description": "Parameters for updating organization data retention controls.",
+        "properties": {
+          "retention_type": {
+            "type": "string",
+            "enum": [
+              "zero_data_retention",
+              "modified_abuse_monitoring",
+              "enhanced_zero_data_retention",
+              "enhanced_modified_abuse_monitoring"
+            ],
+            "description": "The desired organization data retention type."
+          }
+        },
+        "required": [
+          "retention_type"
+        ]
+      },
+      "UpdateProjectDataRetentionBody": {
+        "type": "object",
+        "description": "Parameters for updating project data retention controls.",
+        "properties": {
+          "retention_type": {
+            "type": "string",
+            "enum": [
+              "organization_default",
+              "none",
+              "zero_data_retention",
+              "modified_abuse_monitoring",
+              "enhanced_zero_data_retention",
+              "enhanced_modified_abuse_monitoring"
+            ],
+            "description": "The desired project data retention type."
+          }
+        },
+        "required": [
+          "retention_type"
+        ]
+      },
+      "UpdateProjectServiceAccountBody": {
+        "type": "object",
+        "description": "Parameters for updating a project service account.",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The updated service account name."
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "member",
+              "owner"
+            ],
+            "description": "The updated service account role."
+          }
+        }
+      },
+      "UpdateVectorStoreFileAttributesRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "attributes": {
+            "$ref": "#/components/schemas/VectorStoreFileAttributes"
+          }
+        },
+        "required": [
+          "attributes"
+        ],
+        "x-oaiMeta": {
+          "name": "Update vector store file attributes request"
+        }
+      },
+      "UpdateVectorStoreRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "name": {
+            "description": "The name of the vector store.",
+            "type": "string",
+            "nullable": true
+          },
+          "expires_after": {
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/VectorStoreExpirationAfter"
+              },
+              {
+                "nullable": true
+              }
+            ]
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          }
+        }
+      },
+      "UpdateVoiceConsentRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The updated label for this consent recording."
+          }
+        },
+        "required": [
+          "name"
+        ]
+      },
+      "Upload": {
+        "type": "object",
+        "title": "Upload",
+        "description": "The Upload object can accept byte chunks in the form of Parts.\n",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The Upload unique identifier, which can be referenced in API endpoints."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the Upload was created."
+          },
+          "filename": {
+            "type": "string",
+            "description": "The name of the file to be uploaded."
+          },
+          "bytes": {
+            "type": "integer",
+            "description": "The intended number of bytes to be uploaded."
+          },
+          "purpose": {
+            "type": "string",
+            "description": "The intended purpose of the file. [Please refer here](https://developers.openai.com/api/reference/resources/files#%28resource%29%20files%20%3E%20%28model%29%20file_object%20%3E%20%28schema%29%20%3E%20%28property%29%20purpose) for acceptable values."
+          },
+          "status": {
+            "type": "string",
+            "description": "The status of the Upload.",
+            "enum": [
+              "pending",
+              "completed",
+              "cancelled",
+              "expired"
+            ]
+          },
+          "expires_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the Upload will expire."
+          },
+          "object": {
+            "type": "string",
+            "description": "The object type, which is always \"upload\".",
+            "enum": [
+              "upload"
+            ],
+            "x-stainless-const": true
+          },
+          "file": {
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/OpenAIFile"
+              },
+              {
+                "nullable": true,
+                "description": "The ready File object after the Upload is completed."
+              }
+            ]
+          }
+        },
+        "required": [
+          "bytes",
+          "created_at",
+          "expires_at",
+          "filename",
+          "id",
+          "purpose",
+          "status"
+        ],
+        "x-oaiMeta": {
+          "name": "The upload object",
+          "example": "{\n  \"id\": \"upload_abc123\",\n  \"object\": \"upload\",\n  \"bytes\": 2147483648,\n  \"created_at\": 1719184911,\n  \"filename\": \"training_examples.jsonl\",\n  \"purpose\": \"fine-tune\",\n  \"status\": \"completed\",\n  \"expires_at\": 1719127296,\n  \"file\": {\n    \"id\": \"file-xyz321\",\n    \"object\": \"file\",\n    \"bytes\": 2147483648,\n    \"created_at\": 1719186911,\n    \"filename\": \"training_examples.jsonl\",\n    \"purpose\": \"fine-tune\",\n  }\n}\n"
+        }
+      },
+      "UploadCertificateRequest": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "An optional name for the certificate"
+          },
+          "certificate": {
+            "type": "string",
+            "description": "The certificate content in PEM format"
+          }
+        },
+        "required": [
+          "certificate"
+        ]
+      },
+      "UploadPart": {
+        "type": "object",
+        "title": "UploadPart",
+        "description": "The upload Part represents a chunk of bytes we can add to an Upload object.\n",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The upload Part unique identifier, which can be referenced in API endpoints."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the Part was created."
+          },
+          "upload_id": {
+            "type": "string",
+            "description": "The ID of the Upload object that this Part was added to."
+          },
+          "object": {
+            "type": "string",
+            "description": "The object type, which is always `upload.part`.",
+            "enum": [
+              "upload.part"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "created_at",
+          "id",
+          "object",
+          "upload_id"
+        ],
+        "x-oaiMeta": {
+          "name": "The upload part object",
+          "example": "{\n    \"id\": \"part_def456\",\n    \"object\": \"upload.part\",\n    \"created_at\": 1719186911,\n    \"upload_id\": \"upload_abc123\"\n}\n"
+        }
+      },
+      "UsageAudioSpeechesResult": {
+        "type": "object",
+        "description": "The aggregated audio speeches usage details of the specific time bucket.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.usage.audio_speeches.result"
+            ],
+            "x-stainless-const": true
+          },
+          "characters": {
+            "type": "integer",
+            "description": "The number of characters processed."
+          },
+          "num_model_requests": {
+            "type": "integer",
+            "description": "The count of requests made to the model."
+          },
+          "project_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=project_id`, this field provides the project ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "user_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=user_id`, this field provides the user ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "api_key_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=api_key_id`, this field provides the API key ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "model": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=model`, this field provides the model name of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "characters",
+          "num_model_requests"
+        ],
+        "x-oaiMeta": {
+          "name": "Audio speeches usage object",
+          "example": "{\n    \"object\": \"organization.usage.audio_speeches.result\",\n    \"characters\": 45,\n    \"num_model_requests\": 1,\n    \"project_id\": \"proj_abc\",\n    \"user_id\": \"user-abc\",\n    \"api_key_id\": \"key_abc\",\n    \"model\": \"tts-1\"\n}\n"
+        }
+      },
+      "UsageAudioTranscriptionsResult": {
+        "type": "object",
+        "description": "The aggregated audio transcriptions usage details of the specific time bucket.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.usage.audio_transcriptions.result"
+            ],
+            "x-stainless-const": true
+          },
+          "seconds": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The number of seconds processed."
+          },
+          "num_model_requests": {
+            "type": "integer",
+            "description": "The count of requests made to the model."
+          },
+          "project_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=project_id`, this field provides the project ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "user_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=user_id`, this field provides the user ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "api_key_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=api_key_id`, this field provides the API key ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "model": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=model`, this field provides the model name of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "seconds",
+          "num_model_requests"
+        ],
+        "x-oaiMeta": {
+          "name": "Audio transcriptions usage object",
+          "example": "{\n    \"object\": \"organization.usage.audio_transcriptions.result\",\n    \"seconds\": 10,\n    \"num_model_requests\": 1,\n    \"project_id\": \"proj_abc\",\n    \"user_id\": \"user-abc\",\n    \"api_key_id\": \"key_abc\",\n    \"model\": \"tts-1\"\n}\n"
+        }
+      },
+      "UsageCodeInterpreterSessionsResult": {
+        "type": "object",
+        "description": "The aggregated code interpreter sessions usage details of the specific time bucket.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.usage.code_interpreter_sessions.result"
+            ],
+            "x-stainless-const": true
+          },
+          "num_sessions": {
+            "type": "integer",
+            "description": "The number of code interpreter sessions."
+          },
+          "project_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=project_id`, this field provides the project ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "num_sessions"
+        ],
+        "x-oaiMeta": {
+          "name": "Code interpreter sessions usage object",
+          "example": "{\n    \"object\": \"organization.usage.code_interpreter_sessions.result\",\n    \"num_sessions\": 1,\n    \"project_id\": \"proj_abc\"\n}\n"
+        }
+      },
+      "UsageCompletionsResult": {
+        "type": "object",
+        "description": "The aggregated completions usage details of the specific time bucket.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.usage.completions.result"
+            ],
+            "x-stainless-const": true
+          },
+          "input_tokens": {
+            "type": "integer",
+            "description": "The aggregated number of input tokens used, including cached and cache-write tokens. This includes text, audio, and image tokens. For customers subscribed to Scale Tier, this includes Scale Tier tokens."
+          },
+          "input_cached_tokens": {
+            "type": "integer",
+            "description": "The aggregated number of cached input tokens used across text, audio, and image inputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens."
+          },
+          "input_cache_write_tokens": {
+            "type": "integer",
+            "description": "The aggregated number of input tokens written to the cache."
+          },
+          "input_uncached_tokens": {
+            "type": "integer",
+            "description": "The aggregated number of uncached input tokens used across text, audio, and image inputs, excluding cache-write tokens."
+          },
+          "output_tokens": {
+            "type": "integer",
+            "description": "The aggregated number of output tokens used across text, audio, and image outputs. For customers subscribed to Scale Tier, this includes Scale Tier tokens."
+          },
+          "input_text_tokens": {
+            "type": "integer",
+            "description": "The aggregated number of uncached text input tokens used, excluding cache-write tokens."
+          },
+          "output_text_tokens": {
+            "type": "integer",
+            "description": "The aggregated number of text output tokens used."
+          },
+          "input_cached_text_tokens": {
+            "type": "integer",
+            "description": "The aggregated number of cached text input tokens used."
+          },
+          "input_audio_tokens": {
+            "type": "integer",
+            "description": "The aggregated number of uncached audio input tokens used."
+          },
+          "input_cached_audio_tokens": {
+            "type": "integer",
+            "description": "The aggregated number of cached audio input tokens used."
+          },
+          "output_audio_tokens": {
+            "type": "integer",
+            "description": "The aggregated number of audio output tokens used."
+          },
+          "input_image_tokens": {
+            "type": "integer",
+            "description": "The aggregated number of uncached image input tokens used."
+          },
+          "input_cached_image_tokens": {
+            "type": "integer",
+            "description": "The aggregated number of cached image input tokens used."
+          },
+          "output_image_tokens": {
+            "type": "integer",
+            "description": "The aggregated number of image output tokens used."
+          },
+          "num_model_requests": {
+            "type": "integer",
+            "description": "The count of requests made to the model."
+          },
+          "project_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=project_id`, this field provides the project ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "user_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=user_id`, this field provides the user ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "api_key_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=api_key_id`, this field provides the API key ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "model": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=model`, this field provides the model name of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "batch": {
+            "anyOf": [
+              {
+                "type": "boolean",
+                "description": "When `group_by=batch`, this field tells whether the grouped usage result is batch or not."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "service_tier": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=service_tier`, this field provides the service tier of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "input_tokens",
+          "output_tokens",
+          "num_model_requests"
+        ],
+        "x-oaiMeta": {
+          "name": "Completions usage object",
+          "example": "{\n    \"object\": \"organization.usage.completions.result\",\n    \"input_tokens\": 5000,\n    \"input_cached_tokens\": 1800,\n    \"input_cache_write_tokens\": 200,\n    \"input_uncached_tokens\": 3000,\n    \"output_tokens\": 1000,\n    \"input_text_tokens\": 2500,\n    \"output_text_tokens\": 800,\n    \"input_cached_text_tokens\": 1500,\n    \"input_audio_tokens\": 300,\n    \"input_cached_audio_tokens\": 100,\n    \"output_audio_tokens\": 100,\n    \"input_image_tokens\": 200,\n    \"input_cached_image_tokens\": 200,\n    \"output_image_tokens\": 100,\n    \"num_model_requests\": 5,\n    \"project_id\": \"proj_abc\",\n    \"user_id\": \"user-abc\",\n    \"api_key_id\": \"key_abc\",\n    \"model\": \"gpt-6-astra\",\n    \"batch\": false,\n    \"service_tier\": \"default\"\n}\n"
+        }
+      },
+      "UsageEmbeddingsResult": {
+        "type": "object",
+        "description": "The aggregated embeddings usage details of the specific time bucket.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.usage.embeddings.result"
+            ],
+            "x-stainless-const": true
+          },
+          "input_tokens": {
+            "type": "integer",
+            "description": "The aggregated number of input tokens used."
+          },
+          "num_model_requests": {
+            "type": "integer",
+            "description": "The count of requests made to the model."
+          },
+          "project_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=project_id`, this field provides the project ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "user_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=user_id`, this field provides the user ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "api_key_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=api_key_id`, this field provides the API key ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "model": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=model`, this field provides the model name of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "input_tokens",
+          "num_model_requests"
+        ],
+        "x-oaiMeta": {
+          "name": "Embeddings usage object",
+          "example": "{\n    \"object\": \"organization.usage.embeddings.result\",\n    \"input_tokens\": 20,\n    \"num_model_requests\": 2,\n    \"project_id\": \"proj_abc\",\n    \"user_id\": \"user-abc\",\n    \"api_key_id\": \"key_abc\",\n    \"model\": \"text-embedding-ada-002-v2\"\n}\n"
+        }
+      },
+      "UsageFileSearchCallsResult": {
+        "type": "object",
+        "description": "The aggregated file search calls usage details of the specific time bucket.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.usage.file_searches.result"
+            ],
+            "x-stainless-const": true
+          },
+          "num_requests": {
+            "type": "integer",
+            "description": "The count of file search calls."
+          },
+          "project_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=project_id`, this field provides the project ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "user_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=user_id`, this field provides the user ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "api_key_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=api_key_id`, this field provides the API key ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "vector_store_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=vector_store_id`, this field provides the vector store ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "num_requests"
+        ],
+        "x-oaiMeta": {
+          "name": "File search calls usage object",
+          "example": "{\n    \"object\": \"organization.usage.file_searches.result\",\n    \"num_requests\": 2,\n    \"project_id\": \"proj_abc\",\n    \"user_id\": \"user-abc\",\n    \"api_key_id\": \"key_abc\",\n    \"vector_store_id\": \"vs_abc\"\n}\n"
+        }
+      },
+      "UsageImagesResult": {
+        "type": "object",
+        "description": "The aggregated images usage details of the specific time bucket.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.usage.images.result"
+            ],
+            "x-stainless-const": true
+          },
+          "images": {
+            "type": "integer",
+            "description": "The number of images processed."
+          },
+          "num_model_requests": {
+            "type": "integer",
+            "description": "The count of requests made to the model."
+          },
+          "source": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=source`, this field provides the source of the grouped usage result, possible values are `image.generation`, `image.edit`, `image.variation`."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "size": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=size`, this field provides the image size of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "project_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=project_id`, this field provides the project ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "user_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=user_id`, this field provides the user ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "api_key_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=api_key_id`, this field provides the API key ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "model": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=model`, this field provides the model name of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "images",
+          "num_model_requests"
+        ],
+        "x-oaiMeta": {
+          "name": "Images usage object",
+          "example": "{\n    \"object\": \"organization.usage.images.result\",\n    \"images\": 2,\n    \"num_model_requests\": 2,\n    \"size\": \"1024x1024\",\n    \"source\": \"image.generation\",\n    \"project_id\": \"proj_abc\",\n    \"user_id\": \"user-abc\",\n    \"api_key_id\": \"key_abc\",\n    \"model\": \"dall-e-3\"\n}\n"
+        }
+      },
+      "UsageModerationsResult": {
+        "type": "object",
+        "description": "The aggregated moderations usage details of the specific time bucket.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.usage.moderations.result"
+            ],
+            "x-stainless-const": true
+          },
+          "input_tokens": {
+            "type": "integer",
+            "description": "The aggregated number of input tokens used."
+          },
+          "num_model_requests": {
+            "type": "integer",
+            "description": "The count of requests made to the model."
+          },
+          "project_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=project_id`, this field provides the project ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "user_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=user_id`, this field provides the user ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "api_key_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=api_key_id`, this field provides the API key ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "model": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=model`, this field provides the model name of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "input_tokens",
+          "num_model_requests"
+        ],
+        "x-oaiMeta": {
+          "name": "Moderations usage object",
+          "example": "{\n    \"object\": \"organization.usage.moderations.result\",\n    \"input_tokens\": 20,\n    \"num_model_requests\": 2,\n    \"project_id\": \"proj_abc\",\n    \"user_id\": \"user-abc\",\n    \"api_key_id\": \"key_abc\",\n    \"model\": \"text-moderation\"\n}\n"
+        }
+      },
+      "UsageResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "page"
+            ],
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/UsageTimeBucket"
+            }
+          },
+          "has_more": {
+            "type": "boolean"
+          },
+          "next_page": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more",
+          "next_page"
+        ]
+      },
+      "UsageTimeBucket": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "bucket"
+            ],
+            "x-stainless-const": true
+          },
+          "start_time": {
+            "type": "integer"
+          },
+          "end_time": {
+            "type": "integer"
+          },
+          "results": {
+            "type": "array",
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/UsageCompletionsResult"
+                },
+                {
+                  "$ref": "#/components/schemas/UsageEmbeddingsResult"
+                },
+                {
+                  "$ref": "#/components/schemas/UsageModerationsResult"
+                },
+                {
+                  "$ref": "#/components/schemas/UsageImagesResult"
+                },
+                {
+                  "$ref": "#/components/schemas/UsageAudioSpeechesResult"
+                },
+                {
+                  "$ref": "#/components/schemas/UsageAudioTranscriptionsResult"
+                },
+                {
+                  "$ref": "#/components/schemas/UsageVectorStoresResult"
+                },
+                {
+                  "$ref": "#/components/schemas/UsageCodeInterpreterSessionsResult"
+                },
+                {
+                  "$ref": "#/components/schemas/UsageFileSearchCallsResult"
+                },
+                {
+                  "$ref": "#/components/schemas/UsageWebSearchCallsResult"
+                },
+                {
+                  "$ref": "#/components/schemas/CostsResult"
+                }
+              ],
+              "discriminator": {
+                "propertyName": "object"
+              }
+            }
+          }
+        },
+        "required": [
+          "object",
+          "start_time",
+          "end_time",
+          "results"
+        ]
+      },
+      "UsageVectorStoresResult": {
+        "type": "object",
+        "description": "The aggregated vector stores usage details of the specific time bucket.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.usage.vector_stores.result"
+            ],
+            "x-stainless-const": true
+          },
+          "usage_bytes": {
+            "type": "integer",
+            "description": "The vector stores usage in bytes."
+          },
+          "project_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=project_id`, this field provides the project ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "usage_bytes"
+        ],
+        "x-oaiMeta": {
+          "name": "Vector stores usage object",
+          "example": "{\n    \"object\": \"organization.usage.vector_stores.result\",\n    \"usage_bytes\": 1024,\n    \"project_id\": \"proj_abc\"\n}\n"
+        }
+      },
+      "UsageWebSearchCallsResult": {
+        "type": "object",
+        "description": "The aggregated web search calls usage details of the specific time bucket.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.usage.web_searches.result"
+            ],
+            "x-stainless-const": true
+          },
+          "num_model_requests": {
+            "type": "integer",
+            "description": "The count of model requests."
+          },
+          "num_requests": {
+            "type": "integer",
+            "description": "The count of web search calls."
+          },
+          "project_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=project_id`, this field provides the project ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "user_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=user_id`, this field provides the user ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "api_key_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=api_key_id`, this field provides the API key ID of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "model": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=model`, this field provides the model name of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "context_level": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "When `group_by=context_level`, this field provides the search context size of the grouped usage result."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "num_model_requests",
+          "num_requests"
+        ],
+        "x-oaiMeta": {
+          "name": "Web search calls usage object",
+          "example": "{\n    \"object\": \"organization.usage.web_searches.result\",\n    \"num_model_requests\": 2,\n    \"num_requests\": 2,\n    \"project_id\": \"proj_abc\",\n    \"user_id\": \"user-abc\",\n    \"api_key_id\": \"key_abc\",\n    \"model\": \"gpt-6-astra\",\n    \"context_level\": \"medium\"\n}\n"
+        }
+      },
+      "User": {
+        "type": "object",
+        "description": "Represents an individual `user` within an organization.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.user"
+            ],
+            "description": "The object type, which is always `organization.user`",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The identifier, which can be referenced in API endpoints"
+          },
+          "name": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The name of the user"
+          },
+          "email": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The email address of the user"
+          },
+          "role": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "`owner` or `reader`"
+          },
+          "added_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the user was added."
+          },
+          "is_default": {
+            "type": "boolean",
+            "description": "Whether this is the organization's default user."
+          },
+          "created": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the user was created."
+          },
+          "user": {
+            "type": "object",
+            "description": "Nested user details.",
+            "properties": {
+              "object": {
+                "type": "string",
+                "enum": [
+                  "user"
+                ],
+                "x-stainless-const": true
+              },
+              "id": {
+                "type": "string"
+              },
+              "email": {
+                "anyOf": [
+                  {
+                    "type": "string"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "name": {
+                "anyOf": [
+                  {
+                    "type": "string"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "picture": {
+                "anyOf": [
+                  {
+                    "type": "string"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "enabled": {
+                "anyOf": [
+                  {
+                    "type": "boolean"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "banned": {
+                "anyOf": [
+                  {
+                    "type": "boolean"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "banned_at": {
+                "anyOf": [
+                  {
+                    "type": "integer",
+                    "format": "unixtime"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              }
+            },
+            "required": [
+              "object",
+              "id"
+            ]
+          },
+          "is_service_account": {
+            "type": "boolean",
+            "description": "Whether the user is a service account."
+          },
+          "is_scale_tier_authorized_purchaser": {
+            "anyOf": [
+              {
+                "type": "boolean"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Whether the user is an authorized purchaser for Scale Tier."
+          },
+          "is_scim_managed": {
+            "type": "boolean",
+            "description": "Whether the user is managed through SCIM."
+          },
+          "api_key_last_used_at": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "format": "unixtime"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The Unix timestamp (in seconds) of the user's last API key usage."
+          },
+          "technical_level": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The technical level metadata for the user."
+          },
+          "developer_persona": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The developer persona metadata for the user."
+          },
+          "projects": {
+            "anyOf": [
+              {
+                "type": "object",
+                "properties": {
+                  "object": {
+                    "type": "string",
+                    "enum": [
+                      "list"
+                    ],
+                    "x-stainless-const": true
+                  },
+                  "data": {
+                    "type": "array",
+                    "items": {
+                      "type": "object",
+                      "properties": {
+                        "id": {
+                          "anyOf": [
+                            {
+                              "type": "string"
+                            },
+                            {
+                              "type": "null"
+                            }
+                          ]
+                        },
+                        "name": {
+                          "anyOf": [
+                            {
+                              "type": "string"
+                            },
+                            {
+                              "type": "null"
+                            }
+                          ]
+                        },
+                        "role": {
+                          "anyOf": [
+                            {
+                              "type": "string"
+                            },
+                            {
+                              "type": "null"
+                            }
+                          ]
+                        }
+                      }
+                    }
+                  }
+                },
+                "required": [
+                  "object",
+                  "data"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Projects associated with the user, if included."
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "added_at"
+        ],
+        "x-oaiMeta": {
+          "name": "The user object",
+          "example": "{\n    \"object\": \"organization.user\",\n    \"id\": \"user_abc\",\n    \"name\": \"First Last\",\n    \"email\": \"user@example.com\",\n    \"role\": \"owner\",\n    \"added_at\": 1711471533\n}\n"
+        }
+      },
+      "UserDeleteResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.user.deleted"
+            ],
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string"
+          },
+          "deleted": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "deleted"
+        ]
+      },
+      "UserListResource": {
+        "type": "object",
+        "description": "Paginated list of user objects returned when inspecting group membership.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "description": "Always `list`.",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "description": "Users in the current page.",
+            "items": {
+              "$ref": "#/components/schemas/GroupUser"
+            }
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether more users are available when paginating."
+          },
+          "next": {
+            "description": "Cursor to fetch the next page of results, or `null` when no further users are available.",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more",
+          "next"
+        ],
+        "x-oaiMeta": {
+          "name": "Group user list",
+          "example": "{\n    \"object\": \"list\",\n    \"data\": [\n        {\n            \"id\": \"user_abc123\",\n            \"name\": \"Ada Lovelace\",\n            \"email\": \"ada@example.com\"\n        }\n    ],\n    \"has_more\": false,\n    \"next\": null\n}\n"
+        }
+      },
+      "UserListResponse": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/User"
+            }
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "has_more": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more"
+        ]
+      },
+      "UserRoleAssignment": {
+        "type": "object",
+        "description": "Role assignment linking a user to a role.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "user.role"
+            ],
+            "description": "Always `user.role`.",
+            "x-stainless-const": true
+          },
+          "user": {
+            "$ref": "#/components/schemas/User"
+          },
+          "role": {
+            "$ref": "#/components/schemas/Role"
+          }
+        },
+        "required": [
+          "object",
+          "user",
+          "role"
+        ],
+        "x-oaiMeta": {
+          "name": "The user role object",
+          "example": "{\n    \"object\": \"user.role\",\n    \"user\": {\n        \"object\": \"organization.user\",\n        \"id\": \"user_abc123\",\n        \"name\": \"Ada Lovelace\",\n        \"email\": \"ada@example.com\",\n        \"role\": \"owner\",\n        \"added_at\": 1711470000\n    },\n    \"role\": {\n        \"object\": \"role\",\n        \"id\": \"role_01J1F8ROLE01\",\n        \"name\": \"API Group Manager\",\n        \"description\": \"Allows managing organization groups\",\n        \"permissions\": [\n            \"api.groups.read\",\n            \"api.groups.write\"\n        ],\n        \"resource_type\": \"api.organization\",\n        \"predefined_role\": false\n    }\n}\n"
+        }
+      },
+      "UserRoleUpdateRequest": {
+        "type": "object",
+        "properties": {
+          "role": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "`owner` or `reader`"
+          },
+          "role_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Role ID to assign to the user."
+          },
+          "technical_level": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Technical level metadata."
+          },
+          "developer_persona": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Developer persona metadata."
+          }
+        }
+      },
+      "VadConfig": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": [
+          "type"
+        ],
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "server_vad"
+            ],
+            "description": "Must be set to `server_vad` to enable manual chunking using server side VAD."
+          },
+          "prefix_padding_ms": {
+            "type": "integer",
+            "default": 300,
+            "description": "Amount of audio to include before the VAD detected speech (in \nmilliseconds).\n"
+          },
+          "silence_duration_ms": {
+            "type": "integer",
+            "default": 200,
+            "description": "Duration of silence to detect speech stop (in milliseconds).\nWith shorter values the model will respond more quickly, \nbut may jump in on short pauses from the user.\n"
+          },
+          "threshold": {
+            "type": "number",
+            "default": 0.5,
+            "description": "Sensitivity threshold (0.0 to 1.0) for voice activity detection. A \nhigher threshold will require louder audio to activate the model, and \nthus might perform better in noisy environments.\n"
+          }
+        }
+      },
+      "ValidateGraderRequest": {
+        "type": "object",
+        "title": "ValidateGraderRequest",
+        "properties": {
+          "grader": {
+            "type": "object",
+            "description": "The grader used for the fine-tuning job.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/GraderStringCheck"
+              },
+              {
+                "$ref": "#/components/schemas/GraderTextSimilarity"
+              },
+              {
+                "$ref": "#/components/schemas/GraderPython"
+              },
+              {
+                "$ref": "#/components/schemas/GraderScoreModel"
+              },
+              {
+                "$ref": "#/components/schemas/GraderMulti"
+              }
+            ]
+          }
+        },
+        "required": [
+          "grader"
+        ]
+      },
+      "ValidateGraderResponse": {
+        "type": "object",
+        "title": "ValidateGraderResponse",
+        "properties": {
+          "grader": {
+            "type": "object",
+            "description": "The grader used for the fine-tuning job.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/GraderStringCheck"
+              },
+              {
+                "$ref": "#/components/schemas/GraderTextSimilarity"
+              },
+              {
+                "$ref": "#/components/schemas/GraderPython"
+              },
+              {
+                "$ref": "#/components/schemas/GraderScoreModel"
+              },
+              {
+                "$ref": "#/components/schemas/GraderMulti"
+              }
+            ]
+          }
+        }
+      },
+      "VectorStoreExpirationAfter": {
+        "type": "object",
+        "title": "Vector store expiration policy",
+        "description": "The expiration policy for a vector store.",
+        "properties": {
+          "anchor": {
+            "description": "Anchor timestamp after which the expiration policy applies. Supported anchors: `last_active_at`.",
+            "type": "string",
+            "enum": [
+              "last_active_at"
+            ],
+            "x-stainless-const": true
+          },
+          "days": {
+            "description": "The number of days after the anchor time that the vector store will expire.",
+            "type": "integer",
+            "minimum": 1,
+            "maximum": 365
+          }
+        },
+        "required": [
+          "anchor",
+          "days"
+        ]
+      },
+      "VectorStoreFileAttributes": {
+        "anyOf": [
+          {
+            "type": "object",
+            "description": "Set of 16 key-value pairs that can be attached to an object. This can be\nuseful for storing additional information about the object in a structured\nformat, and querying for objects via API or the dashboard. Keys are strings\nwith a maximum length of 64 characters. Values are strings with a maximum\nlength of 512 characters, booleans, or numbers.\n",
+            "maxProperties": 16,
+            "propertyNames": {
+              "type": "string",
+              "maxLength": 64
+            },
+            "additionalProperties": {
+              "oneOf": [
+                {
+                  "type": "string",
+                  "maxLength": 512
+                },
+                {
+                  "type": "number"
+                },
+                {
+                  "type": "boolean"
+                }
+              ]
+            },
+            "x-oaiTypeLabel": "map"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "VectorStoreFileBatchObject": {
+        "type": "object",
+        "title": "Vector store file batch",
+        "description": "A batch of files attached to a vector store.",
+        "properties": {
+          "id": {
+            "description": "The identifier, which can be referenced in API endpoints.",
+            "type": "string"
+          },
+          "object": {
+            "description": "The object type, which is always `vector_store.file_batch`.",
+            "type": "string",
+            "enum": [
+              "vector_store.files_batch"
+            ],
+            "x-stainless-const": true
+          },
+          "created_at": {
+            "description": "The Unix timestamp (in seconds) for when the vector store files batch was created.",
+            "type": "integer",
+            "format": "unixtime"
+          },
+          "vector_store_id": {
+            "description": "The ID of the [vector store](https://developers.openai.com/api/reference/resources/vector_stores) that the [File](https://developers.openai.com/api/reference/resources/files) is attached to.",
+            "type": "string"
+          },
+          "status": {
+            "description": "The status of the vector store files batch, which can be either `in_progress`, `completed`, `cancelled` or `failed`.",
+            "type": "string",
+            "enum": [
+              "in_progress",
+              "completed",
+              "cancelled",
+              "failed"
+            ]
+          },
+          "file_counts": {
+            "type": "object",
+            "properties": {
+              "in_progress": {
+                "description": "The number of files that are currently being processed.",
+                "type": "integer"
+              },
+              "completed": {
+                "description": "The number of files that have been processed.",
+                "type": "integer"
+              },
+              "failed": {
+                "description": "The number of files that have failed to process.",
+                "type": "integer"
+              },
+              "cancelled": {
+                "description": "The number of files that where cancelled.",
+                "type": "integer"
+              },
+              "total": {
+                "description": "The total number of files.",
+                "type": "integer"
+              }
+            },
+            "required": [
+              "in_progress",
+              "completed",
+              "cancelled",
+              "failed",
+              "total"
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "created_at",
+          "vector_store_id",
+          "status",
+          "file_counts"
+        ],
+        "x-oaiMeta": {
+          "name": "The vector store files batch object",
+          "beta": true,
+          "example": "{\n  \"id\": \"vsfb_123\",\n  \"object\": \"vector_store.files_batch\",\n  \"created_at\": 1698107661,\n  \"vector_store_id\": \"vs_abc123\",\n  \"status\": \"completed\",\n  \"file_counts\": {\n    \"in_progress\": 0,\n    \"completed\": 100,\n    \"failed\": 0,\n    \"cancelled\": 0,\n    \"total\": 100\n  }\n}\n"
+        }
+      },
+      "VectorStoreFileContentResponse": {
+        "type": "object",
+        "description": "Represents the parsed content of a vector store file.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "vector_store.file_content.page"
+            ],
+            "description": "The object type, which is always `vector_store.file_content.page`",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "description": "Parsed content of the file.",
+            "items": {
+              "type": "object",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "description": "The content type (currently only `\"text\"`)"
+                },
+                "text": {
+                  "type": "string",
+                  "description": "The text content"
+                }
+              }
+            }
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Indicates if there are more content pages to fetch."
+          },
+          "next_page": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The token for the next page, if any."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more",
+          "next_page"
+        ]
+      },
+      "VectorStoreFileObject": {
+        "type": "object",
+        "title": "Vector store files",
+        "description": "A list of files attached to a vector store.",
+        "properties": {
+          "id": {
+            "description": "The identifier, which can be referenced in API endpoints.",
+            "type": "string"
+          },
+          "object": {
+            "description": "The object type, which is always `vector_store.file`.",
+            "type": "string",
+            "enum": [
+              "vector_store.file"
+            ],
+            "x-stainless-const": true
+          },
+          "usage_bytes": {
+            "description": "The total vector store usage in bytes. Note that this may be different from the original file size.",
+            "type": "integer"
+          },
+          "created_at": {
+            "description": "The Unix timestamp (in seconds) for when the vector store file was created.",
+            "type": "integer",
+            "format": "unixtime"
+          },
+          "vector_store_id": {
+            "description": "The ID of the [vector store](https://developers.openai.com/api/reference/resources/vector_stores) that the [File](https://developers.openai.com/api/reference/resources/files) is attached to.",
+            "type": "string"
+          },
+          "status": {
+            "description": "The status of the vector store file, which can be either `in_progress`, `completed`, `cancelled`, or `failed`. The status `completed` indicates that the vector store file is ready for use.",
+            "type": "string",
+            "enum": [
+              "in_progress",
+              "completed",
+              "cancelled",
+              "failed"
+            ]
+          },
+          "last_error": {
+            "anyOf": [
+              {
+                "type": "object",
+                "description": "The last error associated with this vector store file. Will be `null` if there are no errors.",
+                "properties": {
+                  "code": {
+                    "type": "string",
+                    "description": "One of `server_error`, `unsupported_file`, or `invalid_file`.",
+                    "enum": [
+                      "server_error",
+                      "unsupported_file",
+                      "invalid_file"
+                    ]
+                  },
+                  "message": {
+                    "type": "string",
+                    "description": "A human-readable description of the error."
+                  }
+                },
+                "required": [
+                  "code",
+                  "message"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "chunking_strategy": {
+            "type": "object",
+            "description": "The strategy used to chunk the file.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/StaticChunkingStrategyResponseParam"
+              },
+              {
+                "$ref": "#/components/schemas/OtherChunkingStrategyResponseParam"
+              }
+            ]
+          },
+          "attributes": {
+            "$ref": "#/components/schemas/VectorStoreFileAttributes"
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "usage_bytes",
+          "created_at",
+          "vector_store_id",
+          "status",
+          "last_error"
+        ],
+        "x-oaiMeta": {
+          "name": "The vector store file object",
+          "beta": true,
+          "example": "{\n  \"id\": \"file-abc123\",\n  \"object\": \"vector_store.file\",\n  \"usage_bytes\": 1234,\n  \"created_at\": 1698107661,\n  \"vector_store_id\": \"vs_abc123\",\n  \"status\": \"completed\",\n  \"last_error\": null,\n  \"chunking_strategy\": {\n    \"type\": \"static\",\n    \"static\": {\n      \"max_chunk_size_tokens\": 800,\n      \"chunk_overlap_tokens\": 400\n    }\n  }\n}\n"
+        }
+      },
+      "VectorStoreObject": {
+        "type": "object",
+        "title": "Vector store",
+        "description": "A vector store is a collection of processed files can be used by the `file_search` tool.",
+        "properties": {
+          "id": {
+            "description": "The identifier, which can be referenced in API endpoints.",
+            "type": "string"
+          },
+          "object": {
+            "description": "The object type, which is always `vector_store`.",
+            "type": "string",
+            "enum": [
+              "vector_store"
+            ],
+            "x-stainless-const": true
+          },
+          "created_at": {
+            "description": "The Unix timestamp (in seconds) for when the vector store was created.",
+            "type": "integer",
+            "format": "unixtime"
+          },
+          "name": {
+            "description": "The name of the vector store.",
+            "type": "string"
+          },
+          "usage_bytes": {
+            "description": "The total number of bytes used by the files in the vector store.",
+            "type": "integer"
+          },
+          "file_counts": {
+            "type": "object",
+            "properties": {
+              "in_progress": {
+                "description": "The number of files that are currently being processed.",
+                "type": "integer"
+              },
+              "completed": {
+                "description": "The number of files that have been successfully processed.",
+                "type": "integer"
+              },
+              "failed": {
+                "description": "The number of files that have failed to process.",
+                "type": "integer"
+              },
+              "cancelled": {
+                "description": "The number of files that were cancelled.",
+                "type": "integer"
+              },
+              "total": {
+                "description": "The total number of files.",
+                "type": "integer"
+              }
+            },
+            "required": [
+              "in_progress",
+              "completed",
+              "failed",
+              "cancelled",
+              "total"
+            ]
+          },
+          "status": {
+            "description": "The status of the vector store, which can be either `expired`, `in_progress`, or `completed`. A status of `completed` indicates that the vector store is ready for use.",
+            "type": "string",
+            "enum": [
+              "expired",
+              "in_progress",
+              "completed"
+            ]
+          },
+          "expires_after": {
+            "$ref": "#/components/schemas/VectorStoreExpirationAfter"
+          },
+          "expires_at": {
+            "anyOf": [
+              {
+                "description": "The Unix timestamp (in seconds) for when the vector store will expire.",
+                "type": "integer",
+                "format": "unixtime"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "last_active_at": {
+            "anyOf": [
+              {
+                "description": "The Unix timestamp (in seconds) for when the vector store was last active.",
+                "type": "integer",
+                "format": "unixtime"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata"
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "usage_bytes",
+          "created_at",
+          "status",
+          "last_active_at",
+          "name",
+          "file_counts",
+          "metadata"
+        ],
+        "x-oaiMeta": {
+          "name": "The vector store object",
+          "example": "{\n  \"id\": \"vs_123\",\n  \"object\": \"vector_store\",\n  \"created_at\": 1698107661,\n  \"usage_bytes\": 123456,\n  \"last_active_at\": 1698107661,\n  \"name\": \"my_vector_store\",\n  \"status\": \"completed\",\n  \"file_counts\": {\n    \"in_progress\": 0,\n    \"completed\": 100,\n    \"cancelled\": 0,\n    \"failed\": 0,\n    \"total\": 100\n  },\n  \"last_used_at\": 1698107661\n}\n"
+        }
+      },
+      "VectorStoreSearchRequest": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "query": {
+            "description": "A query string for a search",
+            "oneOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "array",
+                "items": {
+                  "type": "string",
+                  "description": "A list of queries to search for.",
+                  "minItems": 1
+                }
+              }
+            ]
+          },
+          "rewrite_query": {
+            "description": "Whether to rewrite the natural language query for vector search.",
+            "type": "boolean",
+            "default": false
+          },
+          "max_num_results": {
+            "description": "The maximum number of results to return. This number should be between 1 and 50 inclusive.",
+            "type": "integer",
+            "default": 10,
+            "minimum": 1,
+            "maximum": 50
+          },
+          "filters": {
+            "description": "A filter to apply based on file attributes.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/ComparisonFilter"
+              },
+              {
+                "$ref": "#/components/schemas/CompoundFilter"
+              }
+            ]
+          },
+          "ranking_options": {
+            "description": "Ranking options for search.",
+            "type": "object",
+            "additionalProperties": false,
+            "properties": {
+              "ranker": {
+                "description": "Enable re-ranking; set to `none` to disable, which can help reduce latency.",
+                "type": "string",
+                "enum": [
+                  "none",
+                  "auto",
+                  "default-2024-11-15"
+                ],
+                "default": "auto"
+              },
+              "score_threshold": {
+                "type": "number",
+                "minimum": 0,
+                "maximum": 1,
+                "default": 0
+              }
+            }
+          }
+        },
+        "required": [
+          "query"
+        ],
+        "x-oaiMeta": {
+          "name": "Vector store search request"
+        }
+      },
+      "VectorStoreSearchResultContentObject": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "type": {
+            "description": "The type of content.",
+            "type": "string",
+            "enum": [
+              "text"
+            ]
+          },
+          "text": {
+            "description": "The text content returned from search.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ],
+        "x-oaiMeta": {
+          "name": "Vector store search result content object"
+        }
+      },
+      "VectorStoreSearchResultItem": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "file_id": {
+            "type": "string",
+            "description": "The ID of the vector store file."
+          },
+          "filename": {
+            "type": "string",
+            "description": "The name of the vector store file."
+          },
+          "score": {
+            "type": "number",
+            "description": "The similarity score for the result.",
+            "minimum": 0,
+            "maximum": 1
+          },
+          "attributes": {
+            "$ref": "#/components/schemas/VectorStoreFileAttributes"
+          },
+          "content": {
+            "type": "array",
+            "description": "Content chunks from the file.",
+            "items": {
+              "$ref": "#/components/schemas/VectorStoreSearchResultContentObject"
+            }
+          }
+        },
+        "required": [
+          "file_id",
+          "filename",
+          "score",
+          "attributes",
+          "content"
+        ],
+        "x-oaiMeta": {
+          "name": "Vector store search result item"
+        }
+      },
+      "VectorStoreSearchResultsPage": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "vector_store.search_results.page"
+            ],
+            "description": "The object type, which is always `vector_store.search_results.page`",
+            "x-stainless-const": true
+          },
+          "search_query": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "description": "The query used for this search.",
+              "minItems": 1
+            }
+          },
+          "data": {
+            "type": "array",
+            "description": "The list of search result items.",
+            "items": {
+              "$ref": "#/components/schemas/VectorStoreSearchResultItem"
+            }
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Indicates if there are more results to fetch."
+          },
+          "next_page": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The token for the next page, if any."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "object",
+          "search_query",
+          "data",
+          "has_more",
+          "next_page"
+        ],
+        "x-oaiMeta": {
+          "name": "Vector store search results page"
+        }
+      },
+      "Verbosity": {
+        "anyOf": [
+          {
+            "type": "string",
+            "enum": [
+              "low",
+              "medium",
+              "high"
+            ],
+            "default": "medium",
+            "description": "Constrains the verbosity of the model's response. Lower values will result in\nmore concise responses, while higher values will result in more verbose responses.\nCurrently supported values are `low`, `medium`, and `high`. The default is\n`medium`.\n"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "VoiceConsentDeletedResource": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The consent recording identifier.",
+            "example": "cons_1234"
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "audio.voice_consent"
+            ],
+            "x-stainless-const": true
+          },
+          "deleted": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ],
+        "x-oaiMeta": {
+          "name": "The voice consent deletion object",
+          "example": "{\n  \"object\": \"audio.voice_consent\",\n  \"id\": \"cons_1234\",\n  \"deleted\": true\n}\n"
+        }
+      },
+      "VoiceConsentListResource": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/VoiceConsentResource"
+            }
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "has_more": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more"
+        ],
+        "x-oaiMeta": {
+          "name": "The voice consent list object",
+          "example": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"object\": \"audio.voice_consent\",\n      \"id\": \"cons_1234\",\n      \"name\": \"John Doe\",\n      \"language\": \"en-US\",\n      \"created_at\": 1734220800\n    }\n  ],\n  \"first_id\": \"cons_1234\",\n  \"last_id\": \"cons_1234\",\n  \"has_more\": false\n}\n"
+        }
+      },
+      "VoiceConsentResource": {
+        "type": "object",
+        "title": "Voice consent",
+        "description": "A consent recording used to authorize creation of a custom voice.",
+        "additionalProperties": false,
+        "properties": {
+          "object": {
+            "type": "string",
+            "description": "The object type, which is always `audio.voice_consent`.",
+            "enum": [
+              "audio.voice_consent"
+            ],
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The consent recording identifier.",
+            "example": "cons_1234"
+          },
+          "name": {
+            "type": "string",
+            "description": "The label provided when the consent recording was uploaded."
+          },
+          "language": {
+            "type": "string",
+            "description": "The BCP 47 language tag for the consent phrase (for example, `en-US`)."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the consent recording was created."
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "name",
+          "language",
+          "created_at"
+        ],
+        "x-oaiMeta": {
+          "name": "The voice consent object",
+          "example": "{\n  \"object\": \"audio.voice_consent\",\n  \"id\": \"cons_1234\",\n  \"name\": \"John Doe\",\n  \"language\": \"en-US\",\n  \"created_at\": 1734220800\n}\n"
+        }
+      },
+      "VoiceIdsOrCustomVoice": {
+        "title": "Voice",
+        "description": "A built-in voice name or a custom voice reference.\n",
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/VoiceIdsShared"
+          },
+          {
+            "type": "object",
+            "description": "Custom voice reference.",
+            "additionalProperties": false,
+            "required": [
+              "id"
+            ],
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The custom voice ID, e.g. `voice_1234`.",
+                "example": "voice_1234"
+              }
+            }
+          }
+        ]
+      },
+      "VoiceIdsShared": {
+        "example": "ash",
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "string",
+            "enum": [
+              "alloy",
+              "ash",
+              "ballad",
+              "coral",
+              "echo",
+              "sage",
+              "shimmer",
+              "verse",
+              "marin",
+              "cedar"
+            ]
+          }
+        ]
+      },
+      "VoiceResource": {
+        "type": "object",
+        "title": "Voice",
+        "description": "A custom voice that can be used for audio output.",
+        "additionalProperties": false,
+        "properties": {
+          "object": {
+            "type": "string",
+            "description": "The object type, which is always `audio.voice`.",
+            "enum": [
+              "audio.voice"
+            ],
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The voice identifier, which can be referenced in API endpoints."
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the voice."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) for when the voice was created."
+          }
+        },
+        "required": [
+          "object",
+          "id",
+          "name",
+          "created_at"
+        ],
+        "x-oaiMeta": {
+          "name": "The voice object",
+          "example": "{\n  \"object\": \"audio.voice\",\n  \"id\": \"voice_123abc\",\n  \"name\": \"My new voice\",\n  \"created_at\": 1734220800\n}\n"
+        }
+      },
+      "WebSearchActionFind": {
+        "type": "object",
+        "title": "Find action",
+        "description": "Action type \"find_in_page\": Searches for a pattern within a loaded page.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "find_in_page"
+            ],
+            "description": "The action type.\n",
+            "x-stainless-const": true
+          },
+          "url": {
+            "type": "string",
+            "format": "uri",
+            "description": "The URL of the page searched for the pattern.\n"
+          },
+          "pattern": {
+            "type": "string",
+            "description": "The pattern or text to search for within the page.\n"
+          }
+        },
+        "required": [
+          "type",
+          "url",
+          "pattern"
+        ]
+      },
+      "WebSearchActionOpenPage": {
+        "type": "object",
+        "title": "Open page action",
+        "description": "Action type \"open_page\" - Opens a specific URL from search results.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "open_page"
+            ],
+            "description": "The action type.\n",
+            "x-stainless-const": true
+          },
+          "url": {
+            "description": "The URL opened by the model.\n",
+            "anyOf": [
+              {
+                "type": "string",
+                "format": "uri"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "WebSearchActionSearch": {
+        "type": "object",
+        "title": "Search action",
+        "description": "Action type \"search\" - Performs a web search query.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "search"
+            ],
+            "description": "The action type.\n",
+            "x-stainless-const": true
+          },
+          "query": {
+            "type": "string",
+            "deprecated": true,
+            "description": "The search query.\n"
+          },
+          "queries": {
+            "type": "array",
+            "title": "Search queries",
+            "description": "The search queries.\n",
+            "items": {
+              "type": "string",
+              "description": "A search query.\n"
+            }
+          },
+          "sources": {
+            "type": "array",
+            "title": "Web search sources",
+            "description": "The sources used in the search.\n",
+            "items": {
+              "type": "object",
+              "title": "Web search source",
+              "description": "A source used in the search.\n",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "url"
+                  ],
+                  "description": "The type of source. Always `url`.\n",
+                  "x-stainless-const": true
+                },
+                "url": {
+                  "type": "string",
+                  "format": "uri",
+                  "description": "The URL of the source.\n"
+                }
+              },
+              "required": [
+                "type",
+                "url"
+              ]
+            }
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "WebSearchApproximateLocation": {
+        "anyOf": [
+          {
+            "type": "object",
+            "title": "Web search approximate location",
+            "description": "The approximate location of the user.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "approximate"
+                ],
+                "description": "The type of location approximation. Always `approximate`.",
+                "default": "approximate",
+                "x-stainless-const": true
+              },
+              "country": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`."
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "region": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "Free text input for the region of the user, e.g. `California`."
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "city": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "Free text input for the city of the user, e.g. `San Francisco`."
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "timezone": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`."
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              }
+            }
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "WebSearchContextSize": {
+        "type": "string",
+        "description": "High level guidance for the amount of context window space to use for the \nsearch. One of `low`, `medium`, or `high`. `medium` is the default.\n",
+        "enum": [
+          "low",
+          "medium",
+          "high"
+        ],
+        "default": "medium"
+      },
+      "WebSearchLocation": {
+        "type": "object",
+        "title": "Web search location",
+        "description": "Approximate location parameters for the search.",
+        "properties": {
+          "country": {
+            "type": "string",
+            "description": "The two-letter \n[ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user,\ne.g. `US`.\n"
+          },
+          "region": {
+            "type": "string",
+            "description": "Free text input for the region of the user, e.g. `California`.\n"
+          },
+          "city": {
+            "type": "string",
+            "description": "Free text input for the city of the user, e.g. `San Francisco`.\n"
+          },
+          "timezone": {
+            "type": "string",
+            "description": "The [IANA timezone](https://timeapi.io/documentation/iana-timezones) \nof the user, e.g. `America/Los_Angeles`.\n"
+          }
+        }
+      },
+      "WebSearchTool": {
+        "type": "object",
+        "title": "Web search",
+        "description": "Search the Internet for sources related to the prompt. Learn more about the\n[web search tool](https://developers.openai.com/api/docs/guides/tools-web-search).\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "web_search",
+              "web_search_2025_08_26"
+            ],
+            "description": "The type of the web search tool. One of `web_search` or `web_search_2025_08_26`.",
+            "default": "web_search"
+          },
+          "external_web_access": {
+            "type": "boolean",
+            "default": true,
+            "description": "Allow live internet access for web search. Defaults to true when omitted. When false, the web search tool runs in offline/cache-only mode and will not fetch new external content."
+          },
+          "filters": {
+            "anyOf": [
+              {
+                "type": "object",
+                "description": "Filters for the search.\n",
+                "properties": {
+                  "allowed_domains": {
+                    "anyOf": [
+                      {
+                        "type": "array",
+                        "title": "Allowed domains for the search.",
+                        "description": "Allowed domains for the search. If not provided, all domains are allowed.\nSubdomains of the provided domains are allowed as well.\n\nExample: `[\"pubmed.ncbi.nlm.nih.gov\"]`\n",
+                        "items": {
+                          "type": "string",
+                          "description": "Allowed domain for the search."
+                        },
+                        "default": []
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ]
+                  }
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "user_location": {
+            "$ref": "#/components/schemas/WebSearchApproximateLocation"
+          },
+          "search_context_size": {
+            "type": "string",
+            "enum": [
+              "low",
+              "medium",
+              "high"
+            ],
+            "default": "medium",
+            "description": "High level guidance for the amount of context window space to use for the search. One of `low`, `medium`, or `high`. `medium` is the default."
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "WebSearchToolCall": {
+        "type": "object",
+        "title": "Web search tool call",
+        "description": "The results of a web search tool call. See the\n[web search guide](https://developers.openai.com/api/docs/guides/tools-web-search) for more information.\n",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the web search tool call.\n"
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "web_search_call"
+            ],
+            "description": "The type of the web search tool call. Always `web_search_call`.\n",
+            "x-stainless-const": true
+          },
+          "status": {
+            "description": "The status of the web search tool call.\n",
+            "$ref": "#/components/schemas/WebSearchCallStatus"
+          },
+          "action": {
+            "type": "object",
+            "description": "An object describing the specific action taken in this web search call.\nIncludes details on how the model used the web (search, open_page, find_in_page).\n",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/WebSearchActionSearch"
+              },
+              {
+                "$ref": "#/components/schemas/WebSearchActionOpenPage"
+              },
+              {
+                "$ref": "#/components/schemas/WebSearchActionFind"
+              }
+            ],
+            "discriminator": {
+              "propertyName": "type"
+            }
+          }
+        },
+        "required": [
+          "id",
+          "type",
+          "status",
+          "action"
+        ]
+      },
+      "WebhookBatchCancelled": {
+        "type": "object",
+        "title": "batch.cancelled",
+        "description": "Sent when a batch API request has been cancelled.\n",
+        "required": [
+          "created_at",
+          "id",
+          "data",
+          "type"
+        ],
+        "properties": {
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the batch API request was cancelled.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the event.\n"
+          },
+          "data": {
+            "type": "object",
+            "description": "Event data payload.\n",
+            "required": [
+              "id"
+            ],
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the batch API request.\n"
+              }
+            }
+          },
+          "object": {
+            "type": "string",
+            "description": "The object of the event. Always `event`.\n",
+            "enum": [
+              "event"
+            ],
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `batch.cancelled`.\n",
+            "enum": [
+              "batch.cancelled"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "x-oaiMeta": {
+          "name": "batch.cancelled",
+          "group": "webhook-events",
+          "example": "{\n  \"id\": \"evt_abc123\",\n  \"type\": \"batch.cancelled\",\n  \"created_at\": 1719168000,\n  \"data\": {\n    \"id\": \"batch_abc123\"\n  }\n}\n"
+        }
+      },
+      "WebhookBatchCompleted": {
+        "type": "object",
+        "title": "batch.completed",
+        "description": "Sent when a batch API request has been completed.\n",
+        "required": [
+          "created_at",
+          "id",
+          "data",
+          "type"
+        ],
+        "properties": {
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the batch API request was completed.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the event.\n"
+          },
+          "data": {
+            "type": "object",
+            "description": "Event data payload.\n",
+            "required": [
+              "id"
+            ],
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the batch API request.\n"
+              }
+            }
+          },
+          "object": {
+            "type": "string",
+            "description": "The object of the event. Always `event`.\n",
+            "enum": [
+              "event"
+            ],
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `batch.completed`.\n",
+            "enum": [
+              "batch.completed"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "x-oaiMeta": {
+          "name": "batch.completed",
+          "group": "webhook-events",
+          "example": "{\n  \"id\": \"evt_abc123\",\n  \"type\": \"batch.completed\",\n  \"created_at\": 1719168000,\n  \"data\": {\n    \"id\": \"batch_abc123\"\n  }\n}\n"
+        }
+      },
+      "WebhookBatchExpired": {
+        "type": "object",
+        "title": "batch.expired",
+        "description": "Sent when a batch API request has expired.\n",
+        "required": [
+          "created_at",
+          "id",
+          "data",
+          "type"
+        ],
+        "properties": {
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the batch API request expired.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the event.\n"
+          },
+          "data": {
+            "type": "object",
+            "description": "Event data payload.\n",
+            "required": [
+              "id"
+            ],
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the batch API request.\n"
+              }
+            }
+          },
+          "object": {
+            "type": "string",
+            "description": "The object of the event. Always `event`.\n",
+            "enum": [
+              "event"
+            ],
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `batch.expired`.\n",
+            "enum": [
+              "batch.expired"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "x-oaiMeta": {
+          "name": "batch.expired",
+          "group": "webhook-events",
+          "example": "{\n  \"id\": \"evt_abc123\",\n  \"type\": \"batch.expired\",\n  \"created_at\": 1719168000,\n  \"data\": {\n    \"id\": \"batch_abc123\"\n  }\n}\n"
+        }
+      },
+      "WebhookBatchFailed": {
+        "type": "object",
+        "title": "batch.failed",
+        "description": "Sent when a batch API request has failed.\n",
+        "required": [
+          "created_at",
+          "id",
+          "data",
+          "type"
+        ],
+        "properties": {
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the batch API request failed.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the event.\n"
+          },
+          "data": {
+            "type": "object",
+            "description": "Event data payload.\n",
+            "required": [
+              "id"
+            ],
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the batch API request.\n"
+              }
+            }
+          },
+          "object": {
+            "type": "string",
+            "description": "The object of the event. Always `event`.\n",
+            "enum": [
+              "event"
+            ],
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `batch.failed`.\n",
+            "enum": [
+              "batch.failed"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "x-oaiMeta": {
+          "name": "batch.failed",
+          "group": "webhook-events",
+          "example": "{\n  \"id\": \"evt_abc123\",\n  \"type\": \"batch.failed\",\n  \"created_at\": 1719168000,\n  \"data\": {\n    \"id\": \"batch_abc123\"\n  }\n}\n"
+        }
+      },
+      "WebhookEvalRunCanceled": {
+        "type": "object",
+        "title": "eval.run.canceled",
+        "description": "Sent when an eval run has been canceled.\n",
+        "required": [
+          "created_at",
+          "id",
+          "data",
+          "type"
+        ],
+        "properties": {
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the eval run was canceled.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the event.\n"
+          },
+          "data": {
+            "type": "object",
+            "description": "Event data payload.\n",
+            "required": [
+              "id"
+            ],
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the eval run.\n"
+              }
+            }
+          },
+          "object": {
+            "type": "string",
+            "description": "The object of the event. Always `event`.\n",
+            "enum": [
+              "event"
+            ],
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `eval.run.canceled`.\n",
+            "enum": [
+              "eval.run.canceled"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "x-oaiMeta": {
+          "name": "eval.run.canceled",
+          "group": "webhook-events",
+          "example": "{\n  \"id\": \"evt_abc123\",\n  \"type\": \"eval.run.canceled\",\n  \"created_at\": 1719168000,\n  \"data\": {\n    \"id\": \"evalrun_abc123\"\n  }\n} \n"
+        }
+      },
+      "WebhookEvalRunFailed": {
+        "type": "object",
+        "title": "eval.run.failed",
+        "description": "Sent when an eval run has failed.\n",
+        "required": [
+          "created_at",
+          "id",
+          "data",
+          "type"
+        ],
+        "properties": {
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the eval run failed.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the event.\n"
+          },
+          "data": {
+            "type": "object",
+            "description": "Event data payload.\n",
+            "required": [
+              "id"
+            ],
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the eval run.\n"
+              }
+            }
+          },
+          "object": {
+            "type": "string",
+            "description": "The object of the event. Always `event`.\n",
+            "enum": [
+              "event"
+            ],
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `eval.run.failed`.\n",
+            "enum": [
+              "eval.run.failed"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "x-oaiMeta": {
+          "name": "eval.run.failed",
+          "group": "webhook-events",
+          "example": "{\n  \"id\": \"evt_abc123\",\n  \"type\": \"eval.run.failed\",\n  \"created_at\": 1719168000,\n  \"data\": {\n    \"id\": \"evalrun_abc123\"\n  }\n} \n"
+        }
+      },
+      "WebhookEvalRunSucceeded": {
+        "type": "object",
+        "title": "eval.run.succeeded",
+        "description": "Sent when an eval run has succeeded.\n",
+        "required": [
+          "created_at",
+          "id",
+          "data",
+          "type"
+        ],
+        "properties": {
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the eval run succeeded.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the event.\n"
+          },
+          "data": {
+            "type": "object",
+            "description": "Event data payload.\n",
+            "required": [
+              "id"
+            ],
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the eval run.\n"
+              }
+            }
+          },
+          "object": {
+            "type": "string",
+            "description": "The object of the event. Always `event`.\n",
+            "enum": [
+              "event"
+            ],
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `eval.run.succeeded`.\n",
+            "enum": [
+              "eval.run.succeeded"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "x-oaiMeta": {
+          "name": "eval.run.succeeded",
+          "group": "webhook-events",
+          "example": "{\n  \"id\": \"evt_abc123\",\n  \"type\": \"eval.run.succeeded\",\n  \"created_at\": 1719168000,\n  \"data\": {\n    \"id\": \"evalrun_abc123\"\n  }\n} \n"
+        }
+      },
+      "WebhookFineTuningJobCancelled": {
+        "type": "object",
+        "title": "fine_tuning.job.cancelled",
+        "description": "Sent when a fine-tuning job has been cancelled.\n",
+        "required": [
+          "created_at",
+          "id",
+          "data",
+          "type"
+        ],
+        "properties": {
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the fine-tuning job was cancelled.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the event.\n"
+          },
+          "data": {
+            "type": "object",
+            "description": "Event data payload.\n",
+            "required": [
+              "id"
+            ],
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the fine-tuning job.\n"
+              }
+            }
+          },
+          "object": {
+            "type": "string",
+            "description": "The object of the event. Always `event`.\n",
+            "enum": [
+              "event"
+            ],
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `fine_tuning.job.cancelled`.\n",
+            "enum": [
+              "fine_tuning.job.cancelled"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "x-oaiMeta": {
+          "name": "fine_tuning.job.cancelled",
+          "group": "webhook-events",
+          "example": "{\n  \"id\": \"evt_abc123\",\n  \"type\": \"fine_tuning.job.cancelled\",\n  \"created_at\": 1719168000,\n  \"data\": {\n    \"id\": \"ftjob_abc123\"\n  }\n} \n"
+        }
+      },
+      "WebhookFineTuningJobFailed": {
+        "type": "object",
+        "title": "fine_tuning.job.failed",
+        "description": "Sent when a fine-tuning job has failed.\n",
+        "required": [
+          "created_at",
+          "id",
+          "data",
+          "type"
+        ],
+        "properties": {
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the fine-tuning job failed.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the event.\n"
+          },
+          "data": {
+            "type": "object",
+            "description": "Event data payload.\n",
+            "required": [
+              "id"
+            ],
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the fine-tuning job.\n"
+              }
+            }
+          },
+          "object": {
+            "type": "string",
+            "description": "The object of the event. Always `event`.\n",
+            "enum": [
+              "event"
+            ],
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `fine_tuning.job.failed`.\n",
+            "enum": [
+              "fine_tuning.job.failed"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "x-oaiMeta": {
+          "name": "fine_tuning.job.failed",
+          "group": "webhook-events",
+          "example": "{\n  \"id\": \"evt_abc123\",\n  \"type\": \"fine_tuning.job.failed\",\n  \"created_at\": 1719168000,\n  \"data\": {\n    \"id\": \"ftjob_abc123\"\n  }\n} \n"
+        }
+      },
+      "WebhookFineTuningJobSucceeded": {
+        "type": "object",
+        "title": "fine_tuning.job.succeeded",
+        "description": "Sent when a fine-tuning job has succeeded.\n",
+        "required": [
+          "created_at",
+          "id",
+          "data",
+          "type"
+        ],
+        "properties": {
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the fine-tuning job succeeded.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the event.\n"
+          },
+          "data": {
+            "type": "object",
+            "description": "Event data payload.\n",
+            "required": [
+              "id"
+            ],
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the fine-tuning job.\n"
+              }
+            }
+          },
+          "object": {
+            "type": "string",
+            "description": "The object of the event. Always `event`.\n",
+            "enum": [
+              "event"
+            ],
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `fine_tuning.job.succeeded`.\n",
+            "enum": [
+              "fine_tuning.job.succeeded"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "x-oaiMeta": {
+          "name": "fine_tuning.job.succeeded",
+          "group": "webhook-events",
+          "example": "{\n  \"id\": \"evt_abc123\",\n  \"type\": \"fine_tuning.job.succeeded\",\n  \"created_at\": 1719168000,\n  \"data\": {\n    \"id\": \"ftjob_abc123\"\n  }\n} \n"
+        }
+      },
+      "WebhookLiveCallIncoming": {
+        "type": "object",
+        "title": "live.call.incoming",
+        "deprecated": true,
+        "description": "Deprecated: use `live.transport.incoming`. Retained for existing subscriptions\nduring migration; new subscriptions to this event are not allowed.\nSent when an incoming API SIP session is available for Live acceptance. The\nsame pending session can also emit `realtime.call.incoming`; the first\nsuccessful Realtime or Live accept endpoint selects the runtime surface.\n",
+        "required": [
+          "created_at",
+          "id",
+          "data",
+          "type"
+        ],
+        "properties": {
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the event was created.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the event.\n"
+          },
+          "data": {
+            "type": "object",
+            "description": "Event data payload.\n",
+            "required": [
+              "session_id",
+              "sip_headers"
+            ],
+            "properties": {
+              "session_id": {
+                "type": "string",
+                "description": "The `live_...` ID of the pending SIP session. Pass this value unchanged\nto Live call controls and sideband connections. The corresponding\n`realtime.call.incoming` event uses a separate `rtc_...` call ID.\n"
+              },
+              "sip_headers": {
+                "type": "array",
+                "description": "Headers from the SIP INVITE, excluding SIP authorization headers.\nRetained names, values, repeated entries, and order are preserved.\nTreat these values as untrusted call metadata.\n",
+                "items": {
+                  "type": "object",
+                  "description": "A header from the SIP Invite.\n",
+                  "required": [
+                    "name",
+                    "value"
+                  ],
+                  "properties": {
+                    "name": {
+                      "type": "string",
+                      "description": "Name of the SIP Header.\n"
+                    },
+                    "value": {
+                      "type": "string",
+                      "description": "Value of the SIP Header.\n"
+                    }
+                  }
+                }
+              }
+            }
+          },
+          "object": {
+            "type": "string",
+            "description": "The object of the event. Always `event`.\n",
+            "enum": [
+              "event"
+            ],
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `live.call.incoming`.\n",
+            "enum": [
+              "live.call.incoming"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "x-oaiMeta": {
+          "name": "live.call.incoming",
+          "group": "webhook-events",
+          "example": "{\n  \"id\": \"evt_abc123\",\n  \"type\": \"live.call.incoming\",\n  \"created_at\": 1719168000,\n  \"data\": {\n    \"session_id\": \"live_u0_479a275623b54bdb9b6fbae2f7cbd408\",\n    \"sip_headers\": [\n      {\"name\": \"From\", \"value\": \"<sip:alice@example.com>;tag=abc123\"},\n      {\"name\": \"To\", \"value\": \"<sip:recipient@example.com>\"},\n      {\"name\": \"Call-ID\", \"value\": \"call-123@example.com\"}\n    ]\n  }\n}\n"
+        }
+      },
+      "WebhookLiveTransportIncoming": {
+        "type": "object",
+        "title": "live.transport.incoming",
+        "description": "Sent when an incoming API SIP session is available for Live acceptance. The\nsame pending session can also emit `realtime.call.incoming`; the first\nsuccessful Realtime or Live accept endpoint selects the runtime surface.\n",
+        "required": [
+          "created_at",
+          "id",
+          "data",
+          "type"
+        ],
+        "properties": {
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the event was created.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the event.\n"
+          },
+          "data": {
+            "type": "object",
+            "description": "Event data payload.\n",
+            "required": [
+              "type",
+              "session_id",
+              "sip_headers"
+            ],
+            "properties": {
+              "type": {
+                "type": "string",
+                "description": "The incoming transport type. Always `sip`.",
+                "enum": [
+                  "sip"
+                ],
+                "x-stainless-const": true
+              },
+              "session_id": {
+                "type": "string",
+                "description": "The `live_...` ID of the pending SIP session. Forward this value\nunchanged when accepting or rejecting the call through the Live API.\n"
+              },
+              "sip_headers": {
+                "type": "array",
+                "description": "Headers from the SIP INVITE, excluding SIP authorization headers.\nRetained names, values, repeated entries, and order are preserved.\nTreat these values as untrusted call metadata.\n",
+                "items": {
+                  "type": "object",
+                  "description": "A header from the SIP Invite.\n",
+                  "required": [
+                    "name",
+                    "value"
+                  ],
+                  "properties": {
+                    "name": {
+                      "type": "string",
+                      "description": "Name of the SIP Header.\n"
+                    },
+                    "value": {
+                      "type": "string",
+                      "description": "Value of the SIP Header.\n"
+                    }
+                  }
+                }
+              }
+            }
+          },
+          "object": {
+            "type": "string",
+            "description": "The object of the event. Always `event`.\n",
+            "enum": [
+              "event"
+            ],
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `live.transport.incoming`.\n",
+            "enum": [
+              "live.transport.incoming"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "x-oaiMeta": {
+          "name": "live.transport.incoming",
+          "group": "webhook-events",
+          "example": "{\n  \"id\": \"evt_abc123\",\n  \"type\": \"live.transport.incoming\",\n  \"created_at\": 1719168000,\n  \"data\": {\n    \"type\": \"sip\",\n    \"session_id\": \"live_u0_479a275623b54bdb9b6fbae2f7cbd408\",\n    \"sip_headers\": [\n      {\"name\": \"From\", \"value\": \"<sip:alice@example.com>;tag=abc123\"},\n      {\"name\": \"To\", \"value\": \"<sip:recipient@example.com>\"},\n      {\"name\": \"Call-ID\", \"value\": \"call-123@example.com\"}\n    ]\n  }\n}\n"
+        }
+      },
+      "WebhookRealtimeCallIncoming": {
+        "type": "object",
+        "title": "realtime.call.incoming",
+        "description": "Sent when an incoming API SIP session is available for Realtime acceptance.\nThe same pending session can also emit `live.transport.incoming`; the first\nsuccessful Realtime or Live accept endpoint selects the runtime surface.\n",
+        "required": [
+          "created_at",
+          "id",
+          "data",
+          "type"
+        ],
+        "properties": {
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the model response was completed.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the event.\n"
+          },
+          "data": {
+            "type": "object",
+            "description": "Event data payload.\n",
+            "required": [
+              "call_id",
+              "sip_headers"
+            ],
+            "properties": {
+              "call_id": {
+                "type": "string",
+                "description": "The Transceiver `rtc_...` ID of the pending SIP session. The paired\n`live.transport.incoming` event derives its `session_id` by replacing the\n`rtc_` prefix with `live_`. Use the ID returned by the event with the\ncorresponding Realtime or Live API.\n"
+              },
+              "sip_headers": {
+                "type": "array",
+                "description": "Headers from the SIP INVITE, excluding SIP authorization headers.\nRetained names, values, repeated entries, and order are preserved.\nTreat these values as untrusted call metadata.\n",
+                "items": {
+                  "type": "object",
+                  "description": "A header from the SIP Invite.\n",
+                  "required": [
+                    "name",
+                    "value"
+                  ],
+                  "properties": {
+                    "name": {
+                      "type": "string",
+                      "description": "Name of the SIP Header.\n"
+                    },
+                    "value": {
+                      "type": "string",
+                      "description": "Value of the SIP Header.\n"
+                    }
+                  }
+                }
+              }
+            }
+          },
+          "object": {
+            "type": "string",
+            "description": "The object of the event. Always `event`.\n",
+            "enum": [
+              "event"
+            ],
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `realtime.call.incoming`.\n",
+            "enum": [
+              "realtime.call.incoming"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "x-oaiMeta": {
+          "name": "realtime.call.incoming",
+          "group": "webhook-events",
+          "example": "{\n  \"id\": \"evt_abc123\",\n  \"type\": \"realtime.call.incoming\",\n  \"created_at\": 1719168000,\n  \"data\": {\n    \"call_id\": \"rtc_479a275623b54bdb9b6fbae2f7cbd408\",\n    \"sip_headers\": [\n      {\"name\": \"Max-Forwards\", \"value\": \"63\"},\n      {\"name\": \"CSeq\", \"value\": \"851287 INVITE\"},\n      {\"name\": \"Content-Type\", \"value\": \"application/sdp\"}\n    ]\n  }\n}\n"
+        }
+      },
+      "WebhookResponseCancelled": {
+        "type": "object",
+        "title": "response.cancelled",
+        "description": "Sent when a background response has been cancelled.\n",
+        "required": [
+          "created_at",
+          "id",
+          "data",
+          "type"
+        ],
+        "properties": {
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the model response was cancelled.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the event.\n"
+          },
+          "data": {
+            "type": "object",
+            "description": "Event data payload.\n",
+            "required": [
+              "id"
+            ],
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the model response.\n"
+              }
+            }
+          },
+          "object": {
+            "type": "string",
+            "description": "The object of the event. Always `event`.\n",
+            "enum": [
+              "event"
+            ],
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.cancelled`.\n",
+            "enum": [
+              "response.cancelled"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "x-oaiMeta": {
+          "name": "response.cancelled",
+          "group": "webhook-events",
+          "example": "{\n  \"id\": \"evt_abc123\",\n  \"type\": \"response.cancelled\",\n  \"created_at\": 1719168000,\n  \"data\": {\n    \"id\": \"resp_abc123\"\n  }\n}\n"
+        }
+      },
+      "WebhookResponseCompleted": {
+        "type": "object",
+        "title": "response.completed",
+        "description": "Sent when a background response has been completed.\n",
+        "required": [
+          "created_at",
+          "id",
+          "data",
+          "type"
+        ],
+        "properties": {
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the model response was completed.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the event.\n"
+          },
+          "data": {
+            "type": "object",
+            "description": "Event data payload.\n",
+            "required": [
+              "id"
+            ],
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the model response.\n"
+              }
+            }
+          },
+          "object": {
+            "type": "string",
+            "description": "The object of the event. Always `event`.\n",
+            "enum": [
+              "event"
+            ],
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.completed`.\n",
+            "enum": [
+              "response.completed"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "x-oaiMeta": {
+          "name": "response.completed",
+          "group": "webhook-events",
+          "example": "{\n  \"id\": \"evt_abc123\",\n  \"type\": \"response.completed\",\n  \"created_at\": 1719168000,\n  \"data\": {\n    \"id\": \"resp_abc123\"\n  }\n}\n"
+        }
+      },
+      "WebhookResponseFailed": {
+        "type": "object",
+        "title": "response.failed",
+        "description": "Sent when a background response has failed.\n",
+        "required": [
+          "created_at",
+          "id",
+          "data",
+          "type"
+        ],
+        "properties": {
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the model response failed.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the event.\n"
+          },
+          "data": {
+            "type": "object",
+            "description": "Event data payload.\n",
+            "required": [
+              "id"
+            ],
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the model response.\n"
+              }
+            }
+          },
+          "object": {
+            "type": "string",
+            "description": "The object of the event. Always `event`.\n",
+            "enum": [
+              "event"
+            ],
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.failed`.\n",
+            "enum": [
+              "response.failed"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "x-oaiMeta": {
+          "name": "response.failed",
+          "group": "webhook-events",
+          "example": "{\n  \"id\": \"evt_abc123\",\n  \"type\": \"response.failed\",\n  \"created_at\": 1719168000,\n  \"data\": {\n    \"id\": \"resp_abc123\"\n  }\n}\n"
+        }
+      },
+      "WebhookResponseIncomplete": {
+        "type": "object",
+        "title": "response.incomplete",
+        "description": "Sent when a background response has been interrupted.\n",
+        "required": [
+          "created_at",
+          "id",
+          "data",
+          "type"
+        ],
+        "properties": {
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) of when the model response was interrupted.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the event.\n"
+          },
+          "data": {
+            "type": "object",
+            "description": "Event data payload.\n",
+            "required": [
+              "id"
+            ],
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the model response.\n"
+              }
+            }
+          },
+          "object": {
+            "type": "string",
+            "description": "The object of the event. Always `event`.\n",
+            "enum": [
+              "event"
+            ],
+            "x-stainless-const": true
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.incomplete`.\n",
+            "enum": [
+              "response.incomplete"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "x-oaiMeta": {
+          "name": "response.incomplete",
+          "group": "webhook-events",
+          "example": "{\n  \"id\": \"evt_abc123\",\n  \"type\": \"response.incomplete\",\n  \"created_at\": 1719168000,\n  \"data\": {\n    \"id\": \"resp_abc123\"\n  }\n}\n"
+        }
+      },
+      "WebhookSafetyAlertCreated": {
+        "type": "object",
+        "title": "safety.alert.created",
+        "description": "Sent when an approved safety alert is available for an API project.",
+        "required": [
+          "id",
+          "object",
+          "created_at",
+          "type",
+          "data"
+        ],
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the webhook event."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "event"
+            ],
+            "x-stainless-const": true,
+            "description": "Always `event`."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp in seconds when the event was created."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "safety.alert.created"
+            ],
+            "x-stainless-const": true,
+            "description": "Always `safety.alert.created`."
+          },
+          "data": {
+            "type": "object",
+            "additionalProperties": false,
+            "required": [
+              "id"
+            ],
+            "properties": {
+              "id": {
+                "type": "string",
+                "pattern": "^alert_[0-9a-f]{32}$",
+                "description": "The safety alert ID to pass to `GET /v1/safety/alerts/{id}`."
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "safety.alert.created",
+          "group": "webhook-events",
+          "example": "{\n  \"id\": \"evt_123\",\n  \"object\": \"event\",\n  \"created_at\": 1787659200,\n  \"type\": \"safety.alert.created\",\n  \"data\": {\"id\": \"alert_0123456789abcdef0123456789abcdef\"}\n}\n"
+        }
+      },
+      "WebhookSafetyOrgAlertCreated": {
+        "type": "object",
+        "title": "safety.org_alert.created",
+        "description": "Sent when an approved safety alert is available for an enterprise workspace.",
+        "required": [
+          "id",
+          "object",
+          "created_at",
+          "type",
+          "data"
+        ],
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the webhook event."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "event"
+            ],
+            "x-stainless-const": true,
+            "description": "Always `event`."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp in seconds when the event was created."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "safety.org_alert.created"
+            ],
+            "x-stainless-const": true,
+            "description": "Always `safety.org_alert.created`."
+          },
+          "data": {
+            "type": "object",
+            "additionalProperties": false,
+            "required": [
+              "id"
+            ],
+            "properties": {
+              "id": {
+                "type": "string",
+                "pattern": "^alert_[0-9a-f]{32}$",
+                "description": "The safety alert ID to pass to `GET /v1/safety/alerts/{id}`."
+              }
+            }
+          }
+        },
+        "x-oaiMeta": {
+          "name": "safety.org_alert.created",
+          "group": "webhook-events",
+          "example": "{\n  \"id\": \"evt_123\",\n  \"object\": \"event\",\n  \"created_at\": 1787659200,\n  \"type\": \"safety.org_alert.created\",\n  \"data\": {\"id\": \"alert_0123456789abcdef0123456789abcdef\"}\n}\n"
+        }
+      },
+      "ModerationInputType": {
+        "type": "string",
+        "enum": [
+          "text",
+          "image"
+        ]
+      },
+      "ModerationResultBody": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "moderation_result"
+            ],
+            "description": "The object type, which was always `moderation_result` for successful moderation results.",
+            "default": "moderation_result",
+            "x-stainless-const": true
+          },
+          "model": {
+            "type": "string",
+            "description": "The moderation model that produced this result."
+          },
+          "flagged": {
+            "type": "boolean",
+            "description": "A boolean indicating whether the content was flagged by any category."
+          },
+          "categories": {
+            "additionalProperties": {
+              "type": "boolean"
+            },
+            "type": "object",
+            "description": "A dictionary of moderation categories to booleans, True if the input is flagged under this category.",
+            "x-oaiTypeLabel": "map"
+          },
+          "category_scores": {
+            "additionalProperties": {
+              "type": "number"
+            },
+            "type": "object",
+            "description": "A dictionary of moderation categories to scores.",
+            "x-oaiTypeLabel": "map"
+          },
+          "category_applied_input_types": {
+            "additionalProperties": {
+              "items": {
+                "$ref": "#/components/schemas/ModerationInputType"
+              },
+              "type": "array"
+            },
+            "type": "object",
+            "description": "Which modalities of input are reflected by the score for each category.",
+            "x-oaiTypeLabel": "map"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "model",
+          "flagged",
+          "categories",
+          "category_scores",
+          "category_applied_input_types"
+        ],
+        "title": "Moderation result",
+        "description": "A moderation result produced for the response input or output."
+      },
+      "PromptCacheTTLEnum": {
+        "type": "string",
+        "enum": [
+          "30m"
+        ]
+      },
+      "PromptCacheModeEnum": {
+        "type": "string",
+        "enum": [
+          "implicit",
+          "explicit"
+        ]
+      },
+      "PromptCacheOptionsParam": {
+        "properties": {
+          "ttl": {
+            "$ref": "#/components/schemas/PromptCacheTTLEnum",
+            "description": "The minimum lifetime applied to every implicit and explicit cache breakpoint written by the request. Defaults to `30m`, which is currently the only supported value. The backend may retain cache entries for longer."
+          },
+          "mode": {
+            "$ref": "#/components/schemas/PromptCacheModeEnum",
+            "description": "Controls whether OpenAI automatically creates an implicit cache breakpoint. Defaults to `implicit`. With `implicit`, OpenAI creates one implicit breakpoint and writes up to the latest three explicit breakpoints in the request. With `explicit`, OpenAI does not create an implicit breakpoint and writes up to the latest four explicit breakpoints. If there are no explicit breakpoints, the request does not use prompt caching."
+          }
+        },
+        "type": "object",
+        "required": [],
+        "title": "Prompt cache options",
+        "description": "Options for prompt caching. Supported for `gpt-5.6` and later models. By default, OpenAI automatically chooses one implicit cache breakpoint. You can add explicit breakpoints to content blocks with `prompt_cache_breakpoint`. Each request can write up to four breakpoints. For cache matching, OpenAI considers up to the latest 80 breakpoints in the conversation, without a content-block lookback limit. Set `mode` to `explicit` to disable the implicit breakpoint. The `ttl` defaults to `30m`, which is currently the only supported value. See the [prompt caching guide](https://developers.openai.com/api/docs/guides/prompt-caching) for current details."
+      },
+      "PromptCacheBreakpointParam": {
+        "properties": {
+          "mode": {
+            "type": "string",
+            "enum": [
+              "explicit"
+            ],
+            "description": "The breakpoint mode. Always `explicit`.",
+            "default": "explicit",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "mode"
+        ],
+        "title": "Prompt cache breakpoint",
+        "description": "Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block."
+      },
+      "ModerationMode": {
+        "type": "string",
+        "enum": [
+          "score",
+          "block"
+        ]
+      },
+      "ModerationConfigParam": {
+        "properties": {
+          "mode": {
+            "$ref": "#/components/schemas/ModerationMode"
+          }
+        },
+        "type": "object",
+        "required": [
+          "mode"
+        ],
+        "description": "The moderation policy for the response input."
+      },
+      "ModerationPolicyParam": {
+        "properties": {
+          "input": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ModerationConfigParam",
+                "description": "The moderation policy for the response input."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "output": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ModerationConfigParam",
+                "description": "The moderation policy for the response output."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [],
+        "description": "The policy to apply to moderated response input and output."
+      },
+      "ModerationParam": {
+        "properties": {
+          "model": {
+            "type": "string",
+            "description": "The moderation model to use for moderated completions, e.g. 'omni-moderation-latest'."
+          },
+          "policy": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ModerationPolicyParam",
+                "description": "The policy to apply to moderated response input and output."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "model"
+        ],
+        "description": "Configuration for running moderation on the input and output of this response."
+      },
+      "SkillReferenceParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "skill_reference"
+            ],
+            "description": "References a skill created with the /v1/skills endpoint.",
+            "default": "skill_reference",
+            "x-stainless-const": true
+          },
+          "skill_id": {
+            "type": "string",
+            "maxLength": 64,
+            "minLength": 1,
+            "description": "The ID of the referenced skill."
+          },
+          "version": {
+            "type": "string",
+            "description": "Optional skill version. Use a positive integer or 'latest'. Omit for default."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "skill_id"
+        ]
+      },
+      "InlineSkillSourceParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "base64"
+            ],
+            "description": "The type of the inline skill source. Must be `base64`.",
+            "default": "base64",
+            "x-stainless-const": true
+          },
+          "media_type": {
+            "type": "string",
+            "enum": [
+              "application/zip"
+            ],
+            "description": "The media type of the inline skill payload. Must be `application/zip`.",
+            "default": "application/zip",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "string",
+            "maxLength": 70254592,
+            "minLength": 1,
+            "description": "Base64-encoded skill zip bundle."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "media_type",
+          "data"
+        ],
+        "description": "Inline skill payload"
+      },
+      "InlineSkillParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "inline"
+            ],
+            "description": "Defines an inline skill for this request.",
+            "default": "inline",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the skill."
+          },
+          "description": {
+            "type": "string",
+            "description": "The description of the skill."
+          },
+          "source": {
+            "$ref": "#/components/schemas/InlineSkillSourceParam",
+            "description": "Inline skill payload"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "name",
+          "description",
+          "source"
+        ]
+      },
+      "ContainerNetworkPolicyDisabledParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "disabled"
+            ],
+            "description": "Disable outbound network access. Always `disabled`.",
+            "default": "disabled",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "ContainerNetworkPolicyDomainSecretParam": {
+        "properties": {
+          "domain": {
+            "type": "string",
+            "minLength": 1,
+            "description": "The domain associated with the secret."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 1,
+            "description": "The name of the secret to inject for the domain."
+          },
+          "value": {
+            "type": "string",
+            "maxLength": 10485760,
+            "minLength": 1,
+            "description": "The secret value to inject for the domain."
+          }
+        },
+        "type": "object",
+        "required": [
+          "domain",
+          "name",
+          "value"
+        ]
+      },
+      "ContainerNetworkPolicyAllowlistParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "allowlist"
+            ],
+            "description": "Allow outbound network access only to specified domains. Always `allowlist`.",
+            "default": "allowlist",
+            "x-stainless-const": true
+          },
+          "allowed_domains": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array",
+            "minItems": 1,
+            "description": "A list of allowed domains when type is `allowlist`."
+          },
+          "domain_secrets": {
+            "items": {
+              "$ref": "#/components/schemas/ContainerNetworkPolicyDomainSecretParam"
+            },
+            "type": "array",
+            "minItems": 1,
+            "description": "Optional domain-scoped secrets for allowlisted domains."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "allowed_domains"
+        ]
+      },
+      "IncludeEnum": {
+        "type": "string",
+        "enum": [
+          "file_search_call.results",
+          "web_search_call.results",
+          "web_search_call.action.sources",
+          "message.input_image.image_url",
+          "computer_call_output.output.image_url",
+          "code_interpreter_call.outputs",
+          "reasoning.encrypted_content",
+          "message.output_text.logprobs"
+        ],
+        "description": "Specify additional output data to include in the model response. Currently supported values are:\n- `web_search_call.results`: Include the search results of the web search tool call.\n- `web_search_call.action.sources`: Include the sources of the web search tool call.\n- `code_interpreter_call.outputs`: Includes the outputs of python code execution in code interpreter tool call items.\n- `computer_call_output.output.image_url`: Include image urls from the computer call output.\n- `file_search_call.results`: Include the search results of the file search tool call.\n- `message.input_image.image_url`: Include image urls from the input message.\n- `message.output_text.logprobs`: Include logprobs with assistant messages.\n- `reasoning.encrypted_content`: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when the `store` parameter is set to `false`, or when an organization is enrolled in the zero data retention program)."
+      },
+      "MessageStatus": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed",
+          "incomplete"
+        ]
+      },
+      "MessageRole": {
+        "type": "string",
+        "enum": [
+          "unknown",
+          "user",
+          "assistant",
+          "system",
+          "critic",
+          "discriminator",
+          "developer",
+          "tool"
+        ]
+      },
+      "PromptCacheBreakpointConfig": {
+        "properties": {
+          "mode": {
+            "type": "string",
+            "enum": [
+              "explicit"
+            ],
+            "description": "The breakpoint mode. Always `explicit`.",
+            "default": "explicit",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "mode"
+        ],
+        "title": "Prompt cache breakpoint",
+        "description": "Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block."
+      },
+      "InputTextContent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_text"
+            ],
+            "description": "The type of the input item. Always `input_text`.",
+            "default": "input_text",
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string",
+            "description": "The text input to the model."
+          },
+          "prompt_cache_breakpoint": {
+            "$ref": "#/components/schemas/PromptCacheBreakpointConfig"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "text"
+        ],
+        "title": "Input text",
+        "description": "A text input to the model."
+      },
+      "FileCitationBody": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "file_citation"
+            ],
+            "description": "The type of the file citation. Always `file_citation`.",
+            "default": "file_citation",
+            "x-stainless-const": true
+          },
+          "file_id": {
+            "type": "string",
+            "description": "The ID of the file."
+          },
+          "index": {
+            "type": "integer",
+            "description": "The index of the file in the list of files."
+          },
+          "filename": {
+            "type": "string",
+            "description": "The filename of the file cited."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "file_id",
+          "index",
+          "filename"
+        ],
+        "title": "File citation",
+        "description": "A citation to a file."
+      },
+      "UrlCitationBody": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "url_citation"
+            ],
+            "description": "The type of the URL citation. Always `url_citation`.",
+            "default": "url_citation",
+            "x-stainless-const": true
+          },
+          "url": {
+            "type": "string",
+            "format": "uri",
+            "description": "The URL of the web resource."
+          },
+          "start_index": {
+            "type": "integer",
+            "description": "The index of the first character of the URL citation in the message."
+          },
+          "end_index": {
+            "type": "integer",
+            "description": "The index of the last character of the URL citation in the message."
+          },
+          "title": {
+            "type": "string",
+            "description": "The title of the web resource."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "url",
+          "start_index",
+          "end_index",
+          "title"
+        ],
+        "title": "URL citation",
+        "description": "A citation for a web resource used to generate a model response."
+      },
+      "ContainerFileCitationBody": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "container_file_citation"
+            ],
+            "description": "The type of the container file citation. Always `container_file_citation`.",
+            "default": "container_file_citation",
+            "x-stainless-const": true
+          },
+          "container_id": {
+            "type": "string",
+            "description": "The ID of the container file."
+          },
+          "file_id": {
+            "type": "string",
+            "description": "The ID of the file."
+          },
+          "start_index": {
+            "type": "integer",
+            "description": "The index of the first character of the container file citation in the message."
+          },
+          "end_index": {
+            "type": "integer",
+            "description": "The index of the last character of the container file citation in the message."
+          },
+          "filename": {
+            "type": "string",
+            "description": "The filename of the container file cited."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "container_id",
+          "file_id",
+          "start_index",
+          "end_index",
+          "filename"
+        ],
+        "title": "Container file citation",
+        "description": "A citation for a container file used to generate a model response."
+      },
+      "Annotation": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/FileCitationBody"
+          },
+          {
+            "$ref": "#/components/schemas/UrlCitationBody"
+          },
+          {
+            "$ref": "#/components/schemas/ContainerFileCitationBody"
+          },
+          {
+            "$ref": "#/components/schemas/FilePath"
+          }
+        ],
+        "description": "An annotation that applies to a span of output text.",
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "TopLogProb": {
+        "properties": {
+          "token": {
+            "type": "string"
+          },
+          "logprob": {
+            "type": "number"
+          },
+          "bytes": {
+            "items": {
+              "type": "integer"
+            },
+            "type": "array"
+          }
+        },
+        "type": "object",
+        "required": [
+          "token",
+          "logprob",
+          "bytes"
+        ],
+        "title": "Top log probability",
+        "description": "The top log probability of a token."
+      },
+      "LogProb": {
+        "properties": {
+          "token": {
+            "type": "string"
+          },
+          "logprob": {
+            "type": "number"
+          },
+          "bytes": {
+            "items": {
+              "type": "integer"
+            },
+            "type": "array"
+          },
+          "top_logprobs": {
+            "items": {
+              "$ref": "#/components/schemas/TopLogProb"
+            },
+            "type": "array"
+          }
+        },
+        "type": "object",
+        "required": [
+          "token",
+          "logprob",
+          "bytes",
+          "top_logprobs"
+        ],
+        "title": "Log probability",
+        "description": "The log probability of a token."
+      },
+      "OutputTextContent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "output_text"
+            ],
+            "description": "The type of the output text. Always `output_text`.",
+            "default": "output_text",
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string",
+            "description": "The text output from the model."
+          },
+          "annotations": {
+            "items": {
+              "$ref": "#/components/schemas/Annotation"
+            },
+            "type": "array",
+            "description": "The annotations of the text output."
+          },
+          "logprobs": {
+            "items": {
+              "$ref": "#/components/schemas/LogProb"
+            },
+            "type": "array"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "text",
+          "annotations",
+          "logprobs"
+        ],
+        "title": "Output text",
+        "description": "A text output from the model."
+      },
+      "TextContent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "text"
+            ],
+            "default": "text",
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "text"
+        ],
+        "title": "Text Content",
+        "description": "A text content."
+      },
+      "SummaryTextContent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "summary_text"
+            ],
+            "description": "The type of the object. Always `summary_text`.",
+            "default": "summary_text",
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string",
+            "description": "A summary of the reasoning output from the model so far."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "text"
+        ],
+        "title": "Summary text",
+        "description": "A summary text from the model."
+      },
+      "ReasoningTextContent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "reasoning_text"
+            ],
+            "description": "The type of the reasoning text. Always `reasoning_text`.",
+            "default": "reasoning_text",
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string",
+            "description": "The reasoning text from the model."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "text"
+        ],
+        "title": "Reasoning text",
+        "description": "Reasoning text from the model."
+      },
+      "RefusalContent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "refusal"
+            ],
+            "description": "The type of the refusal. Always `refusal`.",
+            "default": "refusal",
+            "x-stainless-const": true
+          },
+          "refusal": {
+            "type": "string",
+            "description": "The refusal explanation from the model."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "refusal"
+        ],
+        "title": "Refusal",
+        "description": "A refusal from the model."
+      },
+      "ImageDetail": {
+        "type": "string",
+        "enum": [
+          "low",
+          "high",
+          "auto",
+          "original"
+        ]
+      },
+      "InputImageContent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_image"
+            ],
+            "description": "The type of the input item. Always `input_image`.",
+            "default": "input_image",
+            "x-stainless-const": true
+          },
+          "image_url": {
+            "anyOf": [
+              {
+                "type": "string",
+                "format": "uri",
+                "description": "The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "file_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the file to be sent to the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "detail": {
+            "$ref": "#/components/schemas/ImageDetail",
+            "description": "The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`."
+          },
+          "prompt_cache_breakpoint": {
+            "$ref": "#/components/schemas/PromptCacheBreakpointConfig"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "detail"
+        ],
+        "title": "Input image",
+        "description": "An image input to the model. Learn about [image inputs](https://developers.openai.com/api/docs/guides/images-vision)."
+      },
+      "ComputerScreenshotContent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "computer_screenshot"
+            ],
+            "description": "Specifies the event type. For a computer screenshot, this property is always set to `computer_screenshot`.",
+            "default": "computer_screenshot",
+            "x-stainless-const": true
+          },
+          "image_url": {
+            "anyOf": [
+              {
+                "type": "string",
+                "format": "uri",
+                "description": "The URL of the screenshot image."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "file_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The identifier of an uploaded file that contains the screenshot."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "detail": {
+            "$ref": "#/components/schemas/ImageDetail",
+            "description": "The detail level of the screenshot image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`."
+          },
+          "prompt_cache_breakpoint": {
+            "$ref": "#/components/schemas/PromptCacheBreakpointConfig"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "image_url",
+          "file_id",
+          "detail"
+        ],
+        "title": "Computer screenshot",
+        "description": "A screenshot of a computer."
+      },
+      "FileInputDetail": {
+        "type": "string",
+        "enum": [
+          "auto",
+          "low",
+          "high"
+        ]
+      },
+      "InputFileContent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_file"
+            ],
+            "description": "The type of the input item. Always `input_file`.",
+            "default": "input_file",
+            "x-stainless-const": true
+          },
+          "file_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the file to be sent to the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "filename": {
+            "type": "string",
+            "description": "The name of the file to be sent to the model."
+          },
+          "file_data": {
+            "type": "string",
+            "description": "The content of the file to be sent to the model.\n"
+          },
+          "prompt_cache_breakpoint": {
+            "$ref": "#/components/schemas/PromptCacheBreakpointConfig"
+          },
+          "file_url": {
+            "type": "string",
+            "format": "uri",
+            "description": "The URL of the file to be sent to the model."
+          },
+          "detail": {
+            "$ref": "#/components/schemas/FileInputDetail",
+            "description": "The detail level of the file to be sent to the model. Use `auto` to let the system select the detail level; for GPT-5.6 and later models, `auto` uses high-quality rendering, which may increase input token usage. Use `low` for lower-cost rendering, or `high` to render the file at higher quality. Defaults to `auto`."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Input file",
+        "description": "A file input to the model."
+      },
+      "MessagePhase-2": {
+        "type": "string",
+        "enum": [
+          "commentary",
+          "final_answer"
+        ]
+      },
+      "Message": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "message"
+            ],
+            "description": "The type of the message. Always set to `message`.",
+            "default": "message",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the message."
+          },
+          "status": {
+            "$ref": "#/components/schemas/MessageStatus",
+            "description": "The status of item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API."
+          },
+          "role": {
+            "$ref": "#/components/schemas/MessageRole",
+            "description": "The role of the message. One of `unknown`, `user`, `assistant`, `system`, `critic`, `discriminator`, `developer`, or `tool`."
+          },
+          "content": {
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/InputTextContent"
+                },
+                {
+                  "$ref": "#/components/schemas/OutputTextContent"
+                },
+                {
+                  "$ref": "#/components/schemas/TextContent"
+                },
+                {
+                  "$ref": "#/components/schemas/SummaryTextContent"
+                },
+                {
+                  "$ref": "#/components/schemas/ReasoningTextContent"
+                },
+                {
+                  "$ref": "#/components/schemas/RefusalContent"
+                },
+                {
+                  "$ref": "#/components/schemas/InputImageContent"
+                },
+                {
+                  "$ref": "#/components/schemas/ComputerScreenshotContent"
+                },
+                {
+                  "$ref": "#/components/schemas/InputFileContent"
+                }
+              ],
+              "description": "A content part that makes up an input or output item.",
+              "discriminator": {
+                "propertyName": "type"
+              }
+            },
+            "type": "array",
+            "description": "The content of the message"
+          },
+          "phase": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/MessagePhase-2",
+                "description": "Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "status",
+          "role",
+          "content"
+        ],
+        "title": "Message",
+        "description": "A message to or from the model."
+      },
+      "DirectToolCallCaller": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "direct"
+            ],
+            "default": "direct",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "ProgramToolCallCaller": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "program"
+            ],
+            "default": "program",
+            "x-stainless-const": true
+          },
+          "caller_id": {
+            "type": "string",
+            "description": "The call ID of the program item that produced this tool call."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "caller_id"
+        ]
+      },
+      "ToolCallCaller": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/DirectToolCallCaller"
+          },
+          {
+            "$ref": "#/components/schemas/ProgramToolCallCaller"
+          }
+        ],
+        "description": "The execution context that produced this tool call.",
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "FunctionCallStatus": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed",
+          "incomplete"
+        ]
+      },
+      "DirectToolCallCallerParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "direct"
+            ],
+            "description": "The caller type. Always `direct`.",
+            "default": "direct",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "ProgramToolCallCallerParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "program"
+            ],
+            "description": "The caller type. Always `program`.",
+            "default": "program",
+            "x-stainless-const": true
+          },
+          "caller_id": {
+            "type": "string",
+            "maxLength": 64,
+            "minLength": 1,
+            "description": "The call ID of the program item that produced this tool call."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "caller_id"
+        ]
+      },
+      "ToolCallCallerParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/DirectToolCallCallerParam"
+          },
+          {
+            "$ref": "#/components/schemas/ProgramToolCallCallerParam"
+          }
+        ],
+        "description": "The execution context that produced this tool call.",
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "FunctionCallOutputStatusEnum": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed",
+          "incomplete"
+        ]
+      },
+      "WebSearchCallStatus": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "searching",
+          "completed",
+          "failed",
+          "incomplete"
+        ]
+      },
+      "ImageGenActionEnum": {
+        "type": "string",
+        "enum": [
+          "generate",
+          "edit",
+          "auto"
+        ]
+      },
+      "ImageBackground": {
+        "type": "string",
+        "enum": [
+          "transparent",
+          "opaque",
+          "auto"
+        ]
+      },
+      "ImageOutputFormat": {
+        "type": "string",
+        "enum": [
+          "png",
+          "webp",
+          "jpeg"
+        ]
+      },
+      "ImageGenToolCall": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "image_generation_call"
+            ],
+            "description": "The type of the image generation call. Always `image_generation_call`.",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the image generation call."
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "in_progress",
+              "completed",
+              "generating",
+              "failed"
+            ],
+            "description": "The status of the image generation call."
+          },
+          "result": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The generated image encoded in base64."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "size": {
+            "anyOf": [
+              {
+                "anyOf": [
+                  {
+                    "type": "string"
+                  },
+                  {
+                    "type": "string",
+                    "enum": [
+                      "1024x1024",
+                      "1024x1536",
+                      "1536x1024"
+                    ]
+                  }
+                ],
+                "description": "The image dimensions as a `WIDTHxHEIGHT` string, for example `1536x864`."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "quality": {
+            "anyOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "low",
+                  "medium",
+                  "high",
+                  "xhigh",
+                  "max",
+                  "auto"
+                ],
+                "description": "The quality of the image generated by the image generation tool call. One of `low`, `medium`, `high`, `xhigh`, `max`, or `auto`."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "action": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ImageGenActionEnum",
+                "description": "The action used for image generation."
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "x-openai-go-optional-enum": true
+          },
+          "background": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ImageBackground",
+                "description": "The background setting used for generation."
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "x-openai-go-optional-enum": true
+          },
+          "output_format": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ImageOutputFormat",
+                "description": "The output format used for generation."
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "x-openai-go-optional-enum": true
+          },
+          "revised_prompt": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The prompt that was used after any model prompt rewriting."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "status",
+          "result"
+        ],
+        "title": "Image generation call",
+        "description": "An image generation request made by the model."
+      },
+      "ClickButtonType": {
+        "type": "string",
+        "enum": [
+          "left",
+          "right",
+          "wheel",
+          "back",
+          "forward"
+        ]
+      },
+      "ClickParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "click"
+            ],
+            "description": "Specifies the event type. For a click action, this property is always `click`.",
+            "default": "click",
+            "x-stainless-const": true
+          },
+          "button": {
+            "$ref": "#/components/schemas/ClickButtonType",
+            "description": "Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`."
+          },
+          "x": {
+            "type": "integer",
+            "description": "The x-coordinate where the click occurred."
+          },
+          "y": {
+            "type": "integer",
+            "description": "The y-coordinate where the click occurred."
+          },
+          "keys": {
+            "anyOf": [
+              {
+                "items": {
+                  "type": "string"
+                },
+                "type": "array",
+                "description": "The keys being held while clicking."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "button",
+          "x",
+          "y"
+        ],
+        "title": "Click",
+        "description": "A click action."
+      },
+      "DoubleClickAction": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "double_click"
+            ],
+            "description": "Specifies the event type. For a double click action, this property is always set to `double_click`.",
+            "default": "double_click",
+            "x-stainless-const": true
+          },
+          "x": {
+            "type": "integer",
+            "description": "The x-coordinate where the double click occurred."
+          },
+          "y": {
+            "type": "integer",
+            "description": "The y-coordinate where the double click occurred."
+          },
+          "keys": {
+            "anyOf": [
+              {
+                "items": {
+                  "type": "string"
+                },
+                "type": "array",
+                "description": "The keys being held while double-clicking."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "x",
+          "y",
+          "keys"
+        ],
+        "title": "DoubleClick",
+        "description": "A double click action."
+      },
+      "CoordParam": {
+        "properties": {
+          "x": {
+            "type": "integer",
+            "description": "The x-coordinate."
+          },
+          "y": {
+            "type": "integer",
+            "description": "The y-coordinate."
+          }
+        },
+        "type": "object",
+        "required": [
+          "x",
+          "y"
+        ],
+        "title": "Coordinate",
+        "description": "An x/y coordinate pair, e.g. `{ x: 100, y: 200 }`."
+      },
+      "DragParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "drag"
+            ],
+            "description": "Specifies the event type. For a drag action, this property is always set to `drag`.",
+            "default": "drag",
+            "x-stainless-const": true
+          },
+          "path": {
+            "items": {
+              "$ref": "#/components/schemas/CoordParam"
+            },
+            "type": "array",
+            "description": "An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg\n```\n[\n  { x: 100, y: 200 },\n  { x: 200, y: 300 }\n]\n```"
+          },
+          "keys": {
+            "anyOf": [
+              {
+                "items": {
+                  "type": "string"
+                },
+                "type": "array",
+                "description": "The keys being held while dragging the mouse."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "path"
+        ],
+        "title": "Drag",
+        "description": "A drag action."
+      },
+      "KeyPressAction": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "keypress"
+            ],
+            "description": "Specifies the event type. For a keypress action, this property is always set to `keypress`.",
+            "default": "keypress",
+            "x-stainless-const": true
+          },
+          "keys": {
+            "items": {
+              "type": "string",
+              "description": "One of the keys the model is requesting to be pressed."
+            },
+            "type": "array",
+            "description": "The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "keys"
+        ],
+        "title": "KeyPress",
+        "description": "A collection of keypresses the model would like to perform."
+      },
+      "MoveParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "move"
+            ],
+            "description": "Specifies the event type. For a move action, this property is always set to `move`.",
+            "default": "move",
+            "x-stainless-const": true
+          },
+          "x": {
+            "type": "integer",
+            "description": "The x-coordinate to move to."
+          },
+          "y": {
+            "type": "integer",
+            "description": "The y-coordinate to move to."
+          },
+          "keys": {
+            "anyOf": [
+              {
+                "items": {
+                  "type": "string"
+                },
+                "type": "array",
+                "description": "The keys being held while moving the mouse."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "x",
+          "y"
+        ],
+        "title": "Move",
+        "description": "A mouse move action."
+      },
+      "ScreenshotParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "screenshot"
+            ],
+            "description": "Specifies the event type. For a screenshot action, this property is always set to `screenshot`.",
+            "default": "screenshot",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Screenshot",
+        "description": "A screenshot action."
+      },
+      "ScrollParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "scroll"
+            ],
+            "description": "Specifies the event type. For a scroll action, this property is always set to `scroll`.",
+            "default": "scroll",
+            "x-stainless-const": true
+          },
+          "x": {
+            "type": "integer",
+            "description": "The x-coordinate where the scroll occurred."
+          },
+          "y": {
+            "type": "integer",
+            "description": "The y-coordinate where the scroll occurred."
+          },
+          "scroll_x": {
+            "type": "integer",
+            "description": "The horizontal scroll distance."
+          },
+          "scroll_y": {
+            "type": "integer",
+            "description": "The vertical scroll distance."
+          },
+          "keys": {
+            "anyOf": [
+              {
+                "items": {
+                  "type": "string"
+                },
+                "type": "array",
+                "description": "The keys being held while scrolling."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "x",
+          "y",
+          "scroll_x",
+          "scroll_y"
+        ],
+        "title": "Scroll",
+        "description": "A scroll action."
+      },
+      "TypeParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "type"
+            ],
+            "description": "Specifies the event type. For a type action, this property is always set to `type`.",
+            "default": "type",
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string",
+            "description": "The text to type."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "text"
+        ],
+        "title": "Type",
+        "description": "An action to type in text."
+      },
+      "WaitParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "wait"
+            ],
+            "description": "Specifies the event type. For a wait action, this property is always set to `wait`.",
+            "default": "wait",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Wait",
+        "description": "A wait action."
+      },
+      "ComputerCallSafetyCheckParam": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The ID of the pending safety check."
+          },
+          "code": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The type of the pending safety check."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "message": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Details about the pending safety check."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "id"
+        ],
+        "description": "A pending safety check for the computer call."
+      },
+      "ComputerCallOutputStatus": {
+        "type": "string",
+        "enum": [
+          "completed",
+          "incomplete",
+          "failed"
+        ]
+      },
+      "ToolSearchExecutionType": {
+        "type": "string",
+        "enum": [
+          "server",
+          "client"
+        ]
+      },
+      "ToolSearchCall": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "tool_search_call"
+            ],
+            "description": "The type of the item. Always `tool_search_call`.",
+            "default": "tool_search_call",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the tool search call item."
+          },
+          "call_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the tool search call generated by the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "execution": {
+            "$ref": "#/components/schemas/ToolSearchExecutionType",
+            "description": "Whether tool search was executed by the server or by the client."
+          },
+          "arguments": {
+            "description": "Arguments used for the tool search call."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatus",
+            "description": "The status of the tool search call item that was recorded."
+          },
+          "created_by": {
+            "type": "string",
+            "description": "The identifier of the actor that created the item."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "execution",
+          "arguments",
+          "status"
+        ]
+      },
+      "CallableToolAllowedCaller": {
+        "type": "string",
+        "enum": [
+          "direct",
+          "programmatic"
+        ]
+      },
+      "FunctionTool": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "function"
+            ],
+            "description": "The type of the function tool. Always `function`.",
+            "default": "function",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the function to call."
+          },
+          "async": {
+            "type": "boolean"
+          },
+          "description": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "A description of the function. Used by the model to determine whether or not to call the function."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "parameters": {
+            "anyOf": [
+              {
+                "additionalProperties": {},
+                "type": "object",
+                "description": "A JSON schema object describing the parameters of the function.",
+                "x-oaiTypeLabel": "map"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "output_schema": {
+            "anyOf": [
+              {
+                "additionalProperties": {},
+                "type": "object",
+                "description": "A JSON schema object describing the JSON value encoded in string outputs for this function.",
+                "x-oaiTypeLabel": "map"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "strict": {
+            "anyOf": [
+              {
+                "type": "boolean",
+                "description": "Whether strict parameter validation is enforced for this function tool."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "defer_loading": {
+            "type": "boolean",
+            "description": "Whether this function is deferred and loaded via tool search."
+          },
+          "allowed_callers": {
+            "anyOf": [
+              {
+                "items": {
+                  "$ref": "#/components/schemas/CallableToolAllowedCaller"
+                },
+                "type": "array",
+                "description": "The tool invocation context(s)."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "name",
+          "strict",
+          "parameters"
+        ],
+        "title": "Function",
+        "description": "Defines a function in your own code the model can choose to call. Learn more about [function calling](https://developers.openai.com/api/docs/guides/function-calling)."
+      },
+      "RankerVersionType": {
+        "type": "string",
+        "enum": [
+          "auto",
+          "default-2024-11-15"
+        ]
+      },
+      "HybridSearchOptions": {
+        "properties": {
+          "embedding_weight": {
+            "type": "number",
+            "description": "The weight of the embedding in the reciprocal ranking fusion."
+          },
+          "text_weight": {
+            "type": "number",
+            "description": "The weight of the text in the reciprocal ranking fusion."
+          }
+        },
+        "type": "object",
+        "required": [
+          "embedding_weight",
+          "text_weight"
+        ]
+      },
+      "RankingOptions": {
+        "properties": {
+          "ranker": {
+            "$ref": "#/components/schemas/RankerVersionType",
+            "description": "The ranker to use for the file search."
+          },
+          "score_threshold": {
+            "type": "number",
+            "description": "The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results."
+          },
+          "hybrid_search": {
+            "$ref": "#/components/schemas/HybridSearchOptions",
+            "description": "Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled."
+          }
+        },
+        "type": "object",
+        "required": []
+      },
+      "Filters": {
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/ComparisonFilter"
+          },
+          {
+            "$ref": "#/components/schemas/CompoundFilter"
+          }
+        ]
+      },
+      "FileSearchTool": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "file_search"
+            ],
+            "description": "The type of the file search tool. Always `file_search`.",
+            "default": "file_search",
+            "x-stainless-const": true
+          },
+          "vector_store_ids": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array",
+            "description": "The IDs of the vector stores to search."
+          },
+          "max_num_results": {
+            "type": "integer",
+            "description": "The maximum number of results to return. This number should be between 1 and 50 inclusive."
+          },
+          "ranking_options": {
+            "$ref": "#/components/schemas/RankingOptions",
+            "description": "Ranking options for search."
+          },
+          "filters": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Filters",
+                "description": "A filter to apply."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "vector_store_ids"
+        ],
+        "title": "File search",
+        "description": "A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](https://developers.openai.com/api/docs/guides/tools-file-search)."
+      },
+      "ComputerTool": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "computer"
+            ],
+            "description": "The type of the computer tool. Always `computer`.",
+            "default": "computer",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Computer",
+        "description": "A tool that controls a virtual computer. Learn more about the [computer tool](https://developers.openai.com/api/docs/guides/tools-computer-use)."
+      },
+      "ComputerEnvironment": {
+        "type": "string",
+        "enum": [
+          "windows",
+          "mac",
+          "linux",
+          "ubuntu",
+          "browser"
+        ]
+      },
+      "ComputerUsePreviewTool": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "computer_use_preview"
+            ],
+            "description": "The type of the computer use tool. Always `computer_use_preview`.",
+            "default": "computer_use_preview",
+            "x-stainless-const": true
+          },
+          "environment": {
+            "$ref": "#/components/schemas/ComputerEnvironment",
+            "description": "The type of computer environment to control."
+          },
+          "display_width": {
+            "type": "integer",
+            "description": "The width of the computer display."
+          },
+          "display_height": {
+            "type": "integer",
+            "description": "The height of the computer display."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "environment",
+          "display_width",
+          "display_height"
+        ],
+        "title": "Computer use preview",
+        "description": "A tool that controls a virtual computer. Learn more about the [computer tool](https://developers.openai.com/api/docs/guides/tools-computer-use)."
+      },
+      "ContainerMemoryLimit": {
+        "type": "string",
+        "enum": [
+          "1g",
+          "4g",
+          "16g",
+          "64g"
+        ]
+      },
+      "AutoCodeInterpreterToolParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "auto"
+            ],
+            "description": "Always `auto`.",
+            "default": "auto",
+            "x-stainless-const": true
+          },
+          "file_ids": {
+            "items": {
+              "type": "string",
+              "example": "file-123"
+            },
+            "type": "array",
+            "maxItems": 50,
+            "description": "An optional list of uploaded files to make available to your code."
+          },
+          "memory_limit": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ContainerMemoryLimit",
+                "description": "The memory limit for the code interpreter container."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "network_policy": {
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/ContainerNetworkPolicyDisabledParam"
+              },
+              {
+                "$ref": "#/components/schemas/ContainerNetworkPolicyAllowlistParam"
+              }
+            ],
+            "description": "Network access policy for the container.",
+            "discriminator": {
+              "propertyName": "type"
+            }
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "CodeInterpreterToolAuto",
+        "description": "Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on."
+      },
+      "ProgrammaticToolCallingParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "programmatic_tool_calling"
+            ],
+            "description": "The type of the tool. Always `programmatic_tool_calling`.",
+            "default": "programmatic_tool_calling",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "InputFidelity": {
+        "type": "string",
+        "enum": [
+          "high",
+          "low"
+        ],
+        "description": "Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`."
+      },
+      "LocalShellToolParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "local_shell"
+            ],
+            "description": "The type of the local shell tool. Always `local_shell`.",
+            "default": "local_shell",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Local shell tool",
+        "description": "A tool that allows the model to execute shell commands in a local environment."
+      },
+      "ContainerAutoParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "container_auto"
+            ],
+            "description": "Automatically creates a container for this request",
+            "default": "container_auto",
+            "x-stainless-const": true
+          },
+          "file_ids": {
+            "items": {
+              "type": "string",
+              "example": "file-123"
+            },
+            "type": "array",
+            "maxItems": 50,
+            "description": "An optional list of uploaded files to make available to your code."
+          },
+          "memory_limit": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ContainerMemoryLimit",
+                "description": "The memory limit for the container."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "network_policy": {
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/ContainerNetworkPolicyDisabledParam"
+              },
+              {
+                "$ref": "#/components/schemas/ContainerNetworkPolicyAllowlistParam"
+              }
+            ],
+            "description": "Network access policy for the container.",
+            "discriminator": {
+              "propertyName": "type"
+            }
+          },
+          "skills": {
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/SkillReferenceParam"
+                },
+                {
+                  "$ref": "#/components/schemas/InlineSkillParam"
+                }
+              ],
+              "discriminator": {
+                "propertyName": "type"
+              }
+            },
+            "type": "array",
+            "maxItems": 200,
+            "description": "An optional list of skills referenced by id or inline data."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "LocalSkillParam": {
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The name of the skill."
+          },
+          "description": {
+            "type": "string",
+            "description": "The description of the skill."
+          },
+          "path": {
+            "type": "string",
+            "description": "The path to the directory containing the skill."
+          }
+        },
+        "type": "object",
+        "required": [
+          "name",
+          "description",
+          "path"
+        ]
+      },
+      "LocalEnvironmentParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "local"
+            ],
+            "description": "Use a local computer environment.",
+            "default": "local",
+            "x-stainless-const": true
+          },
+          "skills": {
+            "items": {
+              "$ref": "#/components/schemas/LocalSkillParam"
+            },
+            "type": "array",
+            "maxItems": 200,
+            "description": "An optional list of skills."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "ContainerReferenceParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "container_reference"
+            ],
+            "description": "References a container created with the /v1/containers endpoint",
+            "default": "container_reference",
+            "x-stainless-const": true
+          },
+          "container_id": {
+            "type": "string",
+            "description": "The ID of the referenced container.",
+            "example": "cntr_123"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "container_id"
+        ]
+      },
+      "FunctionShellToolParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "shell"
+            ],
+            "description": "The type of the shell tool. Always `shell`.",
+            "default": "shell",
+            "x-stainless-const": true
+          },
+          "environment": {
+            "anyOf": [
+              {
+                "oneOf": [
+                  {
+                    "$ref": "#/components/schemas/ContainerAutoParam"
+                  },
+                  {
+                    "$ref": "#/components/schemas/LocalEnvironmentParam"
+                  },
+                  {
+                    "$ref": "#/components/schemas/ContainerReferenceParam"
+                  }
+                ],
+                "discriminator": {
+                  "propertyName": "type"
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "allowed_callers": {
+            "anyOf": [
+              {
+                "items": {
+                  "$ref": "#/components/schemas/CallableToolAllowedCaller"
+                },
+                "type": "array",
+                "minItems": 1,
+                "description": "The tool invocation context(s)."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Shell tool",
+        "description": "A tool that allows the model to execute shell commands."
+      },
+      "CustomTextFormatParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "text"
+            ],
+            "description": "Unconstrained text format. Always `text`.",
+            "default": "text",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Text format",
+        "description": "Unconstrained free-form text."
+      },
+      "GrammarSyntax1": {
+        "type": "string",
+        "enum": [
+          "lark",
+          "regex"
+        ]
+      },
+      "CustomGrammarFormatParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "grammar"
+            ],
+            "description": "Grammar format. Always `grammar`.",
+            "default": "grammar",
+            "x-stainless-const": true
+          },
+          "syntax": {
+            "$ref": "#/components/schemas/GrammarSyntax1",
+            "description": "The syntax of the grammar definition. One of `lark` or `regex`."
+          },
+          "definition": {
+            "type": "string",
+            "description": "The grammar definition."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "syntax",
+          "definition"
+        ],
+        "title": "Grammar format",
+        "description": "A grammar defined by the user."
+      },
+      "CustomToolParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "custom"
+            ],
+            "description": "The type of the custom tool. Always `custom`.",
+            "default": "custom",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the custom tool, used to identify it in tool calls."
+          },
+          "async": {
+            "type": "boolean",
+            "description": "Whether the tool response can be returned asynchronously versus immediately returned on next response creation."
+          },
+          "description": {
+            "type": "string",
+            "description": "Optional description of the custom tool, used to provide more context."
+          },
+          "format": {
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/CustomTextFormatParam"
+              },
+              {
+                "$ref": "#/components/schemas/CustomGrammarFormatParam"
+              }
+            ],
+            "description": "The input format for the custom tool. Default is unconstrained text.",
+            "discriminator": {
+              "propertyName": "type"
+            }
+          },
+          "defer_loading": {
+            "type": "boolean",
+            "description": "Whether this tool should be deferred and discovered via tool search."
+          },
+          "allowed_callers": {
+            "anyOf": [
+              {
+                "items": {
+                  "$ref": "#/components/schemas/CallableToolAllowedCaller"
+                },
+                "type": "array",
+                "minItems": 1,
+                "description": "The tool invocation context(s)."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "name"
+        ],
+        "title": "Custom tool",
+        "description": "A custom tool that processes input using a specified format. Learn more about   [custom tools](https://developers.openai.com/api/docs/guides/function-calling#custom-tools)"
+      },
+      "EmptyModelParam": {
+        "properties": {},
+        "type": "object",
+        "required": []
+      },
+      "FunctionToolParam": {
+        "properties": {
+          "name": {
+            "type": "string",
+            "maxLength": 128,
+            "minLength": 1,
+            "pattern": "^[a-zA-Z0-9_-]+$"
+          },
+          "description": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "parameters": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/EmptyModelParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "strict": {
+            "anyOf": [
+              {
+                "type": "boolean",
+                "description": "Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "function"
+            ],
+            "default": "function",
+            "x-stainless-const": true
+          },
+          "async": {
+            "type": "boolean",
+            "description": "Whether the tool response can be returned asynchronously versus immediately returned on next response creation."
+          },
+          "output_schema": {
+            "anyOf": [
+              {
+                "additionalProperties": {},
+                "type": "object",
+                "description": "A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs.",
+                "x-oaiTypeLabel": "map"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "defer_loading": {
+            "type": "boolean",
+            "description": "Whether this function should be deferred and discovered via tool search."
+          },
+          "allowed_callers": {
+            "anyOf": [
+              {
+                "items": {
+                  "$ref": "#/components/schemas/CallableToolAllowedCaller"
+                },
+                "type": "array",
+                "minItems": 1,
+                "description": "The tool invocation context(s)."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "name",
+          "type"
+        ]
+      },
+      "NamespaceToolParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "namespace"
+            ],
+            "description": "The type of the tool. Always `namespace`.",
+            "default": "namespace",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "minLength": 1,
+            "description": "The namespace name used in tool calls (for example, `crm`)."
+          },
+          "description": {
+            "type": "string",
+            "description": "A description of the namespace shown to the model."
+          },
+          "tools": {
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/FunctionToolParam"
+                },
+                {
+                  "$ref": "#/components/schemas/CustomToolParam"
+                }
+              ],
+              "description": "A function or custom tool that belongs to a namespace.",
+              "discriminator": {
+                "propertyName": "type"
+              }
+            },
+            "type": "array",
+            "minItems": 1,
+            "description": "The function/custom tools available inside this namespace."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "name",
+          "description",
+          "tools"
+        ],
+        "title": "Namespace",
+        "description": "Groups function/custom tools under a shared namespace."
+      },
+      "ToolSearchToolParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "tool_search"
+            ],
+            "description": "The type of the tool. Always `tool_search`.",
+            "default": "tool_search",
+            "x-stainless-const": true
+          },
+          "execution": {
+            "$ref": "#/components/schemas/ToolSearchExecutionType",
+            "description": "Whether tool search is executed by the server or by the client."
+          },
+          "description": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Description shown to the model for a client-executed tool search tool."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "parameters": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/EmptyModelParam",
+                "description": "Parameter schema for a client-executed tool search tool."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Tool search tool",
+        "description": "Hosted or BYOT tool search configuration for deferred tools."
+      },
+      "ApproximateLocation": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "approximate"
+            ],
+            "description": "The type of location approximation. Always `approximate`.",
+            "default": "approximate",
+            "x-stainless-const": true
+          },
+          "country": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "region": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Free text input for the region of the user, e.g. `California`."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "city": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Free text input for the city of the user, e.g. `San Francisco`."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "timezone": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "SearchContextSize": {
+        "type": "string",
+        "enum": [
+          "low",
+          "medium",
+          "high"
+        ]
+      },
+      "SearchContentType": {
+        "type": "string",
+        "enum": [
+          "text",
+          "image"
+        ]
+      },
+      "WebSearchPreviewTool": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "web_search_preview",
+              "web_search_preview_2025_03_11"
+            ],
+            "description": "The type of the web search tool. One of `web_search_preview` or `web_search_preview_2025_03_11`.",
+            "default": "web_search_preview",
+            "x-stainless-const": true
+          },
+          "user_location": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ApproximateLocation",
+                "description": "The user's location."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "search_context_size": {
+            "$ref": "#/components/schemas/SearchContextSize",
+            "description": "High level guidance for the amount of context window space to use for the search. One of `low`, `medium`, or `high`. `medium` is the default."
+          },
+          "search_content_types": {
+            "items": {
+              "$ref": "#/components/schemas/SearchContentType"
+            },
+            "type": "array"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Web search preview",
+        "description": "This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](https://developers.openai.com/api/docs/guides/tools-web-search)."
+      },
+      "ApplyPatchToolParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "apply_patch"
+            ],
+            "description": "The type of the tool. Always `apply_patch`.",
+            "default": "apply_patch",
+            "x-stainless-const": true
+          },
+          "allowed_callers": {
+            "anyOf": [
+              {
+                "items": {
+                  "$ref": "#/components/schemas/CallableToolAllowedCaller"
+                },
+                "type": "array",
+                "minItems": 1,
+                "description": "The tool invocation context(s)."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Apply patch tool",
+        "description": "Allows the assistant to create, delete, or update files using unified diffs."
+      },
+      "ToolSearchOutput": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "tool_search_output"
+            ],
+            "description": "The type of the item. Always `tool_search_output`.",
+            "default": "tool_search_output",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the tool search output item."
+          },
+          "call_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the tool search call generated by the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "execution": {
+            "$ref": "#/components/schemas/ToolSearchExecutionType",
+            "description": "Whether tool search was executed by the server or by the client."
+          },
+          "tools": {
+            "items": {
+              "$ref": "#/components/schemas/Tool"
+            },
+            "type": "array",
+            "description": "The loaded tool definitions returned by tool search."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallOutputStatusEnum",
+            "description": "The status of the tool search output item that was recorded."
+          },
+          "created_by": {
+            "type": "string",
+            "description": "The identifier of the actor that created the item."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "execution",
+          "tools",
+          "status"
+        ]
+      },
+      "AdditionalTools": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "additional_tools"
+            ],
+            "description": "The type of the item. Always `additional_tools`.",
+            "default": "additional_tools",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the additional tools item."
+          },
+          "role": {
+            "$ref": "#/components/schemas/MessageRole",
+            "description": "The role that provided the additional tools."
+          },
+          "tools": {
+            "items": {
+              "$ref": "#/components/schemas/Tool"
+            },
+            "type": "array",
+            "description": "The additional tool definitions made available at this item."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "role",
+          "tools"
+        ]
+      },
+      "Program": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "program"
+            ],
+            "description": "The type of the item. Always `program`.",
+            "default": "program",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the program item."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The stable call ID of the program item."
+          },
+          "code": {
+            "type": "string",
+            "description": "The JavaScript source executed by programmatic tool calling."
+          },
+          "fingerprint": {
+            "type": "string",
+            "description": "Opaque program replay fingerprint that must be round-tripped."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "code",
+          "fingerprint"
+        ]
+      },
+      "ProgramOutputStatus": {
+        "type": "string",
+        "enum": [
+          "completed",
+          "incomplete"
+        ]
+      },
+      "ProgramOutput": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "program_output"
+            ],
+            "description": "The type of the item. Always `program_output`.",
+            "default": "program_output",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the program output item."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The call ID of the program item."
+          },
+          "result": {
+            "type": "string",
+            "description": "The result produced by the program item."
+          },
+          "status": {
+            "$ref": "#/components/schemas/ProgramOutputStatus",
+            "description": "The terminal status of the program output item."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "result",
+          "status"
+        ]
+      },
+      "CompactionBody": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "compaction"
+            ],
+            "description": "The type of the item. Always `compaction`.",
+            "default": "compaction",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the compaction item."
+          },
+          "encrypted_content": {
+            "type": "string",
+            "description": "The encrypted content that was produced by compaction."
+          },
+          "created_by": {
+            "type": "string",
+            "description": "The identifier of the actor that created the item."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "encrypted_content"
+        ],
+        "title": "Compaction item",
+        "description": "A compaction item generated by the [`v1/responses/compact` API](https://developers.openai.com/api/reference/resources/responses/methods/compact)."
+      },
+      "CodeInterpreterOutputLogs": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "logs"
+            ],
+            "description": "The type of the output. Always `logs`.",
+            "default": "logs",
+            "x-stainless-const": true
+          },
+          "logs": {
+            "type": "string",
+            "description": "The logs output from the code interpreter."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "logs"
+        ],
+        "title": "Code interpreter output logs",
+        "description": "The logs output from the code interpreter."
+      },
+      "CodeInterpreterOutputImage": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "image"
+            ],
+            "description": "The type of the output. Always `image`.",
+            "default": "image",
+            "x-stainless-const": true
+          },
+          "url": {
+            "type": "string",
+            "format": "uri",
+            "description": "The URL of the image output from the code interpreter."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "url"
+        ],
+        "title": "Code interpreter output image",
+        "description": "The image output from the code interpreter."
+      },
+      "LocalShellExecAction": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "exec"
+            ],
+            "description": "The type of the local shell action. Always `exec`.",
+            "default": "exec",
+            "x-stainless-const": true
+          },
+          "command": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array",
+            "description": "The command to run."
+          },
+          "timeout_ms": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "Optional timeout in milliseconds for the command."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "working_directory": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Optional working directory to run the command in."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "env": {
+            "additionalProperties": {
+              "type": "string"
+            },
+            "type": "object",
+            "description": "Environment variables to set for the command.",
+            "x-oaiTypeLabel": "map"
+          },
+          "user": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Optional user to run the command as."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "command",
+          "env"
+        ],
+        "title": "Local shell exec action",
+        "description": "Execute a shell command on the server."
+      },
+      "FunctionShellAction": {
+        "properties": {
+          "commands": {
+            "items": {
+              "type": "string",
+              "description": "A list of commands to run."
+            },
+            "type": "array"
+          },
+          "timeout_ms": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "Optional timeout in milliseconds for the commands."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "max_output_length": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "Optional maximum number of characters to return from each command."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "commands",
+          "timeout_ms",
+          "max_output_length"
+        ],
+        "title": "Shell exec action",
+        "description": "Execute a shell command."
+      },
+      "FunctionShellCallStatus": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed",
+          "incomplete"
+        ]
+      },
+      "LocalEnvironmentResource": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "local"
+            ],
+            "description": "The environment type. Always `local`.",
+            "default": "local",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Local Environment",
+        "description": "Represents the use of a local environment to perform shell actions."
+      },
+      "ContainerReferenceResource": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "container_reference"
+            ],
+            "description": "The environment type. Always `container_reference`.",
+            "default": "container_reference",
+            "x-stainless-const": true
+          },
+          "container_id": {
+            "type": "string"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "container_id"
+        ],
+        "title": "Container Reference",
+        "description": "Represents a container created with /v1/containers."
+      },
+      "FunctionShellCall": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "shell_call"
+            ],
+            "description": "The type of the item. Always `shell_call`.",
+            "default": "shell_call",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the shell tool call. Populated when this item is returned via API."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The unique ID of the shell tool call generated by the model."
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ToolCallCaller",
+                "description": "The execution context that produced this tool call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "action": {
+            "$ref": "#/components/schemas/FunctionShellAction",
+            "description": "The shell commands and limits that describe how to run the tool call."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionShellCallStatus",
+            "description": "The status of the shell call. One of `in_progress`, `completed`, or `incomplete`."
+          },
+          "environment": {
+            "anyOf": [
+              {
+                "oneOf": [
+                  {
+                    "$ref": "#/components/schemas/LocalEnvironmentResource"
+                  },
+                  {
+                    "$ref": "#/components/schemas/ContainerReferenceResource"
+                  }
+                ],
+                "discriminator": {
+                  "propertyName": "type"
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "created_by": {
+            "type": "string",
+            "description": "The ID of the entity that created this tool call."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "action",
+          "status",
+          "environment"
+        ],
+        "title": "Shell tool call",
+        "description": "A tool call that executes one or more shell commands in a managed environment."
+      },
+      "FunctionShellCallOutputStatusEnum": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed",
+          "incomplete"
+        ]
+      },
+      "FunctionShellCallOutputTimeoutOutcome": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "timeout"
+            ],
+            "description": "The outcome type. Always `timeout`.",
+            "default": "timeout",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Shell call timeout outcome",
+        "description": "Indicates that the shell call exceeded its configured time limit."
+      },
+      "FunctionShellCallOutputExitOutcome": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "exit"
+            ],
+            "description": "The outcome type. Always `exit`.",
+            "default": "exit",
+            "x-stainless-const": true
+          },
+          "exit_code": {
+            "type": "integer",
+            "description": "Exit code from the shell process."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "exit_code"
+        ],
+        "title": "Shell call exit outcome",
+        "description": "Indicates that the shell commands finished and returned an exit code."
+      },
+      "FunctionShellCallOutputContent": {
+        "properties": {
+          "stdout": {
+            "type": "string",
+            "description": "The standard output that was captured."
+          },
+          "stderr": {
+            "type": "string",
+            "description": "The standard error output that was captured."
+          },
+          "outcome": {
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/FunctionShellCallOutputTimeoutOutcome"
+              },
+              {
+                "$ref": "#/components/schemas/FunctionShellCallOutputExitOutcome"
+              }
+            ],
+            "title": "Shell call outcome",
+            "description": "Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.",
+            "discriminator": {
+              "propertyName": "type"
+            }
+          },
+          "created_by": {
+            "type": "string",
+            "description": "The identifier of the actor that created the item."
+          }
+        },
+        "type": "object",
+        "required": [
+          "stdout",
+          "stderr",
+          "outcome"
+        ],
+        "title": "Shell call output content",
+        "description": "The content of a shell tool call output that was emitted."
+      },
+      "FunctionShellCallOutput": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "shell_call_output"
+            ],
+            "description": "The type of the shell call output. Always `shell_call_output`.",
+            "default": "shell_call_output",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the shell call output. Populated when this item is returned via API."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The unique ID of the shell tool call generated by the model."
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ToolCallCaller",
+                "description": "The execution context that produced this tool call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionShellCallOutputStatusEnum",
+            "description": "The status of the shell call output. One of `in_progress`, `completed`, or `incomplete`."
+          },
+          "output": {
+            "items": {
+              "$ref": "#/components/schemas/FunctionShellCallOutputContent"
+            },
+            "type": "array",
+            "description": "An array of shell call output contents"
+          },
+          "max_output_length": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "created_by": {
+            "type": "string",
+            "description": "The identifier of the actor that created the item."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "status",
+          "output",
+          "max_output_length"
+        ],
+        "title": "Shell call output",
+        "description": "The output of a shell tool call that was emitted."
+      },
+      "ApplyPatchCallStatus": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed"
+        ]
+      },
+      "ApplyPatchCreateFileOperation": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "create_file"
+            ],
+            "description": "Create a new file with the provided diff.",
+            "default": "create_file",
+            "x-stainless-const": true
+          },
+          "path": {
+            "type": "string",
+            "description": "Path of the file to create."
+          },
+          "diff": {
+            "type": "string",
+            "description": "Diff to apply."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "path",
+          "diff"
+        ],
+        "title": "Apply patch create file operation",
+        "description": "Instruction describing how to create a file via the apply_patch tool."
+      },
+      "ApplyPatchDeleteFileOperation": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "delete_file"
+            ],
+            "description": "Delete the specified file.",
+            "default": "delete_file",
+            "x-stainless-const": true
+          },
+          "path": {
+            "type": "string",
+            "description": "Path of the file to delete."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "path"
+        ],
+        "title": "Apply patch delete file operation",
+        "description": "Instruction describing how to delete a file via the apply_patch tool."
+      },
+      "ApplyPatchUpdateFileOperation": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "update_file"
+            ],
+            "description": "Update an existing file with the provided diff.",
+            "default": "update_file",
+            "x-stainless-const": true
+          },
+          "path": {
+            "type": "string",
+            "description": "Path of the file to update."
+          },
+          "diff": {
+            "type": "string",
+            "description": "Diff to apply."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "path",
+          "diff"
+        ],
+        "title": "Apply patch update file operation",
+        "description": "Instruction describing how to update a file via the apply_patch tool."
+      },
+      "ApplyPatchToolCall": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "apply_patch_call"
+            ],
+            "description": "The type of the item. Always `apply_patch_call`.",
+            "default": "apply_patch_call",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the apply patch tool call. Populated when this item is returned via API."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The unique ID of the apply patch tool call generated by the model."
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ToolCallCaller",
+                "description": "The execution context that produced this tool call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "$ref": "#/components/schemas/ApplyPatchCallStatus",
+            "description": "The status of the apply patch tool call. One of `in_progress` or `completed`."
+          },
+          "operation": {
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/ApplyPatchCreateFileOperation"
+              },
+              {
+                "$ref": "#/components/schemas/ApplyPatchDeleteFileOperation"
+              },
+              {
+                "$ref": "#/components/schemas/ApplyPatchUpdateFileOperation"
+              }
+            ],
+            "title": "Apply patch operation",
+            "description": "One of the create_file, delete_file, or update_file operations applied via apply_patch.",
+            "discriminator": {
+              "propertyName": "type"
+            }
+          },
+          "created_by": {
+            "type": "string",
+            "description": "The ID of the entity that created this tool call."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "status",
+          "operation"
+        ],
+        "title": "Apply patch tool call",
+        "description": "A tool call that applies file diffs by creating, deleting, or updating files."
+      },
+      "ApplyPatchCallOutputStatus": {
+        "type": "string",
+        "enum": [
+          "completed",
+          "failed"
+        ]
+      },
+      "ApplyPatchToolCallOutput": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "apply_patch_call_output"
+            ],
+            "description": "The type of the item. Always `apply_patch_call_output`.",
+            "default": "apply_patch_call_output",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the apply patch tool call output. Populated when this item is returned via API."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The unique ID of the apply patch tool call generated by the model."
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ToolCallCaller",
+                "description": "The execution context that produced this tool call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "$ref": "#/components/schemas/ApplyPatchCallOutputStatus",
+            "description": "The status of the apply patch tool call output. One of `completed` or `failed`."
+          },
+          "output": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Optional textual output returned by the apply patch tool."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "created_by": {
+            "type": "string",
+            "description": "The ID of the entity that created this tool call output."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "status"
+        ],
+        "title": "Apply patch tool call output",
+        "description": "The output emitted by an apply patch tool call."
+      },
+      "MCPProtocolError": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_protocol_error"
+            ],
+            "default": "mcp_protocol_error",
+            "x-stainless-const": true
+          },
+          "code": {
+            "type": "integer"
+          },
+          "message": {
+            "type": "string"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "code",
+          "message"
+        ]
+      },
+      "MCPToolExecutionError": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_tool_execution_error"
+            ],
+            "default": "mcp_tool_execution_error",
+            "x-stainless-const": true
+          },
+          "content": {}
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "content"
+        ]
+      },
+      "HTTPError": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "http_error"
+            ],
+            "default": "http_error",
+            "x-stainless-const": true
+          },
+          "code": {
+            "type": "integer"
+          },
+          "message": {
+            "type": "string"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "code",
+          "message"
+        ]
+      },
+      "MCPToolCallStatus": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed",
+          "incomplete",
+          "calling",
+          "failed"
+        ]
+      },
+      "DetailEnum": {
+        "type": "string",
+        "enum": [
+          "low",
+          "high",
+          "auto",
+          "original"
+        ]
+      },
+      "FunctionCallItemStatus": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed",
+          "incomplete"
+        ]
+      },
+      "ComputerCallOutputItemParam": {
+        "properties": {
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the computer tool call output.",
+                "example": "cuo_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "call_id": {
+            "type": "string",
+            "maxLength": 64,
+            "minLength": 1,
+            "description": "The ID of the computer tool call that produced the output."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "computer_call_output"
+            ],
+            "description": "The type of the computer tool call output. Always `computer_call_output`.",
+            "default": "computer_call_output",
+            "x-stainless-const": true
+          },
+          "output": {
+            "$ref": "#/components/schemas/ComputerScreenshotImage"
+          },
+          "acknowledged_safety_checks": {
+            "anyOf": [
+              {
+                "items": {
+                  "$ref": "#/components/schemas/ComputerCallSafetyCheckParam"
+                },
+                "type": "array",
+                "description": "The safety checks reported by the API that have been acknowledged by the developer."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/FunctionCallItemStatus",
+                "description": "The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "call_id",
+          "type",
+          "output"
+        ],
+        "title": "Computer tool call output",
+        "description": "The output of a computer tool call."
+      },
+      "InputTextContentParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_text"
+            ],
+            "description": "The type of the input item. Always `input_text`.",
+            "default": "input_text",
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string",
+            "maxLength": 10485760,
+            "description": "The text input to the model."
+          },
+          "prompt_cache_breakpoint": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/PromptCacheBreakpointParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "text"
+        ],
+        "title": "Input text",
+        "description": "A text input to the model."
+      },
+      "InputImageContentParamAutoParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_image"
+            ],
+            "description": "The type of the input item. Always `input_image`.",
+            "default": "input_image",
+            "x-stainless-const": true
+          },
+          "image_url": {
+            "anyOf": [
+              {
+                "type": "string",
+                "maxLength": 20971520,
+                "format": "uri",
+                "description": "The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "file_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the file to be sent to the model.",
+                "example": "file-123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "detail": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/DetailEnum",
+                "description": "The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "prompt_cache_breakpoint": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/PromptCacheBreakpointParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Input image",
+        "description": "An image input to the model. Learn about [image inputs](https://developers.openai.com/api/docs/guides/images-vision)"
+      },
+      "FileDetailEnum": {
+        "type": "string",
+        "enum": [
+          "auto",
+          "low",
+          "high"
+        ]
+      },
+      "InputFileContentParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_file"
+            ],
+            "description": "The type of the input item. Always `input_file`.",
+            "default": "input_file",
+            "x-stainless-const": true
+          },
+          "file_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the file to be sent to the model.",
+                "example": "file-123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "filename": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The name of the file to be sent to the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "file_data": {
+            "anyOf": [
+              {
+                "type": "string",
+                "maxLength": 73400320,
+                "description": "The base64-encoded data of the file to be sent to the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "file_url": {
+            "anyOf": [
+              {
+                "type": "string",
+                "format": "uri",
+                "description": "The URL of the file to be sent to the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "detail": {
+            "$ref": "#/components/schemas/FileDetailEnum",
+            "description": "The detail level of the file to be sent to the model. Use `auto` to let the system select the detail level; for GPT-5.6 and later models, `auto` uses high-quality rendering, which may increase input token usage. Use `low` for lower-cost rendering, or `high` to render the file at higher quality. Defaults to `auto`."
+          },
+          "prompt_cache_breakpoint": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/PromptCacheBreakpointParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Input file",
+        "description": "A file input to the model."
+      },
+      "FunctionCallOutputItemParam": {
+        "properties": {
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the function tool call output. Populated when this item is returned via API.",
+                "example": "fc_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "call_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "maxLength": 64,
+                "minLength": 1,
+                "description": "The unique ID of the function tool call generated by the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "function_call_output"
+            ],
+            "description": "The type of the function tool call output. Always `function_call_output`.",
+            "default": "function_call_output",
+            "x-stainless-const": true
+          },
+          "output": {
+            "oneOf": [
+              {
+                "type": "string",
+                "maxLength": 10485760,
+                "description": "A JSON string of the output of the function tool call."
+              },
+              {
+                "items": {
+                  "oneOf": [
+                    {
+                      "$ref": "#/components/schemas/InputTextContentParam"
+                    },
+                    {
+                      "$ref": "#/components/schemas/InputImageContentParamAutoParam"
+                    },
+                    {
+                      "$ref": "#/components/schemas/InputFileContentParam"
+                    }
+                  ],
+                  "description": "A piece of message content, such as text, an image, or a file.",
+                  "discriminator": {
+                    "propertyName": "type"
+                  }
+                },
+                "type": "array",
+                "description": "An array of content outputs (text, image, file) for the function tool call."
+              }
+            ],
+            "description": "Text, image, or file output of the function tool call."
+          },
+          "name": {
+            "anyOf": [
+              {
+                "type": "string",
+                "maxLength": 128,
+                "minLength": 1,
+                "description": "The name of the tool that produced the output."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "namespace": {
+            "anyOf": [
+              {
+                "type": "string",
+                "maxLength": 64,
+                "minLength": 1,
+                "pattern": "^[a-zA-Z0-9_-]+$",
+                "description": "The namespace of the tool that produced the output."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ToolCallCallerParam",
+                "description": "The execution context that produced this tool call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/FunctionCallItemStatus",
+                "description": "The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "output"
+        ],
+        "title": "Function tool call output",
+        "description": "The output of a function tool call."
+      },
+      "FileCitationParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "file_citation"
+            ],
+            "description": "The citation type. Always `file_citation`.",
+            "default": "file_citation",
+            "x-stainless-const": true
+          },
+          "index": {
+            "type": "integer",
+            "minimum": 0,
+            "description": "The index of the file in the list of files."
+          },
+          "file_id": {
+            "type": "string",
+            "description": "The ID of the file.",
+            "example": "file-123"
+          },
+          "filename": {
+            "type": "string",
+            "description": "The filename of the file cited."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "index",
+          "file_id",
+          "filename"
+        ]
+      },
+      "UrlCitationParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "url_citation"
+            ],
+            "description": "The citation type. Always `url_citation`.",
+            "default": "url_citation",
+            "x-stainless-const": true
+          },
+          "start_index": {
+            "type": "integer",
+            "minimum": 0,
+            "description": "The index of the first character of the citation in the message."
+          },
+          "end_index": {
+            "type": "integer",
+            "minimum": 0,
+            "description": "The index of the last character of the citation in the message."
+          },
+          "url": {
+            "type": "string",
+            "format": "uri",
+            "description": "The URL of the cited resource."
+          },
+          "title": {
+            "type": "string",
+            "description": "The title of the cited resource."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "start_index",
+          "end_index",
+          "url",
+          "title"
+        ]
+      },
+      "ContainerFileCitationParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "container_file_citation"
+            ],
+            "description": "The citation type. Always `container_file_citation`.",
+            "default": "container_file_citation",
+            "x-stainless-const": true
+          },
+          "start_index": {
+            "type": "integer",
+            "minimum": 0,
+            "description": "The index of the first character of the citation in the message."
+          },
+          "end_index": {
+            "type": "integer",
+            "minimum": 0,
+            "description": "The index of the last character of the citation in the message."
+          },
+          "container_id": {
+            "type": "string",
+            "description": "The ID of the container.",
+            "example": "cntr_123"
+          },
+          "file_id": {
+            "type": "string",
+            "description": "The ID of the container file.",
+            "example": "cfile_123"
+          },
+          "filename": {
+            "type": "string",
+            "description": "The filename of the container file cited."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "start_index",
+          "end_index",
+          "container_id",
+          "file_id",
+          "filename"
+        ]
+      },
+      "ToolSearchCallItemParam": {
+        "properties": {
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of this tool search call.",
+                "example": "tsc_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "call_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "maxLength": 64,
+                "minLength": 1,
+                "description": "The unique ID of the tool search call generated by the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "tool_search_call"
+            ],
+            "description": "The item type. Always `tool_search_call`.",
+            "default": "tool_search_call",
+            "x-stainless-const": true
+          },
+          "execution": {
+            "$ref": "#/components/schemas/ToolSearchExecutionType",
+            "description": "Whether tool search was executed by the server or by the client."
+          },
+          "arguments": {
+            "$ref": "#/components/schemas/EmptyModelParam",
+            "description": "The arguments supplied to the tool search call."
+          },
+          "status": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/FunctionCallItemStatus",
+                "description": "The status of the tool search call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "arguments"
+        ]
+      },
+      "ToolSearchOutputItemParam": {
+        "properties": {
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of this tool search output.",
+                "example": "tso_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "call_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "maxLength": 64,
+                "minLength": 1,
+                "description": "The unique ID of the tool search call generated by the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "tool_search_output"
+            ],
+            "description": "The item type. Always `tool_search_output`.",
+            "default": "tool_search_output",
+            "x-stainless-const": true
+          },
+          "execution": {
+            "$ref": "#/components/schemas/ToolSearchExecutionType",
+            "description": "Whether tool search was executed by the server or by the client."
+          },
+          "tools": {
+            "items": {
+              "$ref": "#/components/schemas/Tool"
+            },
+            "type": "array",
+            "description": "The loaded tool definitions returned by the tool search output."
+          },
+          "status": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/FunctionCallItemStatus",
+                "description": "The status of the tool search output."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "tools"
+        ]
+      },
+      "AdditionalToolsItemParam": {
+        "properties": {
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of this additional tools item.",
+                "example": "at_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "additional_tools"
+            ],
+            "description": "The item type. Always `additional_tools`.",
+            "default": "additional_tools",
+            "x-stainless-const": true
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "developer"
+            ],
+            "description": "The role that provided the additional tools. Only `developer` is supported.",
+            "default": "developer",
+            "x-stainless-const": true
+          },
+          "tools": {
+            "items": {
+              "$ref": "#/components/schemas/Tool"
+            },
+            "type": "array",
+            "description": "A list of additional tools made available at this item."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "role",
+          "tools"
+        ]
+      },
+      "CompactionSummaryItemParam": {
+        "properties": {
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the compaction item.",
+                "example": "cmp_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "compaction"
+            ],
+            "description": "The type of the item. Always `compaction`.",
+            "default": "compaction",
+            "x-stainless-const": true
+          },
+          "encrypted_content": {
+            "type": "string",
+            "maxLength": 20971520,
+            "description": "The encrypted content of the compaction summary."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "encrypted_content"
+        ],
+        "title": "Compaction item",
+        "description": "A compaction item generated by the [`v1/responses/compact` API](https://developers.openai.com/api/reference/resources/responses/methods/compact)."
+      },
+      "FunctionShellActionParam": {
+        "properties": {
+          "commands": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array",
+            "description": "Ordered shell commands for the execution environment to run."
+          },
+          "timeout_ms": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "Maximum wall-clock time in milliseconds to allow the shell commands to run."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "max_output_length": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "Maximum number of UTF-8 characters to capture from combined stdout and stderr output."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "commands"
+        ],
+        "title": "Shell action",
+        "description": "Commands and limits describing how to run the shell tool call."
+      },
+      "FunctionShellCallItemStatus": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed",
+          "incomplete"
+        ],
+        "title": "Shell call status",
+        "description": "Status values reported for shell tool calls."
+      },
+      "FunctionShellCallItemParam": {
+        "properties": {
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the shell tool call. Populated when this item is returned via API.",
+                "example": "sh_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "call_id": {
+            "type": "string",
+            "maxLength": 64,
+            "minLength": 1,
+            "description": "The unique ID of the shell tool call generated by the model."
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ToolCallCallerParam",
+                "description": "The execution context that produced this tool call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "shell_call"
+            ],
+            "description": "The type of the item. Always `shell_call`.",
+            "default": "shell_call",
+            "x-stainless-const": true
+          },
+          "action": {
+            "$ref": "#/components/schemas/FunctionShellActionParam",
+            "description": "The shell commands and limits that describe how to run the tool call."
+          },
+          "status": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/FunctionShellCallItemStatus",
+                "description": "The status of the shell call. One of `in_progress`, `completed`, or `incomplete`."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "environment": {
+            "anyOf": [
+              {
+                "oneOf": [
+                  {
+                    "$ref": "#/components/schemas/LocalEnvironmentParam"
+                  },
+                  {
+                    "$ref": "#/components/schemas/ContainerReferenceParam"
+                  }
+                ],
+                "description": "The environment to execute the shell commands in.",
+                "discriminator": {
+                  "propertyName": "type"
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "call_id",
+          "type",
+          "action"
+        ],
+        "title": "Shell tool call",
+        "description": "A tool representing a request to execute one or more shell commands."
+      },
+      "FunctionShellCallOutputTimeoutOutcomeParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "timeout"
+            ],
+            "description": "The outcome type. Always `timeout`.",
+            "default": "timeout",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Shell call timeout outcome",
+        "description": "Indicates that the shell call exceeded its configured time limit."
+      },
+      "FunctionShellCallOutputExitOutcomeParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "exit"
+            ],
+            "description": "The outcome type. Always `exit`.",
+            "default": "exit",
+            "x-stainless-const": true
+          },
+          "exit_code": {
+            "type": "integer",
+            "description": "The exit code returned by the shell process."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "exit_code"
+        ],
+        "title": "Shell call exit outcome",
+        "description": "Indicates that the shell commands finished and returned an exit code."
+      },
+      "FunctionShellCallOutputOutcomeParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/FunctionShellCallOutputTimeoutOutcomeParam"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionShellCallOutputExitOutcomeParam"
+          }
+        ],
+        "title": "Shell call outcome",
+        "description": "The exit or timeout outcome associated with this shell call.",
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "FunctionShellCallOutputContentParam": {
+        "properties": {
+          "stdout": {
+            "type": "string",
+            "maxLength": 10485760,
+            "description": "Captured stdout output for the shell call."
+          },
+          "stderr": {
+            "type": "string",
+            "maxLength": 10485760,
+            "description": "Captured stderr output for the shell call."
+          },
+          "outcome": {
+            "$ref": "#/components/schemas/FunctionShellCallOutputOutcomeParam",
+            "description": "The exit or timeout outcome associated with this shell call."
+          }
+        },
+        "type": "object",
+        "required": [
+          "stdout",
+          "stderr",
+          "outcome"
+        ],
+        "title": "Shell output content",
+        "description": "Captured stdout and stderr for a portion of a shell tool call output."
+      },
+      "FunctionShellCallOutputItemParam": {
+        "properties": {
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the shell tool call output. Populated when this item is returned via API.",
+                "example": "sho_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "call_id": {
+            "type": "string",
+            "maxLength": 64,
+            "minLength": 1,
+            "description": "The unique ID of the shell tool call generated by the model."
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ToolCallCallerParam",
+                "description": "The execution context that produced this tool call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "shell_call_output"
+            ],
+            "description": "The type of the item. Always `shell_call_output`.",
+            "default": "shell_call_output",
+            "x-stainless-const": true
+          },
+          "output": {
+            "items": {
+              "$ref": "#/components/schemas/FunctionShellCallOutputContentParam"
+            },
+            "type": "array",
+            "description": "Captured chunks of stdout and stderr output, along with their associated outcomes."
+          },
+          "status": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/FunctionShellCallItemStatus",
+                "description": "The status of the shell call output."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "max_output_length": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "The maximum number of UTF-8 characters captured for this shell call's combined output."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "call_id",
+          "type",
+          "output"
+        ],
+        "title": "Shell tool call output",
+        "description": "The streamed output items emitted by a shell tool call."
+      },
+      "ApplyPatchCallStatusParam": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed"
+        ],
+        "title": "Apply patch call status",
+        "description": "Status values reported for apply_patch tool calls."
+      },
+      "ApplyPatchCreateFileOperationParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "create_file"
+            ],
+            "description": "The operation type. Always `create_file`.",
+            "default": "create_file",
+            "x-stainless-const": true
+          },
+          "path": {
+            "type": "string",
+            "minLength": 1,
+            "description": "Path of the file to create relative to the workspace root."
+          },
+          "diff": {
+            "type": "string",
+            "maxLength": 10485760,
+            "description": "Unified diff content to apply when creating the file."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "path",
+          "diff"
+        ],
+        "title": "Apply patch create file operation",
+        "description": "Instruction for creating a new file via the apply_patch tool."
+      },
+      "ApplyPatchDeleteFileOperationParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "delete_file"
+            ],
+            "description": "The operation type. Always `delete_file`.",
+            "default": "delete_file",
+            "x-stainless-const": true
+          },
+          "path": {
+            "type": "string",
+            "minLength": 1,
+            "description": "Path of the file to delete relative to the workspace root."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "path"
+        ],
+        "title": "Apply patch delete file operation",
+        "description": "Instruction for deleting an existing file via the apply_patch tool."
+      },
+      "ApplyPatchUpdateFileOperationParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "update_file"
+            ],
+            "description": "The operation type. Always `update_file`.",
+            "default": "update_file",
+            "x-stainless-const": true
+          },
+          "path": {
+            "type": "string",
+            "minLength": 1,
+            "description": "Path of the file to update relative to the workspace root."
+          },
+          "diff": {
+            "type": "string",
+            "maxLength": 10485760,
+            "description": "Unified diff content to apply to the existing file."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "path",
+          "diff"
+        ],
+        "title": "Apply patch update file operation",
+        "description": "Instruction for updating an existing file via the apply_patch tool."
+      },
+      "ApplyPatchOperationParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/ApplyPatchCreateFileOperationParam"
+          },
+          {
+            "$ref": "#/components/schemas/ApplyPatchDeleteFileOperationParam"
+          },
+          {
+            "$ref": "#/components/schemas/ApplyPatchUpdateFileOperationParam"
+          }
+        ],
+        "title": "Apply patch operation",
+        "description": "One of the create_file, delete_file, or update_file operations supplied to the apply_patch tool.",
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "ApplyPatchToolCallItemParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "apply_patch_call"
+            ],
+            "description": "The type of the item. Always `apply_patch_call`.",
+            "default": "apply_patch_call",
+            "x-stainless-const": true
+          },
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the apply patch tool call. Populated when this item is returned via API.",
+                "example": "apc_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "call_id": {
+            "type": "string",
+            "maxLength": 64,
+            "minLength": 1,
+            "description": "The unique ID of the apply patch tool call generated by the model."
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ToolCallCallerParam",
+                "description": "The execution context that produced this tool call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "$ref": "#/components/schemas/ApplyPatchCallStatusParam",
+            "description": "The status of the apply patch tool call. One of `in_progress` or `completed`."
+          },
+          "operation": {
+            "$ref": "#/components/schemas/ApplyPatchOperationParam",
+            "description": "The specific create, delete, or update instruction for the apply_patch tool call."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "call_id",
+          "status",
+          "operation"
+        ],
+        "title": "Apply patch tool call",
+        "description": "A tool call representing a request to create, delete, or update files using diff patches."
+      },
+      "ApplyPatchCallOutputStatusParam": {
+        "type": "string",
+        "enum": [
+          "completed",
+          "failed"
+        ],
+        "title": "Apply patch call output status",
+        "description": "Outcome values reported for apply_patch tool call outputs."
+      },
+      "ApplyPatchToolCallOutputItemParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "apply_patch_call_output"
+            ],
+            "description": "The type of the item. Always `apply_patch_call_output`.",
+            "default": "apply_patch_call_output",
+            "x-stainless-const": true
+          },
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the apply patch tool call output. Populated when this item is returned via API.",
+                "example": "apco_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "call_id": {
+            "type": "string",
+            "maxLength": 64,
+            "minLength": 1,
+            "description": "The unique ID of the apply patch tool call generated by the model."
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ToolCallCallerParam",
+                "description": "The execution context that produced this tool call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "$ref": "#/components/schemas/ApplyPatchCallOutputStatusParam",
+            "description": "The status of the apply patch tool call output. One of `completed` or `failed`."
+          },
+          "output": {
+            "anyOf": [
+              {
+                "type": "string",
+                "maxLength": 10485760,
+                "description": "Optional human-readable log text from the apply patch tool (e.g., patch results or errors)."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "call_id",
+          "status"
+        ],
+        "title": "Apply patch tool call output",
+        "description": "The streamed output emitted by an apply patch tool call."
+      },
+      "CompactionTriggerItemParam": {
+        "properties": {
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of this compaction trigger.",
+                "example": "msg_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "compaction_trigger"
+            ],
+            "description": "The type of the item. Always `compaction_trigger`.",
+            "default": "compaction_trigger",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Compaction trigger",
+        "description": "Compacts the current context. Must be the final input item."
+      },
+      "ItemReferenceParam": {
+        "properties": {
+          "type": {
+            "anyOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "item_reference"
+                ],
+                "description": "The type of item to reference. Always `item_reference`.",
+                "default": "item_reference",
+                "x-stainless-const": true
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "id": {
+            "type": "string",
+            "description": "The ID of the item to reference."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id"
+        ],
+        "title": "Item reference",
+        "description": "An internal identifier for an item to reference."
+      },
+      "ProgramItemParam": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of this program item.",
+            "example": "cm_123"
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "program"
+            ],
+            "description": "The item type. Always `program`.",
+            "default": "program",
+            "x-stainless-const": true
+          },
+          "call_id": {
+            "type": "string",
+            "maxLength": 64,
+            "minLength": 1,
+            "description": "The stable call ID of the program item."
+          },
+          "code": {
+            "type": "string",
+            "maxLength": 10485760,
+            "description": "The JavaScript source executed by programmatic tool calling."
+          },
+          "fingerprint": {
+            "type": "string",
+            "maxLength": 10485760,
+            "description": "Opaque program replay fingerprint that must be round-tripped."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "type",
+          "call_id",
+          "code",
+          "fingerprint"
+        ]
+      },
+      "ProgramOutputItemStatus": {
+        "type": "string",
+        "enum": [
+          "completed",
+          "incomplete"
+        ]
+      },
+      "ProgramOutputItemParam": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of this program output item.",
+            "example": "cmo_123"
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "program_output"
+            ],
+            "description": "The item type. Always `program_output`.",
+            "default": "program_output",
+            "x-stainless-const": true
+          },
+          "call_id": {
+            "type": "string",
+            "maxLength": 64,
+            "minLength": 1,
+            "description": "The call ID of the program item."
+          },
+          "result": {
+            "type": "string",
+            "maxLength": 10485760,
+            "description": "The result produced by the program item."
+          },
+          "status": {
+            "$ref": "#/components/schemas/ProgramOutputItemStatus",
+            "description": "The terminal status of the program output."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "type",
+          "call_id",
+          "result",
+          "status"
+        ]
+      },
+      "ConversationResource": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the conversation."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "conversation"
+            ],
+            "description": "The object type, which is always `conversation`.",
+            "default": "conversation",
+            "x-stainless-const": true
+          },
+          "metadata": {
+            "description": "Set of 16 key-value pairs that can be attached to an object. This can be         useful for storing additional information about the object in a structured         format, and querying for objects via API or the dashboard.\n        Keys are strings with a maximum length of 64 characters. Values are strings         with a maximum length of 512 characters."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The time at which the conversation was created, measured in seconds since the Unix epoch."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "object",
+          "metadata",
+          "created_at"
+        ]
+      },
+      "_MisalignmentErrorType": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "string",
+            "enum": [
+              "potentially_unintended_data_transfer",
+              "potentially_unintended_data_access",
+              "potentially_unintended_destructive_activity",
+              "other"
+            ]
+          }
+        ]
+      },
+      "_MisalignmentSteer": {
+        "properties": {
+          "message": {
+            "type": "string",
+            "description": "The public continuation instruction."
+          }
+        },
+        "type": "object",
+        "required": [
+          "message"
+        ]
+      },
+      "MisalignmentErrorDetailsResource": {
+        "properties": {
+          "error_type": {
+            "$ref": "#/components/schemas/_MisalignmentErrorType",
+            "description": "An optional classification; clients must accept additional values."
+          },
+          "detailed_explanation": {
+            "type": "string",
+            "description": "The public explanation for this block."
+          },
+          "steer": {
+            "$ref": "#/components/schemas/_MisalignmentSteer",
+            "description": "An optional public continuation instruction."
+          }
+        },
+        "type": "object",
+        "required": []
+      },
+      "ImageGenOutputTokensDetails": {
+        "properties": {
+          "image_tokens": {
+            "type": "integer",
+            "description": "The number of image output tokens generated by the model."
+          },
+          "text_tokens": {
+            "type": "integer",
+            "description": "The number of text output tokens generated by the model."
+          }
+        },
+        "type": "object",
+        "required": [
+          "image_tokens",
+          "text_tokens"
+        ],
+        "title": "Image generation output token details",
+        "description": "The output token details for the image generation."
+      },
+      "ImageGenInputUsageDetails": {
+        "properties": {
+          "text_tokens": {
+            "type": "integer",
+            "description": "The number of text tokens in the input prompt."
+          },
+          "image_tokens": {
+            "type": "integer",
+            "description": "The number of image tokens in the input prompt."
+          }
+        },
+        "type": "object",
+        "required": [
+          "text_tokens",
+          "image_tokens"
+        ],
+        "title": "Input usage details",
+        "description": "The input tokens detailed information for the image generation."
+      },
+      "ImageGenUsage": {
+        "properties": {
+          "input_tokens": {
+            "type": "integer",
+            "description": "The number of tokens (images and text) in the input prompt."
+          },
+          "total_tokens": {
+            "type": "integer",
+            "description": "The total number of tokens (images and text) used for the image generation."
+          },
+          "output_tokens": {
+            "type": "integer",
+            "description": "The number of output tokens generated by the model."
+          },
+          "output_tokens_details": {
+            "$ref": "#/components/schemas/ImageGenOutputTokensDetails"
+          },
+          "input_tokens_details": {
+            "$ref": "#/components/schemas/ImageGenInputUsageDetails"
+          }
+        },
+        "type": "object",
+        "required": [
+          "input_tokens",
+          "total_tokens",
+          "output_tokens",
+          "input_tokens_details"
+        ],
+        "title": "Image generation usage",
+        "description": "For `gpt-image-1` only, the token usage information for the image generation."
+      },
+      "instructions": {
+        "anyOf": [
+          {
+            "description": "Frontend instructions for voice, conversation, interruptions, and when to delegate. Start with the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting); put business rules and tool workflows in a separate [backend prompt](https://developers.openai.com/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). Limited to 16,384 client-supplied tokens. Omitted or blank instructions use server defaults. Immutable after startup.",
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "LiveCustomVoiceParam": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 128
+          }
+        },
+        "required": [
+          "id"
+        ]
+      },
+      "LiveInitialSessionAudioOutputParam": {
+        "description": "Settings for speech generated by the Live model. Choose the voice before starting the session.",
+        "type": "object",
+        "properties": {
+          "voice": {
+            "description": "The voice used for Live speech, as a built-in voice name or a custom voice object containing its ID. Defaults to `marin` and cannot change after startup.",
+            "oneOf": [
+              {
+                "anyOf": [
+                  {
+                    "type": "string"
+                  },
+                  {
+                    "type": "string",
+                    "enum": [
+                      "alloy",
+                      "ash",
+                      "ballad",
+                      "beacon",
+                      "bossa",
+                      "cedar",
+                      "cinder",
+                      "coral",
+                      "delta",
+                      "echo",
+                      "gleam",
+                      "marin",
+                      "meridian",
+                      "quartz",
+                      "ripple",
+                      "sage",
+                      "shimmer",
+                      "stone",
+                      "tempo",
+                      "verse",
+                      "vesper",
+                      "willow"
+                    ]
+                  }
+                ]
+              },
+              {
+                "$ref": "#/components/schemas/LiveCustomVoiceParam"
+              }
+            ]
+          }
+        },
+        "required": []
+      },
+      "LiveClientDelegationParam": {
+        "description": "Delegate tasks to your application. The Live session emits delegation events that your backend handles.",
+        "type": "object",
+        "properties": {
+          "type": {
+            "description": "The delegation owner. Always `client` for tasks handled by your application.",
+            "default": "client",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "client"
+            ]
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "LiveResponsesServiceTier": {
+        "type": "string",
+        "enum": [
+          "auto",
+          "default",
+          "fast_tier_temp_pilot",
+          "flex",
+          "priority",
+          "ultrafast"
+        ]
+      },
+      "LiveReasoningEffort": {
+        "type": "string",
+        "enum": [
+          "none",
+          "minimal",
+          "low",
+          "medium",
+          "high",
+          "xhigh"
+        ]
+      },
+      "LiveReasoningSummary": {
+        "type": "string",
+        "enum": [
+          "concise",
+          "detailed",
+          "auto"
+        ]
+      },
+      "LiveDelegationReasoningInputParam": {
+        "description": "Reasoning options for Responses requests made on behalf of the Live session.",
+        "type": "object",
+        "properties": {
+          "effort": {
+            "anyOf": [
+              {
+                "description": "How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model.",
+                "$ref": "#/components/schemas/LiveReasoningEffort"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "summary": {
+            "anyOf": [
+              {
+                "description": "The reasoning summary to request from the delegated Responses model, when supported.",
+                "$ref": "#/components/schemas/LiveReasoningSummary"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": []
+      },
+      "LiveTextVerbosity": {
+        "type": "string",
+        "enum": [
+          "low",
+          "medium",
+          "high"
+        ]
+      },
+      "LiveDelegationTextInputParam": {
+        "description": "Text generation options for the Live session’s Responses backend.",
+        "type": "object",
+        "properties": {
+          "verbosity": {
+            "anyOf": [
+              {
+                "description": "The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery.",
+                "$ref": "#/components/schemas/LiveTextVerbosity"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": []
+      },
+      "LiveFunctionToolInputParam": {
+        "description": "A function tool available to the Responses backend when the Live model delegates a task.",
+        "type": "object",
+        "properties": {
+          "type": {
+            "description": "The tool type. Always `function`.",
+            "default": "function",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "function"
+            ]
+          },
+          "name": {
+            "description": "The name the delegated Responses model uses when calling this function.",
+            "type": "string"
+          },
+          "description": {
+            "anyOf": [
+              {
+                "description": "What the function does and when the delegated Responses model should call it.",
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "parameters": {
+            "anyOf": [
+              {
+                "description": "A JSON Schema object describing the arguments accepted by the function.",
+                "type": "object",
+                "additionalProperties": {}
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "strict": {
+            "anyOf": [
+              {
+                "description": "Whether the delegated Responses model must follow the function’s parameter schema exactly.",
+                "type": "boolean"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "name"
+        ]
+      },
+      "LiveWebSearchToolInputParam": {
+        "description": "A web search tool available to the Live session’s Responses backend.",
+        "type": "object",
+        "properties": {
+          "type": {
+            "description": "The tool type. Always `web_search`.",
+            "default": "web_search",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "web_search"
+            ]
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "LiveToolChoiceEnum": {
+        "type": "string",
+        "enum": [
+          "auto",
+          "none",
+          "required"
+        ]
+      },
+      "LiveFunctionToolChoiceParam": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "default": "function",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "function"
+            ]
+          },
+          "name": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 64,
+            "pattern": "^[a-zA-Z0-9_-]+$"
+          }
+        },
+        "required": [
+          "type",
+          "name"
+        ]
+      },
+      "LiveMCPToolChoiceParam": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "default": "mcp",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "mcp"
+            ]
+          },
+          "server_label": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 64,
+            "pattern": "^[a-zA-Z0-9_-]+$"
+          },
+          "name": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 64,
+            "pattern": "^[a-zA-Z0-9_-]+$"
+          }
+        },
+        "required": [
+          "type",
+          "server_label",
+          "name"
+        ]
+      },
+      "LiveResponsesDelegationSettingsInputParam": {
+        "description": "Model, prompt, and tool settings for tasks delegated by the Live session to a Responses backend.",
+        "type": "object",
+        "properties": {
+          "model": {
+            "description": "The model used for server-owned Responses delegations.",
+            "type": "string"
+          },
+          "instructions": {
+            "anyOf": [
+              {
+                "description": "Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](https://developers.openai.com/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt).",
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "max_output_tokens": {
+            "anyOf": [
+              {
+                "description": "Maximum number of output tokens for each delegated response.",
+                "type": "integer",
+                "minimum": 16
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "service_tier": {
+            "anyOf": [
+              {
+                "description": "Service tier for delegated Responses requests.",
+                "$ref": "#/components/schemas/LiveResponsesServiceTier"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "reasoning": {
+            "anyOf": [
+              {
+                "description": "Reasoning settings passed to each delegated Responses request.",
+                "$ref": "#/components/schemas/LiveDelegationReasoningInputParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "text": {
+            "anyOf": [
+              {
+                "description": "Text generation settings passed to each delegated Responses request.",
+                "$ref": "#/components/schemas/LiveDelegationTextInputParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "tools": {
+            "description": "Tools available to the Responses backend while it handles tasks delegated by the Live model.",
+            "type": "array",
+            "items": {
+              "discriminator": {
+                "propertyName": "type"
+              },
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/LiveFunctionToolInputParam"
+                },
+                {
+                  "$ref": "#/components/schemas/LiveWebSearchToolInputParam"
+                }
+              ]
+            }
+          },
+          "tool_choice": {
+            "description": "Controls which tool the Responses backend uses when handling a task delegated by the Live model.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/LiveToolChoiceEnum"
+              },
+              {
+                "$ref": "#/components/schemas/LiveFunctionToolChoiceParam"
+              },
+              {
+                "$ref": "#/components/schemas/LiveMCPToolChoiceParam"
+              }
+            ]
+          },
+          "parallel_tool_calls": {
+            "anyOf": [
+              {
+                "description": "Whether the delegated Responses model may request multiple tool calls in a single response.",
+                "type": "boolean"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "model"
+        ]
+      },
+      "LiveResponsesDelegationParam": {
+        "description": "Delegate tasks to a Responses model managed by the Live session.",
+        "type": "object",
+        "properties": {
+          "type": {
+            "description": "The delegation owner. Always `responses` for tasks handled by the Responses API.",
+            "default": "responses",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "responses"
+            ]
+          },
+          "responses": {
+            "description": "Backend model, prompt, and tools used when the Live session delegates a task to Responses.",
+            "$ref": "#/components/schemas/LiveResponsesDelegationSettingsInputParam"
+          }
+        },
+        "required": [
+          "type",
+          "responses"
+        ]
+      },
+      "delegation": {
+        "anyOf": [
+          {
+            "description": "Who handles tasks delegated by the Live model. Omitted or null selects your application; use `responses` to let the API manage a Responses backend.",
+            "discriminator": {
+              "propertyName": "type"
+            },
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/LiveClientDelegationParam"
+              },
+              {
+                "$ref": "#/components/schemas/LiveResponsesDelegationParam"
+              }
+            ]
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "store": {
+        "description": "Whether to store the session for later forking and recording download. Defaults to false for new sessions.",
+        "type": "boolean"
+      },
+      "LiveInitialMessageStatus": {
+        "type": "string",
+        "enum": [
+          "incomplete",
+          "completed"
+        ]
+      },
+      "LiveInitialInputTextContentPartParam": {
+        "description": "Text supplied in a developer or user message when starting a Live session.",
+        "type": "object",
+        "properties": {
+          "type": {
+            "description": "The text content type. Always `input_text`.",
+            "default": "input_text",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "input_text"
+            ]
+          },
+          "text": {
+            "description": "The message text to include in the Live session’s initial conversation history.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "text"
+        ]
+      },
+      "LiveInitialDeveloperMessageItemParam": {
+        "description": "A developer message included in the initial text history of a Live session.",
+        "type": "object",
+        "properties": {
+          "id": {
+            "anyOf": [
+              {
+                "description": "An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation.",
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "description": "The history item type. Always `message`.",
+            "default": "message",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "message"
+            ]
+          },
+          "status": {
+            "anyOf": [
+              {
+                "description": "The supplied message’s status. Live uses its text as history and does not resume an incomplete message.",
+                "$ref": "#/components/schemas/LiveInitialMessageStatus"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "role": {
+            "description": "The author of this history message. Always `developer`.",
+            "default": "developer",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "developer"
+            ]
+          },
+          "content": {
+            "description": "The message content. Supply exactly one text part for the initial Live conversation history.",
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/LiveInitialInputTextContentPartParam"
+            },
+            "minItems": 1,
+            "maxItems": 1
+          }
+        },
+        "required": [
+          "role",
+          "content"
+        ]
+      },
+      "LiveInitialUserMessageItemParam": {
+        "description": "A user message included in the initial text history of a Live session.",
+        "type": "object",
+        "properties": {
+          "id": {
+            "anyOf": [
+              {
+                "description": "An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation.",
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "description": "The history item type. Always `message`.",
+            "default": "message",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "message"
+            ]
+          },
+          "status": {
+            "anyOf": [
+              {
+                "description": "The supplied message’s status. Live uses its text as history and does not resume an incomplete message.",
+                "$ref": "#/components/schemas/LiveInitialMessageStatus"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "role": {
+            "description": "The author of this history message. Always `user`.",
+            "default": "user",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "user"
+            ]
+          },
+          "content": {
+            "description": "The message content. Supply exactly one text part for the initial Live conversation history.",
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/LiveInitialInputTextContentPartParam"
+            },
+            "minItems": 1,
+            "maxItems": 1
+          }
+        },
+        "required": [
+          "role",
+          "content"
+        ]
+      },
+      "LiveInitialTextContentPartParam": {
+        "description": "Assistant text supplied as conversation history when starting a Live session.",
+        "type": "object",
+        "properties": {
+          "type": {
+            "description": "The text content type. Always `text`.",
+            "default": "text",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "text"
+            ]
+          },
+          "text": {
+            "description": "The message text to include in the Live session’s initial conversation history.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "text"
+        ]
+      },
+      "LiveInitialOutputTextContentPartParam": {
+        "description": "Assistant output text supplied as conversation history when starting a Live session.",
+        "type": "object",
+        "properties": {
+          "type": {
+            "description": "The text content type. Always `output_text`.",
+            "default": "output_text",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "output_text"
+            ]
+          },
+          "text": {
+            "description": "The message text to include in the Live session’s initial conversation history.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ]
+      },
+      "LiveInitialAssistantMessageItemParam": {
+        "description": "An assistant message included in the initial text history of a Live session.",
+        "type": "object",
+        "properties": {
+          "id": {
+            "anyOf": [
+              {
+                "description": "An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation.",
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "description": "The history item type. Always `message`.",
+            "default": "message",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "message"
+            ]
+          },
+          "status": {
+            "anyOf": [
+              {
+                "description": "The supplied message’s status. Live uses its text as history and does not resume an incomplete message.",
+                "$ref": "#/components/schemas/LiveInitialMessageStatus"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "role": {
+            "description": "The author of this history message. Always `assistant`.",
+            "default": "assistant",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "assistant"
+            ]
+          },
+          "content": {
+            "description": "The message content. Supply exactly one text part for the initial Live conversation history.",
+            "type": "array",
+            "items": {
+              "discriminator": {
+                "propertyName": "type"
+              },
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/LiveInitialTextContentPartParam"
+                },
+                {
+                  "$ref": "#/components/schemas/LiveInitialOutputTextContentPartParam"
+                }
+              ],
+              "x-oai-default-discriminator-value": "text"
+            },
+            "minItems": 1,
+            "maxItems": 1
+          }
+        },
+        "required": [
+          "role",
+          "content"
+        ]
+      },
+      "LiveInitialItem": {
+        "description": "A developer, user, or assistant message supplied as text history before the Live session starts.",
+        "discriminator": {
+          "propertyName": "role"
+        },
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/LiveInitialDeveloperMessageItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInitialUserMessageItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInitialAssistantMessageItemParam"
+          }
+        ]
+      },
+      "input": {
+        "description": "Ordered text-only history supplied before startup. Supports developer, user, and assistant messages with one text part each; at most 128 messages and 8,192 rendered tokens in total.",
+        "type": "array",
+        "items": {
+          "$ref": "#/components/schemas/LiveInitialItem"
+        },
+        "maxItems": 128
+      },
+      "LiveAllowedServerEventParam": {
+        "description": "A Live server event selector for the WebRTC frontend data channel.",
+        "example": {
+          "type": "session.started"
+        },
+        "type": "object",
+        "properties": {
+          "type": {
+            "description": "The outer Live server event type. Use 'response.event' for Responses events.",
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 256
+          },
+          "response_event": {
+            "description": "The nested Responses event type. Required when type is 'response.event'; forbidden for other event types.",
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 256
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.started"
+          }
+        }
+      },
+      "LiveDataChannelConfigParam": {
+        "description": "Control which Live events an untrusted WebRTC frontend can send and receive over its data channel. These restrictions do not apply to trusted sideband connections.",
+        "type": "object",
+        "properties": {
+          "allowed_client_events": {
+            "description": "Client event types that the frontend data channel may send. Use 'all' to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior.",
+            "oneOf": [
+              {
+                "default": "all",
+                "x-stainless-const": true,
+                "type": "string",
+                "enum": [
+                  "all"
+                ]
+              },
+              {
+                "type": "array",
+                "items": {
+                  "description": "A Live client event type allowed on the frontend data channel, such as `session.input_audio.mute`.",
+                  "type": "string",
+                  "minLength": 1,
+                  "maxLength": 256,
+                  "pattern": "^(?:error|info|[a-z][a-z0-9_-]*(?:\\.[a-z0-9_-]+)+)$"
+                },
+                "maxItems": 256
+              }
+            ]
+          },
+          "allowed_server_events": {
+            "description": "Server events that may be sent to the frontend data channel. Use 'all' to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type 'response.event' and a response_event selector.",
+            "oneOf": [
+              {
+                "default": "all",
+                "x-stainless-const": true,
+                "type": "string",
+                "enum": [
+                  "all"
+                ]
+              },
+              {
+                "type": "array",
+                "items": {
+                  "$ref": "#/components/schemas/LiveAllowedServerEventParam"
+                },
+                "maxItems": 256
+              }
+            ]
+          }
+        },
+        "required": []
+      },
+      "LiveClientConfigParam": {
+        "description": "Startup-only capabilities for an untrusted frontend attached to a unified WebRTC session. Trusted sideband connections are unaffected.",
+        "type": "object",
+        "properties": {
+          "data_channel": {
+            "description": "Client and server event permissions for the WebRTC frontend data channel.",
+            "$ref": "#/components/schemas/LiveDataChannelConfigParam"
+          }
+        },
+        "required": [
+          "data_channel"
+        ]
+      },
+      "properties-store": {
+        "description": "Whether to store the forked session. Omission inherits the stored session's setting.",
+        "type": "boolean"
+      },
+      "LiveResponsesDelegationSettingsUpdateInputParam": {
+        "description": "Updates to the Responses backend of an existing Live session. Omitted settings retain their current values.",
+        "type": "object",
+        "properties": {
+          "model": {
+            "description": "The Responses backend model to use for subsequent delegated requests. Omit to keep the current backend model.",
+            "type": "string"
+          },
+          "instructions": {
+            "anyOf": [
+              {
+                "description": "Instructions for the delegated Responses model, separate from Live instructions. See [backend prompting](https://developers.openai.com/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt).",
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "max_output_tokens": {
+            "anyOf": [
+              {
+                "description": "Maximum number of output tokens for each delegated response.",
+                "type": "integer",
+                "minimum": 16
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "service_tier": {
+            "anyOf": [
+              {
+                "description": "Service tier for delegated Responses requests.",
+                "$ref": "#/components/schemas/LiveResponsesServiceTier"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "reasoning": {
+            "anyOf": [
+              {
+                "description": "Reasoning settings passed to each delegated Responses request.",
+                "$ref": "#/components/schemas/LiveDelegationReasoningInputParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "text": {
+            "anyOf": [
+              {
+                "description": "Text generation settings passed to each delegated Responses request.",
+                "$ref": "#/components/schemas/LiveDelegationTextInputParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "tools": {
+            "description": "Tools available to the Responses backend while it handles tasks delegated by the Live model.",
+            "type": "array",
+            "items": {
+              "discriminator": {
+                "propertyName": "type"
+              },
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/LiveFunctionToolInputParam"
+                },
+                {
+                  "$ref": "#/components/schemas/LiveWebSearchToolInputParam"
+                }
+              ]
+            }
+          },
+          "tool_choice": {
+            "description": "Controls which tool the Responses backend uses when handling a task delegated by the Live model.",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/LiveToolChoiceEnum"
+              },
+              {
+                "$ref": "#/components/schemas/LiveFunctionToolChoiceParam"
+              },
+              {
+                "$ref": "#/components/schemas/LiveMCPToolChoiceParam"
+              }
+            ]
+          },
+          "parallel_tool_calls": {
+            "anyOf": [
+              {
+                "description": "Whether the delegated Responses model may request multiple tool calls in a single response.",
+                "type": "boolean"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": []
+      },
+      "LiveResponsesDelegationUpdateParam": {
+        "description": "Update the Responses backend for an existing Live session without changing delegation ownership.",
+        "type": "object",
+        "properties": {
+          "type": {
+            "description": "The delegation owner. Always `responses` for tasks handled by the Responses API.",
+            "default": "responses",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "responses"
+            ]
+          },
+          "responses": {
+            "description": "Responses backend settings to update. Omitted settings keep their existing values.",
+            "$ref": "#/components/schemas/LiveResponsesDelegationSettingsUpdateInputParam"
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "target_uri": {
+        "type": "string",
+        "description": "URI that should appear in the SIP Refer-To header. Supports values like\n`tel:+14155550123` or `sip:agent@example.com`.",
+        "example": "tel:+14155550123"
+      },
+      "PublicProjectResidency": {
+        "type": "string",
+        "enum": [
+          "GLOBAL",
+          "US_STORAGE_PROCESSING",
+          "EU_STORAGE_PROCESSING",
+          "JP_STORAGE",
+          "KR_STORAGE",
+          "CA_STORAGE",
+          "SG_STORAGE",
+          "IN_STORAGE",
+          "AU_STORAGE",
+          "GB_STORAGE",
+          "AE_STORAGE",
+          "AE_STORAGE_PROCESSING"
+        ]
+      },
+      "SpecificProgrammaticToolCallingParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "programmatic_tool_calling"
+            ],
+            "description": "The tool to call. Always `programmatic_tool_calling`.",
+            "default": "programmatic_tool_calling",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "SpecificApplyPatchParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "apply_patch"
+            ],
+            "description": "The tool to call. Always `apply_patch`.",
+            "default": "apply_patch",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Specific apply patch tool choice",
+        "description": "Forces the model to call the apply_patch tool when executing a tool call."
+      },
+      "SpecificFunctionShellParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "shell"
+            ],
+            "description": "The tool to call. Always `shell`.",
+            "default": "shell",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Specific shell tool choice",
+        "description": "Forces the model to call the shell tool when a tool call is required."
+      },
+      "ResponsePromptCacheOptionsParam": {
+        "properties": {
+          "ttl": {
+            "$ref": "#/components/schemas/PromptCacheTTLEnum",
+            "description": "The minimum lifetime applied to every implicit and explicit cache breakpoint written by the request. Defaults to `30m`, which is currently the only supported value. The backend may retain cache entries for longer."
+          },
+          "mode": {
+            "$ref": "#/components/schemas/PromptCacheModeEnum",
+            "description": "Controls whether OpenAI automatically creates an implicit cache breakpoint. Defaults to `implicit`. With `implicit`, OpenAI creates one implicit breakpoint and writes up to the latest three explicit breakpoints in the request. With `explicit`, OpenAI does not create an implicit breakpoint and writes up to the latest four explicit breakpoints. If there are no explicit breakpoints, the request does not use prompt caching."
+          },
+          "comparison_response_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of a response to compare when diagnosing prompt cache reuse. Supplying this field requests prompt cache diagnostics when the feature is enabled.",
+                "example": "resp_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [],
+        "title": "Prompt cache options",
+        "description": "Options for prompt caching. Supported for `gpt-5.6` and later models. By default, OpenAI automatically chooses one implicit cache breakpoint. You can add explicit breakpoints to content blocks with `prompt_cache_breakpoint`. Each request can write up to four breakpoints. For cache matching, OpenAI considers up to the latest 80 breakpoints in the conversation, without a content-block lookback limit. Set `mode` to `explicit` to disable the implicit breakpoint. The `ttl` defaults to `30m`, which is currently the only supported value. See the [prompt caching guide](https://developers.openai.com/api/docs/guides/prompt-caching) for current details."
+      },
+      "ReasoningModeEnum": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "string",
+            "enum": [
+              "standard",
+              "pro"
+            ]
+          }
+        ]
+      },
+      "ConversationParam-2": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the conversation.",
+            "example": "conv_123"
+          }
+        },
+        "type": "object",
+        "required": [
+          "id"
+        ],
+        "title": "Conversation object",
+        "description": "The conversation that this response belongs to."
+      },
+      "ContextManagementParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The context management entry type. Currently only 'compaction' is supported."
+          },
+          "compact_threshold": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "minimum": 1000,
+                "description": "Token threshold at which compaction should be triggered for this entry."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "PromptCacheOptions": {
+        "properties": {
+          "ttl": {
+            "$ref": "#/components/schemas/PromptCacheTTLEnum",
+            "description": "The minimum lifetime applied to each cache breakpoint."
+          },
+          "mode": {
+            "$ref": "#/components/schemas/PromptCacheModeEnum",
+            "description": "Whether implicit prompt-cache breakpoints were enabled."
+          },
+          "comparison_response_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The response ID supplied as the prompt cache diagnostics comparison."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "ttl",
+          "mode"
+        ],
+        "title": "Prompt cache options",
+        "description": "The prompt-caching options that were applied to the response. Supported for `gpt-5.6` and later models."
+      },
+      "CacheMissReasonTypeEnum": {
+        "type": "string",
+        "enum": [
+          "model_changed",
+          "prompt_cache_key_changed",
+          "tools_changed",
+          "text_format_changed",
+          "reasoning_effort_changed",
+          "verbosity_changed",
+          "context_compacted",
+          "input_changed",
+          "service_tier_changed"
+        ]
+      },
+      "PromptCacheMissDiagnosticsBody": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "cache_miss"
+            ],
+            "default": "cache_miss",
+            "x-stainless-const": true
+          },
+          "reason": {
+            "$ref": "#/components/schemas/CacheMissReasonTypeEnum",
+            "description": "The reason prompt cache reuse did not occur."
+          },
+          "cache_missed_tokens": {
+            "type": "integer",
+            "description": "The estimated number of input tokens affected after the first detected divergence."
+          },
+          "comparison_reusable_tokens": {
+            "type": "integer",
+            "description": "The raw token count of the reusable prefix in the compared response."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "reason",
+          "cache_missed_tokens"
+        ]
+      },
+      "PromptCacheHitDiagnosticsBody": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "cache_hit"
+            ],
+            "default": "cache_hit",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "PromptCacheComparisonResponseNotFoundDiagnosticsBody": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "comparison_response_not_found"
+            ],
+            "default": "comparison_response_not_found",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "PromptCacheUnavailableDiagnosticsBody": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "unavailable"
+            ],
+            "default": "unavailable",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "PromptCacheDiagnostics": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/PromptCacheMissDiagnosticsBody"
+          },
+          {
+            "$ref": "#/components/schemas/PromptCacheHitDiagnosticsBody"
+          },
+          {
+            "$ref": "#/components/schemas/PromptCacheComparisonResponseNotFoundDiagnosticsBody"
+          },
+          {
+            "$ref": "#/components/schemas/PromptCacheUnavailableDiagnosticsBody"
+          }
+        ],
+        "description": "Prompt cache diagnostics requested for this response.",
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "ModerationErrorBody": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "error"
+            ],
+            "description": "The object type, which was always `error` for moderation failures.",
+            "default": "error",
+            "x-stainless-const": true
+          },
+          "code": {
+            "type": "string",
+            "description": "The error code."
+          },
+          "message": {
+            "type": "string",
+            "description": "The error message."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "code",
+          "message"
+        ],
+        "title": "Moderation error",
+        "description": "An error produced while attempting moderation for the response input or output."
+      },
+      "Moderation": {
+        "properties": {
+          "input": {
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/ModerationResultBody"
+              },
+              {
+                "$ref": "#/components/schemas/ModerationErrorBody"
+              }
+            ],
+            "description": "Moderation for the response input.",
+            "discriminator": {
+              "propertyName": "type"
+            }
+          },
+          "output": {
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/ModerationResultBody"
+              },
+              {
+                "$ref": "#/components/schemas/ModerationErrorBody"
+              }
+            ],
+            "description": "Moderation for the response output.",
+            "discriminator": {
+              "propertyName": "type"
+            }
+          }
+        },
+        "type": "object",
+        "required": [
+          "input",
+          "output"
+        ],
+        "title": "Moderation",
+        "description": "Moderation results or errors for the response input and output."
+      },
+      "ResponseConversation": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the conversation that this response was associated with."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id"
+        ],
+        "title": "Conversation",
+        "description": "The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation."
+      },
+      "ResponseShellCallCommandAddedStreamingEvent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.shell_call_command.added"
+            ],
+            "description": "The type of the event, always `response.shell_call_command.added`.",
+            "default": "response.shell_call_command.added",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the event that was emitted."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that was updated."
+          },
+          "command_index": {
+            "type": "integer",
+            "description": "The index of the shell command that was added."
+          },
+          "command": {
+            "type": "string",
+            "description": "The shell command that was added."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "sequence_number",
+          "output_index",
+          "command_index",
+          "command"
+        ],
+        "title": "Response shell command added event",
+        "description": "A streaming event that indicated a shell command was added to a tool call."
+      },
+      "ResponseShellCallCommandDeltaStreamingEvent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.shell_call_command.delta"
+            ],
+            "description": "The type of the event, always `response.shell_call_command.delta`.",
+            "default": "response.shell_call_command.delta",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the event that was emitted."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that was updated."
+          },
+          "command_index": {
+            "type": "integer",
+            "description": "The index of the shell command that was updated."
+          },
+          "delta": {
+            "type": "string",
+            "description": "The shell command delta that was appended."
+          },
+          "obfuscation": {
+            "type": "string",
+            "description": "An obfuscation string that was added to pad the event payload."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "sequence_number",
+          "output_index",
+          "command_index",
+          "delta"
+        ],
+        "title": "Response shell command delta event",
+        "description": "A streaming event that indicated a shell command was incrementally updated."
+      },
+      "ResponseShellCallCommandDoneStreamingEvent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.shell_call_command.done"
+            ],
+            "description": "The type of the event, always `response.shell_call_command.done`.",
+            "default": "response.shell_call_command.done",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the event that was emitted."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that was updated."
+          },
+          "command_index": {
+            "type": "integer",
+            "description": "The index of the shell command that was completed."
+          },
+          "command": {
+            "type": "string",
+            "description": "The final shell command that was emitted."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "sequence_number",
+          "output_index",
+          "command_index",
+          "command"
+        ],
+        "title": "Response shell command done event",
+        "description": "A streaming event that indicated a shell command was completed."
+      },
+      "ShellCallOutputDelta": {
+        "properties": {
+          "stdout": {
+            "type": "string",
+            "description": "The stdout delta that was emitted."
+          },
+          "stderr": {
+            "type": "string",
+            "description": "The stderr delta that was emitted."
+          }
+        },
+        "type": "object",
+        "required": [],
+        "title": "Shell call output delta",
+        "description": "A delta of stdout/stderr emitted while a shell call was running."
+      },
+      "ResponseShellCallOutputContentDeltaStreamingEvent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.shell_call_output_content.delta"
+            ],
+            "description": "The type of the event, always `response.shell_call_output_content.delta`.",
+            "default": "response.shell_call_output_content.delta",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the event that was emitted."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that was updated."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that was updated."
+          },
+          "command_index": {
+            "type": "integer",
+            "description": "The index of the shell command that produced output."
+          },
+          "delta": {
+            "$ref": "#/components/schemas/ShellCallOutputDelta",
+            "description": "The stdout/stderr delta that was emitted."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "sequence_number",
+          "item_id",
+          "output_index",
+          "command_index",
+          "delta"
+        ],
+        "title": "Response shell call output content delta event",
+        "description": "A streaming event that indicated shell call output was incrementally added."
+      },
+      "ResponseShellCallOutputContentDoneStreamingEvent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.shell_call_output_content.done"
+            ],
+            "description": "The type of the event, always `response.shell_call_output_content.done`.",
+            "default": "response.shell_call_output_content.done",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the event that was emitted."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that was updated."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that was updated."
+          },
+          "command_index": {
+            "type": "integer",
+            "description": "The index of the shell command that produced output."
+          },
+          "output": {
+            "items": {
+              "$ref": "#/components/schemas/FunctionShellCallOutputContent"
+            },
+            "type": "array",
+            "description": "The output contents emitted for the shell command."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "sequence_number",
+          "item_id",
+          "output_index",
+          "command_index",
+          "output"
+        ],
+        "title": "Response shell call output content done event",
+        "description": "A streaming event that indicated shell call output was completed."
+      },
+      "CreateConversationBody": {
+        "properties": {
+          "metadata": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Metadata",
+                "description": "Set of 16 key-value pairs that can be attached to an object. This can be         useful for storing additional information about the object in a structured         format, and querying for objects via API or the dashboard.\n        Keys are strings with a maximum length of 64 characters. Values are strings         with a maximum length of 512 characters."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "items": {
+            "anyOf": [
+              {
+                "items": {
+                  "$ref": "#/components/schemas/InputItem"
+                },
+                "type": "array",
+                "maxItems": 20,
+                "description": "Initial items to include in the conversation context. You may add up to 20 items at a time."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": []
+      },
+      "UpdateConversationBody": {
+        "properties": {
+          "metadata": {
+            "$ref": "#/components/schemas/Metadata",
+            "description": "Set of 16 key-value pairs that can be attached to an object. This can be         useful for storing additional information about the object in a structured         format, and querying for objects via API or the dashboard.\n        Keys are strings with a maximum length of 64 characters. Values are strings         with a maximum length of 512 characters."
+          }
+        },
+        "type": "object",
+        "required": [
+          "metadata"
+        ]
+      },
+      "DeletedConversationResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "conversation.deleted"
+            ],
+            "default": "conversation.deleted",
+            "x-stainless-const": true
+          },
+          "deleted": {
+            "type": "boolean"
+          },
+          "id": {
+            "type": "string"
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "deleted",
+          "id"
+        ]
+      },
+      "SafetyAlertErrorType": {
+        "type": "string",
+        "enum": [
+          "potentially_unintended_data_transfer",
+          "potentially_unintended_data_access",
+          "potentially_unintended_destructive_activity",
+          "other"
+        ]
+      },
+      "SafetyAlertResource": {
+        "properties": {
+          "id": {
+            "type": "string"
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "safety.alert"
+            ],
+            "default": "safety.alert",
+            "x-stainless-const": true
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime"
+          },
+          "request_id": {
+            "type": "string"
+          },
+          "response_id": {
+            "type": "string"
+          },
+          "model": {
+            "type": "string"
+          },
+          "request_paused": {
+            "type": "boolean",
+            "description": "Whether block registration succeeded for this request. This does not confirm that response execution stopped."
+          },
+          "error_type": {
+            "$ref": "#/components/schemas/SafetyAlertErrorType"
+          },
+          "reason": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "A customer-safe description derived from error_type, or null for zero data retention requests."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "object",
+          "created_at",
+          "request_id",
+          "response_id",
+          "model",
+          "request_paused",
+          "error_type",
+          "reason"
+        ]
+      },
+      "SpendLimitCurrency": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "string",
+            "enum": [
+              "USD"
+            ]
+          }
+        ]
+      },
+      "SpendLimitInterval": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "string",
+            "enum": [
+              "month"
+            ]
+          }
+        ]
+      },
+      "SpendLimitEnforcementStatus": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "string",
+            "enum": [
+              "inactive",
+              "enforcing"
+            ]
+          }
+        ]
+      },
+      "SpendLimitEnforcement": {
+        "properties": {
+          "status": {
+            "$ref": "#/components/schemas/SpendLimitEnforcementStatus",
+            "description": "Whether the hard spend limit is currently enforcing."
+          }
+        },
+        "type": "object",
+        "required": [
+          "status"
+        ],
+        "description": "The current enforcement state of a hard spend limit."
+      },
+      "OrganizationSpendLimitResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.spend_limit"
+            ],
+            "description": "The object type, which is always `organization.spend_limit`.",
+            "default": "organization.spend_limit",
+            "x-stainless-const": true
+          },
+          "threshold_amount": {
+            "type": "integer",
+            "description": "The hard spend limit amount, in cents."
+          },
+          "currency": {
+            "$ref": "#/components/schemas/SpendLimitCurrency",
+            "description": "The currency for the threshold amount. Currently, only `USD` is supported."
+          },
+          "interval": {
+            "$ref": "#/components/schemas/SpendLimitInterval",
+            "description": "The time interval for evaluating spend against the threshold. Currently, only `month` is supported."
+          },
+          "enforcement": {
+            "$ref": "#/components/schemas/SpendLimitEnforcement",
+            "description": "The current enforcement state of the hard spend limit."
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "threshold_amount",
+          "currency",
+          "interval",
+          "enforcement"
+        ],
+        "description": "Represents a hard spend limit configured at the organization level."
+      },
+      "UpdateOrganizationSpendLimitBody": {
+        "properties": {
+          "threshold_amount": {
+            "type": "integer",
+            "minimum": 1,
+            "description": "The hard spend limit amount, in cents."
+          },
+          "currency": {
+            "type": "string",
+            "enum": [
+              "USD"
+            ],
+            "description": "The currency for the threshold amount. Currently, only `USD` is supported."
+          },
+          "interval": {
+            "type": "string",
+            "enum": [
+              "month"
+            ],
+            "description": "The time interval for evaluating spend against the threshold. Currently, only `month` is supported."
+          }
+        },
+        "type": "object",
+        "required": [
+          "threshold_amount",
+          "currency",
+          "interval"
+        ],
+        "description": "Parameters for the hard spend limit you want to create or replace."
+      },
+      "OrganizationSpendLimitDeletedResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.spend_limit.deleted"
+            ],
+            "description": "The object type, which is always `organization.spend_limit.deleted`.",
+            "default": "organization.spend_limit.deleted",
+            "x-stainless-const": true
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the hard spend limit was deleted."
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "deleted"
+        ],
+        "description": "Confirmation payload returned after deleting an organization hard spend limit."
+      },
+      "ProjectSpendLimitResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "project.spend_limit"
+            ],
+            "description": "The object type, which is always `project.spend_limit`.",
+            "default": "project.spend_limit",
+            "x-stainless-const": true
+          },
+          "threshold_amount": {
+            "type": "integer",
+            "description": "The hard spend limit amount, in cents."
+          },
+          "currency": {
+            "$ref": "#/components/schemas/SpendLimitCurrency",
+            "description": "The currency for the threshold amount. Currently, only `USD` is supported."
+          },
+          "interval": {
+            "$ref": "#/components/schemas/SpendLimitInterval",
+            "description": "The time interval for evaluating spend against the threshold. Currently, only `month` is supported."
+          },
+          "enforcement": {
+            "$ref": "#/components/schemas/SpendLimitEnforcement",
+            "description": "The current enforcement state of the hard spend limit."
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "threshold_amount",
+          "currency",
+          "interval",
+          "enforcement"
+        ],
+        "description": "Represents a hard spend limit configured at the project level."
+      },
+      "UpdateProjectSpendLimitBody": {
+        "properties": {
+          "threshold_amount": {
+            "type": "integer",
+            "minimum": 1,
+            "description": "The hard spend limit amount, in cents."
+          },
+          "currency": {
+            "type": "string",
+            "enum": [
+              "USD"
+            ],
+            "description": "The currency for the threshold amount. Currently, only `USD` is supported."
+          },
+          "interval": {
+            "type": "string",
+            "enum": [
+              "month"
+            ],
+            "description": "The time interval for evaluating spend against the threshold. Currently, only `month` is supported."
+          }
+        },
+        "type": "object",
+        "required": [
+          "threshold_amount",
+          "currency",
+          "interval"
+        ],
+        "description": "Parameters for the hard spend limit you want to create or replace."
+      },
+      "ProjectSpendLimitDeletedResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "project.spend_limit.deleted"
+            ],
+            "description": "The object type, which is always `project.spend_limit.deleted`.",
+            "default": "project.spend_limit.deleted",
+            "x-stainless-const": true
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the hard spend limit was deleted."
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "deleted"
+        ],
+        "description": "Confirmation payload returned after deleting a project hard spend limit."
+      },
+      "CreateProjectServiceAccountApiKeyBody": {
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "API key name."
+          },
+          "scopes": {
+            "items": {
+              "type": "string",
+              "description": "API key scope."
+            },
+            "type": "array",
+            "description": "API key scopes."
+          },
+          "expires_in_seconds": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "maximum": 31536000,
+                "minimum": 1,
+                "description": "Number of seconds until the API key expires."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [],
+        "description": "The service account API key create request payload."
+      },
+      "ServiceAccountApiKeyBody": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "organization.project.service_account.api_key"
+            ],
+            "description": "The object type, which is always `organization.project.service_account.api_key`",
+            "default": "organization.project.service_account.api_key",
+            "x-stainless-const": true
+          },
+          "value": {
+            "type": "string",
+            "description": "The unredacted API key value."
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the API key."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp (in seconds) when the API key was created."
+          },
+          "expires_at": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "format": "unixtime",
+                "description": "The Unix timestamp (in seconds) when the API key expires, or null if it does not expire."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "id": {
+            "type": "string",
+            "description": "The identifier of the API key."
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "value",
+          "name",
+          "created_at",
+          "id"
+        ]
+      },
+      "CreateContentProvenanceBody": {
+        "properties": {
+          "file": {
+            "type": "string",
+            "format": "binary",
+            "description": "The image or audio file to check for supported OpenAI provenance signals."
+          }
+        },
+        "type": "object",
+        "required": [
+          "file"
+        ]
+      },
+      "ProvenanceCheckObject": {
+        "type": "string",
+        "enum": [
+          "content_provenance_check"
+        ]
+      },
+      "ProvenanceDetectionResultApi": {
+        "type": "string",
+        "enum": [
+          "detected",
+          "not_detected"
+        ]
+      },
+      "C2PAValidationStateApi": {
+        "type": "string",
+        "enum": [
+          "trusted",
+          "valid",
+          "invalid",
+          "not_present"
+        ]
+      },
+      "C2PAProvenanceResult": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "c2pa"
+            ],
+            "description": "The provenance signal type. Always `c2pa`.",
+            "default": "c2pa",
+            "x-stainless-const": true
+          },
+          "outcome": {
+            "$ref": "#/components/schemas/ProvenanceDetectionResultApi",
+            "description": "Whether a supported OpenAI C2PA provenance signal was detected.\nIf `not_detected`, it means the tool did not find supported signals in the uploaded file. The content could still have been generated by OpenAI if the metadata was stripped or has evidence of tampering, the watermark was degraded, it comes from a legacy generation model, or it was created before provenance signals were available. Content could also still be AI-generated by another company's model, which the tool currently does not detect."
+          },
+          "validation_state": {
+            "$ref": "#/components/schemas/C2PAValidationStateApi",
+            "description": "The validation status of the C2PA manifest in the uploaded image."
+          },
+          "issuer": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The C2PA manifest issuer, when available."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "model": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The OpenAI model recorded by the provenance signal, when available."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "generated_at": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The UTC RFC 3339 timestamp recorded by the provenance signal for when the asset was generated, when available."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "outcome",
+          "validation_state",
+          "issuer",
+          "model",
+          "generated_at"
+        ]
+      },
+      "SynthIDProvenanceResult": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "synthid"
+            ],
+            "description": "The provenance signal type. Always `synthid`.",
+            "default": "synthid",
+            "x-stainless-const": true
+          },
+          "outcome": {
+            "$ref": "#/components/schemas/ProvenanceDetectionResultApi",
+            "description": "Whether a supported OpenAI SynthID watermark was detected.\nIf `not_detected`, it means the tool did not find supported signals in the uploaded file. The content could still have been generated by OpenAI if the metadata was stripped or has evidence of tampering, the watermark was degraded, it comes from a legacy generation model, or it was created before provenance signals were available. Content could also still be AI-generated by another company's model, which the tool currently does not detect."
+          },
+          "model": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The OpenAI model recorded by the provenance signal, when available."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "generated_at": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The UTC RFC 3339 timestamp recorded by the provenance signal for when the asset was generated, when available."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "outcome",
+          "model",
+          "generated_at"
+        ]
+      },
+      "ProvenanceResource": {
+        "properties": {
+          "object": {
+            "$ref": "#/components/schemas/ProvenanceCheckObject",
+            "description": "The object type. Always `content_provenance_check` for this endpoint."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "The Unix timestamp, in seconds, when the provenance check was created."
+          },
+          "results": {
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/C2PAProvenanceResult"
+                },
+                {
+                  "$ref": "#/components/schemas/SynthIDProvenanceResult"
+                }
+              ],
+              "discriminator": {
+                "propertyName": "type"
+              }
+            },
+            "type": "array",
+            "description": "The provenance results that apply to the uploaded file. Image results include C2PA and SynthID; audio results include SynthID."
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "created_at",
+          "results"
+        ]
+      },
+      "OrderEnum": {
+        "type": "string",
+        "enum": [
+          "asc",
+          "desc"
+        ]
+      },
+      "VideoModel": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "string",
+            "enum": [
+              "sora-2",
+              "sora-2-pro",
+              "sora-2-2025-10-06",
+              "sora-2-pro-2025-10-06",
+              "sora-2-2025-12-08"
+            ]
+          }
+        ]
+      },
+      "VideoStatus": {
+        "type": "string",
+        "enum": [
+          "queued",
+          "in_progress",
+          "completed",
+          "failed"
+        ]
+      },
+      "VideoSize": {
+        "type": "string",
+        "enum": [
+          "720x1280",
+          "1280x720",
+          "1024x1792",
+          "1792x1024"
+        ]
+      },
+      "Error-2": {
+        "properties": {
+          "code": {
+            "type": "string",
+            "description": "A machine-readable error code that was returned."
+          },
+          "message": {
+            "type": "string",
+            "description": "A human-readable description of the error that was returned."
+          },
+          "misalignment": {
+            "$ref": "#/components/schemas/MisalignmentErrorDetailsResource"
+          }
+        },
+        "type": "object",
+        "required": [
+          "code",
+          "message"
+        ],
+        "title": "Error",
+        "description": "An error that occurred while generating the response."
+      },
+      "VideoResource": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Unique identifier for the video job."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "video"
+            ],
+            "description": "The object type, which is always `video`.",
+            "default": "video",
+            "x-stainless-const": true
+          },
+          "model": {
+            "$ref": "#/components/schemas/VideoModel",
+            "description": "The video generation model that produced the job."
+          },
+          "status": {
+            "$ref": "#/components/schemas/VideoStatus",
+            "description": "Current lifecycle status of the video job."
+          },
+          "progress": {
+            "type": "integer",
+            "description": "Approximate completion percentage for the generation task."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (seconds) for when the job was created."
+          },
+          "completed_at": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "format": "unixtime",
+                "description": "Unix timestamp (seconds) for when the job completed, if finished."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "expires_at": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "format": "unixtime",
+                "description": "Unix timestamp (seconds) for when the downloadable assets expire, if set."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "prompt": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The prompt that was used to generate the video."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "size": {
+            "$ref": "#/components/schemas/VideoSize",
+            "description": "The resolution of the generated video."
+          },
+          "seconds": {
+            "type": "string",
+            "description": "Duration of the generated clip in seconds. For extensions, this is the stitched total duration."
+          },
+          "remixed_from_video_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Identifier of the source video if this video is a remix."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "error": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Error-2",
+                "description": "Error payload that explains why generation failed, if applicable."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "object",
+          "model",
+          "status",
+          "progress",
+          "created_at",
+          "completed_at",
+          "expires_at",
+          "prompt",
+          "size",
+          "seconds",
+          "remixed_from_video_id",
+          "error"
+        ],
+        "title": "Video job",
+        "description": "Structured information describing a generated video job."
+      },
+      "VideoListResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "description": "The type of object returned, must be `list`.",
+            "default": "list",
+            "x-stainless-const": true
+          },
+          "data": {
+            "items": {
+              "$ref": "#/components/schemas/VideoResource"
+            },
+            "type": "array",
+            "description": "A list of items"
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the first item in the list."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the last item in the list."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more items available."
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ]
+      },
+      "ImageRefParam-2": {
+        "properties": {
+          "image_url": {
+            "type": "string",
+            "maxLength": 20971520,
+            "format": "uri",
+            "description": "A fully qualified URL or base64-encoded data URL."
+          },
+          "file_id": {
+            "type": "string",
+            "example": "file-123"
+          }
+        },
+        "type": "object",
+        "required": []
+      },
+      "VideoSeconds": {
+        "type": "string",
+        "enum": [
+          "4",
+          "8",
+          "12"
+        ]
+      },
+      "CreateVideoMultipartBody": {
+        "properties": {
+          "model": {
+            "$ref": "#/components/schemas/VideoModel",
+            "description": "The video generation model to use (allowed values: sora-2, sora-2-pro). Defaults to `sora-2`."
+          },
+          "prompt": {
+            "type": "string",
+            "maxLength": 32000,
+            "minLength": 1,
+            "description": "Text prompt that describes the video to generate."
+          },
+          "input_reference": {
+            "oneOf": [
+              {
+                "type": "string",
+                "format": "binary",
+                "description": "Optional reference asset upload or reference object that guides generation."
+              },
+              {
+                "$ref": "#/components/schemas/ImageRefParam-2",
+                "description": "Optional reference asset upload or reference object that guides generation. Provide exactly one of `image_url` or `file_id` when using an object."
+              }
+            ]
+          },
+          "seconds": {
+            "$ref": "#/components/schemas/VideoSeconds",
+            "description": "Clip duration in seconds (allowed values: 4, 8, 12). Defaults to 4 seconds."
+          },
+          "size": {
+            "$ref": "#/components/schemas/VideoSize",
+            "description": "Output resolution formatted as width x height (allowed values: 720x1280, 1280x720, 1024x1792, 1792x1024). Defaults to 720x1280."
+          }
+        },
+        "type": "object",
+        "required": [
+          "prompt"
+        ],
+        "title": "Create video multipart request",
+        "description": "Multipart parameters for creating a new video generation job."
+      },
+      "CreateVideoJsonBody": {
+        "properties": {
+          "model": {
+            "$ref": "#/components/schemas/VideoModel",
+            "description": "The video generation model to use (allowed values: sora-2, sora-2-pro). Defaults to `sora-2`."
+          },
+          "prompt": {
+            "type": "string",
+            "maxLength": 32000,
+            "minLength": 1,
+            "description": "Text prompt that describes the video to generate."
+          },
+          "input_reference": {
+            "$ref": "#/components/schemas/ImageRefParam-2",
+            "description": "Optional reference object that guides generation. Provide exactly one of `image_url` or `file_id`."
+          },
+          "seconds": {
+            "$ref": "#/components/schemas/VideoSeconds",
+            "description": "Clip duration in seconds (allowed values: 4, 8, 12). Defaults to 4 seconds."
+          },
+          "size": {
+            "$ref": "#/components/schemas/VideoSize",
+            "description": "Output resolution formatted as width x height (allowed values: 720x1280, 1280x720, 1024x1792, 1792x1024). Defaults to 720x1280."
+          }
+        },
+        "type": "object",
+        "required": [
+          "prompt"
+        ],
+        "title": "Create video JSON request",
+        "description": "JSON parameters for creating a new video generation job."
+      },
+      "CreateVideoCharacterBody": {
+        "properties": {
+          "video": {
+            "type": "string",
+            "format": "binary",
+            "description": "Video file used to create a character."
+          },
+          "name": {
+            "type": "string",
+            "maxLength": 80,
+            "minLength": 1,
+            "description": "Display name for this API character."
+          }
+        },
+        "type": "object",
+        "required": [
+          "video",
+          "name"
+        ],
+        "title": "Create character request",
+        "description": "Parameters for creating a character from an uploaded video."
+      },
+      "VideoCharacterResource": {
+        "properties": {
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Identifier for the character creation cameo."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "name": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Display name for the character."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (in seconds) when the character was created."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "name",
+          "created_at"
+        ]
+      },
+      "VideoReferenceInputParam": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The identifier of the completed video.",
+            "example": "video_123"
+          }
+        },
+        "type": "object",
+        "required": [
+          "id"
+        ],
+        "description": "Reference to the completed video."
+      },
+      "CreateVideoEditMultipartBody": {
+        "properties": {
+          "video": {
+            "oneOf": [
+              {
+                "type": "string",
+                "format": "binary",
+                "description": "Reference to the completed video to edit."
+              },
+              {
+                "$ref": "#/components/schemas/VideoReferenceInputParam",
+                "description": "Reference to the completed video to edit."
+              }
+            ]
+          },
+          "prompt": {
+            "type": "string",
+            "maxLength": 32000,
+            "minLength": 1,
+            "description": "Text prompt that describes how to edit the source video."
+          }
+        },
+        "type": "object",
+        "required": [
+          "video",
+          "prompt"
+        ],
+        "title": "Create video edit multipart request",
+        "description": "Parameters for editing an existing generated video."
+      },
+      "CreateVideoEditJsonBody": {
+        "properties": {
+          "video": {
+            "$ref": "#/components/schemas/VideoReferenceInputParam",
+            "description": "Reference to the completed video to edit."
+          },
+          "prompt": {
+            "type": "string",
+            "maxLength": 32000,
+            "minLength": 1,
+            "description": "Text prompt that describes how to edit the source video."
+          }
+        },
+        "type": "object",
+        "required": [
+          "video",
+          "prompt"
+        ],
+        "title": "Create video edit JSON request",
+        "description": "JSON parameters for editing an existing generated video."
+      },
+      "CreateVideoExtendMultipartBody": {
+        "properties": {
+          "video": {
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/VideoReferenceInputParam",
+                "description": "Reference to the completed video to extend."
+              },
+              {
+                "type": "string",
+                "format": "binary",
+                "description": "Reference to the completed video to extend."
+              }
+            ]
+          },
+          "prompt": {
+            "type": "string",
+            "maxLength": 32000,
+            "minLength": 1,
+            "description": "Updated text prompt that directs the extension generation."
+          },
+          "seconds": {
+            "$ref": "#/components/schemas/VideoSeconds",
+            "description": "Length of the newly generated extension segment in seconds (allowed values: 4, 8, 12, 16, 20)."
+          }
+        },
+        "type": "object",
+        "required": [
+          "video",
+          "prompt",
+          "seconds"
+        ],
+        "title": "Create video extension multipart request",
+        "description": "Multipart parameters for extending an existing generated video."
+      },
+      "CreateVideoExtendJsonBody": {
+        "properties": {
+          "video": {
+            "$ref": "#/components/schemas/VideoReferenceInputParam",
+            "description": "Reference to the completed video to extend."
+          },
+          "prompt": {
+            "type": "string",
+            "maxLength": 32000,
+            "minLength": 1,
+            "description": "Updated text prompt that directs the extension generation."
+          },
+          "seconds": {
+            "$ref": "#/components/schemas/VideoSeconds",
+            "description": "Length of the newly generated extension segment in seconds (allowed values: 4, 8, 12, 16, 20)."
+          }
+        },
+        "type": "object",
+        "required": [
+          "video",
+          "prompt",
+          "seconds"
+        ],
+        "title": "Create video extension JSON request",
+        "description": "JSON parameters for extending an existing generated video."
+      },
+      "DeletedVideoResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "video.deleted"
+            ],
+            "description": "The object type that signals the deletion response.",
+            "default": "video.deleted",
+            "x-stainless-const": true
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Indicates that the video resource was deleted."
+          },
+          "id": {
+            "type": "string",
+            "description": "Identifier of the deleted video."
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "deleted",
+          "id"
+        ],
+        "title": "Deleted video response",
+        "description": "Confirmation payload returned after deleting a video."
+      },
+      "VideoContentVariant": {
+        "type": "string",
+        "enum": [
+          "video",
+          "thumbnail",
+          "spritesheet"
+        ]
+      },
+      "CreateVideoRemixBody": {
+        "properties": {
+          "prompt": {
+            "type": "string",
+            "maxLength": 32000,
+            "minLength": 1,
+            "description": "Updated text prompt that directs the remix generation."
+          }
+        },
+        "type": "object",
+        "required": [
+          "prompt"
+        ],
+        "title": "Create video remix request",
+        "description": "Parameters for remixing an existing generated video."
+      },
+      "TruncationEnum": {
+        "type": "string",
+        "enum": [
+          "auto",
+          "disabled"
+        ]
+      },
+      "PersonalityEnum": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "string",
+            "enum": [
+              "friendly",
+              "pragmatic"
+            ]
+          }
+        ]
+      },
+      "TokenCountsBody": {
+        "properties": {
+          "model": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Model ID used to generate the response, like `gpt-4o` or `o3`. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the [model guide](https://developers.openai.com/api/docs/models) to browse and compare available models."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "input": {
+            "anyOf": [
+              {
+                "oneOf": [
+                  {
+                    "type": "string",
+                    "maxLength": 10485760,
+                    "description": "A text input to the model, equivalent to a text input with the `user` role."
+                  },
+                  {
+                    "items": {
+                      "$ref": "#/components/schemas/InputItem"
+                    },
+                    "type": "array",
+                    "maxItems": 131072,
+                    "description": "A list of one or many input items to the model, containing different content types."
+                  }
+                ],
+                "description": "Text, image, or file inputs to the model, used to generate a response"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "previous_response_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](https://developers.openai.com/api/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`.",
+                "example": "resp_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "tools": {
+            "anyOf": [
+              {
+                "items": {
+                  "$ref": "#/components/schemas/Tool"
+                },
+                "type": "array",
+                "description": "An array of tools the model may call while generating a response. You can specify which tool to use by setting the `tool_choice` parameter."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "text": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ResponseTextParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "reasoning": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Reasoning",
+                "description": "**gpt-5 and o-series models only** Configuration options for [reasoning models](https://developers.openai.com/api/docs/guides/reasoning)."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "truncation": {
+            "$ref": "#/components/schemas/TruncationEnum",
+            "description": "The truncation strategy to use for the model response. - `auto`: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. - `disabled` (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error.",
+            "deprecated": true
+          },
+          "instructions": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "A system (or developer) message inserted into the model's context.\nWhen used along with `previous_response_id`, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "personality": {
+            "$ref": "#/components/schemas/PersonalityEnum",
+            "description": "A model-owned style preset to apply to this request. Omit this parameter to use the model's default style. Supported values may expand over time. Values must be at most 64 characters."
+          },
+          "conversation": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ConversationParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "tool_choice": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ToolChoiceParam",
+                "description": "Controls which tool the model should use, if any."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "parallel_tool_calls": {
+            "anyOf": [
+              {
+                "type": "boolean",
+                "description": "Whether to allow the model to run tool calls in parallel."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": []
+      },
+      "TokenCountsResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "response.input_tokens"
+            ],
+            "default": "response.input_tokens",
+            "x-stainless-const": true
+          },
+          "input_tokens": {
+            "type": "integer"
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "input_tokens"
+        ],
+        "title": "Token counts",
+        "example": {
+          "object": "response.input_tokens",
+          "input_tokens": 123
+        }
+      },
+      "PromptCacheRetentionEnum": {
+        "type": "string",
+        "enum": [
+          "in_memory",
+          "24h"
+        ]
+      },
+      "ServiceTierEnum": {
+        "type": "string",
+        "enum": [
+          "auto",
+          "default",
+          "fast",
+          "flex",
+          "priority"
+        ]
+      },
+      "CompactResponseMethodPublicBody": {
+        "properties": {
+          "model": {
+            "$ref": "#/components/schemas/ModelIdsCompaction"
+          },
+          "input": {
+            "anyOf": [
+              {
+                "oneOf": [
+                  {
+                    "type": "string",
+                    "maxLength": 10485760,
+                    "description": "A text input to the model, equivalent to a text input with the `user` role."
+                  },
+                  {
+                    "items": {
+                      "$ref": "#/components/schemas/InputItem"
+                    },
+                    "type": "array",
+                    "maxItems": 131072,
+                    "description": "A list of one or many input items to the model, containing different content types."
+                  }
+                ],
+                "description": "Text, image, or file inputs to the model, used to generate a response"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "previous_response_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](https://developers.openai.com/api/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`.",
+                "example": "resp_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "instructions": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "A system (or developer) message inserted into the model's context.\nWhen used along with `previous_response_id`, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "prompt_cache_key": {
+            "anyOf": [
+              {
+                "type": "string",
+                "maxLength": 64,
+                "description": "A key to use when reading from or writing to the prompt cache."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "prompt_cache_retention": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/PromptCacheRetentionEnum",
+                "description": "How long to retain a prompt cache entry created by this request.",
+                "deprecated": true
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "prompt_cache_options": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/PromptCacheOptionsParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "service_tier": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ServiceTierEnum",
+                "description": "Specifies the processing type used for serving the request.   - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.   - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.   - If set to '[flex](https://developers.openai.com/api/docs/guides/flex-processing)', then the request will be processed with the Flex Processing service tier.   - To opt-in to [Fast mode](https://developers.openai.com/api/docs/guides/fast-mode) at the request level, include the `service_tier=fast` or `service_tier=priority` parameter for Responses or Chat Completions. For models with a dedicated Fast tier, either value resolves to `service_tier=fast`; for other models, either value resolves to `service_tier=priority`.   - When not set, the default behavior is 'auto'.\n  When the `service_tier` parameter is set, the response body will include the `service_tier` value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "model"
+        ]
+      },
+      "ItemField": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/Message"
+          },
+          {
+            "$ref": "#/components/schemas/Program"
+          },
+          {
+            "$ref": "#/components/schemas/ProgramOutput"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/ToolSearchCall"
+          },
+          {
+            "$ref": "#/components/schemas/ToolSearchOutput"
+          },
+          {
+            "$ref": "#/components/schemas/AdditionalTools"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionToolCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/FileSearchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/WebSearchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/ImageGenToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/ComputerToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/ComputerToolCallOutputResource"
+          },
+          {
+            "$ref": "#/components/schemas/ReasoningItem"
+          },
+          {
+            "$ref": "#/components/schemas/CompactionBody"
+          },
+          {
+            "$ref": "#/components/schemas/CodeInterpreterToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/LocalShellToolCall",
+            "deprecated": true
+          },
+          {
+            "$ref": "#/components/schemas/LocalShellToolCallOutput",
+            "deprecated": true
+          },
+          {
+            "$ref": "#/components/schemas/FunctionShellCall"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionShellCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/ApplyPatchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/ApplyPatchToolCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/MCPListTools"
+          },
+          {
+            "$ref": "#/components/schemas/MCPApprovalRequest"
+          },
+          {
+            "$ref": "#/components/schemas/MCPApprovalResponseResource"
+          },
+          {
+            "$ref": "#/components/schemas/MCPToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/CustomToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/CustomToolCallOutput"
+          }
+        ],
+        "description": "An item representing a message, tool call, tool output, reasoning, or other response element.",
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "CompactResource": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique identifier for the compacted response."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "response.compaction"
+            ],
+            "description": "The object type. Always `response.compaction`.",
+            "default": "response.compaction",
+            "x-stainless-const": true
+          },
+          "output": {
+            "items": {
+              "$ref": "#/components/schemas/ItemField"
+            },
+            "type": "array",
+            "description": "The compacted list of output items."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (in seconds) when the compacted conversation was created."
+          },
+          "usage": {
+            "$ref": "#/components/schemas/ResponseUsage",
+            "description": "Token accounting for the compaction pass, including cached, reasoning, and total tokens."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "object",
+          "output",
+          "created_at",
+          "usage"
+        ],
+        "title": "The compacted response object",
+        "example": {
+          "id": "resp_001",
+          "object": "response.compaction",
+          "output": [
+            {
+              "type": "message",
+              "role": "user",
+              "content": [
+                {
+                  "type": "input_text",
+                  "text": "Summarize our launch checklist from last week."
+                }
+              ]
+            },
+            {
+              "type": "message",
+              "role": "user",
+              "content": [
+                {
+                  "type": "input_text",
+                  "text": "You are performing a CONTEXT CHECKPOINT COMPACTION..."
+                }
+              ]
+            },
+            {
+              "type": "compaction",
+              "id": "cmp_001",
+              "encrypted_content": "encrypted-summary"
+            }
+          ],
+          "created_at": 1731459200,
+          "usage": {
+            "input_tokens": 42897,
+            "output_tokens": 12000,
+            "total_tokens": 54912
+          }
+        }
+      },
+      "SkillResource": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Unique identifier for the skill."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "skill"
+            ],
+            "description": "The object type, which is `skill`.",
+            "default": "skill",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "Name of the skill."
+          },
+          "description": {
+            "type": "string",
+            "description": "Description of the skill."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (seconds) for when the skill was created."
+          },
+          "default_version": {
+            "type": "string",
+            "description": "Default version for the skill."
+          },
+          "latest_version": {
+            "type": "string",
+            "description": "Latest version for the skill."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "object",
+          "name",
+          "description",
+          "created_at",
+          "default_version",
+          "latest_version"
+        ]
+      },
+      "SkillListResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "description": "The type of object returned, must be `list`.",
+            "default": "list",
+            "x-stainless-const": true
+          },
+          "data": {
+            "items": {
+              "$ref": "#/components/schemas/SkillResource"
+            },
+            "type": "array",
+            "description": "A list of items"
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the first item in the list."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the last item in the list."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more items available."
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ]
+      },
+      "CreateSkillBody": {
+        "properties": {
+          "files": {
+            "oneOf": [
+              {
+                "items": {
+                  "type": "string",
+                  "format": "binary"
+                },
+                "type": "array",
+                "maxItems": 500,
+                "description": "Skill files to upload (directory upload) or a single zip file."
+              },
+              {
+                "type": "string",
+                "format": "binary",
+                "description": "Skill zip file to upload."
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "files"
+        ],
+        "title": "Create skill request",
+        "description": "Uploads a skill either as a directory (multipart `files[]`) or as a single zip file."
+      },
+      "SetDefaultSkillVersionBody": {
+        "properties": {
+          "default_version": {
+            "type": "string",
+            "description": "The skill version number to set as default."
+          }
+        },
+        "type": "object",
+        "required": [
+          "default_version"
+        ],
+        "title": "Update skill request",
+        "description": "Updates the default version pointer for a skill."
+      },
+      "DeletedSkillResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "skill.deleted"
+            ],
+            "default": "skill.deleted",
+            "x-stainless-const": true
+          },
+          "deleted": {
+            "type": "boolean"
+          },
+          "id": {
+            "type": "string"
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "deleted",
+          "id"
+        ]
+      },
+      "SkillVersionResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "skill.version"
+            ],
+            "description": "The object type, which is `skill.version`.",
+            "default": "skill.version",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "Unique identifier for the skill version."
+          },
+          "skill_id": {
+            "type": "string",
+            "description": "Identifier of the skill for this version."
+          },
+          "version": {
+            "type": "string",
+            "description": "Version number for this skill."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (seconds) for when the version was created."
+          },
+          "name": {
+            "type": "string",
+            "description": "Name of the skill version."
+          },
+          "description": {
+            "type": "string",
+            "description": "Description of the skill version."
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "id",
+          "skill_id",
+          "version",
+          "created_at",
+          "name",
+          "description"
+        ]
+      },
+      "SkillVersionListResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "description": "The type of object returned, must be `list`.",
+            "default": "list",
+            "x-stainless-const": true
+          },
+          "data": {
+            "items": {
+              "$ref": "#/components/schemas/SkillVersionResource"
+            },
+            "type": "array",
+            "description": "A list of items"
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the first item in the list."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the last item in the list."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more items available."
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ]
+      },
+      "CreateSkillVersionBody": {
+        "properties": {
+          "files": {
+            "oneOf": [
+              {
+                "items": {
+                  "type": "string",
+                  "format": "binary"
+                },
+                "type": "array",
+                "maxItems": 500,
+                "description": "Skill files to upload (directory upload) or a single zip file."
+              },
+              {
+                "type": "string",
+                "format": "binary",
+                "description": "Skill zip file to upload."
+              }
+            ]
+          },
+          "default": {
+            "type": "boolean",
+            "description": "Whether to set this version as the default."
+          }
+        },
+        "type": "object",
+        "required": [
+          "files"
+        ],
+        "title": "Create skill version request",
+        "description": "Uploads a new immutable version of a skill."
+      },
+      "DeletedSkillVersionResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "skill.version.deleted"
+            ],
+            "default": "skill.version.deleted",
+            "x-stainless-const": true
+          },
+          "deleted": {
+            "type": "boolean"
+          },
+          "id": {
+            "type": "string"
+          },
+          "version": {
+            "type": "string",
+            "description": "The deleted skill version."
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "deleted",
+          "id",
+          "version"
+        ]
+      },
+      "ChatkitWorkflowTracing": {
+        "properties": {
+          "enabled": {
+            "type": "boolean",
+            "description": "Indicates whether tracing is enabled."
+          }
+        },
+        "type": "object",
+        "required": [
+          "enabled"
+        ],
+        "title": "Tracing Configuration",
+        "description": "Controls diagnostic tracing during the session."
+      },
+      "ChatkitWorkflow": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Identifier of the workflow backing the session."
+          },
+          "version": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Specific workflow version used for the session. Defaults to null when using the latest deployment."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "state_variables": {
+            "anyOf": [
+              {
+                "additionalProperties": {
+                  "oneOf": [
+                    {
+                      "type": "string"
+                    },
+                    {
+                      "type": "integer"
+                    },
+                    {
+                      "type": "boolean"
+                    },
+                    {
+                      "type": "number"
+                    }
+                  ]
+                },
+                "type": "object",
+                "description": "State variable key-value pairs applied when invoking the workflow. Defaults to null when no overrides were provided.",
+                "x-oaiTypeLabel": "map"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "tracing": {
+            "$ref": "#/components/schemas/ChatkitWorkflowTracing",
+            "description": "Tracing settings applied to the workflow."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "version",
+          "state_variables",
+          "tracing"
+        ],
+        "title": "Workflow",
+        "description": "Workflow metadata and state returned for the session."
+      },
+      "ChatSessionRateLimits": {
+        "properties": {
+          "max_requests_per_1_minute": {
+            "type": "integer",
+            "description": "Maximum allowed requests per one-minute window."
+          }
+        },
+        "type": "object",
+        "required": [
+          "max_requests_per_1_minute"
+        ],
+        "title": "Rate limits",
+        "description": "Active per-minute request limit for the session."
+      },
+      "ChatSessionStatus": {
+        "type": "string",
+        "enum": [
+          "active",
+          "expired",
+          "cancelled"
+        ]
+      },
+      "ChatSessionAutomaticThreadTitling": {
+        "properties": {
+          "enabled": {
+            "type": "boolean",
+            "description": "Whether automatic thread titling is enabled."
+          }
+        },
+        "type": "object",
+        "required": [
+          "enabled"
+        ],
+        "title": "Automatic thread titling",
+        "description": "Automatic thread title preferences for the session."
+      },
+      "ChatSessionFileUpload": {
+        "properties": {
+          "enabled": {
+            "type": "boolean",
+            "description": "Indicates if uploads are enabled for the session."
+          },
+          "max_file_size": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "Maximum upload size in megabytes."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "max_files": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "Maximum number of uploads allowed during the session."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "enabled",
+          "max_file_size",
+          "max_files"
+        ],
+        "title": "File upload settings",
+        "description": "Upload permissions and limits applied to the session."
+      },
+      "ChatSessionHistory": {
+        "properties": {
+          "enabled": {
+            "type": "boolean",
+            "description": "Indicates if chat history is persisted for the session."
+          },
+          "recent_threads": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "Number of prior threads surfaced in history views. Defaults to null when all history is retained."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "enabled",
+          "recent_threads"
+        ],
+        "title": "History settings",
+        "description": "History retention preferences returned for the session."
+      },
+      "ChatSessionChatkitConfiguration": {
+        "properties": {
+          "automatic_thread_titling": {
+            "$ref": "#/components/schemas/ChatSessionAutomaticThreadTitling",
+            "description": "Automatic thread titling preferences."
+          },
+          "file_upload": {
+            "$ref": "#/components/schemas/ChatSessionFileUpload",
+            "description": "Upload settings for the session."
+          },
+          "history": {
+            "$ref": "#/components/schemas/ChatSessionHistory",
+            "description": "History retention configuration."
+          }
+        },
+        "type": "object",
+        "required": [
+          "automatic_thread_titling",
+          "file_upload",
+          "history"
+        ],
+        "title": "ChatKit configuration",
+        "description": "ChatKit configuration for the session."
+      },
+      "ChatSessionResource": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Identifier for the ChatKit session."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "chatkit.session"
+            ],
+            "description": "Type discriminator that is always `chatkit.session`.",
+            "default": "chatkit.session",
+            "x-stainless-const": true
+          },
+          "expires_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (in seconds) for when the session expires."
+          },
+          "client_secret": {
+            "type": "string",
+            "description": "Ephemeral client secret that authenticates session requests."
+          },
+          "workflow": {
+            "$ref": "#/components/schemas/ChatkitWorkflow",
+            "description": "Workflow metadata for the session."
+          },
+          "user": {
+            "type": "string",
+            "description": "User identifier associated with the session."
+          },
+          "rate_limits": {
+            "$ref": "#/components/schemas/ChatSessionRateLimits",
+            "description": "Resolved rate limit values."
+          },
+          "max_requests_per_1_minute": {
+            "type": "integer",
+            "description": "Convenience copy of the per-minute request limit."
+          },
+          "status": {
+            "$ref": "#/components/schemas/ChatSessionStatus",
+            "description": "Current lifecycle state of the session."
+          },
+          "chatkit_configuration": {
+            "$ref": "#/components/schemas/ChatSessionChatkitConfiguration",
+            "description": "Resolved ChatKit feature configuration for the session."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "object",
+          "expires_at",
+          "client_secret",
+          "workflow",
+          "user",
+          "rate_limits",
+          "max_requests_per_1_minute",
+          "status",
+          "chatkit_configuration"
+        ],
+        "title": "The chat session object",
+        "description": "Represents a ChatKit session and its resolved configuration.",
+        "example": {
+          "id": "cksess_123",
+          "object": "chatkit.session",
+          "client_secret": "ek_token_123",
+          "expires_at": 1712349876,
+          "workflow": {
+            "id": "workflow_alpha",
+            "version": "2024-10-01"
+          },
+          "user": "user_789",
+          "rate_limits": {
+            "max_requests_per_1_minute": 60
+          },
+          "max_requests_per_1_minute": 60,
+          "status": "cancelled",
+          "chatkit_configuration": {
+            "automatic_thread_titling": {
+              "enabled": true
+            },
+            "file_upload": {
+              "enabled": true,
+              "max_file_size": 16,
+              "max_files": 20
+            },
+            "history": {
+              "enabled": true,
+              "recent_threads": 10
+            }
+          }
+        }
+      },
+      "WorkflowTracingParam": {
+        "properties": {
+          "enabled": {
+            "type": "boolean",
+            "description": "Whether tracing is enabled during the session. Defaults to true."
+          }
+        },
+        "type": "object",
+        "required": [],
+        "title": "Tracing Configuration",
+        "description": "Controls diagnostic tracing during the session."
+      },
+      "WorkflowParam": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Identifier for the workflow invoked by the session."
+          },
+          "version": {
+            "type": "string",
+            "description": "Specific workflow version to run. Defaults to the latest deployed version."
+          },
+          "state_variables": {
+            "additionalProperties": {
+              "oneOf": [
+                {
+                  "type": "string",
+                  "maxLength": 10485760
+                },
+                {
+                  "type": "integer"
+                },
+                {
+                  "type": "boolean"
+                },
+                {
+                  "type": "number"
+                }
+              ]
+            },
+            "type": "object",
+            "maxProperties": 64,
+            "description": "State variables forwarded to the workflow. Keys may be up to 64 characters, values must be primitive types, and the map defaults to an empty object.",
+            "x-oaiTypeLabel": "map"
+          },
+          "tracing": {
+            "$ref": "#/components/schemas/WorkflowTracingParam",
+            "description": "Optional tracing overrides for the workflow invocation. When omitted, tracing is enabled by default."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id"
+        ],
+        "title": "Workflow settings",
+        "description": "Workflow reference and overrides applied to the chat session."
+      },
+      "ExpiresAfterParam": {
+        "properties": {
+          "anchor": {
+            "type": "string",
+            "enum": [
+              "created_at"
+            ],
+            "description": "Base timestamp used to calculate expiration. Currently fixed to `created_at`.",
+            "default": "created_at",
+            "x-stainless-const": true
+          },
+          "seconds": {
+            "type": "integer",
+            "maximum": 600,
+            "minimum": 1,
+            "format": "int64",
+            "description": "Number of seconds after the anchor when the session expires."
+          }
+        },
+        "type": "object",
+        "required": [
+          "anchor",
+          "seconds"
+        ],
+        "title": "Expiration overrides",
+        "description": "Controls when the session expires relative to an anchor timestamp."
+      },
+      "RateLimitsParam": {
+        "properties": {
+          "max_requests_per_1_minute": {
+            "type": "integer",
+            "minimum": 1,
+            "description": "Maximum number of requests allowed per minute for the session. Defaults to 10."
+          }
+        },
+        "type": "object",
+        "required": [],
+        "title": "Rate limit overrides",
+        "description": "Controls request rate limits for the session."
+      },
+      "AutomaticThreadTitlingParam": {
+        "properties": {
+          "enabled": {
+            "type": "boolean",
+            "description": "Enable automatic thread title generation. Defaults to true."
+          }
+        },
+        "type": "object",
+        "required": [],
+        "title": "Automatic thread titling configuration",
+        "description": "Controls whether ChatKit automatically generates thread titles."
+      },
+      "FileUploadParam": {
+        "properties": {
+          "enabled": {
+            "type": "boolean",
+            "description": "Enable uploads for this session. Defaults to false."
+          },
+          "max_file_size": {
+            "type": "integer",
+            "maximum": 512,
+            "minimum": 1,
+            "description": "Maximum size in megabytes for each uploaded file. Defaults to 512 MB, which is the maximum allowable size."
+          },
+          "max_files": {
+            "type": "integer",
+            "minimum": 1,
+            "description": "Maximum number of files that can be uploaded to the session. Defaults to 10."
+          }
+        },
+        "type": "object",
+        "required": [],
+        "title": "File upload configuration",
+        "description": "Controls whether users can upload files."
+      },
+      "HistoryParam": {
+        "properties": {
+          "enabled": {
+            "type": "boolean",
+            "description": "Enables chat users to access previous ChatKit threads. Defaults to true."
+          },
+          "recent_threads": {
+            "type": "integer",
+            "minimum": 1,
+            "description": "Number of recent ChatKit threads users have access to. Defaults to unlimited when unset."
+          }
+        },
+        "type": "object",
+        "required": [],
+        "title": "Chat history configuration",
+        "description": "Controls how much historical context is retained for the session."
+      },
+      "ChatkitConfigurationParam": {
+        "properties": {
+          "automatic_thread_titling": {
+            "$ref": "#/components/schemas/AutomaticThreadTitlingParam",
+            "description": "Configuration for automatic thread titling. When omitted, automatic thread titling is enabled by default."
+          },
+          "file_upload": {
+            "$ref": "#/components/schemas/FileUploadParam",
+            "description": "Configuration for upload enablement and limits. When omitted, uploads are disabled by default (max_files 10, max_file_size 512 MB)."
+          },
+          "history": {
+            "$ref": "#/components/schemas/HistoryParam",
+            "description": "Configuration for chat history retention. When omitted, history is enabled by default with no limit on recent_threads (null)."
+          }
+        },
+        "type": "object",
+        "required": [],
+        "title": "ChatKit configuration overrides",
+        "description": "Optional per-session configuration settings for ChatKit behavior."
+      },
+      "CreateChatSessionBody": {
+        "properties": {
+          "workflow": {
+            "$ref": "#/components/schemas/WorkflowParam",
+            "description": "Workflow that powers the session."
+          },
+          "user": {
+            "type": "string",
+            "minLength": 1,
+            "description": "A free-form string that identifies your end user; ensures this Session can access other objects that have the same `user` scope."
+          },
+          "expires_after": {
+            "$ref": "#/components/schemas/ExpiresAfterParam",
+            "description": "Optional override for session expiration timing in seconds from creation. Defaults to 10 minutes."
+          },
+          "rate_limits": {
+            "$ref": "#/components/schemas/RateLimitsParam",
+            "description": "Optional override for per-minute request limits. When omitted, defaults to 10."
+          },
+          "chatkit_configuration": {
+            "$ref": "#/components/schemas/ChatkitConfigurationParam",
+            "description": "Optional overrides for ChatKit runtime configuration features"
+          }
+        },
+        "type": "object",
+        "required": [
+          "workflow",
+          "user"
+        ],
+        "title": "Create chat session request",
+        "description": "Parameters for provisioning a new ChatKit session."
+      },
+      "UserMessageInputText": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_text"
+            ],
+            "description": "Type discriminator that is always `input_text`.",
+            "default": "input_text",
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string",
+            "description": "Plain-text content supplied by the user."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "text"
+        ],
+        "title": "User message input",
+        "description": "Text block that a user contributed to the thread."
+      },
+      "UserMessageQuotedText": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "quoted_text"
+            ],
+            "description": "Type discriminator that is always `quoted_text`.",
+            "default": "quoted_text",
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string",
+            "description": "Quoted text content."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "text"
+        ],
+        "title": "User message quoted text",
+        "description": "Quoted snippet that the user referenced in their message."
+      },
+      "AttachmentType": {
+        "type": "string",
+        "enum": [
+          "image",
+          "file"
+        ]
+      },
+      "Attachment": {
+        "properties": {
+          "type": {
+            "$ref": "#/components/schemas/AttachmentType",
+            "description": "Attachment discriminator."
+          },
+          "id": {
+            "type": "string",
+            "description": "Identifier for the attachment."
+          },
+          "name": {
+            "type": "string",
+            "description": "Original display name for the attachment."
+          },
+          "mime_type": {
+            "type": "string",
+            "description": "MIME type of the attachment."
+          },
+          "preview_url": {
+            "anyOf": [
+              {
+                "type": "string",
+                "format": "uri",
+                "description": "Preview URL for rendering the attachment inline."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "name",
+          "mime_type",
+          "preview_url"
+        ],
+        "title": "Attachment",
+        "description": "Attachment metadata included on thread items."
+      },
+      "ToolChoice": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Identifier of the requested tool."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id"
+        ],
+        "title": "Tool choice",
+        "description": "Tool selection that the assistant should honor when executing the item."
+      },
+      "InferenceOptions": {
+        "properties": {
+          "tool_choice": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ToolChoice",
+                "description": "Preferred tool to invoke. Defaults to null when ChatKit should auto-select."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "model": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Model name that generated the response. Defaults to null when using the session default."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "tool_choice",
+          "model"
+        ],
+        "title": "Inference options",
+        "description": "Model and tool overrides applied when generating the assistant response."
+      },
+      "UserMessageItem": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Identifier of the thread item."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "chatkit.thread_item"
+            ],
+            "description": "Type discriminator that is always `chatkit.thread_item`.",
+            "default": "chatkit.thread_item",
+            "x-stainless-const": true
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (in seconds) for when the item was created."
+          },
+          "thread_id": {
+            "type": "string",
+            "description": "Identifier of the parent thread."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "chatkit.user_message"
+            ],
+            "default": "chatkit.user_message",
+            "x-stainless-const": true
+          },
+          "content": {
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/UserMessageInputText"
+                },
+                {
+                  "$ref": "#/components/schemas/UserMessageQuotedText"
+                }
+              ],
+              "description": "Content blocks that comprise a user message.",
+              "discriminator": {
+                "propertyName": "type"
+              }
+            },
+            "type": "array",
+            "description": "Ordered content elements supplied by the user."
+          },
+          "attachments": {
+            "items": {
+              "$ref": "#/components/schemas/Attachment"
+            },
+            "type": "array",
+            "description": "Attachments associated with the user message. Defaults to an empty list."
+          },
+          "inference_options": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/InferenceOptions",
+                "description": "Inference overrides applied to the message. Defaults to null when unset."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "object",
+          "created_at",
+          "thread_id",
+          "type",
+          "content",
+          "attachments",
+          "inference_options"
+        ],
+        "title": "User Message Item",
+        "description": "User-authored messages within a thread."
+      },
+      "FileAnnotationSource": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "file"
+            ],
+            "description": "Type discriminator that is always `file`.",
+            "default": "file",
+            "x-stainless-const": true
+          },
+          "filename": {
+            "type": "string",
+            "description": "Filename referenced by the annotation."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "filename"
+        ],
+        "title": "File annotation source",
+        "description": "Attachment source referenced by an annotation."
+      },
+      "FileAnnotation": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "file"
+            ],
+            "description": "Type discriminator that is always `file` for this annotation.",
+            "default": "file",
+            "x-stainless-const": true
+          },
+          "source": {
+            "$ref": "#/components/schemas/FileAnnotationSource",
+            "description": "File attachment referenced by the annotation."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "source"
+        ],
+        "title": "File annotation",
+        "description": "Annotation that references an uploaded file."
+      },
+      "UrlAnnotationSource": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "url"
+            ],
+            "description": "Type discriminator that is always `url`.",
+            "default": "url",
+            "x-stainless-const": true
+          },
+          "url": {
+            "type": "string",
+            "format": "uri",
+            "description": "URL referenced by the annotation."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "url"
+        ],
+        "title": "URL annotation source",
+        "description": "URL backing an annotation entry."
+      },
+      "UrlAnnotation": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "url"
+            ],
+            "description": "Type discriminator that is always `url` for this annotation.",
+            "default": "url",
+            "x-stainless-const": true
+          },
+          "source": {
+            "$ref": "#/components/schemas/UrlAnnotationSource",
+            "description": "URL referenced by the annotation."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "source"
+        ],
+        "title": "URL annotation",
+        "description": "Annotation that references a URL."
+      },
+      "ResponseOutputText": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "output_text"
+            ],
+            "description": "Type discriminator that is always `output_text`.",
+            "default": "output_text",
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string",
+            "description": "Assistant generated text."
+          },
+          "annotations": {
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/FileAnnotation"
+                },
+                {
+                  "$ref": "#/components/schemas/UrlAnnotation"
+                }
+              ],
+              "description": "Annotation object describing a cited source.",
+              "discriminator": {
+                "propertyName": "type"
+              }
+            },
+            "type": "array",
+            "description": "Ordered list of annotations attached to the response text."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "text",
+          "annotations"
+        ],
+        "title": "Assistant message content",
+        "description": "Assistant response text accompanied by optional annotations."
+      },
+      "AssistantMessageItem": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Identifier of the thread item."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "chatkit.thread_item"
+            ],
+            "description": "Type discriminator that is always `chatkit.thread_item`.",
+            "default": "chatkit.thread_item",
+            "x-stainless-const": true
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (in seconds) for when the item was created."
+          },
+          "thread_id": {
+            "type": "string",
+            "description": "Identifier of the parent thread."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "chatkit.assistant_message"
+            ],
+            "description": "Type discriminator that is always `chatkit.assistant_message`.",
+            "default": "chatkit.assistant_message",
+            "x-stainless-const": true
+          },
+          "content": {
+            "items": {
+              "$ref": "#/components/schemas/ResponseOutputText"
+            },
+            "type": "array",
+            "description": "Ordered assistant response segments."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "object",
+          "created_at",
+          "thread_id",
+          "type",
+          "content"
+        ],
+        "title": "Assistant message",
+        "description": "Assistant-authored message within a thread."
+      },
+      "WidgetMessageItem": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Identifier of the thread item."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "chatkit.thread_item"
+            ],
+            "description": "Type discriminator that is always `chatkit.thread_item`.",
+            "default": "chatkit.thread_item",
+            "x-stainless-const": true
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (in seconds) for when the item was created."
+          },
+          "thread_id": {
+            "type": "string",
+            "description": "Identifier of the parent thread."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "chatkit.widget"
+            ],
+            "description": "Type discriminator that is always `chatkit.widget`.",
+            "default": "chatkit.widget",
+            "x-stainless-const": true
+          },
+          "widget": {
+            "type": "string",
+            "description": "Serialized widget payload rendered in the UI."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "object",
+          "created_at",
+          "thread_id",
+          "type",
+          "widget"
+        ],
+        "title": "Widget message",
+        "description": "Thread item that renders a widget payload."
+      },
+      "ClientToolCallStatus": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed"
+        ]
+      },
+      "ClientToolCallItem": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Identifier of the thread item."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "chatkit.thread_item"
+            ],
+            "description": "Type discriminator that is always `chatkit.thread_item`.",
+            "default": "chatkit.thread_item",
+            "x-stainless-const": true
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (in seconds) for when the item was created."
+          },
+          "thread_id": {
+            "type": "string",
+            "description": "Identifier of the parent thread."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "chatkit.client_tool_call"
+            ],
+            "description": "Type discriminator that is always `chatkit.client_tool_call`.",
+            "default": "chatkit.client_tool_call",
+            "x-stainless-const": true
+          },
+          "status": {
+            "$ref": "#/components/schemas/ClientToolCallStatus",
+            "description": "Execution status for the tool call."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "Identifier for the client tool call."
+          },
+          "name": {
+            "type": "string",
+            "description": "Tool name that was invoked."
+          },
+          "arguments": {
+            "type": "string",
+            "description": "JSON-encoded arguments that were sent to the tool."
+          },
+          "output": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "JSON-encoded output captured from the tool. Defaults to null while execution is in progress."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "object",
+          "created_at",
+          "thread_id",
+          "type",
+          "status",
+          "call_id",
+          "name",
+          "arguments",
+          "output"
+        ],
+        "title": "Client tool call",
+        "description": "Record of a client side tool invocation initiated by the assistant."
+      },
+      "TaskType": {
+        "type": "string",
+        "enum": [
+          "custom",
+          "thought"
+        ]
+      },
+      "TaskItem": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Identifier of the thread item."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "chatkit.thread_item"
+            ],
+            "description": "Type discriminator that is always `chatkit.thread_item`.",
+            "default": "chatkit.thread_item",
+            "x-stainless-const": true
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (in seconds) for when the item was created."
+          },
+          "thread_id": {
+            "type": "string",
+            "description": "Identifier of the parent thread."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "chatkit.task"
+            ],
+            "description": "Type discriminator that is always `chatkit.task`.",
+            "default": "chatkit.task",
+            "x-stainless-const": true
+          },
+          "task_type": {
+            "$ref": "#/components/schemas/TaskType",
+            "description": "Subtype for the task."
+          },
+          "heading": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Optional heading for the task. Defaults to null when not provided."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "summary": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Optional summary that describes the task. Defaults to null when omitted."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "object",
+          "created_at",
+          "thread_id",
+          "type",
+          "task_type",
+          "heading",
+          "summary"
+        ],
+        "title": "Task item",
+        "description": "Task emitted by the workflow to show progress and status updates."
+      },
+      "TaskGroupTask": {
+        "properties": {
+          "type": {
+            "$ref": "#/components/schemas/TaskType",
+            "description": "Subtype for the grouped task."
+          },
+          "heading": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Optional heading for the grouped task. Defaults to null when not provided."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "summary": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Optional summary that describes the grouped task. Defaults to null when omitted."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "heading",
+          "summary"
+        ],
+        "title": "Task group task",
+        "description": "Task entry that appears within a TaskGroup."
+      },
+      "TaskGroupItem": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Identifier of the thread item."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "chatkit.thread_item"
+            ],
+            "description": "Type discriminator that is always `chatkit.thread_item`.",
+            "default": "chatkit.thread_item",
+            "x-stainless-const": true
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (in seconds) for when the item was created."
+          },
+          "thread_id": {
+            "type": "string",
+            "description": "Identifier of the parent thread."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "chatkit.task_group"
+            ],
+            "description": "Type discriminator that is always `chatkit.task_group`.",
+            "default": "chatkit.task_group",
+            "x-stainless-const": true
+          },
+          "tasks": {
+            "items": {
+              "$ref": "#/components/schemas/TaskGroupTask"
+            },
+            "type": "array",
+            "description": "Tasks included in the group."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "object",
+          "created_at",
+          "thread_id",
+          "type",
+          "tasks"
+        ],
+        "title": "Task group",
+        "description": "Collection of workflow tasks grouped together in the thread."
+      },
+      "ThreadItem": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/UserMessageItem"
+          },
+          {
+            "$ref": "#/components/schemas/AssistantMessageItem"
+          },
+          {
+            "$ref": "#/components/schemas/WidgetMessageItem"
+          },
+          {
+            "$ref": "#/components/schemas/ClientToolCallItem"
+          },
+          {
+            "$ref": "#/components/schemas/TaskItem"
+          },
+          {
+            "$ref": "#/components/schemas/TaskGroupItem"
+          }
+        ],
+        "title": "The thread item",
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "ThreadItemListResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "description": "The type of object returned, must be `list`.",
+            "default": "list",
+            "x-stainless-const": true
+          },
+          "data": {
+            "items": {
+              "$ref": "#/components/schemas/ThreadItem"
+            },
+            "type": "array",
+            "description": "A list of items"
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the first item in the list."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the last item in the list."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more items available."
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "title": "Thread Items",
+        "description": "A paginated list of thread items rendered for the ChatKit API."
+      },
+      "ActiveStatus": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "active"
+            ],
+            "description": "Status discriminator that is always `active`.",
+            "default": "active",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Active thread status",
+        "description": "Indicates that a thread is active."
+      },
+      "LockedStatus": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "locked"
+            ],
+            "description": "Status discriminator that is always `locked`.",
+            "default": "locked",
+            "x-stainless-const": true
+          },
+          "reason": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Reason that the thread was locked. Defaults to null when no reason is recorded."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "reason"
+        ],
+        "title": "Locked thread status",
+        "description": "Indicates that a thread is locked and cannot accept new input."
+      },
+      "ClosedStatus": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "closed"
+            ],
+            "description": "Status discriminator that is always `closed`.",
+            "default": "closed",
+            "x-stainless-const": true
+          },
+          "reason": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Reason that the thread was closed. Defaults to null when no reason is recorded."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "reason"
+        ],
+        "title": "Closed thread status",
+        "description": "Indicates that a thread has been closed."
+      },
+      "ThreadResource": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Identifier of the thread."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "chatkit.thread"
+            ],
+            "description": "Type discriminator that is always `chatkit.thread`.",
+            "default": "chatkit.thread",
+            "x-stainless-const": true
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (in seconds) for when the thread was created."
+          },
+          "title": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Optional human-readable title for the thread. Defaults to null when no title has been generated."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/ActiveStatus"
+              },
+              {
+                "$ref": "#/components/schemas/LockedStatus"
+              },
+              {
+                "$ref": "#/components/schemas/ClosedStatus"
+              }
+            ],
+            "description": "Current status for the thread. Defaults to `active` for newly created threads.",
+            "discriminator": {
+              "propertyName": "type"
+            }
+          },
+          "user": {
+            "type": "string",
+            "description": "Free-form string that identifies your end user who owns the thread."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "object",
+          "created_at",
+          "title",
+          "status",
+          "user"
+        ],
+        "title": "The thread object",
+        "description": "Represents a ChatKit thread and its current status.",
+        "example": {
+          "id": "cthr_def456",
+          "object": "chatkit.thread",
+          "created_at": 1712345600,
+          "title": "Demo feedback",
+          "status": {
+            "type": "active"
+          },
+          "user": "user_456"
+        }
+      },
+      "DeletedThreadResource": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "Identifier of the deleted thread."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "chatkit.thread.deleted"
+            ],
+            "description": "Type discriminator that is always `chatkit.thread.deleted`.",
+            "default": "chatkit.thread.deleted",
+            "x-stainless-const": true
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Indicates that the thread has been deleted."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ],
+        "title": "Deleted thread",
+        "description": "Confirmation payload returned after deleting a thread."
+      },
+      "ThreadListResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "description": "The type of object returned, must be `list`.",
+            "default": "list",
+            "x-stainless-const": true
+          },
+          "data": {
+            "items": {
+              "$ref": "#/components/schemas/ThreadResource"
+            },
+            "type": "array",
+            "description": "A list of items"
+          },
+          "first_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the first item in the list."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "last_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the last item in the list."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more items available."
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "title": "Threads",
+        "description": "A paginated list of ChatKit threads."
+      },
+      "EnvironmentTypeResource": {
+        "type": "string",
+        "enum": [
+          "openai_hosted",
+          "self_hosted"
+        ],
+        "description": "The kind of execution environment."
+      },
+      "EnvironmentStatusResource": {
+        "type": "string",
+        "enum": [
+          "pending",
+          "connected",
+          "disconnected",
+          "expired",
+          "failed"
+        ],
+        "description": "The public lifecycle status of an execution environment."
+      },
+      "HostedEnvironmentFileResourceFileId": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "file_id"
+            ],
+            "default": "file_id",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `file_id`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The session-scoped ID of the file in the execution environment."
+          },
+          "file_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the uploaded file."
+          },
+          "path": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The file's absolute path inside the environment."
+          },
+          "size_bytes": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "description": "The decoded file size in bytes."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "file_id",
+          "path",
+          "size_bytes"
+        ],
+        "additionalProperties": false,
+        "description": "A file copied from the OpenAI Files API."
+      },
+      "HostedEnvironmentFileResourceInline": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "inline"
+            ],
+            "default": "inline",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `inline`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The session-scoped ID of the file in the execution environment."
+          },
+          "path": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The file's absolute path inside the environment."
+          },
+          "size_bytes": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "description": "The decoded file size in bytes."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "path",
+          "size_bytes"
+        ],
+        "additionalProperties": false,
+        "description": "A file supplied inline when the session was created."
+      },
+      "HostedEnvironmentFileResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/HostedEnvironmentFileResourceFileId"
+          },
+          {
+            "$ref": "#/components/schemas/HostedEnvironmentFileResourceInline"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "file_id": "#/components/schemas/HostedEnvironmentFileResourceFileId",
+            "inline": "#/components/schemas/HostedEnvironmentFileResourceInline"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "file_id",
+          "inline"
+        ],
+        "description": "Metadata for a file materialized in an OpenAI-hosted execution environment."
+      },
+      "HostedSkillResourceSkillReference": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "skill_reference"
+            ],
+            "default": "skill_reference",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `skill_reference`."
+          },
+          "skill_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The referenced skill ID."
+          },
+          "version": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The concrete skill version installed for this session."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The installed skill name."
+          },
+          "description": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The installed skill description."
+          }
+        },
+        "required": [
+          "type",
+          "skill_id",
+          "version",
+          "name",
+          "description"
+        ],
+        "additionalProperties": false,
+        "description": "A skill installed from the Skills API."
+      },
+      "HostedSkillResourceInline": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "inline"
+            ],
+            "default": "inline",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `inline`."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The installed skill name."
+          },
+          "description": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The installed skill description."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "description"
+        ],
+        "additionalProperties": false,
+        "description": "A skill installed from an inline ZIP archive."
+      },
+      "HostedSkillResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/HostedSkillResourceSkillReference"
+          },
+          {
+            "$ref": "#/components/schemas/HostedSkillResourceInline"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "skill_reference": "#/components/schemas/HostedSkillResourceSkillReference",
+            "inline": "#/components/schemas/HostedSkillResourceInline"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "skill_reference",
+          "inline"
+        ],
+        "description": "A skill installed in an OpenAI-hosted environment."
+      },
+      "HostedPluginResourceInline": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "inline"
+            ],
+            "default": "inline",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `inline`."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The installed plugin name."
+          },
+          "description": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The installed plugin description."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "description"
+        ],
+        "additionalProperties": false,
+        "description": "A plugin installed from an inline ZIP archive."
+      },
+      "HostedPluginResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/HostedPluginResourceInline"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "inline": "#/components/schemas/HostedPluginResourceInline"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "inline"
+        ],
+        "description": "A plugin installed in an OpenAI-hosted environment."
+      },
+      "PublicEnvironmentResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the environment."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "agent.environment"
+            ],
+            "default": "agent.environment",
+            "x-stainless-const": true,
+            "description": "The object type. Always `agent.environment`."
+          },
+          "type": {
+            "$ref": "#/components/schemas/EnvironmentTypeResource",
+            "description": "Whether the environment is hosted by OpenAI or by the application."
+          },
+          "status": {
+            "$ref": "#/components/schemas/EnvironmentStatusResource",
+            "description": "The current environment connection status."
+          },
+          "files": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/HostedEnvironmentFileResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Files installed in the environment, without their contents."
+          },
+          "skills": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/HostedSkillResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Skills installed in the environment, without their archive contents."
+          },
+          "plugins": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/HostedPluginResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Plugins installed in the environment, without their archive contents."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "type",
+          "status",
+          "files",
+          "skills",
+          "plugins"
+        ],
+        "additionalProperties": false,
+        "description": "Safe metadata for a first-class execution environment."
+      },
+      "ErrorBodyResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The error type."
+          },
+          "code": {
+            "type": "string",
+            "minLength": 0,
+            "description": "A machine-readable error code."
+          },
+          "message": {
+            "type": "string",
+            "minLength": 0,
+            "description": "A human-readable error message."
+          },
+          "param": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The request parameter that caused the error, or null for a request-wide error."
+          }
+        },
+        "required": [
+          "type",
+          "code",
+          "message",
+          "param"
+        ],
+        "additionalProperties": false,
+        "description": "Details about an API error."
+      },
+      "ErrorResponse-2": {
+        "type": "object",
+        "properties": {
+          "error": {
+            "$ref": "#/components/schemas/ErrorBodyResource",
+            "description": "The error returned by the API."
+          }
+        },
+        "required": [
+          "error"
+        ],
+        "additionalProperties": false,
+        "description": "An API error response."
+      },
+      "ListOrderParam": {
+        "type": "string",
+        "enum": [
+          "asc",
+          "desc"
+        ],
+        "x-enumDescriptions": [
+          "Returns resources in ascending order.",
+          "Returns resources in descending order."
+        ],
+        "description": "The order in which paginated resources are returned."
+      },
+      "EnvironmentFilePageObjectResource": {
+        "type": "string",
+        "enum": [
+          "page"
+        ],
+        "default": "page",
+        "x-stainless-const": true,
+        "description": "The object type for a page of files in an execution environment."
+      },
+      "EnvironmentFileResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "agent.environment.file"
+            ],
+            "default": "agent.environment.file",
+            "x-stainless-const": true,
+            "description": "The object type. Always `agent.environment.file`."
+          },
+          "environment_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the environment containing this file."
+          },
+          "path": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The absolute file path inside the environment's workspace."
+          },
+          "size_bytes": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "description": "The file size in bytes."
+          }
+        },
+        "required": [
+          "object",
+          "environment_id",
+          "path",
+          "size_bytes"
+        ],
+        "additionalProperties": false,
+        "description": "A live file in an execution environment."
+      },
+      "EnvironmentFileListResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "$ref": "#/components/schemas/EnvironmentFilePageObjectResource",
+            "description": "The object type. Always `page`."
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/EnvironmentFileResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Files available on the current page."
+          },
+          "next": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The opaque cursor to use when requesting the next page, if any."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether more files follow this page."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "next",
+          "has_more"
+        ],
+        "additionalProperties": false,
+        "description": "A paginated list of live execution environment files."
+      },
+      "HostedEnvironmentFileParamFileId": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "file_id"
+            ],
+            "default": "file_id",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `file_id`."
+          },
+          "file_id": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 256,
+            "description": "The ID of the uploaded file."
+          },
+          "path": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 4096,
+            "description": "The absolute destination path inside `/workspace`."
+          }
+        },
+        "required": [
+          "type",
+          "file_id",
+          "path"
+        ],
+        "additionalProperties": false,
+        "description": "A file previously uploaded through the OpenAI Files API."
+      },
+      "HostedEnvironmentFileParamInline": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "inline"
+            ],
+            "default": "inline",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `inline`."
+          },
+          "data": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 6990508,
+            "description": "The standard-base64-encoded file contents."
+          },
+          "path": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 4096,
+            "description": "The absolute destination path inside `/workspace`."
+          }
+        },
+        "required": [
+          "type",
+          "data",
+          "path"
+        ],
+        "additionalProperties": false,
+        "description": "A file supplied directly as standard-base64 data."
+      },
+      "HostedEnvironmentFileParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/HostedEnvironmentFileParamFileId"
+          },
+          {
+            "$ref": "#/components/schemas/HostedEnvironmentFileParamInline"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "file_id": "#/components/schemas/HostedEnvironmentFileParamFileId",
+            "inline": "#/components/schemas/HostedEnvironmentFileParamInline"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "file_id",
+          "inline"
+        ],
+        "description": "A file materialized in an OpenAI-hosted execution environment."
+      },
+      "SubagentObjectResource": {
+        "type": "string",
+        "enum": [
+          "agent.session.subagent"
+        ],
+        "default": "agent.session.subagent",
+        "x-stainless-const": true,
+        "description": "The object type for a subagent."
+      },
+      "OutputTextResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "output_text"
+            ],
+            "default": "output_text",
+            "x-stainless-const": true,
+            "description": "The content type. Always `output_text`."
+          },
+          "text": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The text produced by the agent."
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ],
+        "additionalProperties": false,
+        "description": "A text content part produced by the agent."
+      },
+      "EncryptedContentResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "encrypted_content"
+            ],
+            "default": "encrypted_content",
+            "x-stainless-const": true,
+            "description": "The content type. Always `encrypted_content`."
+          },
+          "encrypted_content": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The encrypted content payload."
+          }
+        },
+        "required": [
+          "type",
+          "encrypted_content"
+        ],
+        "additionalProperties": false,
+        "description": "Encrypted content exchanged between agents."
+      },
+      "AgentContentResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/OutputTextResource"
+          },
+          {
+            "$ref": "#/components/schemas/EncryptedContentResource"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "output_text": "#/components/schemas/OutputTextResource",
+            "encrypted_content": "#/components/schemas/EncryptedContentResource"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "output_text",
+          "encrypted_content"
+        ],
+        "description": "A plaintext or encrypted content part exchanged between agents."
+      },
+      "SubagentStatusResource": {
+        "type": "string",
+        "enum": [
+          "active",
+          "closed"
+        ],
+        "x-enumDescriptions": [
+          "The subagent remains available, including while idle between turns.",
+          "The subagent is closed."
+        ],
+        "description": "The current status of a subagent."
+      },
+      "SubagentResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the subagent."
+          },
+          "object": {
+            "$ref": "#/components/schemas/SubagentObjectResource",
+            "description": "The object type. Always `agent.session.subagent`."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session that owns the subagent."
+          },
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The runner-assigned nickname, or null when unavailable."
+          },
+          "instructions": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/AgentContentResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Initial task content, or null when unavailable. Text may contain placeholders for images or audio when only a preview is available."
+          },
+          "parent_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent that created this subagent."
+          },
+          "status": {
+            "$ref": "#/components/schemas/SubagentStatusResource",
+            "description": "The current status of the subagent."
+          },
+          "opened_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the subagent was first opened. Resuming does not change it."
+          },
+          "closed_at": {
+            "type": [
+              "integer",
+              "null"
+            ],
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the subagent was closed. Null while active, including after resume."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "session_id",
+          "name",
+          "instructions",
+          "parent_agent_id",
+          "status",
+          "opened_at",
+          "closed_at"
+        ],
+        "additionalProperties": false,
+        "description": "A subagent created within a session."
+      },
+      "SessionMessageRoleResource": {
+        "type": "string",
+        "enum": [
+          "user",
+          "assistant"
+        ],
+        "description": "The author of a session message."
+      },
+      "MessageContentResourceInputText": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_text"
+            ],
+            "default": "input_text",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `input_text`."
+          },
+          "text": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The text supplied by the user."
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ],
+        "additionalProperties": false,
+        "description": "Text supplied by the user."
+      },
+      "MessageContentResourceInputImage": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_image"
+            ],
+            "default": "input_image",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `input_image`."
+          },
+          "image_url": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The URL of the image supplied by the user, which may be a base64-encoded data URL."
+          }
+        },
+        "required": [
+          "type",
+          "image_url"
+        ],
+        "additionalProperties": false,
+        "description": "An image supplied by the user."
+      },
+      "MessageContentResourceOutputText": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "output_text"
+            ],
+            "default": "output_text",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `output_text`."
+          },
+          "text": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The text produced by the assistant."
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ],
+        "additionalProperties": false,
+        "description": "Text produced by the assistant."
+      },
+      "MessageContentResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/MessageContentResourceInputText"
+          },
+          {
+            "$ref": "#/components/schemas/MessageContentResourceInputImage"
+          },
+          {
+            "$ref": "#/components/schemas/MessageContentResourceOutputText"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "input_text": "#/components/schemas/MessageContentResourceInputText",
+            "input_image": "#/components/schemas/MessageContentResourceInputImage",
+            "output_text": "#/components/schemas/MessageContentResourceOutputText"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "input_text",
+          "input_image",
+          "output_text"
+        ],
+        "description": "A content part in a session message."
+      },
+      "OutputItemStatusResource": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed",
+          "incomplete"
+        ],
+        "x-enumDescriptions": [
+          "The item is in progress.",
+          "The item is complete.",
+          "The item stopped before completing."
+        ],
+        "description": "The status of an agent output item."
+      },
+      "MessagePhaseResource": {
+        "type": "string",
+        "enum": [
+          "commentary",
+          "final_answer"
+        ],
+        "x-enumDescriptions": [
+          "Commentary produced while the agent works.",
+          "The agent's final answer."
+        ],
+        "description": "The phase of an assistant message."
+      },
+      "MessageItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "message"
+            ],
+            "default": "message",
+            "x-stainless-const": true,
+            "description": "The item type. Always `message`."
+          },
+          "id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of this item, or null for legacy user messages whose ID was not recorded."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "role": {
+            "$ref": "#/components/schemas/SessionMessageRoleResource",
+            "description": "The role of the message author."
+          },
+          "content": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/MessageContentResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The content of the message. User messages contain input text or images; assistant messages contain output text."
+          },
+          "status": {
+            "$ref": "#/components/schemas/OutputItemStatusResource",
+            "description": "The status of the message. User messages are always `completed`."
+          },
+          "phase": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/MessagePhaseResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The phase of an assistant message. Null for user messages."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "role",
+          "content",
+          "status",
+          "phase"
+        ],
+        "additionalProperties": false,
+        "description": "A user or assistant message recorded in a session."
+      },
+      "SummaryTextResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "summary_text"
+            ],
+            "default": "summary_text",
+            "x-stainless-const": true,
+            "description": "The content type. Always `summary_text`."
+          },
+          "text": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The reasoning summary text."
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ],
+        "additionalProperties": false,
+        "description": "A reasoning summary content part."
+      },
+      "ReasoningItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "reasoning"
+            ],
+            "default": "reasoning",
+            "x-stainless-const": true,
+            "description": "The item type. Always `reasoning`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the reasoning item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "summary": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/SummaryTextResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The reasoning summaries produced by the agent."
+          },
+          "status": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/OutputItemStatusResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The status of the reasoning item."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "summary",
+          "status"
+        ],
+        "additionalProperties": false,
+        "description": "A reasoning item produced by the agent."
+      },
+      "FunctionCallStatusResource": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed",
+          "failed",
+          "incomplete"
+        ],
+        "x-enumDescriptions": [
+          "The call is in progress.",
+          "The call completed successfully.",
+          "The call failed.",
+          "The call stopped before completing."
+        ],
+        "description": "The status of a tool call."
+      },
+      "FunctionCallItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "function_call"
+            ],
+            "default": "function_call",
+            "x-stainless-const": true,
+            "description": "The item type. Always `function_call`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the function call item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "call_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID used to submit the function result."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The name of the function to call."
+          },
+          "arguments": {
+            "description": "The arguments to pass to the function."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatusResource",
+            "description": "The status of the function call."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "call_id",
+          "name",
+          "arguments",
+          "status"
+        ],
+        "additionalProperties": false,
+        "description": "A function call produced by the agent."
+      },
+      "InputContentResourceInputText": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_text"
+            ],
+            "default": "input_text",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `input_text`."
+          },
+          "text": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The text supplied to the agent."
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ],
+        "additionalProperties": false,
+        "description": "Text input recorded in a session item."
+      },
+      "InputContentResourceInputImage": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_image"
+            ],
+            "default": "input_image",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `input_image`."
+          },
+          "image_url": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The URL of the image supplied to the agent, which may be a base64-encoded data URL."
+          }
+        },
+        "required": [
+          "type",
+          "image_url"
+        ],
+        "additionalProperties": false,
+        "description": "Image input recorded in a session item."
+      },
+      "InputContentResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/InputContentResourceInputText"
+          },
+          {
+            "$ref": "#/components/schemas/InputContentResourceInputImage"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "input_text": "#/components/schemas/InputContentResourceInputText",
+            "input_image": "#/components/schemas/InputContentResourceInputImage"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "input_text",
+          "input_image"
+        ],
+        "description": "User-provided content recorded in a session item."
+      },
+      "FunctionCallOutputResource": {
+        "oneOf": [
+          {
+            "type": "string",
+            "minLength": 0
+          },
+          {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/InputContentResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000
+          }
+        ],
+        "description": "The text or model-input content supplied as a function result."
+      },
+      "FunctionCallOutputItemResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the function call output item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "function_call_output"
+            ],
+            "default": "function_call_output",
+            "x-stainless-const": true,
+            "description": "The item type. Always `function_call_output`."
+          },
+          "call_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the function call that produced this output."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatusResource",
+            "description": "The status of the function call."
+          },
+          "output": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/FunctionCallOutputResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The function result, if the call succeeded."
+          },
+          "error": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The error message, if the call failed."
+          }
+        },
+        "required": [
+          "id",
+          "turn_id",
+          "type",
+          "call_id",
+          "status",
+          "output",
+          "error"
+        ],
+        "additionalProperties": false,
+        "description": "The result supplied for a function call."
+      },
+      "AgentMessageItemResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the message."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent_message"
+            ],
+            "default": "agent_message",
+            "x-stainless-const": true,
+            "description": "The item type. Always `agent_message`."
+          },
+          "sender_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID or name of the sending agent."
+          },
+          "recipient_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID or name of the receiving agent."
+          },
+          "content": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/AgentContentResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The content exchanged between the agents."
+          }
+        },
+        "required": [
+          "id",
+          "turn_id",
+          "type",
+          "sender_agent_id",
+          "recipient_agent_id",
+          "content"
+        ],
+        "additionalProperties": false,
+        "description": "A message exchanged between agent threads."
+      },
+      "McpCallItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_call"
+            ],
+            "default": "mcp_call",
+            "x-stainless-const": true,
+            "description": "The item type. Always `mcp_call`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the MCP call item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "server_label": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The label of the MCP server."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The name of the MCP tool."
+          },
+          "arguments": {
+            "description": "The arguments passed to the MCP tool."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatusResource",
+            "description": "The status of the MCP tool call."
+          },
+          "output": {
+            "anyOf": [
+              {},
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The output returned by the MCP tool, if any."
+          },
+          "error": {
+            "anyOf": [
+              {},
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The error returned by the MCP tool, if any."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "server_label",
+          "name",
+          "arguments",
+          "status",
+          "output",
+          "error"
+        ],
+        "additionalProperties": false,
+        "description": "A call to a tool on an MCP server."
+      },
+      "WebSearchActionResourceSearch": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "search"
+            ],
+            "default": "search",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `search`."
+          },
+          "query": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The search query, when a single query was used."
+          },
+          "queries": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The search queries, when multiple queries were used."
+          }
+        },
+        "required": [
+          "type",
+          "query",
+          "queries"
+        ],
+        "additionalProperties": false,
+        "description": "A search query or group of search queries."
+      },
+      "WebSearchActionResourceOpenPage": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "open_page"
+            ],
+            "default": "open_page",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `open_page`."
+          },
+          "url": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The URL of the page that was opened."
+          }
+        },
+        "required": [
+          "type",
+          "url"
+        ],
+        "additionalProperties": false,
+        "description": "Opens a web page."
+      },
+      "WebSearchActionResourceFindInPage": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "find_in_page"
+            ],
+            "default": "find_in_page",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `find_in_page`."
+          },
+          "url": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The URL of the page that was searched."
+          },
+          "pattern": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The text pattern that was searched for."
+          }
+        },
+        "required": [
+          "type",
+          "url",
+          "pattern"
+        ],
+        "additionalProperties": false,
+        "description": "Finds text within a web page."
+      },
+      "WebSearchActionResourceOther": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "other"
+            ],
+            "default": "other",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `other`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Another web search action."
+      },
+      "WebSearchActionResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/WebSearchActionResourceSearch"
+          },
+          {
+            "$ref": "#/components/schemas/WebSearchActionResourceOpenPage"
+          },
+          {
+            "$ref": "#/components/schemas/WebSearchActionResourceFindInPage"
+          },
+          {
+            "$ref": "#/components/schemas/WebSearchActionResourceOther"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "search": "#/components/schemas/WebSearchActionResourceSearch",
+            "open_page": "#/components/schemas/WebSearchActionResourceOpenPage",
+            "find_in_page": "#/components/schemas/WebSearchActionResourceFindInPage",
+            "other": "#/components/schemas/WebSearchActionResourceOther"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "search",
+          "open_page",
+          "find_in_page",
+          "other"
+        ],
+        "description": "An action performed by the web search tool."
+      },
+      "WebSearchCallItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "web_search_call"
+            ],
+            "default": "web_search_call",
+            "x-stainless-const": true,
+            "description": "The item type. Always `web_search_call`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the web search call."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "status": {
+            "$ref": "#/components/schemas/OutputItemStatusResource",
+            "description": "The status of the web search call."
+          },
+          "action": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/WebSearchActionResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The action performed by the web search tool."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "status",
+          "action"
+        ],
+        "additionalProperties": false,
+        "description": "A web search call produced by the agent."
+      },
+      "CommandExecutionItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "command_execution"
+            ],
+            "default": "command_execution",
+            "x-stainless-const": true,
+            "description": "The item type. Always `command_execution`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the command execution item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "command": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The command that was executed."
+          },
+          "cwd": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The working directory used to execute the command."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatusResource",
+            "description": "The status of the command execution."
+          },
+          "output": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The command output, if available."
+          },
+          "exit_code": {
+            "type": [
+              "integer",
+              "null"
+            ],
+            "format": "int64",
+            "description": "The process exit code, if the command completed."
+          },
+          "duration_ms": {
+            "type": [
+              "integer",
+              "null"
+            ],
+            "format": "int64",
+            "description": "The command duration in milliseconds."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "command",
+          "cwd",
+          "status",
+          "output",
+          "exit_code",
+          "duration_ms"
+        ],
+        "additionalProperties": false,
+        "description": "A command execution produced by the agent."
+      },
+      "InterruptSubagentCallItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "interrupt_subagent_call"
+            ],
+            "default": "interrupt_subagent_call",
+            "x-stainless-const": true,
+            "x-enumDescriptions": [
+              "The current public item type."
+            ],
+            "description": "The item type. Always `interrupt_subagent_call`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the tool call item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatusResource",
+            "description": "The status of the tool call."
+          },
+          "sender_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent requesting the interrupt."
+          },
+          "recipient_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent to interrupt."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "status",
+          "sender_agent_id",
+          "recipient_agent_id"
+        ],
+        "additionalProperties": false,
+        "description": "A request to interrupt a subagent's current turn. The subagent remains available."
+      },
+      "CreateSubagentCallItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "create_subagent_call"
+            ],
+            "default": "create_subagent_call",
+            "x-stainless-const": true,
+            "x-enumDescriptions": [
+              "The current public item type."
+            ],
+            "description": "The item type. Always `create_subagent_call`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the tool call item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatusResource",
+            "description": "The status of the tool call."
+          },
+          "agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent that requested the subagent."
+          },
+          "content": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/AgentContentResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The task given to the spawned agent."
+          },
+          "model": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The model requested for the spawned agent."
+          },
+          "reasoning_effort": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The reasoning effort requested for the spawned agent."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "status",
+          "agent_id",
+          "content",
+          "model",
+          "reasoning_effort"
+        ],
+        "additionalProperties": false,
+        "description": "A request to spawn a subagent."
+      },
+      "SendSubagentInputCallItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "send_subagent_input_call"
+            ],
+            "default": "send_subagent_input_call",
+            "x-stainless-const": true,
+            "x-enumDescriptions": [
+              "The current public item type."
+            ],
+            "description": "The item type. Always `send_subagent_input_call`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the tool call item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatusResource",
+            "description": "The status of the tool call."
+          },
+          "sender_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent sending the input."
+          },
+          "recipient_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent receiving the input."
+          },
+          "content": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/AgentContentResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The input sent to the receiving agent."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "status",
+          "sender_agent_id",
+          "recipient_agent_id",
+          "content"
+        ],
+        "additionalProperties": false,
+        "description": "A request to send input to another agent."
+      },
+      "ResumeSubagentCallItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "resume_subagent_call"
+            ],
+            "default": "resume_subagent_call",
+            "x-stainless-const": true,
+            "x-enumDescriptions": [
+              "The current public item type."
+            ],
+            "description": "The item type. Always `resume_subagent_call`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the tool call item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatusResource",
+            "description": "The status of the tool call."
+          },
+          "sender_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent requesting the resume."
+          },
+          "recipient_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent to resume."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "status",
+          "sender_agent_id",
+          "recipient_agent_id"
+        ],
+        "additionalProperties": false,
+        "description": "A request to resume a subagent."
+      },
+      "WaitForSubagentsCallItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "wait_for_subagents_call"
+            ],
+            "default": "wait_for_subagents_call",
+            "x-stainless-const": true,
+            "x-enumDescriptions": [
+              "The current public item type."
+            ],
+            "description": "The item type. Always `wait_for_subagents_call`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the tool call item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatusResource",
+            "description": "The status of the tool call."
+          },
+          "sender_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent waiting for results."
+          },
+          "recipient_agent_ids": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The IDs of the agents to wait for."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "status",
+          "sender_agent_id",
+          "recipient_agent_ids"
+        ],
+        "additionalProperties": false,
+        "description": "A request to wait for one or more subagents."
+      },
+      "CloseSubagentCallItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "close_subagent_call"
+            ],
+            "default": "close_subagent_call",
+            "x-stainless-const": true,
+            "x-enumDescriptions": [
+              "The current public item type."
+            ],
+            "description": "The item type. Always `close_subagent_call`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the tool call item."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "status": {
+            "$ref": "#/components/schemas/FunctionCallStatusResource",
+            "description": "The status of the tool call."
+          },
+          "sender_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent requesting the close."
+          },
+          "recipient_agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent to close."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "status",
+          "sender_agent_id",
+          "recipient_agent_id"
+        ],
+        "additionalProperties": false,
+        "description": "A request to close a subagent."
+      },
+      "SessionTurnItemResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/MessageItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/ReasoningItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionCallOutputItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/AgentMessageItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/McpCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/WebSearchCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/CommandExecutionItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/CreateSubagentCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/SendSubagentInputCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/ResumeSubagentCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/WaitForSubagentsCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/InterruptSubagentCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/CloseSubagentCallItemResource"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "message": "#/components/schemas/MessageItemResource",
+            "reasoning": "#/components/schemas/ReasoningItemResource",
+            "function_call": "#/components/schemas/FunctionCallItemResource",
+            "function_call_output": "#/components/schemas/FunctionCallOutputItemResource",
+            "agent_message": "#/components/schemas/AgentMessageItemResource",
+            "mcp_call": "#/components/schemas/McpCallItemResource",
+            "web_search_call": "#/components/schemas/WebSearchCallItemResource",
+            "command_execution": "#/components/schemas/CommandExecutionItemResource",
+            "interrupt_subagent_call": "#/components/schemas/InterruptSubagentCallItemResource",
+            "create_subagent_call": "#/components/schemas/CreateSubagentCallItemResource",
+            "send_subagent_input_call": "#/components/schemas/SendSubagentInputCallItemResource",
+            "resume_subagent_call": "#/components/schemas/ResumeSubagentCallItemResource",
+            "wait_for_subagents_call": "#/components/schemas/WaitForSubagentsCallItemResource",
+            "close_subagent_call": "#/components/schemas/CloseSubagentCallItemResource"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "message",
+          "reasoning",
+          "function_call",
+          "function_call_output",
+          "agent_message",
+          "mcp_call",
+          "web_search_call",
+          "command_execution",
+          "create_subagent_call",
+          "send_subagent_input_call",
+          "resume_subagent_call",
+          "wait_for_subagents_call",
+          "interrupt_subagent_call",
+          "close_subagent_call"
+        ],
+        "description": "An item associated with a session turn."
+      },
+      "SessionItemListResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "x-stainless-const": true,
+            "description": "The object type, which is always `list`."
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/SessionTurnItemResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The resources returned in this page, in the requested sort order."
+          },
+          "first_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the first resource in `data`, or `null` if the page is empty."
+          },
+          "last_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the last resource in `data`, or `null` if the page is empty. Pass this as `after` with the same order and filters."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more resources to retrieve after this page."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "additionalProperties": false,
+        "description": "A page of messages, reasoning, and tool calls from a session's item history."
+      },
+      "TurnObjectResource": {
+        "type": "string",
+        "enum": [
+          "agent.session.turn"
+        ],
+        "default": "agent.session.turn",
+        "x-stainless-const": true,
+        "description": "The object type for a turn."
+      },
+      "TurnStatusResource": {
+        "type": "string",
+        "enum": [
+          "queued",
+          "in_progress",
+          "waiting",
+          "completed",
+          "failed",
+          "cancelled"
+        ],
+        "x-enumDescriptions": [
+          "The turn is waiting to start.",
+          "The turn is in progress.",
+          "The turn is waiting for external input.",
+          "The turn completed successfully.",
+          "The turn failed.",
+          "The turn was cancelled."
+        ],
+        "description": "The current status of a turn."
+      },
+      "SessionTurnErrorCodeResource": {
+        "type": "string",
+        "enum": [
+          "context_length_exceeded",
+          "session_budget_exceeded",
+          "usage_limit_exceeded",
+          "rate_limit_exceeded",
+          "server_overloaded",
+          "cyber_policy",
+          "connection_failed",
+          "server_error",
+          "authentication_error",
+          "invalid_request",
+          "resource_not_found",
+          "sandbox_error",
+          "executor_version_incompatible",
+          "active_turn_not_steerable",
+          "request_timeout",
+          "internal_error"
+        ],
+        "x-enumDescriptions": [
+          "The request exceeds the model's context window.",
+          "The session has reached its usage budget.",
+          "The organization has reached a usage, plan, or billing limit.",
+          "The request exceeds the available rate limit.",
+          "The model service is temporarily overloaded.",
+          "The request was rejected by a safety policy.",
+          "The request could not connect to the model service.",
+          "The model service encountered an unexpected error.",
+          "The API credentials are invalid or lack the required access.",
+          "The request contains invalid input or configuration.",
+          "The requested model or resource is unavailable.",
+          "The request could not complete in its execution environment.",
+          "The executor must be upgraded before it can run this turn.",
+          "The session cannot accept additional input while a request is running.",
+          "The request timed out before the model service responded.",
+          "An unexpected internal error prevented the session request from completing."
+        ],
+        "description": "Stable public categories for session request failures."
+      },
+      "SessionTurnErrorResource": {
+        "type": "object",
+        "properties": {
+          "code": {
+            "$ref": "#/components/schemas/SessionTurnErrorCodeResource",
+            "description": "A stable, machine-readable failure category."
+          },
+          "message": {
+            "type": "string",
+            "minLength": 0,
+            "description": "A customer-safe explanation of the failure."
+          }
+        },
+        "required": [
+          "code",
+          "message"
+        ],
+        "additionalProperties": false,
+        "description": "A customer-safe error describing why a session request failed."
+      },
+      "InputTokensDetailsResource": {
+        "type": "object",
+        "properties": {
+          "cached_tokens": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The number of input tokens retrieved from the prompt cache."
+          }
+        },
+        "required": [
+          "cached_tokens"
+        ],
+        "additionalProperties": false,
+        "description": "A breakdown of input token usage for a session or turn."
+      },
+      "OutputTokensDetailsResource": {
+        "type": "object",
+        "properties": {
+          "reasoning_tokens": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The number of output tokens used for reasoning."
+          }
+        },
+        "required": [
+          "reasoning_tokens"
+        ],
+        "additionalProperties": false,
+        "description": "A breakdown of output token usage for a session or turn."
+      },
+      "TokenUsageResource": {
+        "type": "object",
+        "properties": {
+          "input_tokens": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The number of input tokens used by the agent."
+          },
+          "input_tokens_details": {
+            "$ref": "#/components/schemas/InputTokensDetailsResource",
+            "description": "A breakdown of the agent's input token usage."
+          },
+          "output_tokens": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The number of output tokens generated by the agent."
+          },
+          "output_tokens_details": {
+            "$ref": "#/components/schemas/OutputTokensDetailsResource",
+            "description": "A breakdown of the agent's output token usage."
+          },
+          "total_tokens": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The total number of input and output tokens used by the agent."
+          }
+        },
+        "required": [
+          "input_tokens",
+          "input_tokens_details",
+          "output_tokens",
+          "output_tokens_details",
+          "total_tokens"
+        ],
+        "additionalProperties": false,
+        "description": "Recorded token usage for a session or turn. Usage is best effort and may change."
+      },
+      "TurnResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn."
+          },
+          "object": {
+            "$ref": "#/components/schemas/TurnObjectResource",
+            "description": "The object type. Always `agent.session.turn`."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session that owns the turn."
+          },
+          "agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent that ran the turn."
+          },
+          "subagent_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the subagent that ran the turn, if applicable."
+          },
+          "status": {
+            "$ref": "#/components/schemas/TurnStatusResource",
+            "description": "The current status of the turn."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, used to order the turn by creation time. Subagent turns use their start time, falling back to completion time or the subagent opening time when the preceding timestamps are unavailable."
+          },
+          "started_at": {
+            "type": [
+              "integer",
+              "null"
+            ],
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the turn started."
+          },
+          "completed_at": {
+            "type": [
+              "integer",
+              "null"
+            ],
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the turn reached a terminal state."
+          },
+          "error": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/SessionTurnErrorResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "A customer-safe error. Non-null only for a failed turn."
+          },
+          "usage": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/TokenUsageResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Best-effort token usage for the turn, or null if unknown. Recorded usage may change."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "session_id",
+          "agent_id",
+          "subagent_id",
+          "status",
+          "created_at",
+          "started_at",
+          "completed_at",
+          "error",
+          "usage"
+        ],
+        "additionalProperties": false,
+        "description": "The canonical public representation of a session turn."
+      },
+      "SessionTurnListResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "x-stainless-const": true,
+            "description": "The object type, which is always `list`."
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/TurnResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The resources returned in this page, in the requested sort order."
+          },
+          "first_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the first resource in `data`, or `null` if the page is empty."
+          },
+          "last_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the last resource in `data`, or `null` if the page is empty. Pass this as `after` with the same order and filters."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more resources to retrieve after this page."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "additionalProperties": false,
+        "description": "A page of Agents API resources, with IDs for retrieving additional pages."
+      },
+      "ReasoningEffortResource": {
+        "type": "string",
+        "enum": [
+          "none",
+          "minimal",
+          "low",
+          "medium",
+          "high",
+          "xhigh",
+          "max"
+        ],
+        "description": "The amount of reasoning effort used by an agent."
+      },
+      "ReasoningSummaryResource": {
+        "type": "string",
+        "enum": [
+          "concise",
+          "detailed",
+          "auto"
+        ],
+        "x-enumDescriptions": [
+          "Returns a concise reasoning summary when supported.",
+          "Returns a detailed reasoning summary when supported.",
+          "Automatically selects the most detailed summary supported by the model."
+        ],
+        "description": "The reasoning summary format requested from an agent."
+      },
+      "ReasoningResource": {
+        "type": "object",
+        "properties": {
+          "effort": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ReasoningEffortResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The requested reasoning effort, or `null` when the model selects its own default."
+          },
+          "summary": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ReasoningSummaryResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The requested reasoning summary format, or `null` when summaries are disabled."
+          }
+        },
+        "required": [
+          "effort",
+          "summary"
+        ],
+        "additionalProperties": false,
+        "description": "The reasoning configuration used by an agent."
+      },
+      "TextFormatResourceText": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "text"
+            ],
+            "default": "text",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `text`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Generates ordinary text without a structured-output constraint."
+      },
+      "TextFormatResourceJsonSchema": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "json_schema"
+            ],
+            "default": "json_schema",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `json_schema`."
+          },
+          "schema": {
+            "type": "object",
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minProperties": 0,
+            "description": "The JSON Schema that generated text must match."
+          }
+        },
+        "required": [
+          "type",
+          "schema"
+        ],
+        "additionalProperties": false,
+        "description": "Constrains generated text to a JSON Schema."
+      },
+      "TextFormatResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/TextFormatResourceText"
+          },
+          {
+            "$ref": "#/components/schemas/TextFormatResourceJsonSchema"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "text": "#/components/schemas/TextFormatResourceText",
+            "json_schema": "#/components/schemas/TextFormatResourceJsonSchema"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "text",
+          "json_schema"
+        ],
+        "description": "The effective output format for generated text."
+      },
+      "VerbosityResource": {
+        "type": "string",
+        "enum": [
+          "low",
+          "medium",
+          "high"
+        ],
+        "description": "The amount of text produced by an agent."
+      },
+      "TextResource": {
+        "type": "object",
+        "properties": {
+          "format": {
+            "$ref": "#/components/schemas/TextFormatResource",
+            "description": "The effective output format. Defaults to ordinary text."
+          },
+          "verbosity": {
+            "$ref": "#/components/schemas/VerbosityResource",
+            "description": "The amount of text produced by the agent. Defaults to `medium`."
+          }
+        },
+        "required": [
+          "format",
+          "verbosity"
+        ],
+        "additionalProperties": false,
+        "description": "The text configuration used by an agent."
+      },
+      "ServiceTierResource": {
+        "type": "string",
+        "enum": [
+          "auto",
+          "default",
+          "flex",
+          "priority",
+          "fast"
+        ],
+        "description": "The service-tier policy configured for an agent."
+      },
+      "PersistedAgentToolResourceFunction": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "function"
+            ],
+            "default": "function",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `function`."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The name of the function."
+          },
+          "description": {
+            "type": "string",
+            "minLength": 0,
+            "description": "A description of what the function does."
+          },
+          "parameters": {
+            "type": "object",
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minProperties": 0,
+            "description": "A JSON Schema object describing the function's arguments."
+          },
+          "defer_loading": {
+            "type": "boolean",
+            "description": "Whether the function is deferred and discovered through tool search."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "description",
+          "parameters",
+          "defer_loading"
+        ],
+        "additionalProperties": false,
+        "description": "A function defined by the application."
+      },
+      "PersistedAgentToolResourceToolSearch": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "tool_search"
+            ],
+            "default": "tool_search",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `tool_search`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Discovers deferred function tools and loads them into the model context."
+      },
+      "PersistedAgentToolResourceProgrammaticToolCalling": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "programmatic_tool_calling"
+            ],
+            "default": "programmatic_tool_calling",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `programmatic_tool_calling`."
+          },
+          "enabled": {
+            "type": "boolean",
+            "description": "Whether tools can be called from model-generated code."
+          }
+        },
+        "required": [
+          "type",
+          "enabled"
+        ],
+        "additionalProperties": false,
+        "description": "Enables calling tools from model-generated code."
+      },
+      "PersistedMcpTransportResourceHttp": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "http"
+            ],
+            "default": "http",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `http`."
+          },
+          "server_url": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The URL of the MCP server."
+          },
+          "headers": {
+            "type": "object",
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minProperties": 0,
+            "description": "Non-secret HTTP headers sent to the MCP server."
+          }
+        },
+        "required": [
+          "type",
+          "server_url",
+          "headers"
+        ],
+        "additionalProperties": false,
+        "description": "Connects to an MCP server over HTTP."
+      },
+      "PersistedMcpTransportResourceStdio": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "stdio"
+            ],
+            "default": "stdio",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `stdio`."
+          },
+          "command": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The command used to start the MCP server."
+          },
+          "args": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Arguments passed to the MCP server command."
+          },
+          "cwd": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The working directory used to start the MCP server."
+          },
+          "env_vars": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Environment variable names inherited from the execution environment."
+          }
+        },
+        "required": [
+          "type",
+          "command",
+          "args",
+          "cwd",
+          "env_vars"
+        ],
+        "additionalProperties": false,
+        "description": "Starts an MCP server as a local process."
+      },
+      "PersistedMcpTransportResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/PersistedMcpTransportResourceHttp"
+          },
+          {
+            "$ref": "#/components/schemas/PersistedMcpTransportResourceStdio"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "http": "#/components/schemas/PersistedMcpTransportResourceHttp",
+            "stdio": "#/components/schemas/PersistedMcpTransportResourceStdio"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "http",
+          "stdio"
+        ],
+        "description": "A credential-free transport used to connect to an MCP server."
+      },
+      "McpConnectionOriginResource": {
+        "type": "string",
+        "enum": [
+          "service",
+          "environment"
+        ],
+        "description": "Where outbound MCP HTTP connections originate."
+      },
+      "PersistedAgentToolResourceMcp": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp"
+            ],
+            "default": "mcp",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `mcp`."
+          },
+          "server_label": {
+            "type": "string",
+            "minLength": 0,
+            "description": "A label used to identify the MCP server in tool calls."
+          },
+          "credential_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The vault credential selected for this MCP server, if any."
+          },
+          "transport": {
+            "$ref": "#/components/schemas/PersistedMcpTransportResource",
+            "description": "The credential-free transport used to connect to the MCP server."
+          },
+          "request_metadata": {
+            "type": "object",
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minProperties": 0,
+            "description": "Metadata included with requests to this MCP server."
+          },
+          "allowed_tools": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The MCP tools the agent may call, or null when all server tools are allowed."
+          },
+          "required": {
+            "type": "boolean",
+            "description": "Whether this MCP server must initialize before the first turn."
+          },
+          "connection_origin": {
+            "$ref": "#/components/schemas/McpConnectionOriginResource",
+            "description": "Where outbound MCP HTTP connections originate."
+          }
+        },
+        "required": [
+          "type",
+          "server_label",
+          "credential_id",
+          "transport",
+          "request_metadata",
+          "allowed_tools",
+          "required",
+          "connection_origin"
+        ],
+        "additionalProperties": false,
+        "description": "Tools provided by a remote MCP server without stored credentials."
+      },
+      "WebSearchModeResource": {
+        "type": "string",
+        "enum": [
+          "disabled",
+          "cached",
+          "live"
+        ],
+        "description": "The source used for web search results."
+      },
+      "WebSearchContextSizeResource": {
+        "type": "string",
+        "enum": [
+          "low",
+          "medium",
+          "high"
+        ],
+        "description": "The amount of web search context made available to the model."
+      },
+      "WebSearchLocationResource": {
+        "type": "object",
+        "properties": {
+          "country": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The two-letter ISO country code, such as `US`."
+          },
+          "region": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The region or state name."
+          },
+          "city": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The city name."
+          },
+          "timezone": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The IANA timezone, such as `America/Los_Angeles`."
+          }
+        },
+        "required": [
+          "country",
+          "region",
+          "city",
+          "timezone"
+        ],
+        "additionalProperties": false,
+        "description": "Approximate user location used to localize web search results."
+      },
+      "PersistedAgentToolResourceWebSearch": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "web_search"
+            ],
+            "default": "web_search",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `web_search`."
+          },
+          "mode": {
+            "$ref": "#/components/schemas/WebSearchModeResource",
+            "description": "The source used for web search results."
+          },
+          "context_size": {
+            "$ref": "#/components/schemas/WebSearchContextSizeResource",
+            "description": "The amount of search context made available to the model. Defaults to `medium`."
+          },
+          "allowed_domains": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Allowed search domains, or `null` when the search is unrestricted."
+          },
+          "location": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/WebSearchLocationResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Approximate location used to localize search results, if provided."
+          }
+        },
+        "required": [
+          "type",
+          "mode",
+          "context_size",
+          "allowed_domains",
+          "location"
+        ],
+        "additionalProperties": false,
+        "description": "Web search."
+      },
+      "PersistedAgentToolResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/PersistedAgentToolResourceFunction"
+          },
+          {
+            "$ref": "#/components/schemas/PersistedAgentToolResourceToolSearch"
+          },
+          {
+            "$ref": "#/components/schemas/PersistedAgentToolResourceProgrammaticToolCalling"
+          },
+          {
+            "$ref": "#/components/schemas/PersistedAgentToolResourceMcp"
+          },
+          {
+            "$ref": "#/components/schemas/PersistedAgentToolResourceWebSearch"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "function": "#/components/schemas/PersistedAgentToolResourceFunction",
+            "tool_search": "#/components/schemas/PersistedAgentToolResourceToolSearch",
+            "programmatic_tool_calling": "#/components/schemas/PersistedAgentToolResourceProgrammaticToolCalling",
+            "mcp": "#/components/schemas/PersistedAgentToolResourceMcp",
+            "web_search": "#/components/schemas/PersistedAgentToolResourceWebSearch"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "function",
+          "tool_search",
+          "programmatic_tool_calling",
+          "mcp",
+          "web_search"
+        ],
+        "description": "A credential-free tool available to a reusable agent."
+      },
+      "MultiAgentConfigResource": {
+        "type": "object",
+        "properties": {
+          "enabled": {
+            "type": "boolean",
+            "description": "Whether subagent tools are enabled. Defaults to false."
+          },
+          "max_concurrent_subagents": {
+            "type": [
+              "integer",
+              "null"
+            ],
+            "format": "int64",
+            "minimum": 1,
+            "maximum": 4294967295,
+            "description": "Maximum number of subagents that may run concurrently, or null when disabled. Defaults to 6 when enabled."
+          }
+        },
+        "required": [
+          "enabled",
+          "max_concurrent_subagents"
+        ],
+        "additionalProperties": false,
+        "description": "The resolved configuration for creating and coordinating subagents."
+      },
+      "AgentResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the reusable agent."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "agent"
+            ],
+            "default": "agent",
+            "x-stainless-const": true,
+            "description": "The object type. Always `agent`."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the agent was created."
+          },
+          "updated_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the agent was last updated."
+          },
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "A human-readable name for the agent, or null if it is unnamed."
+          },
+          "metadata": {
+            "type": "object",
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minProperties": 0,
+            "description": "Custom string key-value pairs attached to the agent."
+          },
+          "model": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The requested model name used for inference."
+          },
+          "reasoning": {
+            "$ref": "#/components/schemas/ReasoningResource",
+            "description": "The resolved reasoning configuration, including the model default for an omitted effort."
+          },
+          "text": {
+            "$ref": "#/components/schemas/TextResource",
+            "description": "The resolved configuration for text generated by the agent."
+          },
+          "service_tier": {
+            "$ref": "#/components/schemas/ServiceTierResource",
+            "description": "The resolved service-tier policy used for model requests."
+          },
+          "instructions": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "Custom instructions appended to the agent's default base instructions."
+          },
+          "tools": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/PersistedAgentToolResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Tools available to the agent."
+          },
+          "multi_agent": {
+            "$ref": "#/components/schemas/MultiAgentConfigResource",
+            "description": "The resolved configuration for creating and coordinating subagents."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "created_at",
+          "updated_at",
+          "name",
+          "metadata",
+          "model",
+          "reasoning",
+          "text",
+          "service_tier",
+          "instructions",
+          "tools",
+          "multi_agent"
+        ],
+        "additionalProperties": false,
+        "description": "A reusable agent scoped to the caller's project."
+      },
+      "AgentListResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "x-stainless-const": true,
+            "description": "The object type, which is always `list`."
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/AgentResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The resources returned in this page, in the requested sort order."
+          },
+          "first_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the first resource in `data`, or `null` if the page is empty."
+          },
+          "last_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the last resource in `data`, or `null` if the page is empty. Pass this as `after` with the same order and filters."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more resources to retrieve after this page."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "additionalProperties": false,
+        "description": "A page of Agents API resources, with IDs for retrieving additional pages."
+      },
+      "ReasoningEffortParam": {
+        "type": "string",
+        "enum": [
+          "none",
+          "minimal",
+          "low",
+          "medium",
+          "high",
+          "xhigh",
+          "max"
+        ],
+        "description": "The amount of reasoning effort the model should use."
+      },
+      "ReasoningSummaryParam": {
+        "type": "string",
+        "enum": [
+          "concise",
+          "detailed",
+          "auto"
+        ],
+        "x-enumDescriptions": [
+          "Returns a concise reasoning summary when supported.",
+          "Returns a detailed reasoning summary when supported.",
+          "Automatically selects the most detailed summary supported by the model."
+        ],
+        "description": "The reasoning summary format requested from the model."
+      },
+      "ReasoningParam": {
+        "type": "object",
+        "properties": {
+          "effort": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ReasoningEffortParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The amount of reasoning effort the model should use. Omission lets the model select it."
+          },
+          "summary": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ReasoningSummaryParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Controls whether the response includes a reasoning summary."
+          }
+        },
+        "additionalProperties": false,
+        "description": "Reasoning configuration for the agent."
+      },
+      "TextFormatParamText": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "text"
+            ],
+            "default": "text",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `text`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Generates ordinary text without a structured-output constraint."
+      },
+      "TextFormatParamJsonSchema": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "json_schema"
+            ],
+            "default": "json_schema",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `json_schema`."
+          },
+          "schema": {
+            "type": "object",
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "The JSON Schema that generated text must match."
+          }
+        },
+        "required": [
+          "type",
+          "schema"
+        ],
+        "additionalProperties": false,
+        "description": "Constrains generated text to a JSON Schema."
+      },
+      "TextFormatParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/TextFormatParamText"
+          },
+          {
+            "$ref": "#/components/schemas/TextFormatParamJsonSchema"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "text": "#/components/schemas/TextFormatParamText",
+            "json_schema": "#/components/schemas/TextFormatParamJsonSchema"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "text",
+          "json_schema"
+        ],
+        "description": "The output format for generated text."
+      },
+      "VerbosityParam": {
+        "type": "string",
+        "enum": [
+          "low",
+          "medium",
+          "high"
+        ],
+        "x-enumDescriptions": [
+          "Produces less text.",
+          "Uses the default amount of text.",
+          "Produces more text."
+        ],
+        "description": "The amount of text the model should produce."
+      },
+      "TextParam": {
+        "type": "object",
+        "properties": {
+          "format": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/TextFormatParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The output format. Omission uses ordinary text (`{\"type\": \"text\"}`)."
+          },
+          "verbosity": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/VerbosityParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The amount of text the model should produce. Defaults to `medium`, matching Responses."
+          }
+        },
+        "additionalProperties": false,
+        "description": "Configuration for text generated by the agent."
+      },
+      "ServiceTierParam": {
+        "type": "string",
+        "enum": [
+          "auto",
+          "default",
+          "flex",
+          "priority",
+          "fast"
+        ],
+        "x-enumDescriptions": [
+          "Selects the service tier automatically.",
+          "Uses the default service tier.",
+          "Uses the flex service tier.",
+          "Uses the priority service tier.",
+          "Uses the fast service tier."
+        ],
+        "description": "The service tier used for model requests."
+      },
+      "PersistedAgentToolConfigParamFunction": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "function"
+            ],
+            "default": "function",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `function`."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The name of the function."
+          },
+          "description": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "A description of what the function does."
+          },
+          "parameters": {
+            "type": "object",
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "A JSON Schema object describing the function's arguments."
+          },
+          "defer_loading": {
+            "type": "boolean",
+            "default": false,
+            "description": "Whether this function is deferred and discovered through tool search. Defaults to `false`."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "description",
+          "parameters"
+        ],
+        "additionalProperties": false,
+        "description": "A function defined by the application."
+      },
+      "PersistedAgentToolConfigParamToolSearch": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "tool_search"
+            ],
+            "default": "tool_search",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `tool_search`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Discovers deferred function tools and loads them into the model context."
+      },
+      "PersistedAgentToolConfigParamProgrammaticToolCalling": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "programmatic_tool_calling"
+            ],
+            "default": "programmatic_tool_calling",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `programmatic_tool_calling`."
+          },
+          "enabled": {
+            "type": "boolean",
+            "default": true,
+            "description": "Whether tools can be called from model-generated code. Defaults to `true`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Enables calling tools from model-generated code."
+      },
+      "PersistedMcpTransportConfigParamHttp": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "http"
+            ],
+            "default": "http",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `http`."
+          },
+          "server_url": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The URL of the MCP server."
+          },
+          "headers": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "Non-secret HTTP headers sent to the MCP server."
+          }
+        },
+        "required": [
+          "type",
+          "server_url"
+        ],
+        "additionalProperties": false,
+        "description": "Connects to an MCP server over HTTP."
+      },
+      "PersistedMcpTransportConfigParamStdio": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "stdio"
+            ],
+            "default": "stdio",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `stdio`."
+          },
+          "command": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The command used to start the MCP server."
+          },
+          "args": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Arguments passed to the MCP server command."
+          },
+          "cwd": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The working directory used to start the MCP server."
+          },
+          "env_vars": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Environment variable names to inherit from the selected execution environment."
+          }
+        },
+        "required": [
+          "type",
+          "command",
+          "cwd"
+        ],
+        "additionalProperties": false,
+        "description": "Starts an MCP server as a local process."
+      },
+      "PersistedMcpTransportConfigParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/PersistedMcpTransportConfigParamHttp"
+          },
+          {
+            "$ref": "#/components/schemas/PersistedMcpTransportConfigParamStdio"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "http": "#/components/schemas/PersistedMcpTransportConfigParamHttp",
+            "stdio": "#/components/schemas/PersistedMcpTransportConfigParamStdio"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "http",
+          "stdio"
+        ],
+        "description": "A credential-free transport used to connect to an MCP server."
+      },
+      "McpConnectionOriginParam": {
+        "type": "string",
+        "enum": [
+          "service",
+          "environment"
+        ],
+        "x-enumDescriptions": [
+          "Uses the Managed Agents service network.",
+          "Uses the session's execution environment."
+        ],
+        "description": "Where outbound MCP HTTP connections originate."
+      },
+      "PersistedAgentToolConfigParamMcp": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp"
+            ],
+            "default": "mcp",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `mcp`."
+          },
+          "server_label": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "A label used to identify the MCP server in tool calls."
+          },
+          "credential_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The vault credential selected for this MCP server. Optional when exactly one attached credential matches the server URL."
+          },
+          "transport": {
+            "$ref": "#/components/schemas/PersistedMcpTransportConfigParam",
+            "description": "The credential-free transport used to connect to the MCP server."
+          },
+          "request_metadata": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "Metadata included with requests to this MCP server."
+          },
+          "allowed_tools": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "The MCP tools the agent may call. All server tools are allowed when omitted."
+          },
+          "required": {
+            "type": "boolean",
+            "default": false,
+            "description": "Whether this MCP server must initialize before the first turn. Defaults to `false`."
+          },
+          "connection_origin": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/McpConnectionOriginParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Selects where outbound MCP HTTP connections originate."
+          }
+        },
+        "required": [
+          "type",
+          "server_label",
+          "transport"
+        ],
+        "additionalProperties": false,
+        "description": "Tools provided by a remote MCP server without stored credentials."
+      },
+      "WebSearchModeParam": {
+        "type": "string",
+        "enum": [
+          "disabled",
+          "cached",
+          "live"
+        ],
+        "x-enumDescriptions": [
+          "Disables web search.",
+          "Uses cached search results.",
+          "Searches the live web."
+        ],
+        "description": "The source used for web search results."
+      },
+      "WebSearchContextSizeParam": {
+        "type": "string",
+        "enum": [
+          "low",
+          "medium",
+          "high"
+        ],
+        "description": "The amount of web search context made available to the model."
+      },
+      "WebSearchLocationParam": {
+        "type": "object",
+        "properties": {
+          "country": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The two-letter ISO country code, such as `US`."
+          },
+          "region": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The region or state name."
+          },
+          "city": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The city name."
+          },
+          "timezone": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The IANA timezone, such as `America/Los_Angeles`."
+          }
+        },
+        "additionalProperties": false,
+        "description": "Approximate user location used to localize web search results."
+      },
+      "PersistedAgentToolConfigParamWebSearch": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "web_search"
+            ],
+            "default": "web_search",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `web_search`."
+          },
+          "mode": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/WebSearchModeParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The source used for web search results. Defaults to `live`."
+          },
+          "context_size": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/WebSearchContextSizeParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The amount of search context made available to the model. Defaults to `medium`."
+          },
+          "allowed_domains": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Domains the search may include."
+          },
+          "location": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/WebSearchLocationParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Approximate location used to localize search results."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Web search."
+      },
+      "PersistedAgentToolConfigParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/PersistedAgentToolConfigParamFunction"
+          },
+          {
+            "$ref": "#/components/schemas/PersistedAgentToolConfigParamToolSearch"
+          },
+          {
+            "$ref": "#/components/schemas/PersistedAgentToolConfigParamProgrammaticToolCalling"
+          },
+          {
+            "$ref": "#/components/schemas/PersistedAgentToolConfigParamMcp"
+          },
+          {
+            "$ref": "#/components/schemas/PersistedAgentToolConfigParamWebSearch"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "function": "#/components/schemas/PersistedAgentToolConfigParamFunction",
+            "tool_search": "#/components/schemas/PersistedAgentToolConfigParamToolSearch",
+            "programmatic_tool_calling": "#/components/schemas/PersistedAgentToolConfigParamProgrammaticToolCalling",
+            "mcp": "#/components/schemas/PersistedAgentToolConfigParamMcp",
+            "web_search": "#/components/schemas/PersistedAgentToolConfigParamWebSearch"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "function",
+          "tool_search",
+          "programmatic_tool_calling",
+          "mcp",
+          "web_search"
+        ],
+        "description": "A tool that can be stored on a reusable agent without session credentials."
+      },
+      "MultiAgentConfigCurrentParam": {
+        "type": "object",
+        "properties": {
+          "enabled": {
+            "type": "boolean",
+            "description": "Whether subagent tools are enabled."
+          },
+          "max_concurrent_subagents": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 1,
+            "maximum": 4294967295,
+            "description": "Maximum number of subagents that may run concurrently. Defaults to 6."
+          }
+        },
+        "required": [
+          "enabled"
+        ],
+        "additionalProperties": false,
+        "description": "Explicit configuration for creating and coordinating subagents."
+      },
+      "CreateAgentParams": {
+        "type": "object",
+        "properties": {
+          "metadata": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 512
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 64
+            },
+            "minProperties": 0,
+            "maxProperties": 16,
+            "description": "Up to 16 string key-value pairs, with keys up to 64 and values up to 512 characters. Omission or null defaults to an empty map."
+          },
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 128,
+            "description": "A human-readable name for the agent. Omission or null leaves the agent unnamed."
+          },
+          "model": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The model to use for the agent. The requested model name is preserved."
+          },
+          "reasoning": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ReasoningParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Configuration for model reasoning. Omission uses the model's default effort."
+          },
+          "text": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/TextParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Configuration for generated text. Defaults to the `text` format and medium verbosity."
+          },
+          "service_tier": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ServiceTierParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The service tier used for model requests. Defaults to `auto`."
+          },
+          "instructions": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "Additional instructions appended to the agent's default base instructions. Omit or set to null to add no custom instructions."
+          },
+          "tools": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/PersistedAgentToolConfigParam"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Tools available to the agent. Defaults to an empty list."
+          },
+          "multi_agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/MultiAgentConfigCurrentParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Configuration for creating and coordinating subagents. Subagent tools are disabled by default."
+          }
+        },
+        "required": [
+          "model"
+        ],
+        "additionalProperties": false,
+        "description": "Parameters for creating a reusable agent."
+      },
+      "UpdateAgentParams": {
+        "type": "object",
+        "properties": {
+          "model": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The model to use for the agent. The requested model name is preserved."
+          },
+          "reasoning": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ReasoningParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Configuration for model reasoning. Omit to keep the current settings; pass `null` to reset to the model's default effort."
+          },
+          "text": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/TextParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Configuration for text generated by the agent."
+          },
+          "service_tier": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ServiceTierParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The service tier used for model requests."
+          },
+          "instructions": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "Additional instructions appended to the agent's default base instructions. Omit to leave unchanged."
+          },
+          "multi_agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/MultiAgentConfigCurrentParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Configuration for creating and coordinating subagents."
+          },
+          "metadata": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 512
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 64
+            },
+            "minProperties": 0,
+            "maxProperties": 16,
+            "description": "Replaces all metadata. Omit to leave unchanged, or pass null or {} to clear it. Up to 16 string key-value pairs, with keys up to 64 and values up to 512 characters."
+          },
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 128,
+            "description": "A replacement name. Omit to leave unchanged, or pass null to clear it."
+          },
+          "tools": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/PersistedAgentToolConfigParam"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Tools available to the agent."
+          }
+        },
+        "additionalProperties": false,
+        "description": "Fields to replace on an existing reusable agent."
+      },
+      "DeletedAgentResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the deleted agent."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "agent.deleted"
+            ],
+            "default": "agent.deleted",
+            "x-stainless-const": true,
+            "description": "The object type. Always `agent.deleted`."
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the agent was deleted. Always `true`."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ],
+        "additionalProperties": false,
+        "description": "A deleted reusable agent."
+      },
+      "EnvironmentPackagesResource": {
+        "type": "object",
+        "properties": {
+          "python": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Python packages installed in the environment."
+          },
+          "system": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "System packages installed in the environment."
+          },
+          "npm": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "npm packages installed globally in the environment."
+          }
+        },
+        "required": [
+          "python",
+          "system",
+          "npm"
+        ],
+        "additionalProperties": false,
+        "description": "Packages installed in an OpenAI-hosted environment."
+      },
+      "NetworkAccessResource": {
+        "type": "string",
+        "enum": [
+          "enabled",
+          "disabled",
+          "restricted"
+        ],
+        "x-enumDescriptions": [
+          "Allows unrestricted network access.",
+          "Disables network access.",
+          "Allows access only to configured domains."
+        ],
+        "description": "The network access mode for an OpenAI-hosted environment."
+      },
+      "NetworkPolicyResource": {
+        "type": "object",
+        "properties": {
+          "access": {
+            "$ref": "#/components/schemas/NetworkAccessResource",
+            "description": "The environment's network access mode."
+          },
+          "allowed_domains": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Domains the environment may access when network access is restricted."
+          }
+        },
+        "required": [
+          "access",
+          "allowed_domains"
+        ],
+        "additionalProperties": false,
+        "description": "Network access for an OpenAI-hosted environment."
+      },
+      "HostedTemplateSkillResourceSkillReference": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "skill_reference"
+            ],
+            "default": "skill_reference",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `skill_reference`."
+          },
+          "skill_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The referenced skill ID."
+          },
+          "version": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The requested version selector, including `latest`."
+          }
+        },
+        "required": [
+          "type",
+          "skill_id",
+          "version"
+        ],
+        "additionalProperties": false,
+        "description": "A skill resolved afresh from the Skills API whenever a session starts."
+      },
+      "HostedTemplateSkillResourceInline": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "inline"
+            ],
+            "default": "inline",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `inline`."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The skill name declared in `SKILL.md`."
+          },
+          "description": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The skill description declared in `SKILL.md`."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "description"
+        ],
+        "additionalProperties": false,
+        "description": "Safe metadata for an inline skill archive."
+      },
+      "HostedTemplateSkillResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/HostedTemplateSkillResourceSkillReference"
+          },
+          {
+            "$ref": "#/components/schemas/HostedTemplateSkillResourceInline"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "skill_reference": "#/components/schemas/HostedTemplateSkillResourceSkillReference",
+            "inline": "#/components/schemas/HostedTemplateSkillResourceInline"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "skill_reference",
+          "inline"
+        ],
+        "description": "Safe metadata for a skill configured by an environment template."
+      },
+      "HostedTemplateFileResourceFileId": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "file_id"
+            ],
+            "default": "file_id",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `file_id`."
+          },
+          "file_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the uploaded file."
+          },
+          "path": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The file's absolute path inside the environment."
+          }
+        },
+        "required": [
+          "type",
+          "file_id",
+          "path"
+        ],
+        "additionalProperties": false,
+        "description": "A project-scoped Files API reference resolved separately for each session."
+      },
+      "HostedTemplateFileResourceInline": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "inline"
+            ],
+            "default": "inline",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `inline`."
+          },
+          "path": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The file's absolute path inside the environment."
+          },
+          "size_bytes": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "description": "The decoded size of the inline file in bytes."
+          }
+        },
+        "required": [
+          "type",
+          "path",
+          "size_bytes"
+        ],
+        "additionalProperties": false,
+        "description": "Metadata for confidential inline file contents."
+      },
+      "HostedTemplateFileResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/HostedTemplateFileResourceFileId"
+          },
+          {
+            "$ref": "#/components/schemas/HostedTemplateFileResourceInline"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "file_id": "#/components/schemas/HostedTemplateFileResourceFileId",
+            "inline": "#/components/schemas/HostedTemplateFileResourceInline"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "file_id",
+          "inline"
+        ],
+        "description": "Safe metadata for a file configured by an environment template."
+      },
+      "EnvironmentTemplateResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the reusable environment template."
+          },
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "An optional human-readable display name for the template."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "agent.environment.template"
+            ],
+            "default": "agent.environment.template",
+            "x-stainless-const": true,
+            "description": "The object type. Always `agent.environment.template`."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the template was created."
+          },
+          "updated_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the template was last updated."
+          },
+          "packages": {
+            "$ref": "#/components/schemas/EnvironmentPackagesResource",
+            "description": "Packages installed in each fresh OpenAI-hosted environment."
+          },
+          "network": {
+            "$ref": "#/components/schemas/NetworkPolicyResource",
+            "description": "Runtime network access for each OpenAI-hosted environment."
+          },
+          "capability_directories": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Directories that expose capabilities to the agent."
+          },
+          "skills": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/HostedTemplateSkillResource"
+            },
+            "minItems": 0,
+            "maxItems": 200,
+            "description": "Safe skill metadata, preserving unresolved version selectors."
+          },
+          "plugins": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/HostedPluginResource"
+            },
+            "minItems": 0,
+            "maxItems": 32,
+            "description": "Safe plugin metadata, excluding inline archive contents."
+          },
+          "files": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/HostedTemplateFileResource"
+            },
+            "minItems": 0,
+            "maxItems": 50,
+            "description": "Safe file metadata, excluding contents and session-scoped file IDs."
+          }
+        },
+        "required": [
+          "id",
+          "name",
+          "object",
+          "created_at",
+          "updated_at",
+          "packages",
+          "network",
+          "capability_directories",
+          "skills",
+          "plugins",
+          "files"
+        ],
+        "additionalProperties": false,
+        "description": "Reusable configuration that provisions a fresh OpenAI-hosted environment for each session."
+      },
+      "EnvironmentTemplateListResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "x-stainless-const": true,
+            "description": "The object type, which is always `list`."
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/EnvironmentTemplateResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The resources returned in this page, in the requested sort order."
+          },
+          "first_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the first resource in `data`, or `null` if the page is empty."
+          },
+          "last_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the last resource in `data`, or `null` if the page is empty. Pass this as `after` with the same order and filters."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more resources to retrieve after this page."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "additionalProperties": false,
+        "description": "A page of Agents API resources, with IDs for retrieving additional pages."
+      },
+      "EnvironmentPackagesParam": {
+        "type": "object",
+        "properties": {
+          "python": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Python packages to install. Defaults to an empty list."
+          },
+          "system": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "System packages to install. Defaults to an empty list."
+          },
+          "npm": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "npm packages to install globally. Defaults to an empty list."
+          }
+        },
+        "additionalProperties": false,
+        "description": "Packages to install in an OpenAI-hosted environment."
+      },
+      "SetupCommandParam": {
+        "type": "object",
+        "properties": {
+          "command": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 65536,
+            "description": "The shell command to execute."
+          },
+          "cwd": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 4096,
+            "description": "The absolute working directory. Defaults to `/workspace`."
+          }
+        },
+        "required": [
+          "command"
+        ],
+        "additionalProperties": false,
+        "description": "A confidential setup command executed before the hosted agent starts."
+      },
+      "NetworkAccessParam": {
+        "type": "string",
+        "enum": [
+          "enabled",
+          "disabled",
+          "restricted"
+        ],
+        "x-enumDescriptions": [
+          "Allows unrestricted network access, matching an omitted network policy.",
+          "Disables network access.",
+          "Allows access only to configured domains."
+        ],
+        "description": "The network access mode for an OpenAI-hosted environment."
+      },
+      "NetworkPolicyParam": {
+        "type": "object",
+        "properties": {
+          "access": {
+            "$ref": "#/components/schemas/NetworkAccessParam",
+            "description": "The environment's network access mode."
+          },
+          "allowed_domains": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Domains the environment may access when network access is restricted."
+          }
+        },
+        "required": [
+          "access"
+        ],
+        "additionalProperties": false,
+        "description": "Network access for an OpenAI-hosted environment."
+      },
+      "HostedSkillParamSkillReference": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "skill_reference"
+            ],
+            "default": "skill_reference",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `skill_reference`."
+          },
+          "skill_id": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 64,
+            "description": "The ID of the skill created through `/v1/skills`."
+          },
+          "version": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The skill version, a positive integer or `latest`; omission selects the default."
+          }
+        },
+        "required": [
+          "type",
+          "skill_id"
+        ],
+        "additionalProperties": false,
+        "description": "References a skill uploaded through the Skills API."
+      },
+      "InlineCapabilitySourceParamBase64": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "base64"
+            ],
+            "default": "base64",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `base64`."
+          },
+          "media_type": {
+            "type": "string",
+            "enum": [
+              "application/zip"
+            ],
+            "default": "application/zip",
+            "x-stainless-const": true,
+            "x-enumDescriptions": [
+              "A ZIP archive."
+            ],
+            "description": "The archive media type, always `application/zip`."
+          },
+          "data": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 70254592,
+            "description": "Standard-base64 encoded ZIP archive bytes."
+          }
+        },
+        "required": [
+          "type",
+          "media_type",
+          "data"
+        ],
+        "additionalProperties": false,
+        "description": "Provides ZIP bytes encoded with standard base64."
+      },
+      "InlineCapabilitySourceParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/InlineCapabilitySourceParamBase64"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "base64": "#/components/schemas/InlineCapabilitySourceParamBase64"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "base64"
+        ],
+        "description": "The encoded ZIP archive for an inline skill or plugin."
+      },
+      "HostedSkillParamInline": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "inline"
+            ],
+            "default": "inline",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `inline`."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 64,
+            "description": "The skill name declared in `SKILL.md`."
+          },
+          "description": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The skill description declared in `SKILL.md`."
+          },
+          "source": {
+            "$ref": "#/components/schemas/InlineCapabilitySourceParam",
+            "description": "The inline ZIP archive."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "description",
+          "source"
+        ],
+        "additionalProperties": false,
+        "description": "Supplies a skill ZIP directly in the session request."
+      },
+      "HostedSkillParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/HostedSkillParamSkillReference"
+          },
+          {
+            "$ref": "#/components/schemas/HostedSkillParamInline"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "skill_reference": "#/components/schemas/HostedSkillParamSkillReference",
+            "inline": "#/components/schemas/HostedSkillParamInline"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "skill_reference",
+          "inline"
+        ],
+        "description": "A skill installed in an OpenAI-hosted environment."
+      },
+      "HostedPluginParamInline": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "inline"
+            ],
+            "default": "inline",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `inline`."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 64,
+            "description": "The plugin name declared in `.codex-plugin/plugin.json`."
+          },
+          "description": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The plugin description declared in `.codex-plugin/plugin.json`."
+          },
+          "source": {
+            "$ref": "#/components/schemas/InlineCapabilitySourceParam",
+            "description": "The inline ZIP archive."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "description",
+          "source"
+        ],
+        "additionalProperties": false,
+        "description": "Supplies a plugin ZIP directly in the session request."
+      },
+      "HostedPluginParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/HostedPluginParamInline"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "inline": "#/components/schemas/HostedPluginParamInline"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "inline"
+        ],
+        "description": "A plugin installed in an OpenAI-hosted environment."
+      },
+      "CreateEnvironmentTemplateParams": {
+        "type": "object",
+        "properties": {
+          "packages": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/EnvironmentPackagesParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Packages to install in the environment. Defaults to empty package lists."
+          },
+          "setup_commands": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/SetupCommandParam"
+            },
+            "minItems": 0,
+            "maxItems": 16,
+            "description": "Ordered, confidential setup commands. Command bodies are never returned."
+          },
+          "network": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/NetworkPolicyParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Network access policy for the environment. Defaults to enabled."
+          },
+          "env": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "Environment variables made available to the agent."
+          },
+          "capability_directories": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Directories that contain capabilities exposed to the agent. Defaults to an empty list."
+          },
+          "skills": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/HostedSkillParam"
+            },
+            "minItems": 0,
+            "maxItems": 200,
+            "description": "Skills referenced by ID or provided as inline ZIP archives. Defaults to an empty list."
+          },
+          "plugins": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/HostedPluginParam"
+            },
+            "minItems": 0,
+            "maxItems": 32,
+            "description": "Plugins provided as inline ZIP archives. Defaults to an empty list."
+          },
+          "files": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/HostedEnvironmentFileParam"
+            },
+            "minItems": 0,
+            "maxItems": 50,
+            "description": "Files available before the agent starts. Defaults to an empty list."
+          },
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 1,
+            "maxLength": 256,
+            "description": "An optional human-readable display name for the template."
+          }
+        },
+        "additionalProperties": false,
+        "description": "Parameters for creating a reusable, project-scoped OpenAI-hosted environment template."
+      },
+      "UpdateEnvironmentTemplateParams": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 1,
+            "maxLength": 256,
+            "description": "A replacement human-readable display name, or `null` to clear the name."
+          },
+          "packages": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/EnvironmentPackagesParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Packages installed before the runtime network policy applies."
+          },
+          "setup_commands": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/SetupCommandParam"
+            },
+            "minItems": 0,
+            "maxItems": 16,
+            "description": "Replacement confidential setup commands, never included in returned resources."
+          },
+          "network": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/NetworkPolicyParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Network access available after setup completes."
+          },
+          "env": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "Replacement confidential environment values."
+          },
+          "capability_directories": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Directories that expose capabilities to the agent."
+          },
+          "skills": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/HostedSkillParam"
+            },
+            "minItems": 0,
+            "maxItems": 200,
+            "description": "Replacement skill configuration installed for each new session."
+          },
+          "plugins": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/HostedPluginParam"
+            },
+            "minItems": 0,
+            "maxItems": 32,
+            "description": "Replacement plugin configuration installed for each new session."
+          },
+          "files": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/HostedEnvironmentFileParam"
+            },
+            "minItems": 0,
+            "maxItems": 50,
+            "description": "Replacement file configuration materialized for each new session."
+          }
+        },
+        "additionalProperties": false,
+        "description": "Fields to replace on an existing reusable OpenAI-hosted environment template."
+      },
+      "DeletedEnvironmentTemplateResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the deleted environment template."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "agent.environment.template.deleted"
+            ],
+            "default": "agent.environment.template.deleted",
+            "x-stainless-const": true,
+            "description": "The object type. Always `agent.environment.template.deleted`."
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the environment template was deleted. Always `true`."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ],
+        "additionalProperties": false,
+        "description": "A deleted reusable environment template."
+      },
+      "SessionStatusResource": {
+        "type": "string",
+        "enum": [
+          "idle",
+          "in_progress",
+          "requires_action",
+          "failed"
+        ],
+        "x-enumDescriptions": [
+          "The session has no turn in progress and is ready for input. A hosted environment may still be provisioning.",
+          "The session is processing a turn.",
+          "The session is waiting for one or more required actions.",
+          "The session failed."
+        ],
+        "description": "The current status of a session."
+      },
+      "SessionRequiredActionResourceFunctionCall": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "function_call"
+            ],
+            "default": "function_call",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `function_call`."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that requested the function call."
+          },
+          "call_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID to include when submitting the function result."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The function name."
+          },
+          "arguments": {
+            "description": "The arguments supplied by the model."
+          }
+        },
+        "required": [
+          "type",
+          "turn_id",
+          "call_id",
+          "name",
+          "arguments"
+        ],
+        "additionalProperties": false,
+        "description": "Run a function tool and submit its result."
+      },
+      "SessionRequiredActionResourceEnvironmentConnection": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "environment_connection"
+            ],
+            "default": "environment_connection",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `environment_connection`."
+          },
+          "environment_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the environment to reconnect."
+          }
+        },
+        "required": [
+          "type",
+          "environment_id"
+        ],
+        "additionalProperties": false,
+        "description": "Reconnect a session environment."
+      },
+      "SessionRequiredActionResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/SessionRequiredActionResourceFunctionCall"
+          },
+          {
+            "$ref": "#/components/schemas/SessionRequiredActionResourceEnvironmentConnection"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "function_call": "#/components/schemas/SessionRequiredActionResourceFunctionCall",
+            "environment_connection": "#/components/schemas/SessionRequiredActionResourceEnvironmentConnection"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "function_call",
+          "environment_connection"
+        ],
+        "description": "An action that must be completed before a session can continue."
+      },
+      "AgentToolResourceFunction": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "function"
+            ],
+            "default": "function",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `function`."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The name of the function."
+          },
+          "description": {
+            "type": "string",
+            "minLength": 0,
+            "description": "A description of what the function does."
+          },
+          "parameters": {
+            "type": "object",
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minProperties": 0,
+            "description": "A JSON Schema object describing the function's arguments."
+          },
+          "defer_loading": {
+            "type": "boolean",
+            "description": "Whether the function is deferred and discovered through tool search."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "description",
+          "parameters",
+          "defer_loading"
+        ],
+        "additionalProperties": false,
+        "description": "A function defined by the application."
+      },
+      "AgentToolResourceProgrammaticToolCalling": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "programmatic_tool_calling"
+            ],
+            "default": "programmatic_tool_calling",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `programmatic_tool_calling`."
+          },
+          "enabled": {
+            "type": "boolean",
+            "description": "Whether tools can be called from model-generated code."
+          }
+        },
+        "required": [
+          "type",
+          "enabled"
+        ],
+        "additionalProperties": false,
+        "description": "Enables calling tools from model-generated code."
+      },
+      "McpTransportResourceHttp": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "http"
+            ],
+            "default": "http",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `http`."
+          },
+          "server_url": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The URL of the MCP server."
+          }
+        },
+        "required": [
+          "type",
+          "server_url"
+        ],
+        "additionalProperties": false,
+        "description": "Connects to an MCP server over HTTP."
+      },
+      "McpTransportResourceStdio": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "stdio"
+            ],
+            "default": "stdio",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `stdio`."
+          },
+          "command": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The command used to start the MCP server."
+          },
+          "args": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Arguments passed to the MCP server command."
+          },
+          "cwd": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The working directory used to start the MCP server."
+          },
+          "env_vars": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Environment variable names inherited from the execution environment."
+          }
+        },
+        "required": [
+          "type",
+          "command",
+          "args",
+          "cwd",
+          "env_vars"
+        ],
+        "additionalProperties": false,
+        "description": "Starts an MCP server as a local process."
+      },
+      "McpTransportResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/McpTransportResourceHttp"
+          },
+          {
+            "$ref": "#/components/schemas/McpTransportResourceStdio"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "http": "#/components/schemas/McpTransportResourceHttp",
+            "stdio": "#/components/schemas/McpTransportResourceStdio"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "http",
+          "stdio"
+        ],
+        "description": "The transport used to connect to an MCP server."
+      },
+      "AgentToolResourceMcp": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp"
+            ],
+            "default": "mcp",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `mcp`."
+          },
+          "server_label": {
+            "type": "string",
+            "minLength": 0,
+            "description": "A label used to identify the MCP server in tool calls."
+          },
+          "credential_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The attached vault credential selected for this MCP server, if any. Optional when exactly one attached credential matches the server URL."
+          },
+          "transport": {
+            "$ref": "#/components/schemas/McpTransportResource",
+            "description": "The transport used to connect to the MCP server."
+          },
+          "request_metadata": {
+            "type": "object",
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minProperties": 0,
+            "description": "Metadata included with requests to this MCP server."
+          },
+          "allowed_tools": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The MCP tools the agent may call."
+          },
+          "required": {
+            "type": "boolean",
+            "description": "Whether this MCP server must initialize before the first turn."
+          },
+          "connection_origin": {
+            "$ref": "#/components/schemas/McpConnectionOriginResource",
+            "description": "Where outbound MCP HTTP connections originate."
+          }
+        },
+        "required": [
+          "type",
+          "server_label",
+          "credential_id",
+          "transport",
+          "request_metadata",
+          "allowed_tools",
+          "required",
+          "connection_origin"
+        ],
+        "additionalProperties": false,
+        "description": "Tools provided by a remote MCP server."
+      },
+      "AgentToolResourceWebSearch": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "web_search"
+            ],
+            "default": "web_search",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `web_search`."
+          },
+          "mode": {
+            "$ref": "#/components/schemas/WebSearchModeResource",
+            "description": "The source used for web search results."
+          },
+          "context_size": {
+            "$ref": "#/components/schemas/WebSearchContextSizeResource",
+            "description": "The amount of search context made available to the model. Defaults to `medium`."
+          },
+          "allowed_domains": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Allowed search domains, or `null` when the search is unrestricted."
+          },
+          "location": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/WebSearchLocationResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Approximate location used to localize search results, if provided."
+          }
+        },
+        "required": [
+          "type",
+          "mode",
+          "context_size",
+          "allowed_domains",
+          "location"
+        ],
+        "additionalProperties": false,
+        "description": "Web search."
+      },
+      "AgentToolResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/AgentToolResourceFunction"
+          },
+          {
+            "$ref": "#/components/schemas/AgentToolResourceProgrammaticToolCalling"
+          },
+          {
+            "$ref": "#/components/schemas/AgentToolResourceMcp"
+          },
+          {
+            "$ref": "#/components/schemas/AgentToolResourceWebSearch"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "function": "#/components/schemas/AgentToolResourceFunction",
+            "programmatic_tool_calling": "#/components/schemas/AgentToolResourceProgrammaticToolCalling",
+            "mcp": "#/components/schemas/AgentToolResourceMcp",
+            "web_search": "#/components/schemas/AgentToolResourceWebSearch"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "function",
+          "programmatic_tool_calling",
+          "mcp",
+          "web_search"
+        ],
+        "description": "A tool available to the agent."
+      },
+      "SessionAgentResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the agent."
+          },
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The reusable agent's name when the session was created, or null if no name was saved. Later changes to the agent's name do not affect this value."
+          },
+          "model": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The model used by the agent."
+          },
+          "reasoning": {
+            "$ref": "#/components/schemas/ReasoningResource",
+            "description": "The agent's reasoning configuration."
+          },
+          "text": {
+            "$ref": "#/components/schemas/TextResource",
+            "description": "Configuration for text generated by the agent."
+          },
+          "service_tier": {
+            "$ref": "#/components/schemas/ServiceTierResource",
+            "description": "The effective service-tier policy for model requests. Defaults to `auto`."
+          },
+          "instructions": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "Custom instructions appended to the agent's default base instructions."
+          },
+          "tools": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/AgentToolResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Tools available to the agent."
+          },
+          "multi_agent": {
+            "$ref": "#/components/schemas/MultiAgentConfigResource",
+            "description": "Configuration for creating and coordinating subagents."
+          }
+        },
+        "required": [
+          "id",
+          "name",
+          "model",
+          "reasoning",
+          "text",
+          "service_tier",
+          "instructions",
+          "tools",
+          "multi_agent"
+        ],
+        "additionalProperties": false,
+        "description": "The effective agent configuration for a session."
+      },
+      "EnvironmentResourceNone": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "none"
+            ],
+            "default": "none",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `none`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "The session talks to CCA without selecting or provisioning an execution environment."
+      },
+      "EnvironmentResourceOpenaiHosted": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "openai_hosted"
+            ],
+            "default": "openai_hosted",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `openai_hosted`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The public ID of the environment."
+          },
+          "packages": {
+            "$ref": "#/components/schemas/EnvironmentPackagesResource",
+            "description": "Packages installed in the environment."
+          },
+          "network": {
+            "$ref": "#/components/schemas/NetworkPolicyResource",
+            "description": "The effective network access policy for the environment."
+          },
+          "capability_directories": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Directories that contain capabilities exposed to the agent."
+          },
+          "skills": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/HostedSkillResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Skills installed in the environment, excluding their archive contents."
+          },
+          "plugins": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/HostedPluginResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Plugins installed in the environment, excluding their archive contents."
+          },
+          "files": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/HostedEnvironmentFileResource"
+            },
+            "minItems": 0,
+            "maxItems": 50,
+            "description": "Files available in the environment, excluding their contents."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "packages",
+          "network",
+          "capability_directories",
+          "skills",
+          "plugins",
+          "files"
+        ],
+        "additionalProperties": false,
+        "description": "An environment hosted by OpenAI."
+      },
+      "EnvironmentResourceSelfHosted": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "self_hosted"
+            ],
+            "default": "self_hosted",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `self_hosted`."
+          },
+          "remote_url": {
+            "type": "string",
+            "minLength": 0,
+            "description": "Pass this URL unchanged to `codex exec-server --remote` when connecting this environment."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The public ID of the environment."
+          },
+          "workspace_directory": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The absolute project directory inside the environment. Defaults to `/workspace`."
+          },
+          "capability_directories": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Directories that contain capabilities exposed to the agent."
+          }
+        },
+        "required": [
+          "type",
+          "remote_url",
+          "id",
+          "workspace_directory",
+          "capability_directories"
+        ],
+        "additionalProperties": false,
+        "description": "An environment hosted by the application."
+      },
+      "EnvironmentResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/EnvironmentResourceNone"
+          },
+          {
+            "$ref": "#/components/schemas/EnvironmentResourceOpenaiHosted"
+          },
+          {
+            "$ref": "#/components/schemas/EnvironmentResourceSelfHosted"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "none": "#/components/schemas/EnvironmentResourceNone",
+            "openai_hosted": "#/components/schemas/EnvironmentResourceOpenaiHosted",
+            "self_hosted": "#/components/schemas/EnvironmentResourceSelfHosted"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "none",
+          "openai_hosted",
+          "self_hosted"
+        ],
+        "description": "The execution environment for a session."
+      },
+      "SessionResource": {
+        "type": "object",
+        "properties": {
+          "metadata": {
+            "type": "object",
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minProperties": 0,
+            "description": "Custom string key-value pairs attached to the session."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "agent.session"
+            ],
+            "default": "agent.session",
+            "x-stainless-const": true,
+            "description": "The object type. Always `agent.session`."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the session was created."
+          },
+          "last_active_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the session was last active."
+          },
+          "status": {
+            "$ref": "#/components/schemas/SessionStatusResource",
+            "description": "The current status of the session."
+          },
+          "required_actions": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/SessionRequiredActionResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "Actions that must be completed before the session can continue."
+          },
+          "error": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The error that caused the session to fail, if any."
+          },
+          "agent": {
+            "$ref": "#/components/schemas/SessionAgentResource",
+            "description": "The agent running in the session."
+          },
+          "environment": {
+            "$ref": "#/components/schemas/EnvironmentResource",
+            "description": "The execution environment for the session."
+          },
+          "vault_ids": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The IDs of vaults made available to the session."
+          },
+          "usage": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/TokenUsageResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Best-effort token usage for the session, or null if unknown. Recorded usage may change."
+          }
+        },
+        "required": [
+          "metadata",
+          "id",
+          "object",
+          "created_at",
+          "last_active_at",
+          "status",
+          "required_actions",
+          "error",
+          "agent",
+          "environment",
+          "vault_ids",
+          "usage"
+        ],
+        "additionalProperties": false,
+        "description": "A Managed Agents session."
+      },
+      "SessionListResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "x-stainless-const": true,
+            "description": "The object type, which is always `list`."
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/SessionResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The resources returned in this page, in the requested sort order."
+          },
+          "first_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the first resource in `data`, or `null` if the page is empty."
+          },
+          "last_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the last resource in `data`, or `null` if the page is empty. Pass this as `after` with the same order and filters."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more resources to retrieve after this page."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "additionalProperties": false,
+        "description": "A page of Agents API resources, with IDs for retrieving additional pages."
+      },
+      "AgentToolConfigParamFunction": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "function"
+            ],
+            "default": "function",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `function`."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The name of the function."
+          },
+          "description": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "A description of what the function does."
+          },
+          "parameters": {
+            "type": "object",
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "A JSON Schema object describing the function's arguments."
+          },
+          "defer_loading": {
+            "type": "boolean",
+            "default": false,
+            "description": "Whether this function is deferred and discovered through tool search. Defaults to `false`."
+          }
+        },
+        "required": [
+          "type",
+          "name",
+          "description",
+          "parameters"
+        ],
+        "additionalProperties": false,
+        "description": "A function defined by the application."
+      },
+      "AgentToolConfigParamToolSearch": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "tool_search"
+            ],
+            "default": "tool_search",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `tool_search`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Discovers deferred function tools and loads them into the model context."
+      },
+      "AgentToolConfigParamProgrammaticToolCalling": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "programmatic_tool_calling"
+            ],
+            "default": "programmatic_tool_calling",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `programmatic_tool_calling`."
+          },
+          "enabled": {
+            "type": "boolean",
+            "default": true,
+            "description": "Whether tools can be called from model-generated code. Defaults to `true`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Enables calling tools from model-generated code."
+      },
+      "McpTransportConfigParamHttp": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "http"
+            ],
+            "default": "http",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `http`."
+          },
+          "server_url": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The URL of the MCP server."
+          },
+          "authorization": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The authorization value sent to the MCP server, if any."
+          },
+          "headers": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "Additional HTTP headers sent to the MCP server."
+          }
+        },
+        "required": [
+          "type",
+          "server_url"
+        ],
+        "additionalProperties": false,
+        "description": "Connects to an MCP server over HTTP."
+      },
+      "McpTransportConfigParamStdio": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "stdio"
+            ],
+            "default": "stdio",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `stdio`."
+          },
+          "command": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The command used to start the MCP server."
+          },
+          "args": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Arguments passed to the MCP server command."
+          },
+          "cwd": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The working directory used to start the MCP server."
+          },
+          "env": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "Environment variables set for the MCP server process."
+          },
+          "env_vars": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Environment variable names to inherit from the selected execution environment."
+          }
+        },
+        "required": [
+          "type",
+          "command",
+          "cwd"
+        ],
+        "additionalProperties": false,
+        "description": "Starts an MCP server as a local process."
+      },
+      "McpTransportConfigParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/McpTransportConfigParamHttp"
+          },
+          {
+            "$ref": "#/components/schemas/McpTransportConfigParamStdio"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "http": "#/components/schemas/McpTransportConfigParamHttp",
+            "stdio": "#/components/schemas/McpTransportConfigParamStdio"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "http",
+          "stdio"
+        ],
+        "description": "The transport used to connect to an MCP server."
+      },
+      "AgentToolConfigParamMcp": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp"
+            ],
+            "default": "mcp",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `mcp`."
+          },
+          "server_label": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "A label used to identify the MCP server in tool calls."
+          },
+          "credential_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The attached vault credential used to authenticate this MCP server. Optional when exactly one attached credential matches the server URL."
+          },
+          "transport": {
+            "$ref": "#/components/schemas/McpTransportConfigParam",
+            "description": "The transport used to connect to the MCP server."
+          },
+          "request_metadata": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "Metadata included with requests to this MCP server."
+          },
+          "allowed_tools": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "The MCP tools the agent may call. All server tools are allowed when omitted."
+          },
+          "required": {
+            "type": "boolean",
+            "default": false,
+            "description": "Whether this MCP server must initialize before the first turn. Defaults to `false`."
+          },
+          "connection_origin": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/McpConnectionOriginParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Selects where outbound MCP HTTP connections originate. Omitted or `service` uses the Managed Agents service network; `environment` uses the session's selected environment."
+          }
+        },
+        "required": [
+          "type",
+          "server_label",
+          "transport"
+        ],
+        "additionalProperties": false,
+        "description": "Tools provided by a remote MCP server."
+      },
+      "AgentToolConfigParamWebSearch": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "web_search"
+            ],
+            "default": "web_search",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `web_search`."
+          },
+          "mode": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/WebSearchModeParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The source used for web search results. Defaults to `live`."
+          },
+          "context_size": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/WebSearchContextSizeParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The amount of search context made available to the model. Defaults to `medium`."
+          },
+          "allowed_domains": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Domains the search may include."
+          },
+          "location": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/WebSearchLocationParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Approximate location used to localize search results."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Web search."
+      },
+      "AgentToolConfigParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/AgentToolConfigParamFunction"
+          },
+          {
+            "$ref": "#/components/schemas/AgentToolConfigParamToolSearch"
+          },
+          {
+            "$ref": "#/components/schemas/AgentToolConfigParamProgrammaticToolCalling"
+          },
+          {
+            "$ref": "#/components/schemas/AgentToolConfigParamMcp"
+          },
+          {
+            "$ref": "#/components/schemas/AgentToolConfigParamWebSearch"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "function": "#/components/schemas/AgentToolConfigParamFunction",
+            "tool_search": "#/components/schemas/AgentToolConfigParamToolSearch",
+            "programmatic_tool_calling": "#/components/schemas/AgentToolConfigParamProgrammaticToolCalling",
+            "mcp": "#/components/schemas/AgentToolConfigParamMcp",
+            "web_search": "#/components/schemas/AgentToolConfigParamWebSearch"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "function",
+          "tool_search",
+          "programmatic_tool_calling",
+          "mcp",
+          "web_search"
+        ],
+        "description": "A tool available to the agent."
+      },
+      "SessionAgentConfigParam": {
+        "type": "object",
+        "properties": {
+          "model": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The model to use for the agent. The requested model name is preserved."
+          },
+          "reasoning": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ReasoningParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Configuration for model reasoning. Omit to keep the current settings; pass `null` to reset to the model's default effort."
+          },
+          "text": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/TextParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Configuration for text generated by the agent."
+          },
+          "service_tier": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/ServiceTierParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The service tier used for model requests."
+          },
+          "instructions": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "Additional instructions appended to the agent's default base instructions. Omit to leave unchanged."
+          },
+          "multi_agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/MultiAgentConfigCurrentParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Configuration for creating and coordinating subagents."
+          },
+          "tools": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/AgentToolConfigParam"
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Tools available to the agent. Omit to inherit, or pass null to clear them."
+          }
+        },
+        "additionalProperties": false,
+        "description": "Agent configuration for a session. Omitted fields inherit from `agent_id` when supplied. Supplied objects and arrays replace the whole field; null resets nullable fields."
+      },
+      "EnvironmentParamNone": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "none"
+            ],
+            "default": "none",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `none`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Runs the agent without an execution environment."
+      },
+      "EnvironmentParamOpenaiHosted": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "openai_hosted"
+            ],
+            "default": "openai_hosted",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `openai_hosted`."
+          },
+          "packages": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/EnvironmentPackagesParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Packages to install in the environment. Defaults to empty package lists."
+          },
+          "setup_commands": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/SetupCommandParam"
+            },
+            "minItems": 0,
+            "maxItems": 16,
+            "description": "Ordered, confidential setup commands. Command bodies are never returned."
+          },
+          "network": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/NetworkPolicyParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Network access policy for the environment. Defaults to enabled."
+          },
+          "env": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "Environment variables made available to the agent."
+          },
+          "capability_directories": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Directories that contain capabilities exposed to the agent. Defaults to an empty list."
+          },
+          "skills": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/HostedSkillParam"
+            },
+            "minItems": 0,
+            "maxItems": 200,
+            "description": "Skills referenced by ID or provided as inline ZIP archives. Defaults to an empty list."
+          },
+          "plugins": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/HostedPluginParam"
+            },
+            "minItems": 0,
+            "maxItems": 32,
+            "description": "Plugins provided as inline ZIP archives. Defaults to an empty list."
+          },
+          "files": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "$ref": "#/components/schemas/HostedEnvironmentFileParam"
+            },
+            "minItems": 0,
+            "maxItems": 50,
+            "description": "Files available before the agent starts. Defaults to an empty list."
+          },
+          "environment_template_id": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 64,
+            "description": "A reusable hosted template applied before inline session configuration. Omitted fields inherit the template; network overrides cannot broaden its policy."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "An OpenAI-hosted environment, optionally based on a reusable template."
+      },
+      "EnvironmentParamSelfHosted": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "self_hosted"
+            ],
+            "default": "self_hosted",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `self_hosted`."
+          },
+          "workspace_directory": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "Absolute project directory inside the self-hosted environment."
+          },
+          "capability_directories": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "Directories that contain capabilities exposed to the agent. Defaults to an empty list."
+          }
+        },
+        "required": [
+          "type",
+          "workspace_directory"
+        ],
+        "additionalProperties": false,
+        "description": "An application-hosted environment configured inline."
+      },
+      "EnvironmentParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/EnvironmentParamNone"
+          },
+          {
+            "$ref": "#/components/schemas/EnvironmentParamOpenaiHosted"
+          },
+          {
+            "$ref": "#/components/schemas/EnvironmentParamSelfHosted"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "none": "#/components/schemas/EnvironmentParamNone",
+            "openai_hosted": "#/components/schemas/EnvironmentParamOpenaiHosted",
+            "self_hosted": "#/components/schemas/EnvironmentParamSelfHosted"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "none",
+          "openai_hosted",
+          "self_hosted"
+        ],
+        "description": "The execution environment and optional reusable template for a session."
+      },
+      "InputContentParamInputText": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_text"
+            ],
+            "default": "input_text",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `input_text`."
+          },
+          "text": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The text sent to the model."
+          }
+        },
+        "required": [
+          "type",
+          "text"
+        ],
+        "additionalProperties": false,
+        "description": "Text input to the model."
+      },
+      "InputContentParamInputImage": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_image"
+            ],
+            "default": "input_image",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `input_image`."
+          },
+          "image_url": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The URL of the image sent to the model."
+          }
+        },
+        "required": [
+          "type",
+          "image_url"
+        ],
+        "additionalProperties": false,
+        "description": "Image input to the model."
+      },
+      "InputContentParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/InputContentParamInputText"
+          },
+          {
+            "$ref": "#/components/schemas/InputContentParamInputImage"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "input_text": "#/components/schemas/InputContentParamInputText",
+            "input_image": "#/components/schemas/InputContentParamInputImage"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "input_text",
+          "input_image"
+        ],
+        "description": "Content included in an input message."
+      },
+      "InputMessageParam": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "message"
+            ],
+            "default": "message",
+            "x-stainless-const": true,
+            "description": "The type of the input item. Always `message`."
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "user"
+            ],
+            "default": "user",
+            "x-stainless-const": true,
+            "description": "The role of the message author. Always `user`."
+          },
+          "content": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/InputContentParam"
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "The content of the message."
+          }
+        },
+        "required": [
+          "role",
+          "content"
+        ],
+        "additionalProperties": false,
+        "description": "A user message submitted to a session."
+      },
+      "CreateSessionInputParam": {
+        "oneOf": [
+          {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 1048576
+          },
+          {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/InputMessageParam"
+            },
+            "minItems": 0,
+            "maxItems": 16384
+          }
+        ],
+        "description": "Initial input submitted when creating a session."
+      },
+      "CreateAgentSessionParams": {
+        "type": "object",
+        "properties": {
+          "metadata": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 512
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 64
+            },
+            "minProperties": 0,
+            "maxProperties": 16,
+            "description": "Up to 16 string key-value pairs, with keys up to 64 and values up to 512 characters. Omission or null defaults to an empty map."
+          },
+          "agent": {
+            "$ref": "#/components/schemas/SessionAgentConfigParam",
+            "description": "Agent configuration. With `agent_id`, supplied fields override the saved agent for this session. Without `agent_id`, `model` is required."
+          },
+          "agent_id": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 64,
+            "description": "The ID of a saved reusable agent. Omit `agent` to use its configuration unchanged."
+          },
+          "environment": {
+            "$ref": "#/components/schemas/EnvironmentParam",
+            "description": "An inline execution environment or a reference to an environment template."
+          },
+          "vault_ids": {
+            "type": [
+              "array",
+              "null"
+            ],
+            "items": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "The IDs of vaults made available to the session."
+          },
+          "input": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/CreateSessionInputParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Initial input to submit when the session is created. A string is shorthand for a single user message. Required when `environment.type` is `none`, or when `stream` is `true` for an environment that is not `self_hosted`; optional for self-hosted and non-streaming execution environments."
+          },
+          "stream": {
+            "type": "boolean",
+            "default": false,
+            "description": "Whether to stream session events as server-sent events. Defaults to `false`."
+          }
+        },
+        "required": [
+          "environment"
+        ],
+        "additionalProperties": false,
+        "description": "Parameters for creating a Managed Agents session."
+      },
+      "SessionErrorResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The error type."
+          },
+          "code": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The machine-readable error code, if any."
+          },
+          "message": {
+            "type": "string",
+            "minLength": 0,
+            "description": "A customer-safe explanation of the error."
+          },
+          "param": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The request parameter associated with the error, if any."
+          }
+        },
+        "required": [
+          "type",
+          "code",
+          "message",
+          "param"
+        ],
+        "additionalProperties": false,
+        "description": "An error payload with the same public fields as Responses API streaming errors."
+      },
+      "SessionEventError": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "error"
+            ],
+            "default": "error",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `error`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "error": {
+            "$ref": "#/components/schemas/SessionErrorResource",
+            "description": "The error that occurred."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "error"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a turn or session fails.",
+        "x-oaiMeta": {
+          "example": {
+            "type": "error",
+            "event_id": "event_123",
+            "session_id": "sess_123",
+            "error": {
+              "type": "server_error",
+              "code": null,
+              "message": "The session failed due to an internal server error.",
+              "param": null
+            }
+          }
+        }
+      },
+      "SessionEnvironmentStatusResource": {
+        "type": "string",
+        "enum": [
+          "pending",
+          "ready",
+          "connected",
+          "disconnected",
+          "failed"
+        ],
+        "x-enumDescriptions": [
+          "The environment is being prepared.",
+          "The environment is ready to connect.",
+          "The environment is connected.",
+          "The environment is disconnected.",
+          "The environment failed to connect."
+        ],
+        "description": "The connection status of a session environment."
+      },
+      "SessionEnvironmentErrorResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The error type."
+          },
+          "code": {
+            "type": "string",
+            "minLength": 0,
+            "description": "A machine-readable error code."
+          },
+          "message": {
+            "type": "string",
+            "minLength": 0,
+            "description": "A human-readable error message."
+          }
+        },
+        "required": [
+          "type",
+          "code",
+          "message"
+        ],
+        "additionalProperties": false,
+        "description": "An error reported while preparing a session environment."
+      },
+      "SessionEnvironmentStateResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The public ID of the environment."
+          },
+          "type": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The environment type."
+          },
+          "status": {
+            "$ref": "#/components/schemas/SessionEnvironmentStatusResource",
+            "description": "The environment's connection status."
+          },
+          "error": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/SessionEnvironmentErrorResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The error reported while preparing the environment, if any."
+          }
+        },
+        "required": [
+          "id",
+          "type",
+          "status",
+          "error"
+        ],
+        "additionalProperties": false,
+        "description": "The current state of a session environment."
+      },
+      "SessionEventAgentSessionEnvironmentReady": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.environment.ready"
+            ],
+            "default": "agent.session.environment.ready",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.environment.ready`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "environment": {
+            "$ref": "#/components/schemas/SessionEnvironmentStateResource",
+            "description": "The current environment state."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "environment"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a hosted session environment is ready to connect."
+      },
+      "SessionEventAgentOutputCommandExecutionOutputDelta": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.output.command_execution_output.delta"
+            ],
+            "default": "agent.output.command_execution_output.delta",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.output.command_execution_output.delta`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "item_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the command execution item."
+          },
+          "output_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the item in the turn output."
+          },
+          "delta": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The output text that was appended."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "item_id",
+          "output_index",
+          "delta"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when command execution produces an output delta."
+      },
+      "SessionEventAgentSessionCreated": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.created"
+            ],
+            "default": "agent.session.created",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.created`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session": {
+            "$ref": "#/components/schemas/SessionResource",
+            "description": "The session that was created."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a session is created."
+      },
+      "SessionEventAgentSessionTurnCreated": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.created"
+            ],
+            "default": "agent.session.turn.created",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.created`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event."
+          },
+          "turn": {
+            "$ref": "#/components/schemas/TurnResource",
+            "description": "The turn at the time it was created."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "turn"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a turn is created."
+      },
+      "SessionEventAgentSessionTurnInProgress": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.in_progress"
+            ],
+            "default": "agent.session.turn.in_progress",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.in_progress`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event."
+          },
+          "turn": {
+            "$ref": "#/components/schemas/TurnResource",
+            "description": "The turn at the time it started running."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "turn"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a turn starts running."
+      },
+      "SessionEventAgentSessionTurnCompleted": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.completed"
+            ],
+            "default": "agent.session.turn.completed",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.completed`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event."
+          },
+          "turn": {
+            "$ref": "#/components/schemas/TurnResource",
+            "description": "The completed turn."
+          },
+          "usage": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/TokenUsageResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Token usage by the root agent during the turn, when available."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "turn",
+          "usage"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a turn completes."
+      },
+      "SessionEventAgentSessionTurnFailed": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.failed"
+            ],
+            "default": "agent.session.turn.failed",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.failed`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event."
+          },
+          "turn": {
+            "$ref": "#/components/schemas/TurnResource",
+            "description": "The failed turn."
+          },
+          "usage": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/TokenUsageResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Token usage by the root agent during the turn, when available."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "turn",
+          "usage"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a turn fails."
+      },
+      "SessionEventAgentSessionTurnCancelled": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.cancelled"
+            ],
+            "default": "agent.session.turn.cancelled",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.cancelled`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event."
+          },
+          "turn": {
+            "$ref": "#/components/schemas/TurnResource",
+            "description": "The cancelled turn."
+          },
+          "usage": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/TokenUsageResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Token usage by the root agent during the turn, when available."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "turn",
+          "usage"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a turn is cancelled."
+      },
+      "SessionEventAgentSessionTurnItemAdded": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.item.added"
+            ],
+            "default": "agent.session.turn.item.added",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.item.added`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "output_index": {
+            "type": [
+              "integer",
+              "null"
+            ],
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the item in the turn output, when the item is agent output."
+          },
+          "item": {
+            "$ref": "#/components/schemas/SessionTurnItemResource",
+            "description": "The item that was added."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "output_index",
+          "item"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when an item is added to a turn."
+      },
+      "SessionEventAgentSessionIdle": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.idle"
+            ],
+            "default": "agent.session.idle",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.idle`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session": {
+            "$ref": "#/components/schemas/SessionResource",
+            "description": "The session that became idle."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a session becomes idle."
+      },
+      "SessionEventAgentSessionInProgress": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.in_progress"
+            ],
+            "default": "agent.session.in_progress",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.in_progress`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session": {
+            "$ref": "#/components/schemas/SessionResource",
+            "description": "The session that started processing."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a session starts processing a turn."
+      },
+      "SessionEventAgentSessionRequiresAction": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.requires_action"
+            ],
+            "default": "agent.session.requires_action",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.requires_action`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session": {
+            "$ref": "#/components/schemas/SessionResource",
+            "description": "The session and its current required actions."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a session is waiting for one or more required actions."
+      },
+      "SessionEventAgentSessionFailed": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.failed"
+            ],
+            "default": "agent.session.failed",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.failed`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session": {
+            "$ref": "#/components/schemas/SessionResource",
+            "description": "The failed session."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a session fails."
+      },
+      "SessionEventAgentSessionEnvironmentPending": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.environment.pending"
+            ],
+            "default": "agent.session.environment.pending",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.environment.pending`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "environment": {
+            "$ref": "#/components/schemas/SessionEnvironmentStateResource",
+            "description": "The current environment state."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "environment"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted while a session environment is being prepared."
+      },
+      "SessionEventAgentSessionEnvironmentConnected": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.environment.connected"
+            ],
+            "default": "agent.session.environment.connected",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.environment.connected`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "environment": {
+            "$ref": "#/components/schemas/SessionEnvironmentStateResource",
+            "description": "The current environment state."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "environment"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a session environment connects."
+      },
+      "SessionEventAgentSessionEnvironmentDisconnected": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.environment.disconnected"
+            ],
+            "default": "agent.session.environment.disconnected",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.environment.disconnected`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "environment": {
+            "$ref": "#/components/schemas/SessionEnvironmentStateResource",
+            "description": "The current environment state."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "environment"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a session environment disconnects."
+      },
+      "SessionEventAgentSessionEnvironmentFailed": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.environment.failed"
+            ],
+            "default": "agent.session.environment.failed",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.environment.failed`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "environment": {
+            "$ref": "#/components/schemas/SessionEnvironmentStateResource",
+            "description": "The current environment state."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "environment"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a session environment fails."
+      },
+      "SessionEventAgentSessionSubagentCreated": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.subagent.created"
+            ],
+            "default": "agent.session.subagent.created",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.subagent.created`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "subagent": {
+            "$ref": "#/components/schemas/SubagentResource",
+            "description": "The subagent that was created."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "subagent"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a subagent is created."
+      },
+      "SessionEventAgentSessionSubagentActive": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.subagent.active"
+            ],
+            "default": "agent.session.subagent.active",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.subagent.active`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "subagent": {
+            "$ref": "#/components/schemas/SubagentResource",
+            "description": "The subagent that resumed."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "subagent"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a closed subagent successfully resumes."
+      },
+      "SessionEventAgentSessionSubagentClosed": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.subagent.closed"
+            ],
+            "default": "agent.session.subagent.closed",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.subagent.closed`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "subagent": {
+            "$ref": "#/components/schemas/SubagentResource",
+            "description": "The subagent that was closed."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "subagent"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a subagent is closed."
+      },
+      "AssistantMessageItemResource": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "message"
+            ],
+            "default": "message",
+            "x-stainless-const": true,
+            "description": "The item type. Always `message`."
+          },
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the message."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the turn that contains this item."
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "assistant"
+            ],
+            "default": "assistant",
+            "x-stainless-const": true,
+            "description": "The role of the message author. Always `assistant`."
+          },
+          "status": {
+            "$ref": "#/components/schemas/OutputItemStatusResource",
+            "description": "The status of the message."
+          },
+          "content": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/OutputTextResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The content of the message."
+          },
+          "phase": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/MessagePhaseResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The phase of the assistant message."
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "turn_id",
+          "role",
+          "status",
+          "content",
+          "phase"
+        ],
+        "additionalProperties": false,
+        "description": "An assistant message produced by the agent."
+      },
+      "AgentOutputItemResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/AssistantMessageItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/ReasoningItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/FunctionCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/McpCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/WebSearchCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/CommandExecutionItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/CreateSubagentCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/SendSubagentInputCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/ResumeSubagentCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/WaitForSubagentsCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/InterruptSubagentCallItemResource"
+          },
+          {
+            "$ref": "#/components/schemas/CloseSubagentCallItemResource"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "message": "#/components/schemas/AssistantMessageItemResource",
+            "reasoning": "#/components/schemas/ReasoningItemResource",
+            "function_call": "#/components/schemas/FunctionCallItemResource",
+            "mcp_call": "#/components/schemas/McpCallItemResource",
+            "web_search_call": "#/components/schemas/WebSearchCallItemResource",
+            "command_execution": "#/components/schemas/CommandExecutionItemResource",
+            "interrupt_subagent_call": "#/components/schemas/InterruptSubagentCallItemResource",
+            "create_subagent_call": "#/components/schemas/CreateSubagentCallItemResource",
+            "send_subagent_input_call": "#/components/schemas/SendSubagentInputCallItemResource",
+            "resume_subagent_call": "#/components/schemas/ResumeSubagentCallItemResource",
+            "wait_for_subagents_call": "#/components/schemas/WaitForSubagentsCallItemResource",
+            "close_subagent_call": "#/components/schemas/CloseSubagentCallItemResource"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "message",
+          "reasoning",
+          "function_call",
+          "mcp_call",
+          "web_search_call",
+          "command_execution",
+          "create_subagent_call",
+          "send_subagent_input_call",
+          "resume_subagent_call",
+          "wait_for_subagents_call",
+          "interrupt_subagent_call",
+          "close_subagent_call"
+        ],
+        "description": "An output item produced by an agent."
+      },
+      "SessionEventAgentSessionTurnItemDone": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.item.done"
+            ],
+            "default": "agent.session.turn.item.done",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.item.done`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "output_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the output item in the turn output."
+          },
+          "item": {
+            "$ref": "#/components/schemas/AgentOutputItemResource",
+            "description": "The completed output item."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "output_index",
+          "item"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when an output item is complete."
+      },
+      "SessionEventAgentSessionTurnContentPartAdded": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.content_part.added"
+            ],
+            "default": "agent.session.turn.content_part.added",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.content_part.added`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "item_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the message item."
+          },
+          "output_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the item in the turn output."
+          },
+          "content_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the content part in the message."
+          },
+          "part": {
+            "$ref": "#/components/schemas/OutputTextResource",
+            "description": "The initial content part."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "part"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when an output text content part is added."
+      },
+      "SessionEventAgentSessionTurnContentPartDone": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.content_part.done"
+            ],
+            "default": "agent.session.turn.content_part.done",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.content_part.done`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "item_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the message item."
+          },
+          "output_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the item in the turn output."
+          },
+          "content_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the content part in the message."
+          },
+          "part": {
+            "$ref": "#/components/schemas/OutputTextResource",
+            "description": "The completed content part."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "part"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when an output content part is complete."
+      },
+      "SessionEventAgentSessionTurnOutputTextDelta": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.output_text.delta"
+            ],
+            "default": "agent.session.turn.output_text.delta",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.output_text.delta`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "item_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the message item."
+          },
+          "output_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the item in the turn output."
+          },
+          "content_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the content part in the message."
+          },
+          "delta": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The text that was appended."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "delta"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when text is appended to an output text content part."
+      },
+      "SessionEventAgentSessionTurnOutputTextDone": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.output_text.done"
+            ],
+            "default": "agent.session.turn.output_text.done",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.output_text.done`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "item_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the message item."
+          },
+          "output_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the item in the turn output."
+          },
+          "content_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the content part in the message."
+          },
+          "text": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The complete output text."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "item_id",
+          "output_index",
+          "content_index",
+          "text"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when an output text content part is complete."
+      },
+      "SessionEventAgentSessionTurnReasoningSummaryPartAdded": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.reasoning_summary_part.added"
+            ],
+            "default": "agent.session.turn.reasoning_summary_part.added",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.reasoning_summary_part.added`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "item_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the reasoning item."
+          },
+          "output_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the item in the turn output."
+          },
+          "summary_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the summary content part."
+          },
+          "part": {
+            "$ref": "#/components/schemas/SummaryTextResource",
+            "description": "The initial summary part."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "item_id",
+          "output_index",
+          "summary_index",
+          "part"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a reasoning summary content part is added."
+      },
+      "SessionEventAgentSessionTurnReasoningSummaryPartDone": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.reasoning_summary_part.done"
+            ],
+            "default": "agent.session.turn.reasoning_summary_part.done",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.reasoning_summary_part.done`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "item_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the reasoning item."
+          },
+          "output_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the item in the turn output."
+          },
+          "summary_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the summary part."
+          },
+          "part": {
+            "$ref": "#/components/schemas/SummaryTextResource",
+            "description": "The completed summary part."
+          },
+          "status": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "enum": [
+              "incomplete",
+              null
+            ],
+            "description": "Present as `incomplete` when summary generation was interrupted.",
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "item_id",
+          "output_index",
+          "summary_index",
+          "part",
+          "status"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a reasoning summary part is complete."
+      },
+      "SessionEventAgentSessionTurnReasoningSummaryTextDelta": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.reasoning_summary_text.delta"
+            ],
+            "default": "agent.session.turn.reasoning_summary_text.delta",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.reasoning_summary_text.delta`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "item_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the reasoning item."
+          },
+          "output_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the item in the turn output."
+          },
+          "summary_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the summary content part."
+          },
+          "delta": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The summary text that was appended."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "item_id",
+          "output_index",
+          "summary_index",
+          "delta"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when text is appended to a reasoning summary."
+      },
+      "SessionEventAgentSessionTurnReasoningSummaryTextDone": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.turn.reasoning_summary_text.done"
+            ],
+            "default": "agent.session.turn.reasoning_summary_text.done",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.turn.reasoning_summary_text.done`."
+          },
+          "event_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The unique ID of the event."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session associated with the event."
+          },
+          "turn_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the turn associated with the event, when applicable."
+          },
+          "item_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the reasoning item."
+          },
+          "output_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the item in the turn output."
+          },
+          "summary_index": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "maximum": 4294967295,
+            "description": "The index of the summary content part."
+          },
+          "text": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The complete reasoning summary text."
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session_id",
+          "turn_id",
+          "item_id",
+          "output_index",
+          "summary_index",
+          "text"
+        ],
+        "additionalProperties": false,
+        "description": "Emitted when a reasoning summary content part is complete."
+      },
+      "SessionEvent": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/SessionEventError"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionEnvironmentReady"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentOutputCommandExecutionOutputDelta"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionCreated"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnCreated"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnInProgress"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnCompleted"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnFailed"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnCancelled"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnItemAdded"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionIdle"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionInProgress"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionRequiresAction"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionFailed"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionEnvironmentPending"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionEnvironmentConnected"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionEnvironmentDisconnected"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionEnvironmentFailed"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionSubagentCreated"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionSubagentActive"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionSubagentClosed"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnItemDone"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnContentPartAdded"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnContentPartDone"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnOutputTextDelta"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnOutputTextDone"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnReasoningSummaryPartAdded"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnReasoningSummaryPartDone"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnReasoningSummaryTextDelta"
+          },
+          {
+            "$ref": "#/components/schemas/SessionEventAgentSessionTurnReasoningSummaryTextDone"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "error": "#/components/schemas/SessionEventError",
+            "agent.session.environment.ready": "#/components/schemas/SessionEventAgentSessionEnvironmentReady",
+            "agent.output.command_execution_output.delta": "#/components/schemas/SessionEventAgentOutputCommandExecutionOutputDelta",
+            "agent.session.created": "#/components/schemas/SessionEventAgentSessionCreated",
+            "agent.session.turn.created": "#/components/schemas/SessionEventAgentSessionTurnCreated",
+            "agent.session.turn.in_progress": "#/components/schemas/SessionEventAgentSessionTurnInProgress",
+            "agent.session.turn.completed": "#/components/schemas/SessionEventAgentSessionTurnCompleted",
+            "agent.session.turn.failed": "#/components/schemas/SessionEventAgentSessionTurnFailed",
+            "agent.session.turn.cancelled": "#/components/schemas/SessionEventAgentSessionTurnCancelled",
+            "agent.session.turn.item.added": "#/components/schemas/SessionEventAgentSessionTurnItemAdded",
+            "agent.session.idle": "#/components/schemas/SessionEventAgentSessionIdle",
+            "agent.session.in_progress": "#/components/schemas/SessionEventAgentSessionInProgress",
+            "agent.session.requires_action": "#/components/schemas/SessionEventAgentSessionRequiresAction",
+            "agent.session.failed": "#/components/schemas/SessionEventAgentSessionFailed",
+            "agent.session.environment.pending": "#/components/schemas/SessionEventAgentSessionEnvironmentPending",
+            "agent.session.environment.connected": "#/components/schemas/SessionEventAgentSessionEnvironmentConnected",
+            "agent.session.environment.disconnected": "#/components/schemas/SessionEventAgentSessionEnvironmentDisconnected",
+            "agent.session.environment.failed": "#/components/schemas/SessionEventAgentSessionEnvironmentFailed",
+            "agent.session.subagent.created": "#/components/schemas/SessionEventAgentSessionSubagentCreated",
+            "agent.session.subagent.active": "#/components/schemas/SessionEventAgentSessionSubagentActive",
+            "agent.session.subagent.closed": "#/components/schemas/SessionEventAgentSessionSubagentClosed",
+            "agent.session.turn.item.done": "#/components/schemas/SessionEventAgentSessionTurnItemDone",
+            "agent.session.turn.content_part.added": "#/components/schemas/SessionEventAgentSessionTurnContentPartAdded",
+            "agent.session.turn.content_part.done": "#/components/schemas/SessionEventAgentSessionTurnContentPartDone",
+            "agent.session.turn.output_text.delta": "#/components/schemas/SessionEventAgentSessionTurnOutputTextDelta",
+            "agent.session.turn.output_text.done": "#/components/schemas/SessionEventAgentSessionTurnOutputTextDone",
+            "agent.session.turn.reasoning_summary_part.added": "#/components/schemas/SessionEventAgentSessionTurnReasoningSummaryPartAdded",
+            "agent.session.turn.reasoning_summary_part.done": "#/components/schemas/SessionEventAgentSessionTurnReasoningSummaryPartDone",
+            "agent.session.turn.reasoning_summary_text.delta": "#/components/schemas/SessionEventAgentSessionTurnReasoningSummaryTextDelta",
+            "agent.session.turn.reasoning_summary_text.done": "#/components/schemas/SessionEventAgentSessionTurnReasoningSummaryTextDone"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "error",
+          "agent.session.environment.ready",
+          "agent.output.command_execution_output.delta",
+          "agent.session.created",
+          "agent.session.turn.created",
+          "agent.session.turn.in_progress",
+          "agent.session.turn.completed",
+          "agent.session.turn.failed",
+          "agent.session.turn.cancelled",
+          "agent.session.turn.item.added",
+          "agent.session.idle",
+          "agent.session.in_progress",
+          "agent.session.requires_action",
+          "agent.session.failed",
+          "agent.session.environment.pending",
+          "agent.session.environment.connected",
+          "agent.session.environment.disconnected",
+          "agent.session.environment.failed",
+          "agent.session.subagent.created",
+          "agent.session.subagent.active",
+          "agent.session.subagent.closed",
+          "agent.session.turn.item.done",
+          "agent.session.turn.content_part.added",
+          "agent.session.turn.content_part.done",
+          "agent.session.turn.output_text.delta",
+          "agent.session.turn.output_text.done",
+          "agent.session.turn.reasoning_summary_part.added",
+          "agent.session.turn.reasoning_summary_part.done",
+          "agent.session.turn.reasoning_summary_text.delta",
+          "agent.session.turn.reasoning_summary_text.done"
+        ],
+        "description": "An event emitted by a Managed Agents session."
+      },
+      "UpdateAgentSessionParams": {
+        "type": "object",
+        "properties": {
+          "metadata": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 512
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 64
+            },
+            "minProperties": 0,
+            "maxProperties": 16,
+            "description": "Replaces all metadata. Omit to leave unchanged, or pass null or {} to clear it. Up to 16 string key-value pairs, with keys up to 64 and values up to 512 characters."
+          }
+        },
+        "additionalProperties": false,
+        "description": "Fields to update on an existing session."
+      },
+      "DeletedSessionResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the deleted session."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "agent.session.deleted"
+            ],
+            "default": "agent.session.deleted",
+            "x-stainless-const": true,
+            "description": "The object type. Always `agent.session.deleted`."
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the session has been removed from the public API. Always `true`. Physical cleanup may still be in progress."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ],
+        "additionalProperties": false,
+        "description": "A Managed Agents session removed from the public API. Physical cleanup may continue asynchronously."
+      },
+      "SessionArtifactResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The immutable artifact ID."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "agent.session.artifact"
+            ],
+            "default": "agent.session.artifact",
+            "x-stainless-const": true,
+            "description": "The object type. Always `agent.session.artifact`."
+          },
+          "session_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the session that owns the artifact."
+          },
+          "environment_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the environment that produced the artifact."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the completed turn that published the artifact."
+          },
+          "path": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The original absolute file path in the execution environment."
+          },
+          "size_bytes": {
+            "type": "integer",
+            "format": "int64",
+            "minimum": 0,
+            "description": "The immutable artifact size in bytes."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the artifact was published."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "session_id",
+          "environment_id",
+          "turn_id",
+          "path",
+          "size_bytes",
+          "created_at"
+        ],
+        "additionalProperties": false,
+        "description": "An immutable file published by a completed hosted session turn."
+      },
+      "SessionArtifactListResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "x-stainless-const": true,
+            "description": "The object type, which is always `list`."
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/SessionArtifactResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The resources returned in this page, in the requested sort order."
+          },
+          "first_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the first resource in `data`, or `null` if the page is empty."
+          },
+          "last_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the last resource in `data`, or `null` if the page is empty. Pass this as `after` with the same order and filters."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more resources to retrieve after this page."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "additionalProperties": false,
+        "description": "A page of Agents API resources, with IDs for retrieving additional pages."
+      },
+      "DeletedSessionArtifactResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the deleted session artifact."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "agent.session.artifact.deleted"
+            ],
+            "default": "agent.session.artifact.deleted",
+            "x-stainless-const": true,
+            "description": "The object type. Always `agent.session.artifact.deleted`."
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the session artifact was deleted. Always `true`."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ],
+        "additionalProperties": false,
+        "description": "Confirmation that an immutable session artifact was deleted."
+      },
+      "SessionInputParamAgentSessionInputMessage": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.input.message"
+            ],
+            "default": "agent.session.input.message",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.input.message`."
+          },
+          "input": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/InputMessageParam"
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "The user messages to add to the session."
+          }
+        },
+        "required": [
+          "type",
+          "input"
+        ],
+        "additionalProperties": false,
+        "description": "Adds one or more user messages and starts a turn."
+      },
+      "SessionInputParamAgentSessionInputCancel": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.input.cancel"
+            ],
+            "default": "agent.session.input.cancel",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.input.cancel`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Cancels the session's active turn."
+      },
+      "FunctionCallOutputParam": {
+        "oneOf": [
+          {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576
+          },
+          {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/InputContentParam"
+            },
+            "minItems": 0,
+            "maxItems": 16384
+          }
+        ],
+        "description": "A function result represented as text or supported model-input content."
+      },
+      "SessionInputParamAgentSessionInputToolResult": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent.session.input.tool_result"
+            ],
+            "default": "agent.session.input.tool_result",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `agent.session.input.tool_result`."
+          },
+          "turn_id": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The ID of the turn that requested the function call."
+          },
+          "call_id": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The ID of the function call."
+          },
+          "success": {
+            "type": "boolean",
+            "description": "Whether the function call succeeded."
+          },
+          "output": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/FunctionCallOutputParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The function result when the call succeeded."
+          },
+          "error": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The error message when the call failed."
+          }
+        },
+        "required": [
+          "type",
+          "turn_id",
+          "call_id",
+          "success"
+        ],
+        "additionalProperties": false,
+        "description": "Submits the result of a function call."
+      },
+      "SessionInputParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/SessionInputParamAgentSessionInputMessage"
+          },
+          {
+            "$ref": "#/components/schemas/SessionInputParamAgentSessionInputCancel"
+          },
+          {
+            "$ref": "#/components/schemas/SessionInputParamAgentSessionInputToolResult"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "agent.session.input.message": "#/components/schemas/SessionInputParamAgentSessionInputMessage",
+            "agent.session.input.cancel": "#/components/schemas/SessionInputParamAgentSessionInputCancel",
+            "agent.session.input.tool_result": "#/components/schemas/SessionInputParamAgentSessionInputToolResult"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "agent.session.input.message",
+          "agent.session.input.cancel",
+          "agent.session.input.tool_result"
+        ],
+        "description": "Input submitted to an existing session."
+      },
+      "CreateSessionEventsParams": {
+        "type": "object",
+        "properties": {
+          "events": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/SessionInputParam"
+            },
+            "minItems": 0,
+            "maxItems": 16384,
+            "description": "The input events to submit to the session."
+          }
+        },
+        "required": [
+          "events"
+        ],
+        "additionalProperties": false,
+        "description": "Input events submitted to an existing session."
+      },
+      "VaultStatusParam": {
+        "type": "string",
+        "enum": [
+          "active",
+          "archived"
+        ],
+        "description": "Whether a vault or credential is active or archived."
+      },
+      "VaultStatusFilterParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/VaultStatusParam"
+          },
+          {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/VaultStatusParam"
+            },
+            "minItems": 0,
+            "maxItems": 16384
+          }
+        ],
+        "description": "One or more lifecycle statuses to include when listing vaults or credentials."
+      },
+      "VaultResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the vault."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "vault"
+            ],
+            "default": "vault",
+            "x-stainless-const": true,
+            "description": "The object type. Always `vault`."
+          },
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The human-readable name of the vault, if set."
+          },
+          "metadata": {
+            "type": "object",
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 0
+            },
+            "minProperties": 0,
+            "description": "Key-value pairs associated with the vault, such as an application or team identifier."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the vault was created."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "name",
+          "metadata",
+          "created_at"
+        ],
+        "additionalProperties": false,
+        "description": "A collection of credentials that agent tools can use to authenticate to MCP servers."
+      },
+      "VaultListResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "x-stainless-const": true,
+            "description": "The object type, which is always `list`."
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/VaultResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The resources returned in this page, in the requested sort order."
+          },
+          "first_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the first resource in `data`, or `null` if the page is empty."
+          },
+          "last_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the last resource in `data`, or `null` if the page is empty. Pass this as `after` with the same order and filters."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more resources to retrieve after this page."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "additionalProperties": false,
+        "description": "A page of Agents API resources, with IDs for retrieving additional pages."
+      },
+      "CreateVaultParams": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 1048576,
+            "description": "The name is trimmed before storage. It must contain 1 to 256 UTF-8 bytes after trimming."
+          },
+          "metadata": {
+            "type": [
+              "object",
+              "null"
+            ],
+            "additionalProperties": {
+              "type": "string",
+              "minLength": 0,
+              "maxLength": 1048576
+            },
+            "propertyNames": {
+              "type": "string",
+              "minLength": 1,
+              "maxLength": 256
+            },
+            "minProperties": 0,
+            "maxProperties": 1024,
+            "description": "Key-value pairs to associate with the vault, such as an application or team identifier."
+          }
+        },
+        "additionalProperties": false,
+        "description": "Parameters for creating a vault to store credentials used by agent tools."
+      },
+      "DeletedVaultResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the deleted vault."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "vault.deleted"
+            ],
+            "default": "vault.deleted",
+            "x-stainless-const": true,
+            "description": "The object type. Always `vault.deleted`."
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the resource was deleted. Always `true`."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ],
+        "additionalProperties": false,
+        "description": "Confirmation that a vault was deleted."
+      },
+      "McpOauthTokenEndpointAuthResourceNone": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "none"
+            ],
+            "default": "none",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `none`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Sends the client ID without a client secret."
+      },
+      "McpOauthTokenEndpointAuthResourceClientSecretBasic": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "client_secret_basic"
+            ],
+            "default": "client_secret_basic",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `client_secret_basic`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Sends the client ID and secret using HTTP Basic authentication."
+      },
+      "McpOauthTokenEndpointAuthResourceClientSecretPost": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "client_secret_post"
+            ],
+            "default": "client_secret_post",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `client_secret_post`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Sends the client ID and secret in the token request body."
+      },
+      "McpOauthTokenEndpointAuthResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/McpOauthTokenEndpointAuthResourceNone"
+          },
+          {
+            "$ref": "#/components/schemas/McpOauthTokenEndpointAuthResourceClientSecretBasic"
+          },
+          {
+            "$ref": "#/components/schemas/McpOauthTokenEndpointAuthResourceClientSecretPost"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "none": "#/components/schemas/McpOauthTokenEndpointAuthResourceNone",
+            "client_secret_basic": "#/components/schemas/McpOauthTokenEndpointAuthResourceClientSecretBasic",
+            "client_secret_post": "#/components/schemas/McpOauthTokenEndpointAuthResourceClientSecretPost"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "none",
+          "client_secret_basic",
+          "client_secret_post"
+        ],
+        "description": "The client authentication method used for OAuth token refresh."
+      },
+      "McpOauthRefreshResource": {
+        "type": "object",
+        "properties": {
+          "token_endpoint": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The HTTPS OAuth token endpoint used for refresh."
+          },
+          "client_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The OAuth client ID used when requesting a new access token."
+          },
+          "resource": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The resource URI sent to the OAuth token endpoint during refresh, if configured."
+          },
+          "scope": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "Space-separated OAuth scopes requested during refresh, if configured."
+          },
+          "token_endpoint_auth": {
+            "$ref": "#/components/schemas/McpOauthTokenEndpointAuthResource",
+            "description": "How the OAuth client authenticates to the token endpoint, excluding its client secret."
+          }
+        },
+        "required": [
+          "token_endpoint",
+          "client_id",
+          "resource",
+          "scope",
+          "token_endpoint_auth"
+        ],
+        "additionalProperties": false,
+        "description": "Configuration used to refresh an MCP OAuth access token, excluding secret values."
+      },
+      "VaultCredentialAuthResourceMcpOauth": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_oauth"
+            ],
+            "default": "mcp_oauth",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `mcp_oauth`."
+          },
+          "mcp_server_url": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The HTTPS MCP server URL authorized by this credential."
+          },
+          "expires_at": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "When the OAuth access token expires, as an RFC 3339 timestamp, if known."
+          },
+          "refresh": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/McpOauthRefreshResource"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Public refresh metadata without refresh tokens or OAuth client secrets."
+          }
+        },
+        "required": [
+          "type",
+          "mcp_server_url",
+          "expires_at",
+          "refresh"
+        ],
+        "additionalProperties": false,
+        "description": "Public metadata for an OAuth credential; tokens and client secrets are never returned."
+      },
+      "VaultCredentialAuthResourceStaticBearer": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "static_bearer"
+            ],
+            "default": "static_bearer",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `static_bearer`."
+          },
+          "mcp_server_url": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The HTTPS MCP server URL authorized by this credential."
+          }
+        },
+        "required": [
+          "type",
+          "mcp_server_url"
+        ],
+        "additionalProperties": false,
+        "description": "Metadata for a bearer-token credential, without automatic OAuth refresh."
+      },
+      "VaultCredentialAuthResource": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/VaultCredentialAuthResourceMcpOauth"
+          },
+          {
+            "$ref": "#/components/schemas/VaultCredentialAuthResourceStaticBearer"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "mcp_oauth": "#/components/schemas/VaultCredentialAuthResourceMcpOauth",
+            "static_bearer": "#/components/schemas/VaultCredentialAuthResourceStaticBearer"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "mcp_oauth",
+          "static_bearer"
+        ],
+        "description": "The MCP server and authentication configuration of a vault credential, excluding secrets."
+      },
+      "VaultCredentialResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the credential."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "vault.credential"
+            ],
+            "default": "vault.credential",
+            "x-stainless-const": true,
+            "description": "The object type. Always `vault.credential`."
+          },
+          "vault_id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the vault containing this credential."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The human-readable name of the credential."
+          },
+          "auth": {
+            "$ref": "#/components/schemas/VaultCredentialAuthResource",
+            "description": "The authentication method and non-secret configuration for the MCP server."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the credential was created."
+          },
+          "updated_at": {
+            "type": "integer",
+            "format": "int64",
+            "description": "The Unix timestamp, in seconds, when the credential was last updated."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "vault_id",
+          "name",
+          "auth",
+          "created_at",
+          "updated_at"
+        ],
+        "additionalProperties": false,
+        "description": "Metadata for a stored MCP server credential. Secret values are never returned."
+      },
+      "VaultCredentialListResource": {
+        "type": "object",
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "list"
+            ],
+            "default": "list",
+            "x-stainless-const": true,
+            "description": "The object type, which is always `list`."
+          },
+          "data": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/VaultCredentialResource"
+            },
+            "minItems": 0,
+            "maxItems": 2000,
+            "description": "The resources returned in this page, in the requested sort order."
+          },
+          "first_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the first resource in `data`, or `null` if the page is empty."
+          },
+          "last_id": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "description": "The ID of the last resource in `data`, or `null` if the page is empty. Pass this as `after` with the same order and filters."
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more resources to retrieve after this page."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "first_id",
+          "last_id",
+          "has_more"
+        ],
+        "additionalProperties": false,
+        "description": "A page of Agents API resources, with IDs for retrieving additional pages."
+      },
+      "CreateMcpOauthTokenEndpointAuthParamNone": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "none"
+            ],
+            "default": "none",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `none`."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Sends the client ID without a client secret."
+      },
+      "CreateMcpOauthTokenEndpointAuthParamClientSecretBasic": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "client_secret_basic"
+            ],
+            "default": "client_secret_basic",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `client_secret_basic`."
+          },
+          "client_secret": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The OAuth client secret to store. Never returned in credential resources."
+          }
+        },
+        "required": [
+          "type",
+          "client_secret"
+        ],
+        "additionalProperties": false,
+        "description": "Sends the client ID and secret using HTTP Basic authentication."
+      },
+      "CreateMcpOauthTokenEndpointAuthParamClientSecretPost": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "client_secret_post"
+            ],
+            "default": "client_secret_post",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `client_secret_post`."
+          },
+          "client_secret": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The OAuth client secret to store. Never returned in credential resources."
+          }
+        },
+        "required": [
+          "type",
+          "client_secret"
+        ],
+        "additionalProperties": false,
+        "description": "Sends the client ID and secret in the token request body."
+      },
+      "CreateMcpOauthTokenEndpointAuthParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/CreateMcpOauthTokenEndpointAuthParamNone"
+          },
+          {
+            "$ref": "#/components/schemas/CreateMcpOauthTokenEndpointAuthParamClientSecretBasic"
+          },
+          {
+            "$ref": "#/components/schemas/CreateMcpOauthTokenEndpointAuthParamClientSecretPost"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "none": "#/components/schemas/CreateMcpOauthTokenEndpointAuthParamNone",
+            "client_secret_basic": "#/components/schemas/CreateMcpOauthTokenEndpointAuthParamClientSecretBasic",
+            "client_secret_post": "#/components/schemas/CreateMcpOauthTokenEndpointAuthParamClientSecretPost"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "none",
+          "client_secret_basic",
+          "client_secret_post"
+        ],
+        "description": "Client authentication credentials for OAuth token refresh."
+      },
+      "CreateMcpOauthRefreshParam": {
+        "type": "object",
+        "properties": {
+          "token_endpoint": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The HTTPS OAuth token endpoint used to exchange the refresh token for a new access token."
+          },
+          "client_id": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The OAuth client ID used when requesting a new access token."
+          },
+          "resource": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The resource URI to send to the OAuth token endpoint during refresh, if required."
+          },
+          "scope": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "Space-separated OAuth scopes to request during refresh, if required."
+          },
+          "refresh_token": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The refresh token to store. This secret is never returned in credential resources."
+          },
+          "token_endpoint_auth": {
+            "$ref": "#/components/schemas/CreateMcpOauthTokenEndpointAuthParam",
+            "description": "How the OAuth client authenticates to the token endpoint."
+          }
+        },
+        "required": [
+          "token_endpoint",
+          "client_id",
+          "refresh_token",
+          "token_endpoint_auth"
+        ],
+        "additionalProperties": false,
+        "description": "Configuration for refreshing the access token of an MCP OAuth credential."
+      },
+      "CreateVaultCredentialAuthParamMcpOauth": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_oauth"
+            ],
+            "default": "mcp_oauth",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `mcp_oauth`."
+          },
+          "mcp_server_url": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The HTTPS MCP server URL authorized by this credential."
+          },
+          "access_token": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "A write-only OAuth access token; never returned by credential resources."
+          },
+          "expires_at": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "When the OAuth access token expires, as an RFC 3339 timestamp, if known."
+          },
+          "refresh": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/CreateMcpOauthRefreshParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Optional refresh configuration for an HTTPS OAuth token endpoint."
+          }
+        },
+        "required": [
+          "type",
+          "mcp_server_url",
+          "access_token"
+        ],
+        "additionalProperties": false,
+        "description": "An OAuth credential for an HTTPS MCP destination."
+      },
+      "CreateVaultCredentialAuthParamStaticBearer": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "static_bearer"
+            ],
+            "default": "static_bearer",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `static_bearer`."
+          },
+          "mcp_server_url": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The HTTPS MCP server URL authorized by this credential."
+          },
+          "token": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The bearer token to store. This secret is never returned in credential resources."
+          }
+        },
+        "required": [
+          "type",
+          "mcp_server_url",
+          "token"
+        ],
+        "additionalProperties": false,
+        "description": "A bearer token for an MCP server, without automatic OAuth refresh."
+      },
+      "CreateVaultCredentialAuthParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/CreateVaultCredentialAuthParamMcpOauth"
+          },
+          {
+            "$ref": "#/components/schemas/CreateVaultCredentialAuthParamStaticBearer"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "mcp_oauth": "#/components/schemas/CreateVaultCredentialAuthParamMcpOauth",
+            "static_bearer": "#/components/schemas/CreateVaultCredentialAuthParamStaticBearer"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "mcp_oauth",
+          "static_bearer"
+        ],
+        "description": "Authentication credentials for an MCP server used by agent tools."
+      },
+      "CreateVaultCredentialParams": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 1048576,
+            "description": "The name is trimmed before storage. It must contain 1 to 256 UTF-8 bytes after trimming."
+          },
+          "auth": {
+            "$ref": "#/components/schemas/CreateVaultCredentialAuthParam",
+            "description": "The authentication method and secret values to store for the MCP server."
+          }
+        },
+        "required": [
+          "auth",
+          "name"
+        ],
+        "additionalProperties": false,
+        "description": "Parameters for storing a credential that authorizes access to an MCP server."
+      },
+      "RotateMcpOauthTokenEndpointAuthParamClientSecretBasic": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "client_secret_basic"
+            ],
+            "default": "client_secret_basic",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `client_secret_basic`."
+          },
+          "client_secret": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The replacement OAuth client secret. Omit or pass `null` to keep the stored secret. This secret is never returned in resources."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Updates credentials sent using HTTP Basic authentication."
+      },
+      "RotateMcpOauthTokenEndpointAuthParamClientSecretPost": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "client_secret_post"
+            ],
+            "default": "client_secret_post",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `client_secret_post`."
+          },
+          "client_secret": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The replacement OAuth client secret. Omit or pass `null` to keep the stored secret. This secret is never returned in resources."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Updates credentials sent in the token request body."
+      },
+      "RotateMcpOauthTokenEndpointAuthParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/RotateMcpOauthTokenEndpointAuthParamClientSecretBasic"
+          },
+          {
+            "$ref": "#/components/schemas/RotateMcpOauthTokenEndpointAuthParamClientSecretPost"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "client_secret_basic": "#/components/schemas/RotateMcpOauthTokenEndpointAuthParamClientSecretBasic",
+            "client_secret_post": "#/components/schemas/RotateMcpOauthTokenEndpointAuthParamClientSecretPost"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "client_secret_basic",
+          "client_secret_post"
+        ],
+        "description": "Client-secret updates that preserve the credential's OAuth authentication method."
+      },
+      "RotateMcpOauthRefreshParam": {
+        "type": "object",
+        "properties": {
+          "refresh_token": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The replacement refresh token. Omit or pass `null` to keep the stored token. This secret is never returned in resources."
+          },
+          "scope": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "Replacement space-separated OAuth scopes for refresh requests. Omit to keep the scopes, or pass `null` to stop sending a scope parameter."
+          },
+          "token_endpoint_auth": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/RotateMcpOauthTokenEndpointAuthParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Client-secret updates for the existing token endpoint authentication method."
+          }
+        },
+        "additionalProperties": false,
+        "description": "Updates to an MCP credential's existing OAuth refresh configuration."
+      },
+      "RotateVaultCredentialAuthParamMcpOauth": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_oauth"
+            ],
+            "default": "mcp_oauth",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `mcp_oauth`."
+          },
+          "access_token": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "A write-only replacement OAuth access token."
+          },
+          "expires_at": {
+            "type": [
+              "string",
+              "null"
+            ],
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The replacement expiry as an RFC 3339 timestamp, or `null` to clear it. Omitting this field preserves the expiry unless a new access token is supplied, in which case the expiry is cleared."
+          },
+          "refresh": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/RotateMcpOauthRefreshParam"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Optional write-only refresh-token and client-secret updates."
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "additionalProperties": false,
+        "description": "Rotate an OAuth credential for an HTTPS MCP destination."
+      },
+      "RotateVaultCredentialAuthParamStaticBearer": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "static_bearer"
+            ],
+            "default": "static_bearer",
+            "x-stainless-const": true,
+            "description": "The type of the object. Always `static_bearer`."
+          },
+          "token": {
+            "type": "string",
+            "minLength": 0,
+            "maxLength": 1048576,
+            "description": "The replacement bearer token. This secret is never returned in credential resources."
+          }
+        },
+        "required": [
+          "type",
+          "token"
+        ],
+        "additionalProperties": false,
+        "description": "Replace the bearer token for the credential's MCP server."
+      },
+      "RotateVaultCredentialAuthParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/RotateVaultCredentialAuthParamMcpOauth"
+          },
+          {
+            "$ref": "#/components/schemas/RotateVaultCredentialAuthParamStaticBearer"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type",
+          "mapping": {
+            "mcp_oauth": "#/components/schemas/RotateVaultCredentialAuthParamMcpOauth",
+            "static_bearer": "#/components/schemas/RotateVaultCredentialAuthParamStaticBearer"
+          }
+        },
+        "x-oai-discriminator-values": [
+          "mcp_oauth",
+          "static_bearer"
+        ],
+        "description": "Updates to a vault credential without changing its authentication method or MCP server."
+      },
+      "RotateVaultCredentialParams": {
+        "type": "object",
+        "properties": {
+          "auth": {
+            "$ref": "#/components/schemas/RotateVaultCredentialAuthParam",
+            "description": "Replacement values for the credential's existing authentication method."
+          }
+        },
+        "required": [
+          "auth"
+        ],
+        "additionalProperties": false,
+        "description": "Secret, expiry, and OAuth refresh scope updates for an existing vault credential."
+      },
+      "DeletedVaultCredentialResource": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "minLength": 0,
+            "description": "The ID of the deleted credential."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "vault.credential.deleted"
+            ],
+            "default": "vault.credential.deleted",
+            "x-stainless-const": true,
+            "description": "The object type. Always `vault.credential.deleted`."
+          },
+          "deleted": {
+            "type": "boolean",
+            "description": "Whether the resource was deleted. Always `true`."
+          }
+        },
+        "required": [
+          "id",
+          "object",
+          "deleted"
+        ],
+        "additionalProperties": false,
+        "description": "Confirmation that a vault credential was deleted."
+      },
+      "DragPoint": {
+        "properties": {
+          "x": {
+            "type": "integer",
+            "description": "The x-coordinate."
+          },
+          "y": {
+            "type": "integer",
+            "description": "The y-coordinate."
+          }
+        },
+        "type": "object",
+        "required": [
+          "x",
+          "y"
+        ],
+        "title": "Coordinate",
+        "description": "An x/y coordinate pair, e.g. `{ x: 100, y: 200 }`."
+      },
+      "LiveSessionAudioFormatPCMParam": {
+        "description": "Raw, mono 16-bit little-endian PCM audio for a Live WebSocket connection.",
+        "type": "object",
+        "properties": {
+          "type": {
+            "description": "The audio encoding. Always `audio/pcm`.",
+            "default": "audio/pcm",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "audio/pcm"
+            ]
+          },
+          "rate": {
+            "description": "Audio sample rate in hertz. Live WebSocket PCM audio supports 16000 or 24000 Hz.",
+            "type": "integer",
+            "minimum": 16000,
+            "maximum": 24000,
+            "enum": [
+              16000,
+              24000
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "rate"
+        ]
+      },
+      "LiveSessionAudioFormatPCMUParam": {
+        "description": "Raw, mono G.711 μ-law audio for a Live WebSocket connection.",
+        "type": "object",
+        "properties": {
+          "type": {
+            "description": "The audio encoding. Always `audio/pcmu`.",
+            "default": "audio/pcmu",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "audio/pcmu"
+            ]
+          },
+          "rate": {
+            "description": "Audio sample rate in hertz. G.711 audio uses 8000 Hz.",
+            "type": "integer",
+            "minimum": 8000,
+            "maximum": 8000
+          }
+        },
+        "required": [
+          "type",
+          "rate"
+        ]
+      },
+      "LiveSessionAudioFormatPCMAParam": {
+        "description": "Raw, mono G.711 A-law audio for a Live WebSocket connection.",
+        "type": "object",
+        "properties": {
+          "type": {
+            "description": "The audio encoding. Always `audio/pcma`.",
+            "default": "audio/pcma",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "audio/pcma"
+            ]
+          },
+          "rate": {
+            "description": "Audio sample rate in hertz. G.711 audio uses 8000 Hz.",
+            "type": "integer",
+            "minimum": 8000,
+            "maximum": 8000
+          }
+        },
+        "required": [
+          "type",
+          "rate"
+        ]
+      },
+      "LiveAudioFormat": {
+        "description": "Audio encoding and sample rate for audio sent and received over a Live WebSocket connection. WebRTC and SIP negotiate their media format separately.",
+        "discriminator": {
+          "propertyName": "type"
+        },
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/LiveSessionAudioFormatPCMParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveSessionAudioFormatPCMUParam"
+          },
+          {
+            "$ref": "#/components/schemas/LiveSessionAudioFormatPCMAParam"
+          }
+        ]
+      },
+      "LiveInitialSessionAudioParam": {
+        "description": "Startup audio configuration. Only primary WebSockets accept audio.format; WebRTC and SIP negotiate their media format. Voice and format are immutable after startup.",
+        "type": "object",
+        "properties": {
+          "format": {
+            "description": "Audio encoding and sample rate for audio sent and received over a Live WebSocket connection. WebRTC and SIP negotiate their media format separately.",
+            "$ref": "#/components/schemas/LiveAudioFormat"
+          },
+          "output": {
+            "description": "The voice used for speech generated by the Live model.",
+            "$ref": "#/components/schemas/LiveInitialSessionAudioOutputParam"
+          }
+        },
+        "required": []
+      },
+      "LiveSessionCreateParams": {
+        "description": "Initial configuration for a Live session, including its model, conversation instructions, audio, and delegated task handling.",
+        "type": "object",
+        "properties": {
+          "model": {
+            "$ref": "#/components/schemas/ModelIdsLive"
+          },
+          "instructions": {
+            "anyOf": [
+              {
+                "description": "Frontend instructions for voice, conversation, interruptions, and when to delegate. Start with the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting); put business rules and tool workflows in a separate [backend prompt](https://developers.openai.com/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). Limited to 16,384 client-supplied tokens. Omitted or blank instructions use server defaults. Immutable after startup.",
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "input": {
+            "description": "Ordered text-only history supplied before startup. Supports developer, user, and assistant messages with one text part each; at most 128 messages and 8,192 rendered tokens in total.",
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/LiveInitialItem"
+            },
+            "maxItems": 128
+          },
+          "audio": {
+            "description": "Startup audio configuration. Only primary WebSockets accept audio.format; WebRTC and SIP negotiate their media format. Voice and format are immutable after startup.",
+            "$ref": "#/components/schemas/LiveInitialSessionAudioParam"
+          },
+          "delegation": {
+            "anyOf": [
+              {
+                "description": "Who handles tasks delegated by the Live model. Omitted or null selects your application; use `responses` to let the API manage a Responses backend.",
+                "discriminator": {
+                  "propertyName": "type"
+                },
+                "oneOf": [
+                  {
+                    "$ref": "#/components/schemas/LiveClientDelegationParam"
+                  },
+                  {
+                    "$ref": "#/components/schemas/LiveResponsesDelegationParam"
+                  }
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "store": {
+            "description": "Whether to store the session for later forking and recording download. Defaults to false for new sessions.",
+            "type": "boolean"
+          },
+          "client": {
+            "description": "Startup-only capabilities for an untrusted frontend attached to a unified WebRTC session. Trusted sideband connections are unaffected.",
+            "$ref": "#/components/schemas/LiveClientConfigParam"
+          }
+        },
+        "required": [
+          "model"
+        ]
+      },
+      "LiveSessionStartEvent": {
+        "description": "Start a Live session on a primary WebSocket. Send this event before other commands and wait for `session.started`.",
+        "example": {
+          "type": "session.start",
+          "event_id": "evt_start_001",
+          "session": {
+            "model": "gpt-live-1",
+            "instructions": "Help the caller plan a restaurant reservation. Confirm details before booking.",
+            "audio": {
+              "format": {
+                "type": "audio/pcm",
+                "rate": 24000
+              },
+              "output": {
+                "voice": "marin"
+              }
+            },
+            "delegation": {
+              "type": "client"
+            }
+          }
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "anyOf": [
+              {
+                "description": "Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id.",
+                "type": "string",
+                "maxLength": 512
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "description": "The Live client event type. Always `session.start`.",
+            "default": "session.start",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.start"
+            ]
+          },
+          "session": {
+            "description": "Initial configuration for a primary WebSocket. Send session.start first and wait for session.started before application commands. WebRTC creation already starts the session; do not send this event again on its data channel.",
+            "$ref": "#/components/schemas/LiveSessionCreateParams"
+          }
+        },
+        "required": [
+          "type",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.start",
+            "event_id": "evt_start_001",
+            "session": {
+              "model": "gpt-live-1",
+              "instructions": "Help the caller plan a restaurant reservation. Confirm details before booking.",
+              "audio": {
+                "format": {
+                  "type": "audio/pcm",
+                  "rate": 24000
+                },
+                "output": {
+                  "voice": "marin"
+                }
+              },
+              "delegation": {
+                "type": "client"
+              }
+            }
+          }
+        }
+      },
+      "LiveSessionUpdateParams": {
+        "description": "Changes to an active Live session. Only delegation backend settings can be updated after startup.",
+        "type": "object",
+        "properties": {
+          "delegation": {
+            "anyOf": [
+              {
+                "description": "Delegation settings to update. The delegation type must match the current session; omitted settings retain their values.",
+                "discriminator": {
+                  "propertyName": "type"
+                },
+                "oneOf": [
+                  {
+                    "$ref": "#/components/schemas/LiveClientDelegationParam"
+                  },
+                  {
+                    "$ref": "#/components/schemas/LiveResponsesDelegationUpdateParam"
+                  }
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": []
+      },
+      "LiveSessionUpdateParam": {
+        "description": "Update the delegation settings of an active Live session. The server acknowledges accepted changes with `session.updated`.",
+        "example": {
+          "type": "session.update",
+          "event_id": "evt_update_001",
+          "session": {
+            "delegation": {
+              "type": "responses",
+              "responses": {
+                "instructions": "Check restaurant availability. Ask before confirming a booking.",
+                "max_output_tokens": 1024
+              }
+            }
+          }
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "anyOf": [
+              {
+                "description": "Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id.",
+                "type": "string",
+                "maxLength": 512
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "description": "The Live client event type. Always `session.update`.",
+            "default": "session.update",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.update"
+            ]
+          },
+          "session": {
+            "description": "Sparse delegation updates. Omitted settings retain their values. The delegation type cannot change, including resetting Responses delegation to null or client. Model, frontend instructions, audio, and startup input are immutable.",
+            "$ref": "#/components/schemas/LiveSessionUpdateParams"
+          }
+        },
+        "required": [
+          "type",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.update",
+            "event_id": "evt_update_001",
+            "session": {
+              "delegation": {
+                "type": "responses",
+                "responses": {
+                  "instructions": "Check restaurant availability. Ask before confirming a booking.",
+                  "max_output_tokens": 1024
+                }
+              }
+            }
+          }
+        }
+      },
+      "LiveInputAudioAppendEvent": {
+        "description": "Send audio to a Live session over its primary WebSocket. WebRTC and SIP sessions send audio over their media transport.",
+        "example": {
+          "type": "session.input_audio.append",
+          "audio": "AACAAIAAAIAAAP9/AIAAgA=="
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "anyOf": [
+              {
+                "description": "Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id.",
+                "type": "string",
+                "maxLength": 512
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "description": "The Live client event type. Always `session.input_audio.append`.",
+            "default": "session.input_audio.append",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.input_audio.append"
+            ]
+          },
+          "audio": {
+            "description": "Base64-encoded raw audio in the startup-selected format, without a WAV or other container header. Primary WebSocket only; media transports use their audio track. Audio appends have no acknowledgment. Reflected sideband server events reuse this event type and audio key, with no timestamps or event_id; their audio is always mono PCM16LE at 24 kHz.",
+            "type": "string",
+            "minLength": 1
+          }
+        },
+        "required": [
+          "type",
+          "audio"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.input_audio.append",
+            "audio": "AACAAIAAAIAAAP9/AIAAgA=="
+          }
+        }
+      },
+      "LiveInputAudioMuteParam": {
+        "description": "Mute audio input to the Live model without closing the session. The server acknowledges with `session.input_audio.muted`.",
+        "example": {
+          "type": "session.input_audio.mute",
+          "event_id": "evt_mute_001"
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "anyOf": [
+              {
+                "description": "Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id.",
+                "type": "string",
+                "maxLength": 512
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "description": "The Live client event type. Always `session.input_audio.mute`.",
+            "default": "session.input_audio.mute",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.input_audio.mute"
+            ]
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.input_audio.mute",
+            "event_id": "evt_mute_001"
+          }
+        }
+      },
+      "LiveInputAudioUnmuteParam": {
+        "description": "Resume audio input to a Live model after muting it. The server acknowledges with `session.input_audio.unmuted`.",
+        "example": {
+          "type": "session.input_audio.unmute",
+          "event_id": "evt_unmute_001"
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "anyOf": [
+              {
+                "description": "Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id.",
+                "type": "string",
+                "maxLength": 512
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "description": "The Live client event type. Always `session.input_audio.unmute`.",
+            "default": "session.input_audio.unmute",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.input_audio.unmute"
+            ]
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.input_audio.unmute",
+            "event_id": "evt_unmute_001"
+          }
+        }
+      },
+      "LiveInstructionsAppendParam": {
+        "description": "Append instructions to the Live conversation while it is running, optionally associating them with an existing client delegation.",
+        "example": {
+          "type": "session.instructions.append",
+          "event_id": "evt_instructions_001",
+          "delegation_id": null,
+          "content": "The caller prefers outdoor seating."
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "anyOf": [
+              {
+                "description": "Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id.",
+                "type": "string",
+                "maxLength": 512
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "description": "The Live client event type. Always `session.instructions.append`.",
+            "default": "session.instructions.append",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.instructions.append"
+            ]
+          },
+          "delegation_id": {
+            "anyOf": [
+              {
+                "description": "Required, nullable. Set null for general session context, or use the ID from session.delegation.created for an existing client delegation. Non-null IDs are not accepted with Responses delegation.",
+                "type": "string",
+                "minLength": 1
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "content": {
+            "description": "Instruction text to append, limited to 500 tokens. This is a plain string, not an array of content parts.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "type",
+          "delegation_id",
+          "content"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.instructions.append",
+            "event_id": "evt_instructions_001",
+            "delegation_id": null,
+            "content": "The caller prefers outdoor seating."
+          }
+        }
+      },
+      "LiveThinkingAppendParam": {
+        "description": "Provide silent reasoning or progress context to the Live model, optionally for an existing client delegation.",
+        "example": {
+          "type": "session.thinking.append",
+          "event_id": "evt_thinking_001",
+          "delegation_id": "del_abc123",
+          "content": "Checking availability for two guests at 7 PM."
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "anyOf": [
+              {
+                "description": "Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id.",
+                "type": "string",
+                "maxLength": 512
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "description": "The Live client event type. Always `session.thinking.append`.",
+            "default": "session.thinking.append",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.thinking.append"
+            ]
+          },
+          "delegation_id": {
+            "anyOf": [
+              {
+                "description": "Required, nullable. Set null for general session context, or use the ID from session.delegation.created for an existing client delegation. Non-null IDs are not accepted with Responses delegation.",
+                "type": "string",
+                "minLength": 1
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "content": {
+            "description": "Silent reasoning or progress context, limited to 500 tokens. It does not directly request speech, but can influence later speech and is not a secrecy boundary.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "type",
+          "delegation_id",
+          "content"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.thinking.append",
+            "event_id": "evt_thinking_001",
+            "delegation_id": "del_abc123",
+            "content": "Checking availability for two guests at 7 PM."
+          }
+        }
+      },
+      "LiveCommentaryAppendParam": {
+        "description": "Provide context the Live model can communicate to the user, optionally for an existing client delegation.",
+        "example": {
+          "type": "session.commentary.append",
+          "event_id": "evt_commentary_001",
+          "delegation_id": "del_abc123",
+          "content": "There is an outdoor table for two at 7 PM. Ask whether to reserve it."
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "anyOf": [
+              {
+                "description": "Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id.",
+                "type": "string",
+                "maxLength": 512
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "description": "The Live client event type. Always `session.commentary.append`.",
+            "default": "session.commentary.append",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.commentary.append"
+            ]
+          },
+          "delegation_id": {
+            "anyOf": [
+              {
+                "description": "Required, nullable. Set null for general session context, or use the ID from session.delegation.created for an existing client delegation. Non-null IDs are not accepted with Responses delegation.",
+                "type": "string",
+                "minLength": 1
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "content": {
+            "description": "Speakable context for the Live model, limited to 500 tokens. Use this for a result the model should communicate; use session.thinking.append for silent context.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "type",
+          "delegation_id",
+          "content"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.commentary.append",
+            "event_id": "evt_commentary_001",
+            "delegation_id": "del_abc123",
+            "content": "There is an outdoor table for two at 7 PM. Ask whether to reserve it."
+          }
+        }
+      },
+      "LiveResponseItemCreateParam": {
+        "description": "Add an input item to the Live session’s Responses backend. Requires Responses delegation; use `response.create` to request a response.",
+        "example": {
+          "type": "response.item.create",
+          "event_id": "evt_item_001",
+          "item": {
+            "type": "message",
+            "role": "user",
+            "content": [
+              {
+                "type": "input_text",
+                "text": "Please check for a table for two at 7 PM."
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "anyOf": [
+              {
+                "description": "Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id.",
+                "type": "string",
+                "maxLength": 512
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "description": "The Live client event type. Always `response.item.create`.",
+            "default": "response.item.create",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "response.item.create"
+            ]
+          },
+          "item": {
+            "description": "An input item to append to the Responses backend conversation, such as a user message or a function tool result.",
+            "$ref": "#/components/schemas/InputItem"
+          }
+        },
+        "required": [
+          "type",
+          "item"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "response.item.create",
+            "event_id": "evt_item_001",
+            "item": {
+              "type": "message",
+              "role": "user",
+              "content": [
+                {
+                  "type": "input_text",
+                  "text": "Please check for a table for two at 7 PM."
+                }
+              ]
+            }
+          }
+        }
+      },
+      "LiveResponseCreateParam": {
+        "description": "Request a response from the Live session’s Responses backend, or continue a delegated response waiting for tool results. Requires Responses delegation.",
+        "example": {
+          "type": "response.create",
+          "event_id": "evt_response_001"
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "anyOf": [
+              {
+                "description": "Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id.",
+                "type": "string",
+                "maxLength": 512
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "description": "The Live client event type. Always `response.create`.",
+            "default": "response.create",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "response.create"
+            ]
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "response.create",
+            "event_id": "evt_response_001"
+          }
+        }
+      },
+      "LiveSessionCloseParam": {
+        "description": "Request that the Live session close. The terminal `session.closed` event contains the close reason and final usage.",
+        "example": {
+          "type": "session.close",
+          "event_id": "evt_close_001"
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "anyOf": [
+              {
+                "description": "Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id.",
+                "type": "string",
+                "maxLength": 512
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "description": "The Live client event type. Always `session.close`.",
+            "default": "session.close",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.close"
+            ]
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.close",
+            "event_id": "evt_close_001"
+          }
+        }
+      },
+      "LiveForkAudioParam": {
+        "description": "Audio format for the new WebSocket connection to a forked Live session. The stored voice is preserved.",
+        "type": "object",
+        "properties": {
+          "format": {
+            "description": "Audio encoding and sample rate for audio sent and received over a Live WebSocket connection. WebRTC and SIP negotiate their media format separately.",
+            "$ref": "#/components/schemas/LiveAudioFormat"
+          }
+        },
+        "required": []
+      },
+      "LiveForkSessionConfigParam": {
+        "description": "Overrides for a stored session after connecting to the fork WebSocket. An empty object inherits the stored configuration; do not supply a new model. audio.format applies only to the new WebSocket connection. client overrides are only supported for WebRTC forks.",
+        "type": "object",
+        "properties": {
+          "audio": {
+            "description": "Audio format for a WebSocket fork. WebRTC forks negotiate their audio format and must omit this field.",
+            "$ref": "#/components/schemas/LiveForkAudioParam"
+          },
+          "delegation": {
+            "description": "Overrides for the stored session’s Responses backend. Only supported when the stored session already uses Responses delegation; the delegation type cannot change.",
+            "$ref": "#/components/schemas/LiveResponsesDelegationUpdateParam"
+          },
+          "store": {
+            "description": "Whether to store the forked session. Omission inherits the stored session's setting.",
+            "type": "boolean"
+          },
+          "client": {
+            "description": "Frontend data-channel permissions for a WebRTC fork. Omitted permissions inherit the stored values. Not supported for WebSocket forks.",
+            "$ref": "#/components/schemas/LiveClientConfigParam"
+          }
+        },
+        "required": []
+      },
+      "LiveForkSessionStartEvent": {
+        "description": "Start a Live session after connecting to a stored session’s fork WebSocket. Send an empty `session` object to use the stored configuration.",
+        "example": {
+          "type": "session.start",
+          "session": {}
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "anyOf": [
+              {
+                "description": "Optional client identifier for correlating this command with a server event's client_event_id or error.client_event_id.",
+                "type": "string",
+                "maxLength": 512
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "description": "The Live client event type. Always `session.start`.",
+            "default": "session.start",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.start"
+            ]
+          },
+          "session": {
+            "description": "Overrides for a stored session after connecting to the fork WebSocket. An empty object inherits the stored configuration; do not supply a new model. audio.format applies only to the new WebSocket connection. client overrides are only supported for WebRTC forks.",
+            "$ref": "#/components/schemas/LiveForkSessionConfigParam"
+          }
+        },
+        "required": [
+          "type",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.start",
+            "session": {}
+          }
+        }
+      },
+      "LiveSessionResourceParam": {
+        "description": "The resolved Live session configuration and server-assigned session metadata.",
+        "type": "object",
+        "properties": {
+          "model": {
+            "$ref": "#/components/schemas/ModelIdsLive"
+          },
+          "instructions": {
+            "anyOf": [
+              {
+                "description": "Frontend instructions for voice, conversation, interruptions, and when to delegate. Start with the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting); put business rules and tool workflows in a separate [backend prompt](https://developers.openai.com/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt). Limited to 16,384 client-supplied tokens. Omitted or blank instructions use server defaults. Immutable after startup.",
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "input": {
+            "description": "Ordered text-only history supplied before startup. Supports developer, user, and assistant messages with one text part each; at most 128 messages and 8,192 rendered tokens in total.",
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/LiveInitialItem"
+            },
+            "maxItems": 128
+          },
+          "audio": {
+            "description": "Startup audio configuration. Only primary WebSockets accept audio.format; WebRTC and SIP negotiate their media format. Voice and format are immutable after startup.",
+            "$ref": "#/components/schemas/LiveInitialSessionAudioParam"
+          },
+          "delegation": {
+            "anyOf": [
+              {
+                "description": "Who handles tasks delegated by the Live model. Omitted or null selects your application; use `responses` to let the API manage a Responses backend.",
+                "discriminator": {
+                  "propertyName": "type"
+                },
+                "oneOf": [
+                  {
+                    "$ref": "#/components/schemas/LiveClientDelegationParam"
+                  },
+                  {
+                    "$ref": "#/components/schemas/LiveResponsesDelegationParam"
+                  }
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "store": {
+            "description": "Whether to store the session for later forking and recording download. Defaults to false for new sessions.",
+            "type": "boolean"
+          },
+          "client": {
+            "description": "Startup-only capabilities for an untrusted frontend attached to a unified WebRTC session. Trusted sideband connections are unaffected.",
+            "$ref": "#/components/schemas/LiveClientConfigParam"
+          },
+          "id": {
+            "description": "The unique ID of the Live session. Use this ID for sideband connections, forking, and recording download.",
+            "type": "string"
+          },
+          "expires_at": {
+            "description": "The Unix timestamp, in seconds, at which the Live session expires.",
+            "type": "integer"
+          },
+          "status": {
+            "description": "The status of the session snapshot. Always `active`, including the final snapshot in session.closed; use the event type to determine that the session has closed.",
+            "default": "active",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "active"
+            ]
+          }
+        },
+        "required": [
+          "model",
+          "id",
+          "expires_at",
+          "status"
+        ]
+      },
+      "LiveSessionStarted": {
+        "description": "Returned when a Live session has started. Contains the resolved session configuration, including server defaults.",
+        "example": {
+          "type": "session.started",
+          "event_id": "evt_started_001",
+          "client_event_id": "evt_start_001",
+          "session": {
+            "id": "live_abc123",
+            "model": "gpt-live-1",
+            "status": "active",
+            "expires_at": 1788555600,
+            "instructions": "Help the caller plan a restaurant reservation. Confirm details before booking.",
+            "input": [],
+            "audio": {
+              "format": {
+                "type": "audio/pcm",
+                "rate": 24000
+              },
+              "output": {
+                "voice": "marin"
+              }
+            },
+            "delegation": {
+              "type": "client"
+            }
+          }
+        },
+        "type": "object",
+        "properties": {
+          "type": {
+            "description": "The event type, always `session.started`.",
+            "default": "session.started",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.started"
+            ]
+          },
+          "event_id": {
+            "description": "The unique ID of the Live server event.",
+            "type": "string"
+          },
+          "client_event_id": {
+            "description": "The event_id of the client command associated with this server event, when supplied.",
+            "type": "string"
+          },
+          "session": {
+            "$ref": "#/components/schemas/LiveSessionResourceParam"
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.started",
+            "event_id": "evt_started_001",
+            "client_event_id": "evt_start_001",
+            "session": {
+              "id": "live_abc123",
+              "model": "gpt-live-1",
+              "status": "active",
+              "expires_at": 1788555600,
+              "instructions": "Help the caller plan a restaurant reservation. Confirm details before booking.",
+              "input": [],
+              "audio": {
+                "format": {
+                  "type": "audio/pcm",
+                  "rate": 24000
+                },
+                "output": {
+                  "voice": "marin"
+                }
+              },
+              "delegation": {
+                "type": "client"
+              }
+            }
+          }
+        }
+      },
+      "LiveSessionUpdated": {
+        "description": "Returned when a Live session update is accepted. Contains the resolved session configuration after the update.",
+        "example": {
+          "type": "session.updated",
+          "event_id": "evt_updated_001",
+          "client_event_id": "evt_update_001",
+          "session": {
+            "id": "live_def456",
+            "model": "gpt-live-1",
+            "status": "active",
+            "expires_at": 1788555600,
+            "instructions": "Help the caller plan a restaurant reservation. Confirm details before booking.",
+            "input": [],
+            "audio": {
+              "format": {
+                "type": "audio/pcm",
+                "rate": 24000
+              },
+              "output": {
+                "voice": "marin"
+              }
+            },
+            "delegation": {
+              "type": "responses",
+              "responses": {
+                "model": "gpt-6-astra",
+                "instructions": "Check restaurant availability. Ask before confirming a booking.",
+                "max_output_tokens": 1024,
+                "tools": []
+              }
+            }
+          }
+        },
+        "type": "object",
+        "properties": {
+          "type": {
+            "description": "The event type, always `session.updated`.",
+            "default": "session.updated",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.updated"
+            ]
+          },
+          "event_id": {
+            "description": "The unique ID of the Live server event.",
+            "type": "string"
+          },
+          "client_event_id": {
+            "description": "The event_id of the client command associated with this server event, when supplied.",
+            "type": "string"
+          },
+          "session": {
+            "$ref": "#/components/schemas/LiveSessionResourceParam"
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "session"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.updated",
+            "event_id": "evt_updated_001",
+            "client_event_id": "evt_update_001",
+            "session": {
+              "id": "live_def456",
+              "model": "gpt-live-1",
+              "status": "active",
+              "expires_at": 1788555600,
+              "instructions": "Help the caller plan a restaurant reservation. Confirm details before booking.",
+              "input": [],
+              "audio": {
+                "format": {
+                  "type": "audio/pcm",
+                  "rate": 24000
+                },
+                "output": {
+                  "voice": "marin"
+                }
+              },
+              "delegation": {
+                "type": "responses",
+                "responses": {
+                  "model": "gpt-6-astra",
+                  "instructions": "Check restaurant availability. Ask before confirming a booking.",
+                  "max_output_tokens": 1024,
+                  "tools": []
+                }
+              }
+            }
+          }
+        }
+      },
+      "LiveInputAudioMuted": {
+        "description": "Returned when a session.input_audio.mute command is accepted. Input audio is no longer sent to the model; sideband audio reflection continues.",
+        "example": {
+          "type": "session.input_audio.muted",
+          "event_id": "evt_muted_001",
+          "client_event_id": "evt_mute_001"
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "description": "The unique ID of the Live server event.",
+            "type": "string"
+          },
+          "client_event_id": {
+            "description": "The event_id of the client command associated with this server event, when supplied.",
+            "type": "string"
+          },
+          "type": {
+            "description": "The event type, always `session.input_audio.muted`.",
+            "default": "session.input_audio.muted",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.input_audio.muted"
+            ]
+          }
+        },
+        "required": [
+          "event_id",
+          "type"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.input_audio.muted",
+            "event_id": "evt_muted_001",
+            "client_event_id": "evt_mute_001"
+          }
+        }
+      },
+      "LiveInputAudioUnmuted": {
+        "description": "Returned when a session.input_audio.unmute command is accepted. Input audio is sent to the model again.",
+        "example": {
+          "type": "session.input_audio.unmuted",
+          "event_id": "evt_unmuted_001",
+          "client_event_id": "evt_unmute_001"
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "description": "The unique ID of the Live server event.",
+            "type": "string"
+          },
+          "client_event_id": {
+            "description": "The event_id of the client command associated with this server event, when supplied.",
+            "type": "string"
+          },
+          "type": {
+            "description": "The event type, always `session.input_audio.unmuted`.",
+            "default": "session.input_audio.unmuted",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.input_audio.unmuted"
+            ]
+          }
+        },
+        "required": [
+          "event_id",
+          "type"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.input_audio.unmuted",
+            "event_id": "evt_unmuted_001",
+            "client_event_id": "evt_unmute_001"
+          }
+        }
+      },
+      "LiveInstructionsAppended": {
+        "description": "Returned when a session.instructions.append command is accepted into the Live session timeline. Acknowledges the appended instructions without guaranteeing that the model has acted on them.",
+        "example": {
+          "type": "session.instructions.appended",
+          "event_id": "evt_instructions_002",
+          "client_event_id": "evt_instructions_001",
+          "start_ms": 1200,
+          "end_ms": 1400
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "description": "The unique ID of the Live server event.",
+            "type": "string"
+          },
+          "client_event_id": {
+            "description": "The event_id of the client command associated with this server event, when supplied.",
+            "type": "string"
+          },
+          "start_ms": {
+            "description": "The start of this event on the Live session timeline, in milliseconds from the beginning of the session.",
+            "type": "integer"
+          },
+          "end_ms": {
+            "description": "The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms.",
+            "type": "integer"
+          },
+          "type": {
+            "description": "The event type, always `session.instructions.appended`.",
+            "default": "session.instructions.appended",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.instructions.appended"
+            ]
+          }
+        },
+        "required": [
+          "event_id",
+          "start_ms",
+          "end_ms",
+          "type"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.instructions.appended",
+            "event_id": "evt_instructions_002",
+            "client_event_id": "evt_instructions_001",
+            "start_ms": 1200,
+            "end_ms": 1400
+          }
+        }
+      },
+      "LiveThinkingAppended": {
+        "description": "Returned when a session.thinking.append command is accepted into the Live session timeline. Acknowledges the added reasoning context without guaranteeing any spoken output.",
+        "example": {
+          "type": "session.thinking.appended",
+          "event_id": "evt_thinking_002",
+          "client_event_id": "evt_thinking_001",
+          "start_ms": 4600,
+          "end_ms": 4800
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "description": "The unique ID of the Live server event.",
+            "type": "string"
+          },
+          "client_event_id": {
+            "description": "The event_id of the client command associated with this server event, when supplied.",
+            "type": "string"
+          },
+          "start_ms": {
+            "description": "The start of this event on the Live session timeline, in milliseconds from the beginning of the session.",
+            "type": "integer"
+          },
+          "end_ms": {
+            "description": "The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms.",
+            "type": "integer"
+          },
+          "type": {
+            "description": "The event type, always `session.thinking.appended`.",
+            "default": "session.thinking.appended",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.thinking.appended"
+            ]
+          }
+        },
+        "required": [
+          "event_id",
+          "start_ms",
+          "end_ms",
+          "type"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.thinking.appended",
+            "event_id": "evt_thinking_002",
+            "client_event_id": "evt_thinking_001",
+            "start_ms": 4600,
+            "end_ms": 4800
+          }
+        }
+      },
+      "LiveCommentaryAppended": {
+        "description": "Returned when a session.commentary.append command is accepted into the Live session timeline. Acknowledges the added commentary without guaranteeing exact wording or completed audio playback.",
+        "example": {
+          "type": "session.commentary.appended",
+          "event_id": "evt_commentary_002",
+          "client_event_id": "evt_commentary_001",
+          "start_ms": 5200,
+          "end_ms": 5400
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "description": "The unique ID of the Live server event.",
+            "type": "string"
+          },
+          "client_event_id": {
+            "description": "The event_id of the client command associated with this server event, when supplied.",
+            "type": "string"
+          },
+          "start_ms": {
+            "description": "The start of this event on the Live session timeline, in milliseconds from the beginning of the session.",
+            "type": "integer"
+          },
+          "end_ms": {
+            "description": "The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms.",
+            "type": "integer"
+          },
+          "type": {
+            "description": "The event type, always `session.commentary.appended`.",
+            "default": "session.commentary.appended",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.commentary.appended"
+            ]
+          }
+        },
+        "required": [
+          "event_id",
+          "start_ms",
+          "end_ms",
+          "type"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.commentary.appended",
+            "event_id": "evt_commentary_002",
+            "client_event_id": "evt_commentary_001",
+            "start_ms": 5200,
+            "end_ms": 5400
+          }
+        }
+      },
+      "LiveInputAudioAppend": {
+        "description": "Input audio received from the primary transport and reflected to a Live sideband connection before model-input muting.",
+        "example": {
+          "type": "session.input_audio.append",
+          "audio": "AACAAIAAAIAAAP9/AIAAgA=="
+        },
+        "type": "object",
+        "properties": {
+          "type": {
+            "description": "The event type, always `session.input_audio.append`.",
+            "default": "session.input_audio.append",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.input_audio.append"
+            ]
+          },
+          "audio": {
+            "description": "Base64-encoded raw mono PCM16LE at 24 kHz received from the primary transport, reflected to the sideband before model-input muting. This server event uses the same audio key as the client command, but is not an acknowledgment of it.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "type",
+          "audio"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.input_audio.append",
+            "audio": "AACAAIAAAIAAAP9/AIAAgA=="
+          }
+        }
+      },
+      "LiveOutputAudioDelta": {
+        "description": "An audio chunk generated by the Live model. Decode and play primary WebSocket chunks in delivery order using the configured session audio format. Sideband connections receive reflected output audio with timestamps.",
+        "example": {
+          "type": "session.output_audio.delta",
+          "delta": "AACAAIAAAIAAAP9/AIAAgA==",
+          "start_ms": 1000,
+          "end_ms": 1200
+        },
+        "type": "object",
+        "properties": {
+          "type": {
+            "description": "The event type, always `session.output_audio.delta`.",
+            "default": "session.output_audio.delta",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.output_audio.delta"
+            ]
+          },
+          "delta": {
+            "description": "Base64-encoded raw audio. Primary WebSocket events use the session's configured format; reflected sideband events use mono PCM16LE at 24 kHz.",
+            "type": "string"
+          },
+          "start_ms": {
+            "description": "Inclusive session-relative start in milliseconds. Required on reflected sideband events; omitted on the primary WebSocket.",
+            "type": "integer"
+          },
+          "end_ms": {
+            "description": "Exclusive session-relative end in milliseconds. Required on reflected sideband events; omitted on the primary WebSocket. Dropped output frames leave gaps between reflected ranges.",
+            "type": "integer"
+          }
+        },
+        "required": [
+          "type",
+          "delta"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.output_audio.delta",
+            "delta": "AACAAIAAAIAAAP9/AIAAgA==",
+            "start_ms": 1000,
+            "end_ms": 1200
+          }
+        }
+      },
+      "LiveInputTranscriptDelta": {
+        "description": "A transcript fragment for user input audio in the Live session. Accumulate fragments in delivery order; these events do not define complete turns or include a transcript-done event.",
+        "example": {
+          "type": "session.input_transcript.delta",
+          "event_id": "evt_input_transcript_001",
+          "delta": "A table for two at seven, please.",
+          "start_ms": 1600,
+          "end_ms": 3400
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "description": "The unique ID of the Live server event.",
+            "type": "string"
+          },
+          "client_event_id": {
+            "description": "The event_id of the client command associated with this server event, when supplied.",
+            "type": "string"
+          },
+          "start_ms": {
+            "description": "The start of this event on the Live session timeline, in milliseconds from the beginning of the session.",
+            "type": "integer"
+          },
+          "end_ms": {
+            "description": "The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms.",
+            "type": "integer"
+          },
+          "delta": {
+            "description": "The transcript text fragment for the audio in this time range. Append fragments in delivery order to build the transcript.",
+            "type": "string"
+          },
+          "type": {
+            "description": "The event type, always `session.input_transcript.delta`.",
+            "default": "session.input_transcript.delta",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.input_transcript.delta"
+            ]
+          }
+        },
+        "required": [
+          "event_id",
+          "start_ms",
+          "end_ms",
+          "delta",
+          "type"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.input_transcript.delta",
+            "event_id": "evt_input_transcript_001",
+            "delta": "A table for two at seven, please.",
+            "start_ms": 1600,
+            "end_ms": 3400
+          }
+        }
+      },
+      "LiveOutputTranscriptDelta": {
+        "description": "A transcript fragment for assistant output audio in the Live session. Accumulate fragments in delivery order; these events do not define complete turns or include a transcript-done event.",
+        "example": {
+          "type": "session.output_transcript.delta",
+          "event_id": "evt_output_transcript_001",
+          "delta": "Would you like me to reserve that table?",
+          "start_ms": 5400,
+          "end_ms": 7200
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "description": "The unique ID of the Live server event.",
+            "type": "string"
+          },
+          "client_event_id": {
+            "description": "The event_id of the client command associated with this server event, when supplied.",
+            "type": "string"
+          },
+          "start_ms": {
+            "description": "The start of this event on the Live session timeline, in milliseconds from the beginning of the session.",
+            "type": "integer"
+          },
+          "end_ms": {
+            "description": "The end of this event on the Live session timeline, in milliseconds from the beginning of the session. For appended context, this can equal start_ms.",
+            "type": "integer"
+          },
+          "delta": {
+            "description": "The transcript text fragment for the audio in this time range. Append fragments in delivery order to build the transcript.",
+            "type": "string"
+          },
+          "type": {
+            "description": "The event type, always `session.output_transcript.delta`.",
+            "default": "session.output_transcript.delta",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.output_transcript.delta"
+            ]
+          }
+        },
+        "required": [
+          "event_id",
+          "start_ms",
+          "end_ms",
+          "delta",
+          "type"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.output_transcript.delta",
+            "event_id": "evt_output_transcript_001",
+            "delta": "Would you like me to reserve that table?",
+            "start_ms": 5400,
+            "end_ms": 7200
+          }
+        }
+      },
+      "LiveDelegationItem": {
+        "description": "Metadata for work delegated by the Live model. Client delegations are handled by your application; Responses delegations run on the configured backend.",
+        "type": "object",
+        "properties": {
+          "id": {
+            "description": "The unique ID of the delegation. Use this as delegation_id when replying to client-owned work or correlating Responses events.",
+            "type": "string"
+          },
+          "type": {
+            "description": "The object type, always `delegation`.",
+            "default": "delegation",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "delegation"
+            ]
+          },
+          "target": {
+            "description": "Where the Live model delegated the work: `client` for your application, or `responses` for the configured Responses backend.",
+            "oneOf": [
+              {
+                "default": "client",
+                "x-stainless-const": true,
+                "type": "string",
+                "enum": [
+                  "client"
+                ]
+              },
+              {
+                "default": "responses",
+                "x-stainless-const": true,
+                "type": "string",
+                "enum": [
+                  "responses"
+                ]
+              }
+            ]
+          },
+          "response_id": {
+            "description": "The ID of the Responses API response associated with a Responses delegation. Omitted for client delegations.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "type",
+          "target"
+        ]
+      },
+      "LiveDelegationCreated": {
+        "description": "Returned when the Live model delegates work to your application or a Responses backend. Contains delegation metadata and the position on the session timeline where the work was delegated.",
+        "example": {
+          "type": "session.delegation.created",
+          "event_id": "evt_delegation_001",
+          "offset_ms": 3600,
+          "delegation": {
+            "id": "del_abc123",
+            "type": "delegation",
+            "target": "client"
+          }
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "description": "The unique ID of the Live server event.",
+            "type": "string"
+          },
+          "client_event_id": {
+            "description": "The event_id of the client command associated with this server event, when supplied.",
+            "type": "string"
+          },
+          "type": {
+            "description": "The event type, always `session.delegation.created`.",
+            "default": "session.delegation.created",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.delegation.created"
+            ]
+          },
+          "offset_ms": {
+            "description": "The position on the Live session timeline where the delegation was created, in milliseconds from the beginning of the session.",
+            "type": "integer"
+          },
+          "delegation": {
+            "description": "The delegated work identifier and destination. This object contains metadata, not the task text.",
+            "$ref": "#/components/schemas/LiveDelegationItem"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "offset_ms",
+          "delegation"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.delegation.created",
+            "event_id": "evt_delegation_001",
+            "offset_ms": 3600,
+            "delegation": {
+              "id": "del_abc123",
+              "type": "delegation",
+              "target": "client"
+            }
+          }
+        }
+      },
+      "LiveResponseEvent": {
+        "description": "A streaming Responses API event from a backend delegated to by the Live session. Use the outer delegation_id to associate the nested stream with its Live delegation.",
+        "example": {
+          "type": "response.event",
+          "event_id": "evt_response_002",
+          "delegation_id": "del_responses123",
+          "event": {
+            "type": "response.output_text.delta",
+            "item_id": "msg_abc123",
+            "output_index": 0,
+            "content_index": 0,
+            "delta": "An outdoor table is available at 7 PM.",
+            "sequence_number": 3,
+            "logprobs": []
+          }
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "description": "The unique ID of the Live server event.",
+            "type": "string"
+          },
+          "client_event_id": {
+            "description": "The event_id of the client command associated with this server event, when supplied.",
+            "type": "string"
+          },
+          "type": {
+            "description": "The event type, always `response.event`.",
+            "default": "response.event",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "response.event"
+            ]
+          },
+          "delegation_id": {
+            "anyOf": [
+              {
+                "description": "The Live delegation associated with the nested Responses event. May be null or omitted when the event cannot be correlated with a delegation.",
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "event": {
+            "description": "The nested Responses streaming event. Dispatch on its type field. Response lifecycle snapshots omit input and clear instructions, tools, and output to keep messages small; consume granular output events for the generated content.",
+            "type": "object",
+            "additionalProperties": {}
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "event"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "response.event",
+            "event_id": "evt_response_002",
+            "delegation_id": "del_responses123",
+            "event": {
+              "type": "response.output_text.delta",
+              "item_id": "msg_abc123",
+              "output_index": 0,
+              "content_index": 0,
+              "delta": "An outdoor table is available at 7 PM.",
+              "sequence_number": 3,
+              "logprobs": []
+            }
+          }
+        }
+      },
+      "LiveSessionUsage": {
+        "description": "Cumulative audio duration for a Live session. Values are totals for the session, not increments to sum across usage events.",
+        "type": "object",
+        "properties": {
+          "seconds": {
+            "description": "The cumulative Live audio duration in seconds. Do not sum this value across usage events.",
+            "type": "number"
+          }
+        },
+        "required": [
+          "seconds"
+        ]
+      },
+      "LiveContextWindowUsage": {
+        "description": "The latest measured context-window usage of the Live model. This is separate from billing usage and delegated Responses token usage.",
+        "type": "object",
+        "properties": {
+          "usage_ratio": {
+            "description": "The latest active context token count divided by the Live model context limit. Can decrease after compaction and may lag between measured audio frames.",
+            "type": "number"
+          }
+        },
+        "required": [
+          "usage_ratio"
+        ]
+      },
+      "LiveSessionUsageUpdated": {
+        "description": "Reports cumulative Live audio usage and, when available, the most recent context-window usage. Delegated Responses token usage is reported separately in response.event events.",
+        "example": {
+          "type": "session.usage.updated",
+          "event_id": "evt_usage_001",
+          "usage": {
+            "seconds": 32.5
+          },
+          "context_window": {
+            "usage_ratio": 0.12
+          }
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "description": "The unique ID of the Live server event.",
+            "type": "string"
+          },
+          "client_event_id": {
+            "description": "The event_id of the client command associated with this server event, when supplied.",
+            "type": "string"
+          },
+          "type": {
+            "description": "The event type, always `session.usage.updated`.",
+            "default": "session.usage.updated",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.usage.updated"
+            ]
+          },
+          "usage": {
+            "description": "The cumulative Live audio usage so far.",
+            "$ref": "#/components/schemas/LiveSessionUsage"
+          },
+          "context_window": {
+            "description": "The latest measured Live context-window usage. Omitted when the context limit is unknown.",
+            "$ref": "#/components/schemas/LiveContextWindowUsage"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "usage"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.usage.updated",
+            "event_id": "evt_usage_001",
+            "usage": {
+              "seconds": 32.5
+            },
+            "context_window": {
+              "usage_ratio": 0.12
+            }
+          }
+        }
+      },
+      "LiveSessionClosed": {
+        "description": "Returned after the Live session finishes finalizing, with the close reason, final session snapshot, and cumulative audio usage. A connection closing without this event does not confirm successful finalization.",
+        "example": {
+          "type": "session.closed",
+          "event_id": "evt_closed_001",
+          "client_event_id": "evt_close_001",
+          "reason": "close_requested",
+          "session": {
+            "id": "live_abc123",
+            "model": "gpt-live-1",
+            "status": "active",
+            "expires_at": 1788555600,
+            "instructions": "Help the caller plan a restaurant reservation. Confirm details before booking.",
+            "input": [],
+            "audio": {
+              "format": {
+                "type": "audio/pcm",
+                "rate": 24000
+              },
+              "output": {
+                "voice": "marin"
+              }
+            },
+            "delegation": {
+              "type": "client"
+            }
+          },
+          "usage": {
+            "seconds": 45.8
+          }
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "description": "The unique ID of the Live server event.",
+            "type": "string"
+          },
+          "client_event_id": {
+            "description": "The event_id of the client command associated with this server event, when supplied.",
+            "type": "string"
+          },
+          "type": {
+            "description": "The event type, always `session.closed`.",
+            "default": "session.closed",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "session.closed"
+            ]
+          },
+          "reason": {
+            "description": "Why the Live session ended: `close_requested` for an application close or hangup request, `expired` for the session duration limit, `content` for a safety filter, `remote_hangup` for a graceful remote disconnect, or `connection_lost` for an unexpected primary or upstream disconnection.",
+            "oneOf": [
+              {
+                "default": "close_requested",
+                "x-stainless-const": true,
+                "type": "string",
+                "enum": [
+                  "close_requested"
+                ]
+              },
+              {
+                "default": "expired",
+                "x-stainless-const": true,
+                "type": "string",
+                "enum": [
+                  "expired"
+                ]
+              },
+              {
+                "default": "content",
+                "x-stainless-const": true,
+                "type": "string",
+                "enum": [
+                  "content"
+                ]
+              },
+              {
+                "default": "remote_hangup",
+                "x-stainless-const": true,
+                "type": "string",
+                "enum": [
+                  "remote_hangup"
+                ]
+              },
+              {
+                "default": "connection_lost",
+                "x-stainless-const": true,
+                "type": "string",
+                "enum": [
+                  "connection_lost"
+                ]
+              }
+            ]
+          },
+          "session": {
+            "$ref": "#/components/schemas/LiveSessionResourceParam"
+          },
+          "usage": {
+            "description": "The final cumulative Live audio usage after session finalization.",
+            "$ref": "#/components/schemas/LiveSessionUsage"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "reason",
+          "session",
+          "usage"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "session.closed",
+            "event_id": "evt_closed_001",
+            "client_event_id": "evt_close_001",
+            "reason": "close_requested",
+            "session": {
+              "id": "live_abc123",
+              "model": "gpt-live-1",
+              "status": "active",
+              "expires_at": 1788555600,
+              "instructions": "Help the caller plan a restaurant reservation. Confirm details before booking.",
+              "input": [],
+              "audio": {
+                "format": {
+                  "type": "audio/pcm",
+                  "rate": 24000
+                },
+                "output": {
+                  "voice": "marin"
+                }
+              },
+              "delegation": {
+                "type": "client"
+              }
+            },
+            "usage": {
+              "seconds": 45.8
+            }
+          }
+        }
+      },
+      "LiveLiveError": {
+        "description": "Details of an error encountered by the Live session, including the affected parameter or client command when available.",
+        "type": "object",
+        "properties": {
+          "type": {
+            "description": "The category of error, such as `invalid_request_error` for an invalid Live client command.",
+            "type": "string"
+          },
+          "code": {
+            "description": "A machine-readable code identifying the Live error, such as `unknown_parameter`.",
+            "type": "string"
+          },
+          "message": {
+            "description": "A human-readable explanation of the Live error.",
+            "type": "string"
+          },
+          "param": {
+            "description": "The parameter that caused the error, when applicable, such as `session.voice`.",
+            "type": "string"
+          },
+          "client_event_id": {
+            "description": "The event_id of the client command that caused the error, when supplied.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "type",
+          "code",
+          "message"
+        ]
+      },
+      "LiveErrorEvent": {
+        "description": "Reports an error in the Live session, such as an invalid client command. Use error.client_event_id, when present, to identify the command that caused the error.",
+        "example": {
+          "type": "error",
+          "event_id": "evt_error_001",
+          "error": {
+            "type": "invalid_request_error",
+            "code": "unknown_parameter",
+            "message": "Unknown parameter: 'session.voice'.",
+            "param": "session.voice",
+            "client_event_id": "evt_invalid_001"
+          }
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "description": "The unique ID of the Live server event.",
+            "type": "string"
+          },
+          "client_event_id": {
+            "description": "The event_id of the client command associated with this server event, when supplied.",
+            "type": "string"
+          },
+          "type": {
+            "description": "The event type, always `error`.",
+            "default": "error",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "error"
+            ]
+          },
+          "error": {
+            "description": "Details of the Live error and the client command that caused it, when known.",
+            "$ref": "#/components/schemas/LiveLiveError"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "error"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "error",
+            "event_id": "evt_error_001",
+            "error": {
+              "type": "invalid_request_error",
+              "code": "unknown_parameter",
+              "message": "Unknown parameter: 'session.voice'.",
+              "param": "session.voice",
+              "client_event_id": "evt_invalid_001"
+            }
+          }
+        }
+      },
+      "LiveInfoEvent": {
+        "description": "An informational notice about the Live session, such as the event permissions applied to a frontend data channel.",
+        "example": {
+          "type": "info",
+          "event_id": "evt_info_001",
+          "code": "data_channel_permissions",
+          "message": "The frontend data channel is configured with restricted event permissions."
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "description": "The unique ID of the Live server event.",
+            "type": "string"
+          },
+          "client_event_id": {
+            "description": "The event_id of the client command associated with this server event, when supplied.",
+            "type": "string"
+          },
+          "type": {
+            "description": "The event type, always `info`.",
+            "default": "info",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "info"
+            ]
+          },
+          "code": {
+            "description": "A machine-readable code for the notice, such as `data_channel_permissions`.",
+            "type": "string"
+          },
+          "message": {
+            "description": "A human-readable explanation of the Live session notice.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "event_id",
+          "type",
+          "code",
+          "message"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "info",
+            "event_id": "evt_info_001",
+            "code": "data_channel_permissions",
+            "message": "The frontend data channel is configured with restricted event permissions."
+          }
+        }
+      },
+      "LiveTransportDTMFReceived": {
+        "description": "A SIP DTMF keypress received from the caller. Delivered only to sideband observers.",
+        "example": {
+          "type": "transport.dtmf.received",
+          "event_id": "event_dtmf_1",
+          "event": "5"
+        },
+        "type": "object",
+        "properties": {
+          "type": {
+            "default": "transport.dtmf.received",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "transport.dtmf.received"
+            ]
+          },
+          "event_id": {
+            "type": "string"
+          },
+          "event": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 1,
+            "pattern": "^[0-9A-D*#]$"
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "event"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "transport.dtmf.received",
+            "event_id": "event_dtmf_1",
+            "event": "5"
+          }
+        }
+      },
+      "LiveTransportDTMFSend": {
+        "description": "A SIP DTMF keypress successfully sent by the hosted tool. Delivered only to sideband observers; this is not a client command.",
+        "example": {
+          "type": "transport.dtmf.send",
+          "event_id": "event_dtmf_2",
+          "event": "#"
+        },
+        "type": "object",
+        "properties": {
+          "type": {
+            "default": "transport.dtmf.send",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "transport.dtmf.send"
+            ]
+          },
+          "event_id": {
+            "type": "string"
+          },
+          "event": {
+            "type": "string",
+            "minLength": 1,
+            "maxLength": 1,
+            "pattern": "^[0-9A-D*#]$"
+          }
+        },
+        "required": [
+          "type",
+          "event_id",
+          "event"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "transport.dtmf.send",
+            "event_id": "event_dtmf_2",
+            "event": "#"
+          }
+        }
+      },
+      "LiveTransportRinging": {
+        "description": "The outbound SIP provider leg is ringing or providing early media. Delivered only to sideband observers.",
+        "example": {
+          "type": "transport.ringing",
+          "event_id": "event_call_1",
+          "session_id": "live_u0_123"
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "type": "string"
+          },
+          "session_id": {
+            "description": "The canonical Live session ID.",
+            "type": "string"
+          },
+          "type": {
+            "default": "transport.ringing",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "transport.ringing"
+            ]
+          }
+        },
+        "required": [
+          "event_id",
+          "session_id",
+          "type"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "transport.ringing",
+            "event_id": "event_call_1",
+            "session_id": "live_u0_123"
+          }
+        }
+      },
+      "LiveTransportAnswered": {
+        "description": "The outbound SIP provider leg answered and media is established. Delivered only to sideband observers.",
+        "example": {
+          "type": "transport.answered",
+          "event_id": "event_call_2",
+          "session_id": "live_u0_123"
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "type": "string"
+          },
+          "session_id": {
+            "description": "The canonical Live session ID.",
+            "type": "string"
+          },
+          "type": {
+            "default": "transport.answered",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "transport.answered"
+            ]
+          }
+        },
+        "required": [
+          "event_id",
+          "session_id",
+          "type"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "transport.answered",
+            "event_id": "event_call_2",
+            "session_id": "live_u0_123"
+          }
+        }
+      },
+      "LiveTransportCallError": {
+        "type": "object",
+        "properties": {
+          "type": {
+            "default": "call_error",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "call_error"
+            ]
+          },
+          "code": {
+            "description": "The call setup failure code.",
+            "type": "string"
+          },
+          "message": {
+            "type": "string"
+          },
+          "param": {
+            "description": "The parameter related to the error, if any. Empty when no parameter applies.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "type",
+          "code",
+          "message"
+        ]
+      },
+      "LiveTransportFailed": {
+        "description": "An asynchronous outbound SIP setup failure. Delivered only to sideband observers.",
+        "example": {
+          "type": "transport.failed",
+          "event_id": "event_call_4",
+          "session_id": "live_u0_123",
+          "error": {
+            "type": "call_error",
+            "code": "provider_invite_failed",
+            "message": "provider rejected the call",
+            "param": ""
+          }
+        },
+        "type": "object",
+        "properties": {
+          "event_id": {
+            "type": "string"
+          },
+          "session_id": {
+            "description": "The canonical Live session ID.",
+            "type": "string"
+          },
+          "type": {
+            "default": "transport.failed",
+            "x-stainless-const": true,
+            "type": "string",
+            "enum": [
+              "transport.failed"
+            ]
+          },
+          "error": {
+            "$ref": "#/components/schemas/LiveTransportCallError"
+          }
+        },
+        "required": [
+          "event_id",
+          "session_id",
+          "type",
+          "error"
+        ],
+        "x-oaiMeta": {
+          "example": {
+            "type": "transport.failed",
+            "event_id": "event_call_4",
+            "session_id": "live_u0_123",
+            "error": {
+              "type": "call_error",
+              "code": "provider_invite_failed",
+              "message": "provider rejected the call",
+              "param": ""
+            }
+          }
+        }
+      },
+      "LiveServerEvent-2": {
+        "description": "An event sent by the Live API on a primary WebSocket or sideband connection.",
+        "discriminator": {
+          "propertyName": "type"
+        },
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/LiveSessionStarted"
+          },
+          {
+            "$ref": "#/components/schemas/LiveSessionUpdated"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInputAudioMuted"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInputAudioUnmuted"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInstructionsAppended"
+          },
+          {
+            "$ref": "#/components/schemas/LiveThinkingAppended"
+          },
+          {
+            "$ref": "#/components/schemas/LiveCommentaryAppended"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInputAudioAppend"
+          },
+          {
+            "$ref": "#/components/schemas/LiveOutputAudioDelta"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInputTranscriptDelta"
+          },
+          {
+            "$ref": "#/components/schemas/LiveOutputTranscriptDelta"
+          },
+          {
+            "$ref": "#/components/schemas/LiveDelegationCreated"
+          },
+          {
+            "$ref": "#/components/schemas/LiveResponseEvent"
+          },
+          {
+            "$ref": "#/components/schemas/LiveSessionUsageUpdated"
+          },
+          {
+            "$ref": "#/components/schemas/LiveSessionClosed"
+          },
+          {
+            "$ref": "#/components/schemas/LiveErrorEvent"
+          },
+          {
+            "$ref": "#/components/schemas/LiveInfoEvent"
+          },
+          {
+            "$ref": "#/components/schemas/LiveTransportDTMFReceived"
+          },
+          {
+            "$ref": "#/components/schemas/LiveTransportDTMFSend"
+          },
+          {
+            "$ref": "#/components/schemas/LiveTransportRinging"
+          },
+          {
+            "$ref": "#/components/schemas/LiveTransportAnswered"
+          },
+          {
+            "$ref": "#/components/schemas/LiveTransportFailed"
+          }
+        ]
+      },
+      "UserMessageItemParam": {
+        "properties": {
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of this message item.",
+                "example": "msg_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "message"
+            ],
+            "description": "The item type. Always `message`.",
+            "default": "message",
+            "x-stainless-const": true
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "user"
+            ],
+            "description": "The message role. Always `user`.",
+            "default": "user",
+            "x-stainless-const": true
+          },
+          "content": {
+            "oneOf": [
+              {
+                "items": {
+                  "oneOf": [
+                    {
+                      "$ref": "#/components/schemas/InputTextContentParam"
+                    },
+                    {
+                      "$ref": "#/components/schemas/InputImageContentParamAutoParam"
+                    },
+                    {
+                      "$ref": "#/components/schemas/InputFileContentParam"
+                    }
+                  ],
+                  "description": "A piece of message content, such as text, an image, or a file.",
+                  "discriminator": {
+                    "propertyName": "type"
+                  }
+                },
+                "type": "array"
+              },
+              {
+                "type": "string",
+                "maxLength": 10485760,
+                "description": "The message content, as a single string."
+              }
+            ],
+            "description": "The message content, as an array of content parts."
+          },
+          "status": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The status of the message item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "role",
+          "content"
+        ]
+      },
+      "ErrorPayload": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The error type that was emitted."
+          },
+          "code": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The error code that was emitted, if any."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "message": {
+            "type": "string",
+            "description": "The human-readable error message that was emitted."
+          },
+          "param": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The parameter name that was associated with the error, if any."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "headers": {
+            "additionalProperties": {
+              "type": "string",
+              "description": "The header value that was emitted."
+            },
+            "type": "object",
+            "description": "The response headers that were emitted with the error, if any.",
+            "x-oaiTypeLabel": "map"
+          },
+          "misalignment": {
+            "$ref": "#/components/schemas/MisalignmentErrorDetailsResource"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "code",
+          "message",
+          "param"
+        ],
+        "title": "Error payload",
+        "description": "An error payload that was emitted for a streaming error event."
+      },
+      "BetaTokenCountsResource": {
+        "properties": {
+          "object": {
+            "type": "string",
+            "enum": [
+              "response.input_tokens"
+            ],
+            "default": "response.input_tokens",
+            "x-stainless-const": true
+          },
+          "input_tokens": {
+            "type": "integer"
+          }
+        },
+        "type": "object",
+        "required": [
+          "object",
+          "input_tokens"
+        ],
+        "title": "Token counts",
+        "example": {
+          "object": "response.input_tokens",
+          "input_tokens": 123
+        }
+      },
+      "BetaTokenCountsBody": {
+        "properties": {
+          "model": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Model ID used to generate the response, like `gpt-4o` or `o3`. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the [model guide](https://developers.openai.com/api/docs/models) to browse and compare available models."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "input": {
+            "anyOf": [
+              {
+                "oneOf": [
+                  {
+                    "type": "string",
+                    "maxLength": 10485760,
+                    "description": "A text input to the model, equivalent to a text input with the `user` role."
+                  },
+                  {
+                    "items": {
+                      "$ref": "#/components/schemas/BetaInputItem"
+                    },
+                    "type": "array",
+                    "maxItems": 131072,
+                    "description": "A list of one or many input items to the model, containing different content types."
+                  }
+                ],
+                "description": "Text, image, or file inputs to the model, used to generate a response"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "previous_response_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](https://developers.openai.com/api/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`.",
+                "example": "resp_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "tools": {
+            "anyOf": [
+              {
+                "items": {
+                  "$ref": "#/components/schemas/BetaTool"
+                },
+                "type": "array",
+                "description": "An array of tools the model may call while generating a response. You can specify which tool to use by setting the `tool_choice` parameter."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "text": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseTextParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "reasoning": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaReasoning",
+                "description": "**gpt-5 and o-series models only** Configuration options for [reasoning models](https://developers.openai.com/api/docs/guides/reasoning)."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "truncation": {
+            "$ref": "#/components/schemas/BetaTruncationEnum",
+            "description": "The truncation strategy to use for the model response. - `auto`: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. - `disabled` (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error.",
+            "deprecated": true
+          },
+          "instructions": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "A system (or developer) message inserted into the model's context.\nWhen used along with `previous_response_id`, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "personality": {
+            "$ref": "#/components/schemas/BetaPersonalityEnum",
+            "description": "A model-owned style preset to apply to this request. Omit this parameter to use the model's default style. Supported values may expand over time. Values must be at most 64 characters."
+          },
+          "conversation": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaConversationParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "tool_choice": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaToolChoiceParam",
+                "description": "Controls which tool the model should use, if any."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "parallel_tool_calls": {
+            "anyOf": [
+              {
+                "type": "boolean",
+                "description": "Whether to allow the model to run tool calls in parallel."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": []
+      },
+      "BetaToolChoiceParam": {
+        "description": "How the model should select which tool (or tools) to use when generating\na response. See the `tools` parameter to see how to specify which tools\nthe model can call.\n",
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/BetaToolChoiceOptions"
+          },
+          {
+            "$ref": "#/components/schemas/BetaToolChoiceAllowed"
+          },
+          {
+            "$ref": "#/components/schemas/BetaToolChoiceTypes"
+          },
+          {
+            "$ref": "#/components/schemas/BetaToolChoiceFunction"
+          },
+          {
+            "$ref": "#/components/schemas/BetaToolChoiceMCP"
+          },
+          {
+            "$ref": "#/components/schemas/BetaToolChoiceCustom"
+          },
+          {
+            "$ref": "#/components/schemas/BetaSpecificProgrammaticToolCallingParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaSpecificApplyPatchParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaSpecificFunctionShellParam"
+          }
+        ]
+      },
+      "BetaSpecificFunctionShellParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "shell"
+            ],
+            "description": "The tool to call. Always `shell`.",
+            "default": "shell",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Specific shell tool choice",
+        "description": "Forces the model to call the shell tool when a tool call is required."
+      },
+      "BetaSpecificApplyPatchParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "apply_patch"
+            ],
+            "description": "The tool to call. Always `apply_patch`.",
+            "default": "apply_patch",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Specific apply patch tool choice",
+        "description": "Forces the model to call the apply_patch tool when executing a tool call."
+      },
+      "BetaSpecificProgrammaticToolCallingParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "programmatic_tool_calling"
+            ],
+            "description": "The tool to call. Always `programmatic_tool_calling`.",
+            "default": "programmatic_tool_calling",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "BetaToolChoiceCustom": {
+        "type": "object",
+        "title": "Custom tool",
+        "description": "Use this option to force the model to call a specific custom tool.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "custom"
+            ],
+            "description": "For custom tool calling, the type is always `custom`.",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the custom tool to call."
+          }
+        },
+        "required": [
+          "type",
+          "name"
+        ]
+      },
+      "BetaToolChoiceMCP": {
+        "type": "object",
+        "title": "MCP tool",
+        "description": "Use this option to force the model to call a specific tool on a remote MCP server.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp"
+            ],
+            "description": "For MCP tools, the type is always `mcp`.",
+            "x-stainless-const": true
+          },
+          "server_label": {
+            "type": "string",
+            "description": "The label of the MCP server to use.\n"
+          },
+          "name": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The name of the tool to call on the server.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "server_label"
+        ]
+      },
+      "BetaToolChoiceFunction": {
+        "type": "object",
+        "title": "Function tool",
+        "description": "Use this option to force the model to call a specific function.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "function"
+            ],
+            "description": "For function calling, the type is always `function`.",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the function to call."
+          }
+        },
+        "required": [
+          "type",
+          "name"
+        ]
+      },
+      "BetaToolChoiceTypes": {
+        "type": "object",
+        "title": "Hosted tool",
+        "description": "Indicates that the model should use a built-in tool to generate a response.\n[Learn more about built-in tools](https://developers.openai.com/api/docs/guides/tools).\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of hosted tool the model should to use. Learn more about\n[built-in tools](https://developers.openai.com/api/docs/guides/tools).\n\nAllowed values are:\n- `file_search`\n- `web_search_preview`\n- `computer`\n- `computer_use_preview`\n- `computer_use`\n- `code_interpreter`\n- `image_generation`\n",
+            "enum": [
+              "file_search",
+              "web_search_preview",
+              "computer",
+              "computer_use_preview",
+              "computer_use",
+              "web_search_preview_2025_03_11",
+              "image_generation",
+              "code_interpreter"
+            ]
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "BetaToolChoiceAllowed": {
+        "type": "object",
+        "title": "Allowed tools",
+        "description": "Constrains the tools available to the model to a pre-defined set.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "allowed_tools"
+            ],
+            "description": "Allowed tool configuration type. Always `allowed_tools`.",
+            "x-stainless-const": true
+          },
+          "mode": {
+            "type": "string",
+            "enum": [
+              "auto",
+              "required"
+            ],
+            "description": "Constrains the tools available to the model to a pre-defined set.\n\n`auto` allows the model to pick from among the allowed tools and generate a\nmessage.\n\n`required` requires the model to call one or more of the allowed tools.\n"
+          },
+          "tools": {
+            "type": "array",
+            "description": "A list of tool definitions that the model should be allowed to call.\n\nFor the Responses API, the list of tool definitions might look like:\n```json\n[\n  { \"type\": \"function\", \"name\": \"get_weather\" },\n  { \"type\": \"mcp\", \"server_label\": \"deepwiki\" },\n  { \"type\": \"image_generation\" }\n]\n```\n",
+            "items": {
+              "type": "object",
+              "description": "A tool definition that the model should be allowed to call.\n",
+              "additionalProperties": true,
+              "x-oaiExpandable": false
+            }
+          }
+        },
+        "required": [
+          "type",
+          "mode",
+          "tools"
+        ]
+      },
+      "BetaToolChoiceOptions": {
+        "type": "string",
+        "title": "Tool choice mode",
+        "description": "Controls which (if any) tool is called by the model.\n\n`none` means the model will not call any tool and instead generates a message.\n\n`auto` means the model can pick between generating a message or calling one or\nmore tools.\n\n`required` means the model must call one or more tools.\n",
+        "enum": [
+          "none",
+          "auto",
+          "required"
+        ]
+      },
+      "BetaConversationParam": {
+        "description": "The conversation that this response belongs to. Items from this conversation are prepended to `input_items` for this response request.\nInput items and output items from this response are automatically added to this conversation after this response completes.\n",
+        "default": null,
+        "oneOf": [
+          {
+            "type": "string",
+            "title": "Conversation ID",
+            "description": "The unique ID of the conversation.\n"
+          },
+          {
+            "$ref": "#/components/schemas/BetaConversationParam-2"
+          }
+        ]
+      },
+      "BetaConversationParam-2": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the conversation.",
+            "example": "conv_123"
+          }
+        },
+        "type": "object",
+        "required": [
+          "id"
+        ],
+        "title": "Conversation object",
+        "description": "The conversation that this response belongs to."
+      },
+      "BetaPersonalityEnum": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "string",
+            "enum": [
+              "friendly",
+              "pragmatic"
+            ]
+          }
+        ]
+      },
+      "BetaTruncationEnum": {
+        "type": "string",
+        "enum": [
+          "auto",
+          "disabled"
+        ]
+      },
+      "BetaReasoning": {
+        "type": "object",
+        "description": "Configuration options for\n[reasoning models](https://developers.openai.com/api/docs/guides/reasoning).\n",
+        "title": "Reasoning",
+        "properties": {
+          "mode": {
+            "$ref": "#/components/schemas/BetaReasoningModeEnum",
+            "description": "Controls the reasoning execution mode for the request.\n\nWhen returned on a response, this is the effective execution mode.\n"
+          },
+          "effort": {
+            "$ref": "#/components/schemas/BetaReasoningEffort"
+          },
+          "summary": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "A summary of the reasoning performed by the model. This can be\nuseful for debugging and understanding the model's reasoning process.\nOne of `auto`, `concise`, or `detailed`.\n\n`concise` is supported for `computer-use-preview` models and all reasoning models after `gpt-5`.\n",
+                "enum": [
+                  "auto",
+                  "concise",
+                  "detailed"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "context": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Controls which reasoning items are rendered back to the model on later turns.\nIf omitted or set to `auto`, the model determines the context mode. The\n`gpt-5.6` model family defaults to `all_turns`; earlier models default to\n`current_turn`.\n\nWhen returned on a response, this is the effective reasoning context mode\nused for the response.\n",
+                "enum": [
+                  "auto",
+                  "current_turn",
+                  "all_turns"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "generate_summary": {
+            "anyOf": [
+              {
+                "type": "string",
+                "deprecated": true,
+                "description": "**Deprecated:** use `summary` instead.\n\nA summary of the reasoning performed by the model. This can be\nuseful for debugging and understanding the model's reasoning process.\nOne of `auto`, `concise`, or `detailed`.\n",
+                "enum": [
+                  "auto",
+                  "concise",
+                  "detailed"
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        }
+      },
+      "BetaReasoningEffort": {
+        "anyOf": [
+          {
+            "type": "string",
+            "enum": [
+              "none",
+              "minimal",
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max"
+            ],
+            "default": "medium",
+            "description": "Constrains effort on reasoning for reasoning models. Currently supported\nvalues are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`.\nReducing reasoning effort can result in faster responses and fewer tokens\nused on reasoning in a response. Not all reasoning models support every\nvalue. See the\n[reasoning guide](https://developers.openai.com/api/docs/guides/reasoning)\nfor model-specific support.\n"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "BetaReasoningModeEnum": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "string",
+            "enum": [
+              "standard",
+              "pro"
+            ]
+          }
+        ]
+      },
+      "BetaResponseTextParam": {
+        "type": "object",
+        "description": "Configuration options for a text response from the model. Can be plain\ntext or structured JSON data. Learn more:\n- [Text inputs and outputs](https://developers.openai.com/api/docs/guides/text)\n- [Structured Outputs](https://developers.openai.com/api/docs/guides/structured-outputs)\n",
+        "properties": {
+          "format": {
+            "$ref": "#/components/schemas/BetaTextResponseFormatConfiguration"
+          },
+          "verbosity": {
+            "$ref": "#/components/schemas/BetaVerbosity"
+          }
+        }
+      },
+      "BetaVerbosity": {
+        "anyOf": [
+          {
+            "type": "string",
+            "enum": [
+              "low",
+              "medium",
+              "high"
+            ],
+            "default": "medium",
+            "description": "Constrains the verbosity of the model's response. Lower values will result in\nmore concise responses, while higher values will result in more verbose responses.\nCurrently supported values are `low`, `medium`, and `high`. The default is\n`medium`.\n"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "BetaTextResponseFormatConfiguration": {
+        "description": "An object specifying the format that the model must output.\n\nConfiguring `{ \"type\": \"json_schema\" }` enables Structured Outputs,\nwhich ensures the model will match your supplied JSON schema. Learn more in the\n[Structured Outputs guide](https://developers.openai.com/api/docs/guides/structured-outputs).\n\nThe default format is `{ \"type\": \"text\" }` with no additional options.\n\n**Not recommended for gpt-4o and newer models:**\n\nSetting to `{ \"type\": \"json_object\" }` enables the older JSON mode, which\nensures the message the model generates is valid JSON. Using `json_schema`\nis preferred for models that support it.\n",
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/BetaResponseFormatText"
+          },
+          {
+            "$ref": "#/components/schemas/BetaTextResponseFormatJsonSchema"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseFormatJsonObject"
+          }
+        ]
+      },
+      "BetaResponseFormatJsonObject": {
+        "type": "object",
+        "title": "JSON object",
+        "description": "JSON object response format. An older method of generating JSON responses.\nUsing `json_schema` is recommended for models that support it. Note that the\nmodel will not generate JSON without a system or user message instructing it\nto do so.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of response format being defined. Always `json_object`.",
+            "enum": [
+              "json_object"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "BetaTextResponseFormatJsonSchema": {
+        "type": "object",
+        "title": "JSON schema",
+        "description": "JSON Schema response format. Used to generate structured JSON responses.\nLearn more about [Structured Outputs](https://developers.openai.com/api/docs/guides/structured-outputs).\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of response format being defined. Always `json_schema`.",
+            "enum": [
+              "json_schema"
+            ],
+            "x-stainless-const": true
+          },
+          "description": {
+            "type": "string",
+            "description": "A description of what the response format is for, used by the model to\ndetermine how to respond in the format.\n"
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the response format. Must be a-z, A-Z, 0-9, or contain\nunderscores and dashes, with a maximum length of 64.\n"
+          },
+          "schema": {
+            "$ref": "#/components/schemas/BetaResponseFormatJsonSchemaSchema"
+          },
+          "strict": {
+            "anyOf": [
+              {
+                "type": "boolean",
+                "default": false,
+                "description": "Whether to enable strict schema adherence when generating the output.\nIf set to true, the model will always follow the exact schema defined\nin the `schema` field. Only a subset of JSON Schema is supported when\n`strict` is `true`. To learn more, read the [Structured Outputs\nguide](https://developers.openai.com/api/docs/guides/structured-outputs).\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "schema",
+          "name"
+        ]
+      },
+      "BetaResponseFormatJsonSchemaSchema": {
+        "type": "object",
+        "title": "JSON schema",
+        "description": "The schema for the response format, described as a JSON Schema object.\nLearn how to build JSON schemas [here](https://json-schema.org/).\n",
+        "additionalProperties": true
+      },
+      "BetaResponseFormatText": {
+        "type": "object",
+        "title": "Text",
+        "description": "Default response format. Used to generate text responses.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of response format being defined. Always `text`.",
+            "enum": [
+              "text"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "BetaTool": {
+        "description": "A tool that can be used to generate a response.\n",
+        "discriminator": {
+          "propertyName": "type"
+        },
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/BetaFunctionTool"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFileSearchTool"
+          },
+          {
+            "$ref": "#/components/schemas/BetaComputerTool"
+          },
+          {
+            "$ref": "#/components/schemas/BetaComputerUsePreviewTool"
+          },
+          {
+            "$ref": "#/components/schemas/BetaWebSearchTool"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMCPTool"
+          },
+          {
+            "$ref": "#/components/schemas/BetaCodeInterpreterTool"
+          },
+          {
+            "$ref": "#/components/schemas/BetaProgrammaticToolCallingParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaImageGenTool"
+          },
+          {
+            "$ref": "#/components/schemas/BetaLocalShellToolParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFunctionShellToolParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaCustomToolParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaNamespaceToolParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaToolSearchToolParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaWebSearchPreviewTool"
+          },
+          {
+            "$ref": "#/components/schemas/BetaApplyPatchToolParam"
+          }
+        ]
+      },
+      "BetaApplyPatchToolParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "apply_patch"
+            ],
+            "description": "The type of the tool. Always `apply_patch`.",
+            "default": "apply_patch",
+            "x-stainless-const": true
+          },
+          "allowed_callers": {
+            "anyOf": [
+              {
+                "items": {
+                  "$ref": "#/components/schemas/BetaCallableToolAllowedCaller"
+                },
+                "type": "array",
+                "minItems": 1,
+                "description": "The tool invocation context(s)."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Apply patch tool",
+        "description": "Allows the assistant to create, delete, or update files using unified diffs."
+      },
+      "BetaCallableToolAllowedCaller": {
+        "type": "string",
+        "enum": [
+          "direct",
+          "programmatic"
+        ]
+      },
+      "BetaWebSearchPreviewTool": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "web_search_preview",
+              "web_search_preview_2025_03_11"
+            ],
+            "description": "The type of the web search tool. One of `web_search_preview` or `web_search_preview_2025_03_11`.",
+            "default": "web_search_preview",
+            "x-stainless-const": true
+          },
+          "user_location": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaApproximateLocation",
+                "description": "The user's location."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "search_context_size": {
+            "$ref": "#/components/schemas/BetaSearchContextSize",
+            "description": "High level guidance for the amount of context window space to use for the search. One of `low`, `medium`, or `high`. `medium` is the default."
+          },
+          "search_content_types": {
+            "items": {
+              "$ref": "#/components/schemas/BetaSearchContentType"
+            },
+            "type": "array"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Web search preview",
+        "description": "This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](https://developers.openai.com/api/docs/guides/tools-web-search)."
+      },
+      "BetaSearchContentType": {
+        "type": "string",
+        "enum": [
+          "text",
+          "image"
+        ]
+      },
+      "BetaSearchContextSize": {
+        "type": "string",
+        "enum": [
+          "low",
+          "medium",
+          "high"
+        ]
+      },
+      "BetaApproximateLocation": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "approximate"
+            ],
+            "description": "The type of location approximation. Always `approximate`.",
+            "default": "approximate",
+            "x-stainless-const": true
+          },
+          "country": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "region": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Free text input for the region of the user, e.g. `California`."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "city": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Free text input for the city of the user, e.g. `San Francisco`."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "timezone": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "BetaToolSearchToolParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "tool_search"
+            ],
+            "description": "The type of the tool. Always `tool_search`.",
+            "default": "tool_search",
+            "x-stainless-const": true
+          },
+          "execution": {
+            "$ref": "#/components/schemas/BetaToolSearchExecutionType",
+            "description": "Whether tool search is executed by the server or by the client."
+          },
+          "description": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Description shown to the model for a client-executed tool search tool."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "parameters": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaEmptyModelParam",
+                "description": "Parameter schema for a client-executed tool search tool."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Tool search tool",
+        "description": "Hosted or BYOT tool search configuration for deferred tools."
+      },
+      "BetaEmptyModelParam": {
+        "properties": {},
+        "type": "object",
+        "required": []
+      },
+      "BetaToolSearchExecutionType": {
+        "type": "string",
+        "enum": [
+          "server",
+          "client"
+        ]
+      },
+      "BetaNamespaceToolParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "namespace"
+            ],
+            "description": "The type of the tool. Always `namespace`.",
+            "default": "namespace",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "minLength": 1,
+            "description": "The namespace name used in tool calls (for example, `crm`)."
+          },
+          "description": {
+            "type": "string",
+            "description": "A description of the namespace shown to the model."
+          },
+          "tools": {
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/BetaFunctionToolParam"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaCustomToolParam"
+                }
+              ],
+              "description": "A function or custom tool that belongs to a namespace.",
+              "discriminator": {
+                "propertyName": "type"
+              }
+            },
+            "type": "array",
+            "minItems": 1,
+            "description": "The function/custom tools available inside this namespace."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "name",
+          "description",
+          "tools"
+        ],
+        "title": "Namespace",
+        "description": "Groups function/custom tools under a shared namespace."
+      },
+      "BetaCustomToolParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "custom"
+            ],
+            "description": "The type of the custom tool. Always `custom`.",
+            "default": "custom",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the custom tool, used to identify it in tool calls."
+          },
+          "async": {
+            "type": "boolean",
+            "description": "Whether the tool response can be returned asynchronously versus immediately returned on next response creation."
+          },
+          "description": {
+            "type": "string",
+            "description": "Optional description of the custom tool, used to provide more context."
+          },
+          "format": {
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/BetaCustomTextFormatParam"
+              },
+              {
+                "$ref": "#/components/schemas/BetaCustomGrammarFormatParam"
+              }
+            ],
+            "description": "The input format for the custom tool. Default is unconstrained text.",
+            "discriminator": {
+              "propertyName": "type"
+            }
+          },
+          "defer_loading": {
+            "type": "boolean",
+            "description": "Whether this tool should be deferred and discovered via tool search."
+          },
+          "allowed_callers": {
+            "anyOf": [
+              {
+                "items": {
+                  "$ref": "#/components/schemas/BetaCallableToolAllowedCaller"
+                },
+                "type": "array",
+                "minItems": 1,
+                "description": "The tool invocation context(s)."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "name"
+        ],
+        "title": "Custom tool",
+        "description": "A custom tool that processes input using a specified format. Learn more about   [custom tools](https://developers.openai.com/api/docs/guides/function-calling#custom-tools)"
+      },
+      "BetaCustomGrammarFormatParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "grammar"
+            ],
+            "description": "Grammar format. Always `grammar`.",
+            "default": "grammar",
+            "x-stainless-const": true
+          },
+          "syntax": {
+            "$ref": "#/components/schemas/BetaGrammarSyntax1",
+            "description": "The syntax of the grammar definition. One of `lark` or `regex`."
+          },
+          "definition": {
+            "type": "string",
+            "description": "The grammar definition."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "syntax",
+          "definition"
+        ],
+        "title": "Grammar format",
+        "description": "A grammar defined by the user."
+      },
+      "BetaGrammarSyntax1": {
+        "type": "string",
+        "enum": [
+          "lark",
+          "regex"
+        ]
+      },
+      "BetaCustomTextFormatParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "text"
+            ],
+            "description": "Unconstrained text format. Always `text`.",
+            "default": "text",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Text format",
+        "description": "Unconstrained free-form text."
+      },
+      "BetaFunctionToolParam": {
+        "properties": {
+          "name": {
+            "type": "string",
+            "maxLength": 128,
+            "minLength": 1,
+            "pattern": "^[a-zA-Z0-9_-]+$"
+          },
+          "description": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "parameters": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaEmptyModelParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "strict": {
+            "anyOf": [
+              {
+                "type": "boolean",
+                "description": "Whether to enforce strict parameter validation. If omitted, Responses attempts to use strict validation when the schema is compatible, and falls back to non-strict validation otherwise."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "function"
+            ],
+            "default": "function",
+            "x-stainless-const": true
+          },
+          "async": {
+            "type": "boolean",
+            "description": "Whether the tool response can be returned asynchronously versus immediately returned on next response creation."
+          },
+          "output_schema": {
+            "anyOf": [
+              {
+                "additionalProperties": {},
+                "type": "object",
+                "description": "A JSON Schema describing the JSON value encoded in string outputs for this function tool. This does not describe content-array outputs.",
+                "x-oaiTypeLabel": "map"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "defer_loading": {
+            "type": "boolean",
+            "description": "Whether this function should be deferred and discovered via tool search."
+          },
+          "allowed_callers": {
+            "anyOf": [
+              {
+                "items": {
+                  "$ref": "#/components/schemas/BetaCallableToolAllowedCaller"
+                },
+                "type": "array",
+                "minItems": 1,
+                "description": "The tool invocation context(s)."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "name",
+          "type"
+        ]
+      },
+      "BetaFunctionShellToolParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "shell"
+            ],
+            "description": "The type of the shell tool. Always `shell`.",
+            "default": "shell",
+            "x-stainless-const": true
+          },
+          "environment": {
+            "anyOf": [
+              {
+                "oneOf": [
+                  {
+                    "$ref": "#/components/schemas/BetaContainerAutoParam"
+                  },
+                  {
+                    "$ref": "#/components/schemas/BetaLocalEnvironmentParam"
+                  },
+                  {
+                    "$ref": "#/components/schemas/BetaContainerReferenceParam"
+                  }
+                ],
+                "discriminator": {
+                  "propertyName": "type"
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "allowed_callers": {
+            "anyOf": [
+              {
+                "items": {
+                  "$ref": "#/components/schemas/BetaCallableToolAllowedCaller"
+                },
+                "type": "array",
+                "minItems": 1,
+                "description": "The tool invocation context(s)."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Shell tool",
+        "description": "A tool that allows the model to execute shell commands."
+      },
+      "BetaContainerReferenceParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "container_reference"
+            ],
+            "description": "References a container created with the /v1/containers endpoint",
+            "default": "container_reference",
+            "x-stainless-const": true
+          },
+          "container_id": {
+            "type": "string",
+            "description": "The ID of the referenced container.",
+            "example": "cntr_123"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "container_id"
+        ]
+      },
+      "BetaLocalEnvironmentParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "local"
+            ],
+            "description": "Use a local computer environment.",
+            "default": "local",
+            "x-stainless-const": true
+          },
+          "skills": {
+            "items": {
+              "$ref": "#/components/schemas/BetaLocalSkillParam"
+            },
+            "type": "array",
+            "maxItems": 200,
+            "description": "An optional list of skills."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "BetaLocalSkillParam": {
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The name of the skill."
+          },
+          "description": {
+            "type": "string",
+            "description": "The description of the skill."
+          },
+          "path": {
+            "type": "string",
+            "description": "The path to the directory containing the skill."
+          }
+        },
+        "type": "object",
+        "required": [
+          "name",
+          "description",
+          "path"
+        ]
+      },
+      "BetaContainerAutoParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "container_auto"
+            ],
+            "description": "Automatically creates a container for this request",
+            "default": "container_auto",
+            "x-stainless-const": true
+          },
+          "file_ids": {
+            "items": {
+              "type": "string",
+              "example": "file-123"
+            },
+            "type": "array",
+            "maxItems": 50,
+            "description": "An optional list of uploaded files to make available to your code."
+          },
+          "memory_limit": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaContainerMemoryLimit",
+                "description": "The memory limit for the container."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "network_policy": {
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/BetaContainerNetworkPolicyDisabledParam"
+              },
+              {
+                "$ref": "#/components/schemas/BetaContainerNetworkPolicyAllowlistParam"
+              }
+            ],
+            "description": "Network access policy for the container.",
+            "discriminator": {
+              "propertyName": "type"
+            }
+          },
+          "skills": {
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/BetaSkillReferenceParam"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaInlineSkillParam"
+                }
+              ],
+              "discriminator": {
+                "propertyName": "type"
+              }
+            },
+            "type": "array",
+            "maxItems": 200,
+            "description": "An optional list of skills referenced by id or inline data."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "BetaInlineSkillParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "inline"
+            ],
+            "description": "Defines an inline skill for this request.",
+            "default": "inline",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the skill."
+          },
+          "description": {
+            "type": "string",
+            "description": "The description of the skill."
+          },
+          "source": {
+            "$ref": "#/components/schemas/BetaInlineSkillSourceParam",
+            "description": "Inline skill payload"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "name",
+          "description",
+          "source"
+        ]
+      },
+      "BetaInlineSkillSourceParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "base64"
+            ],
+            "description": "The type of the inline skill source. Must be `base64`.",
+            "default": "base64",
+            "x-stainless-const": true
+          },
+          "media_type": {
+            "type": "string",
+            "enum": [
+              "application/zip"
+            ],
+            "description": "The media type of the inline skill payload. Must be `application/zip`.",
+            "default": "application/zip",
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "string",
+            "maxLength": 70254592,
+            "minLength": 1,
+            "description": "Base64-encoded skill zip bundle."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "media_type",
+          "data"
+        ],
+        "description": "Inline skill payload"
+      },
+      "BetaSkillReferenceParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "skill_reference"
+            ],
+            "description": "References a skill created with the /v1/skills endpoint.",
+            "default": "skill_reference",
+            "x-stainless-const": true
+          },
+          "skill_id": {
+            "type": "string",
+            "maxLength": 64,
+            "minLength": 1,
+            "description": "The ID of the referenced skill."
+          },
+          "version": {
+            "type": "string",
+            "description": "Optional skill version. Use a positive integer or 'latest'. Omit for default."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "skill_id"
+        ]
+      },
+      "BetaContainerNetworkPolicyAllowlistParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "allowlist"
+            ],
+            "description": "Allow outbound network access only to specified domains. Always `allowlist`.",
+            "default": "allowlist",
+            "x-stainless-const": true
+          },
+          "allowed_domains": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array",
+            "minItems": 1,
+            "description": "A list of allowed domains when type is `allowlist`."
+          },
+          "domain_secrets": {
+            "items": {
+              "$ref": "#/components/schemas/BetaContainerNetworkPolicyDomainSecretParam"
+            },
+            "type": "array",
+            "minItems": 1,
+            "description": "Optional domain-scoped secrets for allowlisted domains."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "allowed_domains"
+        ]
+      },
+      "BetaContainerNetworkPolicyDomainSecretParam": {
+        "properties": {
+          "domain": {
+            "type": "string",
+            "minLength": 1,
+            "description": "The domain associated with the secret."
+          },
+          "name": {
+            "type": "string",
+            "minLength": 1,
+            "description": "The name of the secret to inject for the domain."
+          },
+          "value": {
+            "type": "string",
+            "maxLength": 10485760,
+            "minLength": 1,
+            "description": "The secret value to inject for the domain."
+          }
+        },
+        "type": "object",
+        "required": [
+          "domain",
+          "name",
+          "value"
+        ]
+      },
+      "BetaContainerNetworkPolicyDisabledParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "disabled"
+            ],
+            "description": "Disable outbound network access. Always `disabled`.",
+            "default": "disabled",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "BetaContainerMemoryLimit": {
+        "type": "string",
+        "enum": [
+          "1g",
+          "4g",
+          "16g",
+          "64g"
+        ]
+      },
+      "BetaLocalShellToolParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "local_shell"
+            ],
+            "description": "The type of the local shell tool. Always `local_shell`.",
+            "default": "local_shell",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Local shell tool",
+        "description": "A tool that allows the model to execute shell commands in a local environment."
+      },
+      "BetaImageGenTool": {
+        "type": "object",
+        "title": "Image generation tool",
+        "description": "A tool that generates images using the GPT image models.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "image_generation"
+            ],
+            "description": "The type of the image generation tool. Always `image_generation`.\n",
+            "x-stainless-const": true
+          },
+          "model": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "gpt-image-1",
+                  "gpt-image-1-mini",
+                  "gpt-image-1.5",
+                  "gpt-image-2",
+                  "gpt-image-2-2026-04-21",
+                  "gpt-image-2.5-sunburst",
+                  "gpt-image-2.5-sunburst-2026-09-08",
+                  "gpt-image-2.5-flare",
+                  "gpt-image-2.5-flare-2026-09-08"
+                ],
+                "description": "The image generation model to use. One of `gpt-image-1`,\n`gpt-image-1-mini`, `gpt-image-1.5`, `gpt-image-2`,\n`gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`,\n`gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`,\n`gpt-image-2.5-flare-2026-09-08`, or `chatgpt-image-latest`. Default:\n`gpt-image-1`.\n",
+                "default": "gpt-image-1"
+              }
+            ]
+          },
+          "quality": {
+            "type": "string",
+            "enum": [
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max",
+              "auto"
+            ],
+            "description": "The quality of the generated image. The GPT image models support `low`,\n`medium`, and `high`. `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`,\nincluding their `2026-09-08` snapshots, also support `xhigh` and `max`.\nDefault: `auto`.\n",
+            "default": "auto"
+          },
+          "size": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "string",
+                "enum": [
+                  "1024x1024",
+                  "1024x1536",
+                  "1536x1024",
+                  "auto"
+                ]
+              }
+            ],
+            "description": "The size of the generated images. For `gpt-image-2`, `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, and `gpt-image-2.5-flare-2026-09-08`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`.",
+            "default": "auto"
+          },
+          "output_format": {
+            "type": "string",
+            "enum": [
+              "png",
+              "webp",
+              "jpeg"
+            ],
+            "description": "The output format of the generated image. One of `png`, `webp`, or\n`jpeg`. Default: `png`.\n",
+            "default": "png"
+          },
+          "output_compression": {
+            "type": "integer",
+            "minimum": 0,
+            "maximum": 100,
+            "description": "Compression level for the output image. Default: 100.\n",
+            "default": 100
+          },
+          "moderation": {
+            "type": "string",
+            "enum": [
+              "auto",
+              "low"
+            ],
+            "description": "Moderation level for the generated image. Default: `auto`.\n",
+            "default": "auto"
+          },
+          "background": {
+            "type": "string",
+            "enum": [
+              "transparent",
+              "opaque",
+              "auto"
+            ],
+            "description": "Set the background of the generated image. One of `transparent`, `opaque`,\nor `auto`. `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`, including\ntheir `2026-09-08` snapshots, support `opaque` and `transparent`\nbackgrounds. Transparent backgrounds are available for supported GPT Image\nmodels. For `gpt-image-2` and `gpt-image-2-2026-04-21`, this support is in\npreview. When using `transparent`, set the output format to `png` or `webp`.\nDefault: `auto`.\n",
+            "default": "auto"
+          },
+          "input_fidelity": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaInputFidelity"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "input_image_mask": {
+            "type": "object",
+            "description": "Optional mask for inpainting. Contains `image_url`\n(string, optional) and `file_id` (string, optional).\n",
+            "properties": {
+              "image_url": {
+                "type": "string",
+                "description": "Base64-encoded mask image.\n"
+              },
+              "file_id": {
+                "type": "string",
+                "description": "File ID for the mask image.\n"
+              }
+            },
+            "required": [],
+            "additionalProperties": false
+          },
+          "partial_images": {
+            "type": "integer",
+            "minimum": 0,
+            "maximum": 3,
+            "description": "Number of partial images to generate in streaming mode, from 0 (default value) to 3.\n",
+            "default": 0
+          },
+          "action": {
+            "description": "Whether to generate a new image or edit an existing image. Default: `auto`.\n",
+            "$ref": "#/components/schemas/BetaImageGenActionEnum"
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "BetaImageGenActionEnum": {
+        "type": "string",
+        "enum": [
+          "generate",
+          "edit",
+          "auto"
+        ]
+      },
+      "BetaInputFidelity": {
+        "type": "string",
+        "enum": [
+          "high",
+          "low"
+        ],
+        "description": "Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`."
+      },
+      "BetaProgrammaticToolCallingParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "programmatic_tool_calling"
+            ],
+            "description": "The type of the tool. Always `programmatic_tool_calling`.",
+            "default": "programmatic_tool_calling",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "BetaCodeInterpreterTool": {
+        "type": "object",
+        "title": "Code interpreter",
+        "description": "A tool that runs Python code to help generate a response to a prompt.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "code_interpreter"
+            ],
+            "description": "The type of the code interpreter tool. Always `code_interpreter`.\n",
+            "x-stainless-const": true
+          },
+          "container": {
+            "description": "The code interpreter container. Can be a container ID or an object that\nspecifies uploaded file IDs to make available to your code, along with an\noptional `memory_limit` setting.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "description": "The container ID."
+              },
+              {
+                "$ref": "#/components/schemas/BetaAutoCodeInterpreterToolParam"
+              }
+            ]
+          },
+          "allowed_callers": {
+            "anyOf": [
+              {
+                "type": "array",
+                "minItems": 1,
+                "items": {
+                  "$ref": "#/components/schemas/BetaCallableToolAllowedCaller"
+                },
+                "description": "The tool invocation context(s)."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "container"
+        ]
+      },
+      "BetaAutoCodeInterpreterToolParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "auto"
+            ],
+            "description": "Always `auto`.",
+            "default": "auto",
+            "x-stainless-const": true
+          },
+          "file_ids": {
+            "items": {
+              "type": "string",
+              "example": "file-123"
+            },
+            "type": "array",
+            "maxItems": 50,
+            "description": "An optional list of uploaded files to make available to your code."
+          },
+          "memory_limit": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaContainerMemoryLimit",
+                "description": "The memory limit for the code interpreter container."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "network_policy": {
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/BetaContainerNetworkPolicyDisabledParam"
+              },
+              {
+                "$ref": "#/components/schemas/BetaContainerNetworkPolicyAllowlistParam"
+              }
+            ],
+            "description": "Network access policy for the container.",
+            "discriminator": {
+              "propertyName": "type"
+            }
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "CodeInterpreterToolAuto",
+        "description": "Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on."
+      },
+      "BetaMCPTool": {
+        "type": "object",
+        "title": "MCP tool",
+        "description": "Give the model access to additional tools via remote Model Context Protocol\n(MCP) servers. [Learn more about MCP](https://developers.openai.com/api/docs/guides/tools-connectors-mcp).\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp"
+            ],
+            "description": "The type of the MCP tool. Always `mcp`.",
+            "x-stainless-const": true
+          },
+          "server_label": {
+            "type": "string",
+            "description": "A label for this MCP server, used to identify it in tool calls.\n"
+          },
+          "server_url": {
+            "type": "string",
+            "format": "uri",
+            "description": "The URL for the MCP server. One of `server_url`, `connector_id`, or\n`tunnel_id` must be provided.\n"
+          },
+          "connector_id": {
+            "type": "string",
+            "enum": [
+              "connector_dropbox",
+              "connector_gmail",
+              "connector_googlecalendar",
+              "connector_googledrive",
+              "connector_microsoftteams",
+              "connector_outlookcalendar",
+              "connector_outlookemail",
+              "connector_sharepoint"
+            ],
+            "description": "Identifier for service connectors, like those available in ChatGPT. One of\n`server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more\nabout service connectors [here](https://developers.openai.com/api/docs/guides/tools-connectors-mcp#connectors).\n\nCurrently supported `connector_id` values are:\n\n- Dropbox: `connector_dropbox`\n- Gmail: `connector_gmail`\n- Google Calendar: `connector_googlecalendar`\n- Google Drive: `connector_googledrive`\n- Microsoft Teams: `connector_microsoftteams`\n- Outlook Calendar: `connector_outlookcalendar`\n- Outlook Email: `connector_outlookemail`\n- SharePoint: `connector_sharepoint`\n"
+          },
+          "tunnel_id": {
+            "type": "string",
+            "pattern": "^tunnel_[a-z0-9]{32}$",
+            "description": "The Secure MCP Tunnel ID to use instead of a direct server URL. One of\n`server_url`, `connector_id`, or `tunnel_id` must be provided.\n"
+          },
+          "authorization": {
+            "type": "string",
+            "description": "An OAuth access token that can be used with a remote MCP server, either\nwith a custom MCP server URL or a service connector. Your application\nmust handle the OAuth authorization flow and provide the token here.\n"
+          },
+          "server_description": {
+            "type": "string",
+            "description": "Optional description of the MCP server, used to provide more context.\n"
+          },
+          "headers": {
+            "anyOf": [
+              {
+                "type": "object",
+                "additionalProperties": {
+                  "type": "string"
+                },
+                "description": "Optional HTTP headers to send to the MCP server. Use for authentication\nor other purposes.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "allowed_tools": {
+            "anyOf": [
+              {
+                "description": "List of allowed tool names or a filter object.\n",
+                "oneOf": [
+                  {
+                    "type": "array",
+                    "title": "MCP allowed tools",
+                    "description": "A string array of allowed tool names",
+                    "items": {
+                      "type": "string"
+                    }
+                  },
+                  {
+                    "$ref": "#/components/schemas/BetaMCPToolFilter"
+                  }
+                ]
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "allowed_callers": {
+            "anyOf": [
+              {
+                "type": "array",
+                "minItems": 1,
+                "items": {
+                  "$ref": "#/components/schemas/BetaCallableToolAllowedCaller"
+                },
+                "description": "The tool invocation context(s)."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "require_approval": {
+            "anyOf": [
+              {
+                "description": "Specify which of the MCP server's tools require approval.",
+                "oneOf": [
+                  {
+                    "type": "object",
+                    "title": "MCP tool approval filter",
+                    "description": "Specify which of the MCP server's tools require approval. Can be\n`always`, `never`, or a filter object associated with tools\nthat require approval.\n",
+                    "properties": {
+                      "always": {
+                        "$ref": "#/components/schemas/BetaMCPToolFilter"
+                      },
+                      "never": {
+                        "$ref": "#/components/schemas/BetaMCPToolFilter"
+                      }
+                    },
+                    "additionalProperties": false
+                  },
+                  {
+                    "type": "string",
+                    "title": "MCP tool approval setting",
+                    "description": "Specify a single approval policy for all tools. One of `always` or\n`never`. When set to `always`, all tools will require approval. When\nset to `never`, all tools will not require approval.\n",
+                    "enum": [
+                      "always",
+                      "never"
+                    ]
+                  }
+                ],
+                "default": "always"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "defer_loading": {
+            "type": "boolean",
+            "description": "Whether this MCP tool is deferred and discovered via tool search.\n"
+          }
+        },
+        "required": [
+          "type",
+          "server_label"
+        ]
+      },
+      "BetaMCPToolFilter": {
+        "type": "object",
+        "title": "MCP tool filter",
+        "description": "A filter object to specify which tools are allowed.\n",
+        "properties": {
+          "tool_names": {
+            "type": "array",
+            "title": "MCP allowed tools",
+            "items": {
+              "type": "string"
+            },
+            "description": "List of allowed tool names."
+          },
+          "read_only": {
+            "type": "boolean",
+            "description": "Indicates whether or not a tool modifies data or is read-only. If an\nMCP server is [annotated with `readOnlyHint`](https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations-readonlyhint),\nit will match this filter.\n"
+          }
+        },
+        "required": [],
+        "additionalProperties": false
+      },
+      "BetaWebSearchTool": {
+        "type": "object",
+        "title": "Web search",
+        "description": "Search the Internet for sources related to the prompt. Learn more about the\n[web search tool](https://developers.openai.com/api/docs/guides/tools-web-search).\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "web_search",
+              "web_search_2025_08_26"
+            ],
+            "description": "The type of the web search tool. One of `web_search` or `web_search_2025_08_26`.",
+            "default": "web_search"
+          },
+          "external_web_access": {
+            "type": "boolean",
+            "default": true,
+            "description": "Allow live internet access for web search. Defaults to true when omitted. When false, the web search tool runs in offline/cache-only mode and will not fetch new external content."
+          },
+          "filters": {
+            "anyOf": [
+              {
+                "type": "object",
+                "description": "Filters for the search.\n",
+                "properties": {
+                  "allowed_domains": {
+                    "anyOf": [
+                      {
+                        "type": "array",
+                        "title": "Allowed domains for the search.",
+                        "description": "Allowed domains for the search. If not provided, all domains are allowed.\nSubdomains of the provided domains are allowed as well.\n\nExample: `[\"pubmed.ncbi.nlm.nih.gov\"]`\n",
+                        "items": {
+                          "type": "string",
+                          "description": "Allowed domain for the search."
+                        },
+                        "default": []
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ]
+                  }
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "user_location": {
+            "$ref": "#/components/schemas/BetaWebSearchApproximateLocation"
+          },
+          "search_context_size": {
+            "type": "string",
+            "enum": [
+              "low",
+              "medium",
+              "high"
+            ],
+            "default": "medium",
+            "description": "High level guidance for the amount of context window space to use for the search. One of `low`, `medium`, or `high`. `medium` is the default."
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "BetaWebSearchApproximateLocation": {
+        "anyOf": [
+          {
+            "type": "object",
+            "title": "Web search approximate location",
+            "description": "The approximate location of the user.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "approximate"
+                ],
+                "description": "The type of location approximation. Always `approximate`.",
+                "default": "approximate",
+                "x-stainless-const": true
+              },
+              "country": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`."
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "region": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "Free text input for the region of the user, e.g. `California`."
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "city": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "Free text input for the city of the user, e.g. `San Francisco`."
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "timezone": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`."
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              }
+            }
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "BetaComputerUsePreviewTool": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "computer_use_preview"
+            ],
+            "description": "The type of the computer use tool. Always `computer_use_preview`.",
+            "default": "computer_use_preview",
+            "x-stainless-const": true
+          },
+          "environment": {
+            "$ref": "#/components/schemas/BetaComputerEnvironment",
+            "description": "The type of computer environment to control."
+          },
+          "display_width": {
+            "type": "integer",
+            "description": "The width of the computer display."
+          },
+          "display_height": {
+            "type": "integer",
+            "description": "The height of the computer display."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "environment",
+          "display_width",
+          "display_height"
+        ],
+        "title": "Computer use preview",
+        "description": "A tool that controls a virtual computer. Learn more about the [computer tool](https://developers.openai.com/api/docs/guides/tools-computer-use)."
+      },
+      "BetaComputerEnvironment": {
+        "type": "string",
+        "enum": [
+          "windows",
+          "mac",
+          "linux",
+          "ubuntu",
+          "browser"
+        ]
+      },
+      "BetaComputerTool": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "computer"
+            ],
+            "description": "The type of the computer tool. Always `computer`.",
+            "default": "computer",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Computer",
+        "description": "A tool that controls a virtual computer. Learn more about the [computer tool](https://developers.openai.com/api/docs/guides/tools-computer-use)."
+      },
+      "BetaFileSearchTool": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "file_search"
+            ],
+            "description": "The type of the file search tool. Always `file_search`.",
+            "default": "file_search",
+            "x-stainless-const": true
+          },
+          "vector_store_ids": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array",
+            "description": "The IDs of the vector stores to search."
+          },
+          "max_num_results": {
+            "type": "integer",
+            "description": "The maximum number of results to return. This number should be between 1 and 50 inclusive."
+          },
+          "ranking_options": {
+            "$ref": "#/components/schemas/BetaRankingOptions",
+            "description": "Ranking options for search."
+          },
+          "filters": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaFilters",
+                "description": "A filter to apply."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "vector_store_ids"
+        ],
+        "title": "File search",
+        "description": "A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](https://developers.openai.com/api/docs/guides/tools-file-search)."
+      },
+      "BetaFilters": {
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/BetaComparisonFilter"
+          },
+          {
+            "$ref": "#/components/schemas/BetaCompoundFilter"
+          }
+        ]
+      },
+      "BetaCompoundFilter": {
+        "$recursiveAnchor": true,
+        "type": "object",
+        "additionalProperties": false,
+        "title": "Compound Filter",
+        "description": "Combine multiple filters using `and` or `or`.",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "Type of operation: `and` or `or`.",
+            "enum": [
+              "and",
+              "or"
+            ]
+          },
+          "filters": {
+            "type": "array",
+            "description": "Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`.",
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/BetaComparisonFilter"
+                },
+                {
+                  "$recursiveRef": "#"
+                }
+              ],
+              "discriminator": {
+                "propertyName": "type"
+              }
+            }
+          }
+        },
+        "required": [
+          "type",
+          "filters"
+        ],
+        "x-oaiMeta": {
+          "name": "CompoundFilter"
+        }
+      },
+      "BetaComparisonFilter": {
+        "type": "object",
+        "additionalProperties": false,
+        "title": "Comparison Filter",
+        "description": "A filter used to compare a specified attribute key to a given value using a defined comparison operation.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "default": "eq",
+            "enum": [
+              "eq",
+              "ne",
+              "gt",
+              "gte",
+              "lt",
+              "lte",
+              "in",
+              "nin"
+            ],
+            "description": "Specifies the comparison operator: `eq`, `ne`, `gt`, `gte`, `lt`, `lte`, `in`, `nin`.\n- `eq`: equals\n- `ne`: not equal\n- `gt`: greater than\n- `gte`: greater than or equal\n- `lt`: less than\n- `lte`: less than or equal\n- `in`: in\n- `nin`: not in\n"
+          },
+          "key": {
+            "type": "string",
+            "description": "The key to compare against the value."
+          },
+          "value": {
+            "oneOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "number"
+              },
+              {
+                "type": "boolean"
+              },
+              {
+                "type": "array",
+                "items": {
+                  "oneOf": [
+                    {
+                      "type": "string"
+                    },
+                    {
+                      "type": "number"
+                    }
+                  ]
+                }
+              }
+            ],
+            "description": "The value to compare against the attribute key; supports string, number, or boolean types."
+          }
+        },
+        "required": [
+          "type",
+          "key",
+          "value"
+        ],
+        "x-oaiMeta": {
+          "name": "ComparisonFilter"
+        }
+      },
+      "BetaRankingOptions": {
+        "properties": {
+          "ranker": {
+            "$ref": "#/components/schemas/BetaRankerVersionType",
+            "description": "The ranker to use for the file search."
+          },
+          "score_threshold": {
+            "type": "number",
+            "description": "The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results."
+          },
+          "hybrid_search": {
+            "$ref": "#/components/schemas/BetaHybridSearchOptions",
+            "description": "Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled."
+          }
+        },
+        "type": "object",
+        "required": []
+      },
+      "BetaHybridSearchOptions": {
+        "properties": {
+          "embedding_weight": {
+            "type": "number",
+            "description": "The weight of the embedding in the reciprocal ranking fusion."
+          },
+          "text_weight": {
+            "type": "number",
+            "description": "The weight of the text in the reciprocal ranking fusion."
+          }
+        },
+        "type": "object",
+        "required": [
+          "embedding_weight",
+          "text_weight"
+        ]
+      },
+      "BetaRankerVersionType": {
+        "type": "string",
+        "enum": [
+          "auto",
+          "default-2024-11-15"
+        ]
+      },
+      "BetaFunctionTool": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "function"
+            ],
+            "description": "The type of the function tool. Always `function`.",
+            "default": "function",
+            "x-stainless-const": true
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the function to call."
+          },
+          "async": {
+            "type": "boolean"
+          },
+          "description": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "A description of the function. Used by the model to determine whether or not to call the function."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "parameters": {
+            "anyOf": [
+              {
+                "additionalProperties": {},
+                "type": "object",
+                "description": "A JSON schema object describing the parameters of the function.",
+                "x-oaiTypeLabel": "map"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "output_schema": {
+            "anyOf": [
+              {
+                "additionalProperties": {},
+                "type": "object",
+                "description": "A JSON schema object describing the JSON value encoded in string outputs for this function.",
+                "x-oaiTypeLabel": "map"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "strict": {
+            "anyOf": [
+              {
+                "type": "boolean",
+                "description": "Whether strict parameter validation is enforced for this function tool."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "defer_loading": {
+            "type": "boolean",
+            "description": "Whether this function is deferred and loaded via tool search."
+          },
+          "allowed_callers": {
+            "anyOf": [
+              {
+                "items": {
+                  "$ref": "#/components/schemas/BetaCallableToolAllowedCaller"
+                },
+                "type": "array",
+                "description": "The tool invocation context(s)."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "name",
+          "strict",
+          "parameters"
+        ],
+        "title": "Function",
+        "description": "Defines a function in your own code the model can choose to call. Learn more about [function calling](https://developers.openai.com/api/docs/guides/function-calling)."
+      },
+      "BetaInputItem": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/BetaEasyInputMessage"
+          },
+          {
+            "type": "object",
+            "title": "Item",
+            "description": "An item representing part of the context for the response to be\ngenerated by the model. Can contain text, images, and audio inputs,\nas well as previous assistant responses and tool call outputs.\n",
+            "$ref": "#/components/schemas/BetaItem"
+          },
+          {
+            "$ref": "#/components/schemas/BetaCompactionTriggerItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaItemReferenceParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaProgramItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaProgramOutputItemParam"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "BetaProgramOutputItemParam": {
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Beta_AgentTagParam",
+                "description": "The agent that produced this item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of this program output item.",
+            "example": "cmo_123"
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "program_output"
+            ],
+            "description": "The item type. Always `program_output`.",
+            "default": "program_output",
+            "x-stainless-const": true
+          },
+          "call_id": {
+            "type": "string",
+            "maxLength": 64,
+            "minLength": 1,
+            "description": "The call ID of the program item."
+          },
+          "result": {
+            "type": "string",
+            "maxLength": 10485760,
+            "description": "The result produced by the program item."
+          },
+          "status": {
+            "$ref": "#/components/schemas/BetaProgramOutputItemStatus",
+            "description": "The terminal status of the program output."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "type",
+          "call_id",
+          "result",
+          "status"
+        ]
+      },
+      "BetaProgramOutputItemStatus": {
+        "type": "string",
+        "enum": [
+          "completed",
+          "incomplete"
+        ]
+      },
+      "Beta_AgentTagParam": {
+        "properties": {
+          "agent_name": {
+            "type": "string",
+            "description": "The canonical name of the agent that produced this item."
+          }
+        },
+        "type": "object",
+        "required": [
+          "agent_name"
+        ],
+        "description": "The agent that produced this item.",
+        "x-oai-beta": "responses_multi_agent=v1"
+      },
+      "BetaProgramItemParam": {
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Beta_AgentTagParam",
+                "description": "The agent that produced this item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of this program item.",
+            "example": "cm_123"
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "program"
+            ],
+            "description": "The item type. Always `program`.",
+            "default": "program",
+            "x-stainless-const": true
+          },
+          "call_id": {
+            "type": "string",
+            "maxLength": 64,
+            "minLength": 1,
+            "description": "The stable call ID of the program item."
+          },
+          "code": {
+            "type": "string",
+            "maxLength": 10485760,
+            "description": "The JavaScript source executed by programmatic tool calling."
+          },
+          "fingerprint": {
+            "type": "string",
+            "maxLength": 10485760,
+            "description": "Opaque program replay fingerprint that must be round-tripped."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "type",
+          "call_id",
+          "code",
+          "fingerprint"
+        ]
+      },
+      "BetaItemReferenceParam": {
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Beta_AgentTagParam",
+                "description": "The agent that produced this item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "anyOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "item_reference"
+                ],
+                "description": "The type of item to reference. Always `item_reference`.",
+                "default": "item_reference",
+                "x-stainless-const": true
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "id": {
+            "type": "string",
+            "description": "The ID of the item to reference."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id"
+        ],
+        "title": "Item reference",
+        "description": "An internal identifier for an item to reference."
+      },
+      "BetaCompactionTriggerItemParam": {
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Beta_AgentTagParam",
+                "description": "The agent that produced this item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of this compaction trigger.",
+                "example": "msg_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "compaction_trigger"
+            ],
+            "description": "The type of the item. Always `compaction_trigger`.",
+            "default": "compaction_trigger",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Compaction trigger",
+        "description": "Compacts the current context. Must be the final input item."
+      },
+      "BetaItem": {
+        "type": "object",
+        "description": "Content item used to generate a response.\n",
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/BetaInputMessage"
+          },
+          {
+            "$ref": "#/components/schemas/BetaOutputMessage"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFileSearchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaComputerToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaComputerCallOutputItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaWebSearchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFunctionToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFunctionCallOutputItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaAgentMessageItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMultiAgentCallItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMultiAgentCallOutputItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaToolSearchCallItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaToolSearchOutputItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaAdditionalToolsItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseConfigurationUpdateItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaReasoningItem"
+          },
+          {
+            "$ref": "#/components/schemas/BetaCompactionSummaryItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaImageGenToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaCodeInterpreterToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaLocalShellToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaLocalShellToolCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFunctionShellCallItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFunctionShellCallOutputItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaApplyPatchToolCallItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaApplyPatchToolCallOutputItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMCPListTools"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMCPApprovalRequest"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMCPApprovalResponse"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMCPToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaCustomToolCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/BetaCustomToolCall"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "BetaCustomToolCall": {
+        "type": "object",
+        "title": "Custom tool call",
+        "description": "A call to a custom tool created by the model.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "custom_tool_call"
+            ],
+            "x-stainless-const": true,
+            "description": "The type of the custom tool call. Always `custom_tool_call`.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the custom tool call in the OpenAI platform.\n"
+          },
+          "call_id": {
+            "type": "string",
+            "description": "An identifier used to map this custom tool call to a tool call output.\n"
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaToolCallCaller"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "namespace": {
+            "type": "string",
+            "description": "The namespace of the custom tool being called.\n"
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the custom tool being called.\n"
+          },
+          "input": {
+            "type": "string",
+            "description": "The input for the custom tool call generated by the model.\n"
+          },
+          "async": {
+            "type": "boolean",
+            "description": "Whether the custom tool call runs asynchronously.\n"
+          }
+        },
+        "required": [
+          "type",
+          "call_id",
+          "name",
+          "input"
+        ]
+      },
+      "BetaToolCallCaller": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/BetaDirectToolCallCaller"
+          },
+          {
+            "$ref": "#/components/schemas/BetaProgramToolCallCaller"
+          }
+        ],
+        "description": "The execution context that produced this tool call.",
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "BetaProgramToolCallCaller": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "program"
+            ],
+            "default": "program",
+            "x-stainless-const": true
+          },
+          "caller_id": {
+            "type": "string",
+            "description": "The call ID of the program item that produced this tool call."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "caller_id"
+        ]
+      },
+      "BetaDirectToolCallCaller": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "direct"
+            ],
+            "default": "direct",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "BetaAgentTag": {
+        "properties": {
+          "agent_name": {
+            "type": "string",
+            "description": "The canonical name of the agent that produced this item."
+          }
+        },
+        "type": "object",
+        "required": [
+          "agent_name"
+        ],
+        "x-oai-beta": "responses_multi_agent=v1"
+      },
+      "BetaCustomToolCallOutput": {
+        "type": "object",
+        "title": "Custom tool call output",
+        "description": "The output of a custom tool call from your code, being sent back to the model.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "custom_tool_call_output"
+            ],
+            "x-stainless-const": true,
+            "description": "The type of the custom tool call output. Always `custom_tool_call_output`.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the custom tool call output in the OpenAI platform.\n"
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The call ID, used to map this custom tool call output to a custom tool call.\n"
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaToolCallCallerParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "output": {
+            "description": "The output from the custom tool call generated by your code.\nCan be a string or an list of output content.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "description": "A string of the output of the custom tool call.\n",
+                "title": "string output"
+              },
+              {
+                "type": "array",
+                "items": {
+                  "$ref": "#/components/schemas/BetaFunctionAndCustomToolCallOutput"
+                },
+                "title": "output content list",
+                "description": "Text, image, or file output of the custom tool call.\n"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "call_id",
+          "output"
+        ]
+      },
+      "BetaFunctionAndCustomToolCallOutput": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/BetaInputTextContent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaInputImageContent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaInputFileContent"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "BetaInputFileContent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_file"
+            ],
+            "description": "The type of the input item. Always `input_file`.",
+            "default": "input_file",
+            "x-stainless-const": true
+          },
+          "file_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the file to be sent to the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "filename": {
+            "type": "string",
+            "description": "The name of the file to be sent to the model."
+          },
+          "file_data": {
+            "type": "string",
+            "description": "The content of the file to be sent to the model.\n"
+          },
+          "prompt_cache_breakpoint": {
+            "$ref": "#/components/schemas/BetaPromptCacheBreakpointConfig"
+          },
+          "file_url": {
+            "type": "string",
+            "format": "uri",
+            "description": "The URL of the file to be sent to the model."
+          },
+          "detail": {
+            "$ref": "#/components/schemas/BetaFileInputDetail",
+            "description": "The detail level of the file to be sent to the model. Use `auto` to let the system select the detail level; for GPT-5.6 and later models, `auto` uses high-quality rendering, which may increase input token usage. Use `low` for lower-cost rendering, or `high` to render the file at higher quality. Defaults to `auto`."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Input file",
+        "description": "A file input to the model."
+      },
+      "BetaFileInputDetail": {
+        "type": "string",
+        "enum": [
+          "auto",
+          "low",
+          "high"
+        ]
+      },
+      "BetaPromptCacheBreakpointConfig": {
+        "properties": {
+          "mode": {
+            "type": "string",
+            "enum": [
+              "explicit"
+            ],
+            "description": "The breakpoint mode. Always `explicit`.",
+            "default": "explicit",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "mode"
+        ],
+        "title": "Prompt cache breakpoint",
+        "description": "Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block."
+      },
+      "BetaInputImageContent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_image"
+            ],
+            "description": "The type of the input item. Always `input_image`.",
+            "default": "input_image",
+            "x-stainless-const": true
+          },
+          "image_url": {
+            "anyOf": [
+              {
+                "type": "string",
+                "format": "uri",
+                "description": "The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "file_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the file to be sent to the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "detail": {
+            "$ref": "#/components/schemas/BetaImageDetail",
+            "description": "The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`."
+          },
+          "prompt_cache_breakpoint": {
+            "$ref": "#/components/schemas/BetaPromptCacheBreakpointConfig"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "detail"
+        ],
+        "title": "Input image",
+        "description": "An image input to the model. Learn about [image inputs](https://developers.openai.com/api/docs/guides/images-vision)."
+      },
+      "BetaImageDetail": {
+        "type": "string",
+        "enum": [
+          "low",
+          "high",
+          "auto",
+          "original"
+        ]
+      },
+      "BetaInputTextContent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_text"
+            ],
+            "description": "The type of the input item. Always `input_text`.",
+            "default": "input_text",
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string",
+            "description": "The text input to the model."
+          },
+          "prompt_cache_breakpoint": {
+            "$ref": "#/components/schemas/BetaPromptCacheBreakpointConfig"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "text"
+        ],
+        "title": "Input text",
+        "description": "A text input to the model."
+      },
+      "BetaToolCallCallerParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/BetaDirectToolCallCallerParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaProgramToolCallCallerParam"
+          }
+        ],
+        "description": "The execution context that produced this tool call.",
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "BetaProgramToolCallCallerParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "program"
+            ],
+            "description": "The caller type. Always `program`.",
+            "default": "program",
+            "x-stainless-const": true
+          },
+          "caller_id": {
+            "type": "string",
+            "maxLength": 64,
+            "minLength": 1,
+            "description": "The call ID of the program item that produced this tool call."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "caller_id"
+        ]
+      },
+      "BetaDirectToolCallCallerParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "direct"
+            ],
+            "description": "The caller type. Always `direct`.",
+            "default": "direct",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "BetaMCPToolCall": {
+        "type": "object",
+        "title": "MCP tool call",
+        "description": "An invocation of a tool on an MCP server.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_call"
+            ],
+            "description": "The type of the item. Always `mcp_call`.\n",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the tool call.\n"
+          },
+          "server_label": {
+            "type": "string",
+            "description": "The label of the MCP server running the tool.\n"
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the tool that was run.\n"
+          },
+          "arguments": {
+            "type": "string",
+            "description": "A JSON string of the arguments passed to the tool.\n"
+          },
+          "output": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The output from the tool call.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "error": {
+            "description": "The error from the tool call, if any.",
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaMCPToolCallError"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "$ref": "#/components/schemas/BetaMCPToolCallStatus",
+            "description": "The status of the tool call. One of `in_progress`, `completed`, `incomplete`, `calling`, or `failed`.\n"
+          },
+          "approval_request_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Unique identifier for the MCP tool call approval request.\nInclude this value in a subsequent `mcp_approval_response` input to approve or reject the corresponding tool call.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "server_label",
+          "name",
+          "arguments"
+        ]
+      },
+      "BetaMCPToolCallStatus": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed",
+          "incomplete",
+          "calling",
+          "failed"
+        ]
+      },
+      "BetaMCPToolCallError": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/BetaMCPProtocolError"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMCPToolExecutionError"
+          },
+          {
+            "$ref": "#/components/schemas/BetaHTTPError"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "BetaHTTPError": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "http_error"
+            ],
+            "default": "http_error",
+            "x-stainless-const": true
+          },
+          "code": {
+            "type": "integer"
+          },
+          "message": {
+            "type": "string"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "code",
+          "message"
+        ]
+      },
+      "BetaMCPToolExecutionError": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_tool_execution_error"
+            ],
+            "default": "mcp_tool_execution_error",
+            "x-stainless-const": true
+          },
+          "content": {}
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "content"
+        ]
+      },
+      "BetaMCPProtocolError": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_protocol_error"
+            ],
+            "default": "mcp_protocol_error",
+            "x-stainless-const": true
+          },
+          "code": {
+            "type": "integer"
+          },
+          "message": {
+            "type": "string"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "code",
+          "message"
+        ]
+      },
+      "BetaMCPApprovalResponse": {
+        "type": "object",
+        "title": "MCP approval response",
+        "description": "A response to an MCP approval request.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_approval_response"
+            ],
+            "description": "The type of the item. Always `mcp_approval_response`.\n",
+            "x-stainless-const": true
+          },
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the approval response\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "approval_request_id": {
+            "type": "string",
+            "description": "The ID of the approval request being answered.\n"
+          },
+          "approve": {
+            "type": "boolean",
+            "description": "Whether the request was approved.\n"
+          },
+          "reason": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Optional reason for the decision.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "request_id",
+          "approve",
+          "approval_request_id"
+        ]
+      },
+      "BetaMCPApprovalRequest": {
+        "type": "object",
+        "title": "MCP approval request",
+        "description": "A request for human approval of a tool invocation.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_approval_request"
+            ],
+            "description": "The type of the item. Always `mcp_approval_request`.\n",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the approval request.\n"
+          },
+          "server_label": {
+            "type": "string",
+            "description": "The label of the MCP server making the request.\n"
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the tool to run.\n"
+          },
+          "arguments": {
+            "type": "string",
+            "description": "A JSON string of arguments for the tool.\n"
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "server_label",
+          "name",
+          "arguments"
+        ]
+      },
+      "BetaMCPListTools": {
+        "type": "object",
+        "title": "MCP list tools",
+        "description": "A list of tools available on an MCP server.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_list_tools"
+            ],
+            "description": "The type of the item. Always `mcp_list_tools`.\n",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the list.\n"
+          },
+          "server_label": {
+            "type": "string",
+            "description": "The label of the MCP server.\n"
+          },
+          "tools": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/BetaMCPListToolsTool"
+            },
+            "description": "The tools available on the server.\n"
+          },
+          "error": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Error message if the server could not list tools.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "server_label",
+          "tools"
+        ]
+      },
+      "BetaMCPListToolsTool": {
+        "type": "object",
+        "title": "MCP list tools tool",
+        "description": "A tool available on an MCP server.\n",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The name of the tool.\n"
+          },
+          "description": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The description of the tool.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "input_schema": {
+            "type": "object",
+            "description": "The JSON schema describing the tool's input.\n"
+          },
+          "annotations": {
+            "anyOf": [
+              {
+                "type": "object",
+                "description": "Additional annotations about the tool.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "name",
+          "input_schema"
+        ]
+      },
+      "BetaApplyPatchToolCallOutputItemParam": {
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Beta_AgentTagParam",
+                "description": "The agent that produced this item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "apply_patch_call_output"
+            ],
+            "description": "The type of the item. Always `apply_patch_call_output`.",
+            "default": "apply_patch_call_output",
+            "x-stainless-const": true
+          },
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the apply patch tool call output. Populated when this item is returned via API.",
+                "example": "apco_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "call_id": {
+            "type": "string",
+            "maxLength": 64,
+            "minLength": 1,
+            "description": "The unique ID of the apply patch tool call generated by the model."
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaToolCallCallerParam",
+                "description": "The execution context that produced this tool call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "$ref": "#/components/schemas/BetaApplyPatchCallOutputStatusParam",
+            "description": "The status of the apply patch tool call output. One of `completed` or `failed`."
+          },
+          "output": {
+            "anyOf": [
+              {
+                "type": "string",
+                "maxLength": 10485760,
+                "description": "Optional human-readable log text from the apply patch tool (e.g., patch results or errors)."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "call_id",
+          "status"
+        ],
+        "title": "Apply patch tool call output",
+        "description": "The streamed output emitted by an apply patch tool call."
+      },
+      "BetaApplyPatchCallOutputStatusParam": {
+        "type": "string",
+        "enum": [
+          "completed",
+          "failed"
+        ],
+        "title": "Apply patch call output status",
+        "description": "Outcome values reported for apply_patch tool call outputs."
+      },
+      "BetaApplyPatchToolCallItemParam": {
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Beta_AgentTagParam",
+                "description": "The agent that produced this item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "apply_patch_call"
+            ],
+            "description": "The type of the item. Always `apply_patch_call`.",
+            "default": "apply_patch_call",
+            "x-stainless-const": true
+          },
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the apply patch tool call. Populated when this item is returned via API.",
+                "example": "apc_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "call_id": {
+            "type": "string",
+            "maxLength": 64,
+            "minLength": 1,
+            "description": "The unique ID of the apply patch tool call generated by the model."
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaToolCallCallerParam",
+                "description": "The execution context that produced this tool call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "$ref": "#/components/schemas/BetaApplyPatchCallStatusParam",
+            "description": "The status of the apply patch tool call. One of `in_progress` or `completed`."
+          },
+          "operation": {
+            "$ref": "#/components/schemas/BetaApplyPatchOperationParam",
+            "description": "The specific create, delete, or update instruction for the apply_patch tool call."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "call_id",
+          "status",
+          "operation"
+        ],
+        "title": "Apply patch tool call",
+        "description": "A tool call representing a request to create, delete, or update files using diff patches."
+      },
+      "BetaApplyPatchOperationParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/BetaApplyPatchCreateFileOperationParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaApplyPatchDeleteFileOperationParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaApplyPatchUpdateFileOperationParam"
+          }
+        ],
+        "title": "Apply patch operation",
+        "description": "One of the create_file, delete_file, or update_file operations supplied to the apply_patch tool.",
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "BetaApplyPatchUpdateFileOperationParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "update_file"
+            ],
+            "description": "The operation type. Always `update_file`.",
+            "default": "update_file",
+            "x-stainless-const": true
+          },
+          "path": {
+            "type": "string",
+            "minLength": 1,
+            "description": "Path of the file to update relative to the workspace root."
+          },
+          "diff": {
+            "type": "string",
+            "maxLength": 10485760,
+            "description": "Unified diff content to apply to the existing file."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "path",
+          "diff"
+        ],
+        "title": "Apply patch update file operation",
+        "description": "Instruction for updating an existing file via the apply_patch tool."
+      },
+      "BetaApplyPatchDeleteFileOperationParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "delete_file"
+            ],
+            "description": "The operation type. Always `delete_file`.",
+            "default": "delete_file",
+            "x-stainless-const": true
+          },
+          "path": {
+            "type": "string",
+            "minLength": 1,
+            "description": "Path of the file to delete relative to the workspace root."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "path"
+        ],
+        "title": "Apply patch delete file operation",
+        "description": "Instruction for deleting an existing file via the apply_patch tool."
+      },
+      "BetaApplyPatchCreateFileOperationParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "create_file"
+            ],
+            "description": "The operation type. Always `create_file`.",
+            "default": "create_file",
+            "x-stainless-const": true
+          },
+          "path": {
+            "type": "string",
+            "minLength": 1,
+            "description": "Path of the file to create relative to the workspace root."
+          },
+          "diff": {
+            "type": "string",
+            "maxLength": 10485760,
+            "description": "Unified diff content to apply when creating the file."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "path",
+          "diff"
+        ],
+        "title": "Apply patch create file operation",
+        "description": "Instruction for creating a new file via the apply_patch tool."
+      },
+      "BetaApplyPatchCallStatusParam": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed"
+        ],
+        "title": "Apply patch call status",
+        "description": "Status values reported for apply_patch tool calls."
+      },
+      "BetaFunctionShellCallOutputItemParam": {
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Beta_AgentTagParam",
+                "description": "The agent that produced this item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the shell tool call output. Populated when this item is returned via API.",
+                "example": "sho_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "call_id": {
+            "type": "string",
+            "maxLength": 64,
+            "minLength": 1,
+            "description": "The unique ID of the shell tool call generated by the model."
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaToolCallCallerParam",
+                "description": "The execution context that produced this tool call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "shell_call_output"
+            ],
+            "description": "The type of the item. Always `shell_call_output`.",
+            "default": "shell_call_output",
+            "x-stainless-const": true
+          },
+          "output": {
+            "items": {
+              "$ref": "#/components/schemas/BetaFunctionShellCallOutputContentParam"
+            },
+            "type": "array",
+            "description": "Captured chunks of stdout and stderr output, along with their associated outcomes."
+          },
+          "status": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaFunctionShellCallItemStatus",
+                "description": "The status of the shell call output."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "max_output_length": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "The maximum number of UTF-8 characters captured for this shell call's combined output."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "call_id",
+          "type",
+          "output"
+        ],
+        "title": "Shell tool call output",
+        "description": "The streamed output items emitted by a shell tool call."
+      },
+      "BetaFunctionShellCallItemStatus": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed",
+          "incomplete"
+        ],
+        "title": "Shell call status",
+        "description": "Status values reported for shell tool calls."
+      },
+      "BetaFunctionShellCallOutputContentParam": {
+        "properties": {
+          "stdout": {
+            "type": "string",
+            "maxLength": 10485760,
+            "description": "Captured stdout output for the shell call."
+          },
+          "stderr": {
+            "type": "string",
+            "maxLength": 10485760,
+            "description": "Captured stderr output for the shell call."
+          },
+          "outcome": {
+            "$ref": "#/components/schemas/BetaFunctionShellCallOutputOutcomeParam",
+            "description": "The exit or timeout outcome associated with this shell call."
+          }
+        },
+        "type": "object",
+        "required": [
+          "stdout",
+          "stderr",
+          "outcome"
+        ],
+        "title": "Shell output content",
+        "description": "Captured stdout and stderr for a portion of a shell tool call output."
+      },
+      "BetaFunctionShellCallOutputOutcomeParam": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/BetaFunctionShellCallOutputTimeoutOutcomeParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFunctionShellCallOutputExitOutcomeParam"
+          }
+        ],
+        "title": "Shell call outcome",
+        "description": "The exit or timeout outcome associated with this shell call.",
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "BetaFunctionShellCallOutputExitOutcomeParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "exit"
+            ],
+            "description": "The outcome type. Always `exit`.",
+            "default": "exit",
+            "x-stainless-const": true
+          },
+          "exit_code": {
+            "type": "integer",
+            "description": "The exit code returned by the shell process."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "exit_code"
+        ],
+        "title": "Shell call exit outcome",
+        "description": "Indicates that the shell commands finished and returned an exit code."
+      },
+      "BetaFunctionShellCallOutputTimeoutOutcomeParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "timeout"
+            ],
+            "description": "The outcome type. Always `timeout`.",
+            "default": "timeout",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Shell call timeout outcome",
+        "description": "Indicates that the shell call exceeded its configured time limit."
+      },
+      "BetaFunctionShellCallItemParam": {
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Beta_AgentTagParam",
+                "description": "The agent that produced this item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the shell tool call. Populated when this item is returned via API.",
+                "example": "sh_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "call_id": {
+            "type": "string",
+            "maxLength": 64,
+            "minLength": 1,
+            "description": "The unique ID of the shell tool call generated by the model."
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaToolCallCallerParam",
+                "description": "The execution context that produced this tool call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "shell_call"
+            ],
+            "description": "The type of the item. Always `shell_call`.",
+            "default": "shell_call",
+            "x-stainless-const": true
+          },
+          "action": {
+            "$ref": "#/components/schemas/BetaFunctionShellActionParam",
+            "description": "The shell commands and limits that describe how to run the tool call."
+          },
+          "status": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaFunctionShellCallItemStatus",
+                "description": "The status of the shell call. One of `in_progress`, `completed`, or `incomplete`."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "environment": {
+            "anyOf": [
+              {
+                "oneOf": [
+                  {
+                    "$ref": "#/components/schemas/BetaLocalEnvironmentParam"
+                  },
+                  {
+                    "$ref": "#/components/schemas/BetaContainerReferenceParam"
+                  }
+                ],
+                "description": "The environment to execute the shell commands in.",
+                "discriminator": {
+                  "propertyName": "type"
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "call_id",
+          "type",
+          "action"
+        ],
+        "title": "Shell tool call",
+        "description": "A tool representing a request to execute one or more shell commands."
+      },
+      "BetaFunctionShellActionParam": {
+        "properties": {
+          "commands": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array",
+            "description": "Ordered shell commands for the execution environment to run."
+          },
+          "timeout_ms": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "Maximum wall-clock time in milliseconds to allow the shell commands to run."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "max_output_length": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "Maximum number of UTF-8 characters to capture from combined stdout and stderr output."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "commands"
+        ],
+        "title": "Shell action",
+        "description": "Commands and limits describing how to run the shell tool call."
+      },
+      "BetaLocalShellToolCallOutput": {
+        "type": "object",
+        "title": "Local shell call output",
+        "description": "The output of a local shell tool call.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "local_shell_call_output"
+            ],
+            "description": "The type of the local shell tool call output. Always `local_shell_call_output`.\n",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the local shell tool call generated by the model.\n"
+          },
+          "output": {
+            "type": "string",
+            "description": "A JSON string of the output of the local shell tool call.\n"
+          },
+          "status": {
+            "anyOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "in_progress",
+                  "completed",
+                  "incomplete"
+                ],
+                "description": "The status of the item. One of `in_progress`, `completed`, or `incomplete`.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "type",
+          "call_id",
+          "output"
+        ]
+      },
+      "BetaLocalShellToolCall": {
+        "type": "object",
+        "title": "Local shell call",
+        "description": "A tool call to run a command on the local shell.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "local_shell_call"
+            ],
+            "description": "The type of the local shell call. Always `local_shell_call`.\n",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the local shell call.\n"
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The unique ID of the local shell tool call generated by the model.\n"
+          },
+          "action": {
+            "$ref": "#/components/schemas/BetaLocalShellExecAction"
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "in_progress",
+              "completed",
+              "incomplete"
+            ],
+            "description": "The status of the local shell call.\n"
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "action",
+          "status"
+        ]
+      },
+      "BetaLocalShellExecAction": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "exec"
+            ],
+            "description": "The type of the local shell action. Always `exec`.",
+            "default": "exec",
+            "x-stainless-const": true
+          },
+          "command": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array",
+            "description": "The command to run."
+          },
+          "timeout_ms": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "Optional timeout in milliseconds for the command."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "working_directory": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Optional working directory to run the command in."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "env": {
+            "additionalProperties": {
+              "type": "string"
+            },
+            "type": "object",
+            "description": "Environment variables to set for the command.",
+            "x-oaiTypeLabel": "map"
+          },
+          "user": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Optional user to run the command as."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "command",
+          "env"
+        ],
+        "title": "Local shell exec action",
+        "description": "Execute a shell command on the server."
+      },
+      "BetaCodeInterpreterToolCall": {
+        "type": "object",
+        "title": "Code interpreter tool call",
+        "description": "A tool call to run code.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "code_interpreter_call"
+            ],
+            "default": "code_interpreter_call",
+            "x-stainless-const": true,
+            "description": "The type of the code interpreter tool call. Always `code_interpreter_call`.\n"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the code interpreter tool call.\n"
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "in_progress",
+              "completed",
+              "incomplete",
+              "interpreting",
+              "failed"
+            ],
+            "description": "The status of the code interpreter tool call. Valid values are `in_progress`, `completed`, `incomplete`, `interpreting`, and `failed`.\n"
+          },
+          "container_id": {
+            "type": "string",
+            "description": "The ID of the container used to run the code.\n"
+          },
+          "code": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The code to run, or null if not available.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "outputs": {
+            "anyOf": [
+              {
+                "type": "array",
+                "items": {
+                  "oneOf": [
+                    {
+                      "$ref": "#/components/schemas/BetaCodeInterpreterOutputLogs"
+                    },
+                    {
+                      "$ref": "#/components/schemas/BetaCodeInterpreterOutputImage"
+                    }
+                  ],
+                  "discriminator": {
+                    "propertyName": "type"
+                  }
+                },
+                "discriminator": {
+                  "propertyName": "type"
+                },
+                "description": "The outputs generated by the code interpreter, such as logs or images.\nCan be null if no outputs are available.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "status",
+          "container_id",
+          "code",
+          "outputs"
+        ]
+      },
+      "BetaCodeInterpreterOutputImage": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "image"
+            ],
+            "description": "The type of the output. Always `image`.",
+            "default": "image",
+            "x-stainless-const": true
+          },
+          "url": {
+            "type": "string",
+            "format": "uri",
+            "description": "The URL of the image output from the code interpreter."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "url"
+        ],
+        "title": "Code interpreter output image",
+        "description": "The image output from the code interpreter."
+      },
+      "BetaCodeInterpreterOutputLogs": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "logs"
+            ],
+            "description": "The type of the output. Always `logs`.",
+            "default": "logs",
+            "x-stainless-const": true
+          },
+          "logs": {
+            "type": "string",
+            "description": "The logs output from the code interpreter."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "logs"
+        ],
+        "title": "Code interpreter output logs",
+        "description": "The logs output from the code interpreter."
+      },
+      "BetaImageGenToolCall": {
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag",
+                "description": "The agent that produced this item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "image_generation_call"
+            ],
+            "description": "The type of the image generation call. Always `image_generation_call`.",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the image generation call."
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "in_progress",
+              "completed",
+              "generating",
+              "failed"
+            ],
+            "description": "The status of the image generation call."
+          },
+          "result": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The generated image encoded in base64."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "size": {
+            "anyOf": [
+              {
+                "anyOf": [
+                  {
+                    "type": "string"
+                  },
+                  {
+                    "type": "string",
+                    "enum": [
+                      "1024x1024",
+                      "1024x1536",
+                      "1536x1024"
+                    ]
+                  }
+                ],
+                "description": "The image dimensions as a `WIDTHxHEIGHT` string, for example `1536x864`."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "quality": {
+            "anyOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "low",
+                  "medium",
+                  "high",
+                  "xhigh",
+                  "max",
+                  "auto"
+                ],
+                "description": "The quality of the image generated by the image generation tool call. One of `low`, `medium`, `high`, `xhigh`, `max`, or `auto`."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "action": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaImageGenActionEnum",
+                "description": "The action used for image generation."
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "x-openai-go-optional-enum": true
+          },
+          "background": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaImageBackground",
+                "description": "The background setting used for generation."
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "x-openai-go-optional-enum": true
+          },
+          "output_format": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaImageOutputFormat",
+                "description": "The output format used for generation."
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "x-openai-go-optional-enum": true
+          },
+          "revised_prompt": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The prompt that was used after any model prompt rewriting."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "status",
+          "result"
+        ],
+        "title": "Image generation call",
+        "description": "An image generation request made by the model."
+      },
+      "BetaImageOutputFormat": {
+        "type": "string",
+        "enum": [
+          "png",
+          "webp",
+          "jpeg"
+        ]
+      },
+      "BetaImageBackground": {
+        "type": "string",
+        "enum": [
+          "transparent",
+          "opaque",
+          "auto"
+        ]
+      },
+      "BetaCompactionSummaryItemParam": {
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Beta_AgentTagParam",
+                "description": "The agent that produced this item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the compaction item.",
+                "example": "cmp_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "compaction"
+            ],
+            "description": "The type of the item. Always `compaction`.",
+            "default": "compaction",
+            "x-stainless-const": true
+          },
+          "encrypted_content": {
+            "type": "string",
+            "maxLength": 20971520,
+            "description": "The encrypted content of the compaction summary."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "encrypted_content"
+        ],
+        "title": "Compaction item",
+        "description": "A compaction item generated by the [`v1/responses/compact` API](https://developers.openai.com/api/reference/resources/responses/methods/compact)."
+      },
+      "BetaReasoningItem": {
+        "type": "object",
+        "description": "A description of the chain of thought used by a reasoning model while generating\na response. Be sure to include these items in your `input` to the Responses API\nfor subsequent turns of a conversation if you are manually\n[managing context](https://developers.openai.com/api/docs/guides/conversation-state).\n",
+        "title": "Reasoning",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the object. Always `reasoning`.\n",
+            "enum": [
+              "reasoning"
+            ],
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique identifier of the reasoning content.\n"
+          },
+          "encrypted_content": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The encrypted content of the reasoning item. This is populated by default\nfor reasoning items returned by `POST /v1/responses` and WebSocket\n`response.create` requests.\n\nWhen streaming, use the completed reasoning item and its\n`encrypted_content` from the `response.output_item.done` event in\nsubsequent requests. The `encrypted_content` in\n`response.output_item.added` may be incomplete. This is especially\nimportant when `store` is `false` or when using Zero Data Retention.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "summary": {
+            "type": "array",
+            "description": "Reasoning summary content.\n",
+            "items": {
+              "$ref": "#/components/schemas/BetaSummaryTextContent"
+            }
+          },
+          "content": {
+            "type": "array",
+            "description": "Reasoning text content.\n",
+            "items": {
+              "$ref": "#/components/schemas/BetaReasoningTextContent"
+            }
+          },
+          "status": {
+            "type": "string",
+            "description": "The status of the item. One of `in_progress`, `completed`, or\n`incomplete`. Populated when items are returned via API.\n",
+            "enum": [
+              "in_progress",
+              "completed",
+              "incomplete"
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "summary",
+          "type"
+        ]
+      },
+      "BetaReasoningTextContent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "reasoning_text"
+            ],
+            "description": "The type of the reasoning text. Always `reasoning_text`.",
+            "default": "reasoning_text",
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string",
+            "description": "The reasoning text from the model."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "text"
+        ],
+        "title": "Reasoning text",
+        "description": "Reasoning text from the model."
+      },
+      "BetaSummaryTextContent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "summary_text"
+            ],
+            "description": "The type of the object. Always `summary_text`.",
+            "default": "summary_text",
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string",
+            "description": "A summary of the reasoning output from the model so far."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "text"
+        ],
+        "title": "Summary text",
+        "description": "A summary text from the model."
+      },
+      "BetaResponseConfigurationUpdateItemParam": {
+        "type": "object",
+        "description": "An update to the conversation's response configuration. The configuration\nremains in effect for subsequent responses until it is replaced by another\nconfiguration update.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Beta_AgentTagParam",
+                "description": "The agent that produced this item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the configuration update item.",
+                "example": "cnfu_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "configuration_update"
+            ],
+            "description": "The item type. Always `configuration_update`.",
+            "default": "configuration_update",
+            "x-stainless-const": true
+          },
+          "reasoning": {
+            "type": "object",
+            "description": "Updates to reasoning configuration. Only effort is supported.",
+            "properties": {
+              "effort": {
+                "$ref": "#/components/schemas/BetaReasoningEffort",
+                "description": "The reasoning effort to use for subsequent responses until another\nconfiguration update replaces it.\n"
+              }
+            }
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "BetaAdditionalToolsItemParam": {
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Beta_AgentTagParam",
+                "description": "The agent that produced this item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of this additional tools item.",
+                "example": "at_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "additional_tools"
+            ],
+            "description": "The item type. Always `additional_tools`.",
+            "default": "additional_tools",
+            "x-stainless-const": true
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "developer"
+            ],
+            "description": "The role that provided the additional tools. Only `developer` is supported.",
+            "default": "developer",
+            "x-stainless-const": true
+          },
+          "tools": {
+            "items": {
+              "$ref": "#/components/schemas/BetaTool"
+            },
+            "type": "array",
+            "description": "A list of additional tools made available at this item."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "role",
+          "tools"
+        ]
+      },
+      "BetaToolSearchOutputItemParam": {
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Beta_AgentTagParam",
+                "description": "The agent that produced this item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of this tool search output.",
+                "example": "tso_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "call_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "maxLength": 64,
+                "minLength": 1,
+                "description": "The unique ID of the tool search call generated by the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "tool_search_output"
+            ],
+            "description": "The item type. Always `tool_search_output`.",
+            "default": "tool_search_output",
+            "x-stainless-const": true
+          },
+          "execution": {
+            "$ref": "#/components/schemas/BetaToolSearchExecutionType",
+            "description": "Whether tool search was executed by the server or by the client."
+          },
+          "tools": {
+            "items": {
+              "$ref": "#/components/schemas/BetaTool"
+            },
+            "type": "array",
+            "description": "The loaded tool definitions returned by the tool search output."
+          },
+          "status": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaFunctionCallItemStatus",
+                "description": "The status of the tool search output."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "tools"
+        ]
+      },
+      "BetaFunctionCallItemStatus": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed",
+          "incomplete"
+        ]
+      },
+      "BetaToolSearchCallItemParam": {
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Beta_AgentTagParam",
+                "description": "The agent that produced this item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of this tool search call.",
+                "example": "tsc_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "call_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "maxLength": 64,
+                "minLength": 1,
+                "description": "The unique ID of the tool search call generated by the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "tool_search_call"
+            ],
+            "description": "The item type. Always `tool_search_call`.",
+            "default": "tool_search_call",
+            "x-stainless-const": true
+          },
+          "execution": {
+            "$ref": "#/components/schemas/BetaToolSearchExecutionType",
+            "description": "Whether tool search was executed by the server or by the client."
+          },
+          "arguments": {
+            "$ref": "#/components/schemas/BetaEmptyModelParam",
+            "description": "The arguments supplied to the tool search call."
+          },
+          "status": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaFunctionCallItemStatus",
+                "description": "The status of the tool search call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "arguments"
+        ]
+      },
+      "BetaMultiAgentCallOutputItemParam": {
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Beta_AgentTagParam",
+                "description": "The agent that produced this item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of this multi-agent call output.",
+                "example": "maco_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "call_id": {
+            "type": "string",
+            "maxLength": 64,
+            "minLength": 1,
+            "description": "The unique ID of the multi-agent call."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "multi_agent_call_output"
+            ],
+            "description": "The item type. Always `multi_agent_call_output`.",
+            "default": "multi_agent_call_output",
+            "x-stainless-const": true
+          },
+          "action": {
+            "$ref": "#/components/schemas/BetaMultiAgentAction1",
+            "description": "The multi-agent action that produced this result."
+          },
+          "output": {
+            "items": {
+              "$ref": "#/components/schemas/BetaOutputTextContentParam"
+            },
+            "type": "array",
+            "description": "Text output returned by the multi-agent action."
+          }
+        },
+        "type": "object",
+        "required": [
+          "call_id",
+          "type",
+          "action",
+          "output"
+        ],
+        "x-oai-beta": "responses_multi_agent=v1"
+      },
+      "BetaOutputTextContentParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "output_text"
+            ],
+            "description": "The content type. Always `output_text`.",
+            "default": "output_text",
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string",
+            "maxLength": 10485760,
+            "description": "The text content."
+          },
+          "annotations": {
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/BetaFileCitationParam"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaUrlCitationParam"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaContainerFileCitationParam"
+                }
+              ],
+              "discriminator": {
+                "propertyName": "type"
+              }
+            },
+            "type": "array",
+            "description": "Citations associated with the text content."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "text"
+        ]
+      },
+      "BetaContainerFileCitationParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "container_file_citation"
+            ],
+            "description": "The citation type. Always `container_file_citation`.",
+            "default": "container_file_citation",
+            "x-stainless-const": true
+          },
+          "start_index": {
+            "type": "integer",
+            "minimum": 0,
+            "description": "The index of the first character of the citation in the message."
+          },
+          "end_index": {
+            "type": "integer",
+            "minimum": 0,
+            "description": "The index of the last character of the citation in the message."
+          },
+          "container_id": {
+            "type": "string",
+            "description": "The ID of the container.",
+            "example": "cntr_123"
+          },
+          "file_id": {
+            "type": "string",
+            "description": "The ID of the container file.",
+            "example": "cfile_123"
+          },
+          "filename": {
+            "type": "string",
+            "description": "The filename of the container file cited."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "start_index",
+          "end_index",
+          "container_id",
+          "file_id",
+          "filename"
+        ]
+      },
+      "BetaUrlCitationParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "url_citation"
+            ],
+            "description": "The citation type. Always `url_citation`.",
+            "default": "url_citation",
+            "x-stainless-const": true
+          },
+          "start_index": {
+            "type": "integer",
+            "minimum": 0,
+            "description": "The index of the first character of the citation in the message."
+          },
+          "end_index": {
+            "type": "integer",
+            "minimum": 0,
+            "description": "The index of the last character of the citation in the message."
+          },
+          "url": {
+            "type": "string",
+            "format": "uri",
+            "description": "The URL of the cited resource."
+          },
+          "title": {
+            "type": "string",
+            "description": "The title of the cited resource."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "start_index",
+          "end_index",
+          "url",
+          "title"
+        ]
+      },
+      "BetaFileCitationParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "file_citation"
+            ],
+            "description": "The citation type. Always `file_citation`.",
+            "default": "file_citation",
+            "x-stainless-const": true
+          },
+          "index": {
+            "type": "integer",
+            "minimum": 0,
+            "description": "The index of the file in the list of files."
+          },
+          "file_id": {
+            "type": "string",
+            "description": "The ID of the file.",
+            "example": "file-123"
+          },
+          "filename": {
+            "type": "string",
+            "description": "The filename of the file cited."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "index",
+          "file_id",
+          "filename"
+        ]
+      },
+      "BetaMultiAgentAction1": {
+        "type": "string",
+        "enum": [
+          "spawn_agent",
+          "interrupt_agent",
+          "list_agents",
+          "send_message",
+          "followup_task",
+          "wait_agent"
+        ]
+      },
+      "BetaMultiAgentCallItemParam": {
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Beta_AgentTagParam",
+                "description": "The agent that produced this item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of this multi-agent call.",
+                "example": "mac_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "call_id": {
+            "type": "string",
+            "maxLength": 64,
+            "minLength": 1,
+            "description": "The unique ID linking this call to its output."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "multi_agent_call"
+            ],
+            "description": "The item type. Always `multi_agent_call`.",
+            "default": "multi_agent_call",
+            "x-stainless-const": true
+          },
+          "action": {
+            "$ref": "#/components/schemas/BetaMultiAgentAction1",
+            "description": "The multi-agent action that was executed."
+          },
+          "arguments": {
+            "type": "string",
+            "description": "The action arguments as a JSON string."
+          }
+        },
+        "type": "object",
+        "required": [
+          "call_id",
+          "type",
+          "action",
+          "arguments"
+        ],
+        "x-oai-beta": "responses_multi_agent=v1"
+      },
+      "BetaAgentMessageItemParam": {
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Beta_AgentTagParam",
+                "description": "The agent that produced this item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of this agent message item.",
+                "example": "amsg_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent_message"
+            ],
+            "description": "The item type. Always `agent_message`.",
+            "default": "agent_message",
+            "x-stainless-const": true
+          },
+          "author": {
+            "type": "string",
+            "description": "The sending agent identity."
+          },
+          "recipient": {
+            "type": "string",
+            "description": "The destination agent identity."
+          },
+          "content": {
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/BetaInputTextContentParam"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaInputImageContentParamAutoParam"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaEncryptedContentParam"
+                }
+              ],
+              "description": "A plaintext, image, or encrypted agent message content part.",
+              "discriminator": {
+                "propertyName": "type"
+              }
+            },
+            "type": "array",
+            "description": "Plaintext, image, or encrypted content sent between agents."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "author",
+          "recipient",
+          "content"
+        ],
+        "title": "Agent message",
+        "description": "A message routed between agents.",
+        "x-oai-beta": "responses_multi_agent=v1"
+      },
+      "BetaEncryptedContentParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "encrypted_content"
+            ],
+            "description": "The type of the input item. Always `encrypted_content`.",
+            "default": "encrypted_content",
+            "x-stainless-const": true
+          },
+          "encrypted_content": {
+            "type": "string",
+            "maxLength": 10485760,
+            "description": "Opaque encrypted content."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "encrypted_content"
+        ],
+        "title": "Encrypted content",
+        "description": "Opaque encrypted content that Responses API decrypts inside trusted model execution.",
+        "x-oai-beta": "responses_multi_agent=v1"
+      },
+      "BetaInputImageContentParamAutoParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_image"
+            ],
+            "description": "The type of the input item. Always `input_image`.",
+            "default": "input_image",
+            "x-stainless-const": true
+          },
+          "image_url": {
+            "anyOf": [
+              {
+                "type": "string",
+                "maxLength": 20971520,
+                "format": "uri",
+                "description": "The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "file_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the file to be sent to the model.",
+                "example": "file-123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "detail": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaDetailEnum",
+                "description": "The detail level of the image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "prompt_cache_breakpoint": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaPromptCacheBreakpointParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Input image",
+        "description": "An image input to the model. Learn about [image inputs](https://developers.openai.com/api/docs/guides/images-vision)"
+      },
+      "BetaPromptCacheBreakpointParam": {
+        "properties": {
+          "mode": {
+            "type": "string",
+            "enum": [
+              "explicit"
+            ],
+            "description": "The breakpoint mode. Always `explicit`.",
+            "default": "explicit",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "mode"
+        ],
+        "title": "Prompt cache breakpoint",
+        "description": "Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block."
+      },
+      "BetaDetailEnum": {
+        "type": "string",
+        "enum": [
+          "low",
+          "high",
+          "auto",
+          "original"
+        ]
+      },
+      "BetaInputTextContentParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_text"
+            ],
+            "description": "The type of the input item. Always `input_text`.",
+            "default": "input_text",
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string",
+            "maxLength": 10485760,
+            "description": "The text input to the model."
+          },
+          "prompt_cache_breakpoint": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaPromptCacheBreakpointParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "text"
+        ],
+        "title": "Input text",
+        "description": "A text input to the model."
+      },
+      "BetaFunctionCallOutputItemParam": {
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Beta_AgentTagParam",
+                "description": "The agent that produced this item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the function tool call output. Populated when this item is returned via API.",
+                "example": "fc_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "call_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "maxLength": 64,
+                "minLength": 1,
+                "description": "The unique ID of the function tool call generated by the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "function_call_output"
+            ],
+            "description": "The type of the function tool call output. Always `function_call_output`.",
+            "default": "function_call_output",
+            "x-stainless-const": true
+          },
+          "output": {
+            "oneOf": [
+              {
+                "type": "string",
+                "maxLength": 10485760,
+                "description": "A JSON string of the output of the function tool call."
+              },
+              {
+                "items": {
+                  "oneOf": [
+                    {
+                      "$ref": "#/components/schemas/BetaInputTextContentParam"
+                    },
+                    {
+                      "$ref": "#/components/schemas/BetaInputImageContentParamAutoParam"
+                    },
+                    {
+                      "$ref": "#/components/schemas/BetaInputFileContentParam"
+                    }
+                  ],
+                  "description": "A piece of message content, such as text, an image, or a file.",
+                  "discriminator": {
+                    "propertyName": "type"
+                  }
+                },
+                "type": "array",
+                "description": "An array of content outputs (text, image, file) for the function tool call."
+              }
+            ],
+            "description": "Text, image, or file output of the function tool call."
+          },
+          "name": {
+            "anyOf": [
+              {
+                "type": "string",
+                "maxLength": 128,
+                "minLength": 1,
+                "description": "The name of the tool that produced the output."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "namespace": {
+            "anyOf": [
+              {
+                "type": "string",
+                "maxLength": 64,
+                "minLength": 1,
+                "pattern": "^[a-zA-Z0-9_-]+$",
+                "description": "The namespace of the tool that produced the output."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaToolCallCallerParam",
+                "description": "The execution context that produced this tool call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaFunctionCallItemStatus",
+                "description": "The status of the item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "output"
+        ],
+        "title": "Function tool call output",
+        "description": "The output of a function tool call."
+      },
+      "BetaInputFileContentParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "input_file"
+            ],
+            "description": "The type of the input item. Always `input_file`.",
+            "default": "input_file",
+            "x-stainless-const": true
+          },
+          "file_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the file to be sent to the model.",
+                "example": "file-123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "filename": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The name of the file to be sent to the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "file_data": {
+            "anyOf": [
+              {
+                "type": "string",
+                "maxLength": 73400320,
+                "description": "The base64-encoded data of the file to be sent to the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "file_url": {
+            "anyOf": [
+              {
+                "type": "string",
+                "format": "uri",
+                "description": "The URL of the file to be sent to the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "detail": {
+            "$ref": "#/components/schemas/BetaFileDetailEnum",
+            "description": "The detail level of the file to be sent to the model. Use `auto` to let the system select the detail level; for GPT-5.6 and later models, `auto` uses high-quality rendering, which may increase input token usage. Use `low` for lower-cost rendering, or `high` to render the file at higher quality. Defaults to `auto`."
+          },
+          "prompt_cache_breakpoint": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaPromptCacheBreakpointParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Input file",
+        "description": "A file input to the model."
+      },
+      "BetaFileDetailEnum": {
+        "type": "string",
+        "enum": [
+          "auto",
+          "low",
+          "high"
+        ]
+      },
+      "BetaFunctionToolCall": {
+        "type": "object",
+        "title": "Function tool call",
+        "description": "A tool call to run a function. See the\n[function calling guide](https://developers.openai.com/api/docs/guides/function-calling) for more information.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that produced this item."
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the function tool call.\n"
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "function_call"
+            ],
+            "description": "The type of the function tool call. Always `function_call`.\n",
+            "x-stainless-const": true
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The unique ID of the function tool call generated by the model.\n"
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaToolCallCaller"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "namespace": {
+            "type": "string",
+            "description": "The namespace of the function to run.\n"
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the function to run.\n"
+          },
+          "arguments": {
+            "type": "string",
+            "description": "A JSON string of the arguments to pass to the function.\n"
+          },
+          "status": {
+            "type": "string",
+            "description": "The status of the item. One of `in_progress`, `completed`, or\n`incomplete`. Populated when items are returned via API.\n",
+            "enum": [
+              "in_progress",
+              "completed",
+              "incomplete"
+            ]
+          },
+          "async": {
+            "type": "boolean",
+            "description": "Whether the function tool call runs asynchronously.\n"
+          }
+        },
+        "required": [
+          "type",
+          "call_id",
+          "name",
+          "arguments"
+        ]
+      },
+      "BetaWebSearchToolCall": {
+        "type": "object",
+        "title": "Web search tool call",
+        "description": "The results of a web search tool call. See the\n[web search guide](https://developers.openai.com/api/docs/guides/tools-web-search) for more information.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that produced this item."
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the web search tool call.\n"
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "web_search_call"
+            ],
+            "description": "The type of the web search tool call. Always `web_search_call`.\n",
+            "x-stainless-const": true
+          },
+          "status": {
+            "description": "The status of the web search tool call.\n",
+            "$ref": "#/components/schemas/BetaWebSearchCallStatus"
+          },
+          "action": {
+            "type": "object",
+            "description": "An object describing the specific action taken in this web search call.\nIncludes details on how the model used the web (search, open_page, find_in_page).\n",
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/BetaWebSearchActionSearch"
+              },
+              {
+                "$ref": "#/components/schemas/BetaWebSearchActionOpenPage"
+              },
+              {
+                "$ref": "#/components/schemas/BetaWebSearchActionFind"
+              }
+            ],
+            "discriminator": {
+              "propertyName": "type"
+            }
+          }
+        },
+        "required": [
+          "id",
+          "type",
+          "status",
+          "action"
+        ]
+      },
+      "BetaWebSearchActionFind": {
+        "type": "object",
+        "title": "Find action",
+        "description": "Action type \"find_in_page\": Searches for a pattern within a loaded page.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "find_in_page"
+            ],
+            "description": "The action type.\n",
+            "x-stainless-const": true
+          },
+          "url": {
+            "type": "string",
+            "format": "uri",
+            "description": "The URL of the page searched for the pattern.\n"
+          },
+          "pattern": {
+            "type": "string",
+            "description": "The pattern or text to search for within the page.\n"
+          }
+        },
+        "required": [
+          "type",
+          "url",
+          "pattern"
+        ]
+      },
+      "BetaWebSearchActionOpenPage": {
+        "type": "object",
+        "title": "Open page action",
+        "description": "Action type \"open_page\" - Opens a specific URL from search results.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "open_page"
+            ],
+            "description": "The action type.\n",
+            "x-stainless-const": true
+          },
+          "url": {
+            "description": "The URL opened by the model.\n",
+            "anyOf": [
+              {
+                "type": "string",
+                "format": "uri"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "BetaWebSearchActionSearch": {
+        "type": "object",
+        "title": "Search action",
+        "description": "Action type \"search\" - Performs a web search query.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "search"
+            ],
+            "description": "The action type.\n",
+            "x-stainless-const": true
+          },
+          "query": {
+            "type": "string",
+            "deprecated": true,
+            "description": "The search query.\n"
+          },
+          "queries": {
+            "type": "array",
+            "title": "Search queries",
+            "description": "The search queries.\n",
+            "items": {
+              "type": "string",
+              "description": "A search query.\n"
+            }
+          },
+          "sources": {
+            "type": "array",
+            "title": "Web search sources",
+            "description": "The sources used in the search.\n",
+            "items": {
+              "type": "object",
+              "title": "Web search source",
+              "description": "A source used in the search.\n",
+              "properties": {
+                "type": {
+                  "type": "string",
+                  "enum": [
+                    "url"
+                  ],
+                  "description": "The type of source. Always `url`.\n",
+                  "x-stainless-const": true
+                },
+                "url": {
+                  "type": "string",
+                  "format": "uri",
+                  "description": "The URL of the source.\n"
+                }
+              },
+              "required": [
+                "type",
+                "url"
+              ]
+            }
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "BetaWebSearchCallStatus": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "searching",
+          "completed",
+          "failed",
+          "incomplete"
+        ]
+      },
+      "BetaComputerCallOutputItemParam": {
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Beta_AgentTagParam",
+                "description": "The agent that produced this item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of the computer tool call output.",
+                "example": "cuo_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "call_id": {
+            "type": "string",
+            "maxLength": 64,
+            "minLength": 1,
+            "description": "The ID of the computer tool call that produced the output."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "computer_call_output"
+            ],
+            "description": "The type of the computer tool call output. Always `computer_call_output`.",
+            "default": "computer_call_output",
+            "x-stainless-const": true
+          },
+          "output": {
+            "$ref": "#/components/schemas/BetaComputerScreenshotImage"
+          },
+          "acknowledged_safety_checks": {
+            "anyOf": [
+              {
+                "items": {
+                  "$ref": "#/components/schemas/BetaComputerCallSafetyCheckParam"
+                },
+                "type": "array",
+                "description": "The safety checks reported by the API that have been acknowledged by the developer."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaFunctionCallItemStatus",
+                "description": "The status of the message input. One of `in_progress`, `completed`, or `incomplete`. Populated when input items are returned via API."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "call_id",
+          "type",
+          "output"
+        ],
+        "title": "Computer tool call output",
+        "description": "The output of a computer tool call."
+      },
+      "BetaComputerCallSafetyCheckParam": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The ID of the pending safety check."
+          },
+          "code": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The type of the pending safety check."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "message": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Details about the pending safety check."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "id"
+        ],
+        "description": "A pending safety check for the computer call."
+      },
+      "BetaComputerScreenshotImage": {
+        "type": "object",
+        "description": "A computer screenshot image used with the computer use tool.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "computer_screenshot"
+            ],
+            "default": "computer_screenshot",
+            "description": "Specifies the event type. For a computer screenshot, this property is \nalways set to `computer_screenshot`.\n",
+            "x-stainless-const": true
+          },
+          "image_url": {
+            "type": "string",
+            "format": "uri",
+            "description": "The URL of the screenshot image."
+          },
+          "file_id": {
+            "type": "string",
+            "description": "The identifier of an uploaded file that contains the screenshot."
+          }
+        },
+        "required": [
+          "type"
+        ]
+      },
+      "BetaComputerToolCall": {
+        "type": "object",
+        "title": "Computer tool call",
+        "description": "A tool call to a computer use tool. See the\n[computer use guide](https://developers.openai.com/api/docs/guides/tools-computer-use) for more information.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the computer call. Always `computer_call`.",
+            "enum": [
+              "computer_call"
+            ],
+            "default": "computer_call"
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the computer call."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "An identifier used when responding to the tool call with output.\n"
+          },
+          "action": {
+            "$ref": "#/components/schemas/BetaComputerAction"
+          },
+          "actions": {
+            "$ref": "#/components/schemas/BetaComputerActionList"
+          },
+          "pending_safety_checks": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/BetaComputerCallSafetyCheckParam"
+            },
+            "description": "The pending safety checks for the computer call.\n"
+          },
+          "status": {
+            "type": "string",
+            "description": "The status of the item. One of `in_progress`, `completed`, or\n`incomplete`. Populated when items are returned via API.\n",
+            "enum": [
+              "in_progress",
+              "completed",
+              "incomplete"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "pending_safety_checks",
+          "status"
+        ]
+      },
+      "BetaComputerActionList": {
+        "title": "Computer Action List",
+        "type": "array",
+        "description": "Flattened batched actions for `computer_use`. Each action includes an\n`type` discriminator and action-specific fields.\n",
+        "items": {
+          "$ref": "#/components/schemas/BetaComputerAction"
+        }
+      },
+      "BetaComputerAction": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/BetaClickParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaDoubleClickAction"
+          },
+          {
+            "$ref": "#/components/schemas/BetaDragParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaKeyPressAction"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMoveParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaScreenshotParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaScrollParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaTypeParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaWaitParam"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "BetaWaitParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "wait"
+            ],
+            "description": "Specifies the event type. For a wait action, this property is always set to `wait`.",
+            "default": "wait",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Wait",
+        "description": "A wait action."
+      },
+      "BetaTypeParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "type"
+            ],
+            "description": "Specifies the event type. For a type action, this property is always set to `type`.",
+            "default": "type",
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string",
+            "description": "The text to type."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "text"
+        ],
+        "title": "Type",
+        "description": "An action to type in text."
+      },
+      "BetaScrollParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "scroll"
+            ],
+            "description": "Specifies the event type. For a scroll action, this property is always set to `scroll`.",
+            "default": "scroll",
+            "x-stainless-const": true
+          },
+          "x": {
+            "type": "integer",
+            "description": "The x-coordinate where the scroll occurred."
+          },
+          "y": {
+            "type": "integer",
+            "description": "The y-coordinate where the scroll occurred."
+          },
+          "scroll_x": {
+            "type": "integer",
+            "description": "The horizontal scroll distance."
+          },
+          "scroll_y": {
+            "type": "integer",
+            "description": "The vertical scroll distance."
+          },
+          "keys": {
+            "anyOf": [
+              {
+                "items": {
+                  "type": "string"
+                },
+                "type": "array",
+                "description": "The keys being held while scrolling."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "x",
+          "y",
+          "scroll_x",
+          "scroll_y"
+        ],
+        "title": "Scroll",
+        "description": "A scroll action."
+      },
+      "BetaScreenshotParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "screenshot"
+            ],
+            "description": "Specifies the event type. For a screenshot action, this property is always set to `screenshot`.",
+            "default": "screenshot",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Screenshot",
+        "description": "A screenshot action."
+      },
+      "BetaMoveParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "move"
+            ],
+            "description": "Specifies the event type. For a move action, this property is always set to `move`.",
+            "default": "move",
+            "x-stainless-const": true
+          },
+          "x": {
+            "type": "integer",
+            "description": "The x-coordinate to move to."
+          },
+          "y": {
+            "type": "integer",
+            "description": "The y-coordinate to move to."
+          },
+          "keys": {
+            "anyOf": [
+              {
+                "items": {
+                  "type": "string"
+                },
+                "type": "array",
+                "description": "The keys being held while moving the mouse."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "x",
+          "y"
+        ],
+        "title": "Move",
+        "description": "A mouse move action."
+      },
+      "BetaKeyPressAction": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "keypress"
+            ],
+            "description": "Specifies the event type. For a keypress action, this property is always set to `keypress`.",
+            "default": "keypress",
+            "x-stainless-const": true
+          },
+          "keys": {
+            "items": {
+              "type": "string",
+              "description": "One of the keys the model is requesting to be pressed."
+            },
+            "type": "array",
+            "description": "The combination of keys the model is requesting to be pressed. This is an array of strings, each representing a key."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "keys"
+        ],
+        "title": "KeyPress",
+        "description": "A collection of keypresses the model would like to perform."
+      },
+      "BetaDragParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "drag"
+            ],
+            "description": "Specifies the event type. For a drag action, this property is always set to `drag`.",
+            "default": "drag",
+            "x-stainless-const": true
+          },
+          "path": {
+            "items": {
+              "$ref": "#/components/schemas/BetaCoordParam"
+            },
+            "type": "array",
+            "description": "An array of coordinates representing the path of the drag action. Coordinates will appear as an array of objects, eg\n```\n[\n  { x: 100, y: 200 },\n  { x: 200, y: 300 }\n]\n```"
+          },
+          "keys": {
+            "anyOf": [
+              {
+                "items": {
+                  "type": "string"
+                },
+                "type": "array",
+                "description": "The keys being held while dragging the mouse."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "path"
+        ],
+        "title": "Drag",
+        "description": "A drag action."
+      },
+      "BetaCoordParam": {
+        "properties": {
+          "x": {
+            "type": "integer",
+            "description": "The x-coordinate."
+          },
+          "y": {
+            "type": "integer",
+            "description": "The y-coordinate."
+          }
+        },
+        "type": "object",
+        "required": [
+          "x",
+          "y"
+        ],
+        "title": "Coordinate",
+        "description": "An x/y coordinate pair, e.g. `{ x: 100, y: 200 }`."
+      },
+      "BetaDoubleClickAction": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "double_click"
+            ],
+            "description": "Specifies the event type. For a double click action, this property is always set to `double_click`.",
+            "default": "double_click",
+            "x-stainless-const": true
+          },
+          "x": {
+            "type": "integer",
+            "description": "The x-coordinate where the double click occurred."
+          },
+          "y": {
+            "type": "integer",
+            "description": "The y-coordinate where the double click occurred."
+          },
+          "keys": {
+            "anyOf": [
+              {
+                "items": {
+                  "type": "string"
+                },
+                "type": "array",
+                "description": "The keys being held while double-clicking."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "x",
+          "y",
+          "keys"
+        ],
+        "title": "DoubleClick",
+        "description": "A double click action."
+      },
+      "BetaClickParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "click"
+            ],
+            "description": "Specifies the event type. For a click action, this property is always `click`.",
+            "default": "click",
+            "x-stainless-const": true
+          },
+          "button": {
+            "$ref": "#/components/schemas/BetaClickButtonType",
+            "description": "Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`."
+          },
+          "x": {
+            "type": "integer",
+            "description": "The x-coordinate where the click occurred."
+          },
+          "y": {
+            "type": "integer",
+            "description": "The y-coordinate where the click occurred."
+          },
+          "keys": {
+            "anyOf": [
+              {
+                "items": {
+                  "type": "string"
+                },
+                "type": "array",
+                "description": "The keys being held while clicking."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "button",
+          "x",
+          "y"
+        ],
+        "title": "Click",
+        "description": "A click action."
+      },
+      "BetaClickButtonType": {
+        "type": "string",
+        "enum": [
+          "left",
+          "right",
+          "wheel",
+          "back",
+          "forward"
+        ]
+      },
+      "BetaFileSearchToolCall": {
+        "type": "object",
+        "title": "File search tool call",
+        "description": "The results of a file search tool call. See the\n[file search guide](https://developers.openai.com/api/docs/guides/tools-file-search) for more information.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that produced this item."
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the file search tool call.\n"
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "file_search_call"
+            ],
+            "description": "The type of the file search tool call. Always `file_search_call`.\n",
+            "x-stainless-const": true
+          },
+          "status": {
+            "type": "string",
+            "description": "The status of the file search tool call. One of `in_progress`,\n`searching`, `incomplete` or `failed`,\n",
+            "enum": [
+              "in_progress",
+              "searching",
+              "completed",
+              "incomplete",
+              "failed"
+            ]
+          },
+          "queries": {
+            "type": "array",
+            "items": {
+              "type": "string"
+            },
+            "description": "The queries used to search for files.\n"
+          },
+          "results": {
+            "anyOf": [
+              {
+                "type": "array",
+                "description": "The results of the file search tool call.\n",
+                "items": {
+                  "type": "object",
+                  "properties": {
+                    "file_id": {
+                      "type": "string",
+                      "description": "The unique ID of the file.\n"
+                    },
+                    "text": {
+                      "type": "string",
+                      "description": "The text that was retrieved from the file.\n"
+                    },
+                    "filename": {
+                      "type": "string",
+                      "description": "The name of the file.\n"
+                    },
+                    "attributes": {
+                      "$ref": "#/components/schemas/BetaVectorStoreFileAttributes"
+                    },
+                    "score": {
+                      "type": "number",
+                      "format": "float",
+                      "description": "The relevance score of the file - a value between 0 and 1.\n"
+                    }
+                  }
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "type",
+          "status",
+          "queries"
+        ]
+      },
+      "BetaVectorStoreFileAttributes": {
+        "anyOf": [
+          {
+            "type": "object",
+            "description": "Set of 16 key-value pairs that can be attached to an object. This can be\nuseful for storing additional information about the object in a structured\nformat, and querying for objects via API or the dashboard. Keys are strings\nwith a maximum length of 64 characters. Values are strings with a maximum\nlength of 512 characters, booleans, or numbers.\n",
+            "maxProperties": 16,
+            "propertyNames": {
+              "type": "string",
+              "maxLength": 64
+            },
+            "additionalProperties": {
+              "oneOf": [
+                {
+                  "type": "string",
+                  "maxLength": 512
+                },
+                {
+                  "type": "number"
+                },
+                {
+                  "type": "boolean"
+                }
+              ]
+            },
+            "x-oaiTypeLabel": "map"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "BetaOutputMessage": {
+        "type": "object",
+        "title": "Output message",
+        "description": "An output message from the model.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that produced this item."
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the output message.\n"
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the output message. Always `message`.\n",
+            "enum": [
+              "message"
+            ],
+            "x-stainless-const": true
+          },
+          "role": {
+            "type": "string",
+            "description": "The role of the output message. Always `assistant`.\n",
+            "enum": [
+              "assistant"
+            ],
+            "x-stainless-const": true
+          },
+          "content": {
+            "type": "array",
+            "description": "The content of the output message.\n",
+            "items": {
+              "$ref": "#/components/schemas/BetaOutputMessageContent"
+            }
+          },
+          "phase": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaMessagePhase"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "type": "string",
+            "description": "The status of the message input. One of `in_progress`, `completed`, or\n`incomplete`. Populated when input items are returned via API.\n",
+            "enum": [
+              "in_progress",
+              "completed",
+              "incomplete"
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "type",
+          "role",
+          "content",
+          "status"
+        ]
+      },
+      "BetaMessagePhase": {
+        "type": "string",
+        "description": "Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`).\nFor models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend\nphase on all assistant messages — dropping it can degrade performance. Not used for user messages.\n",
+        "enum": [
+          "commentary",
+          "final_answer"
+        ]
+      },
+      "BetaOutputMessageContent": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/BetaOutputTextContent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaRefusalContent"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "BetaRefusalContent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "refusal"
+            ],
+            "description": "The type of the refusal. Always `refusal`.",
+            "default": "refusal",
+            "x-stainless-const": true
+          },
+          "refusal": {
+            "type": "string",
+            "description": "The refusal explanation from the model."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "refusal"
+        ],
+        "title": "Refusal",
+        "description": "A refusal from the model."
+      },
+      "BetaOutputTextContent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "output_text"
+            ],
+            "description": "The type of the output text. Always `output_text`.",
+            "default": "output_text",
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string",
+            "description": "The text output from the model."
+          },
+          "annotations": {
+            "items": {
+              "$ref": "#/components/schemas/BetaAnnotation"
+            },
+            "type": "array",
+            "description": "The annotations of the text output."
+          },
+          "logprobs": {
+            "items": {
+              "$ref": "#/components/schemas/BetaLogProb"
+            },
+            "type": "array"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "text",
+          "annotations",
+          "logprobs"
+        ],
+        "title": "Output text",
+        "description": "A text output from the model."
+      },
+      "BetaLogProb": {
+        "properties": {
+          "token": {
+            "type": "string"
+          },
+          "logprob": {
+            "type": "number"
+          },
+          "bytes": {
+            "items": {
+              "type": "integer"
+            },
+            "type": "array"
+          },
+          "top_logprobs": {
+            "items": {
+              "$ref": "#/components/schemas/BetaTopLogProb"
+            },
+            "type": "array"
+          }
+        },
+        "type": "object",
+        "required": [
+          "token",
+          "logprob",
+          "bytes",
+          "top_logprobs"
+        ],
+        "title": "Log probability",
+        "description": "The log probability of a token."
+      },
+      "BetaTopLogProb": {
+        "properties": {
+          "token": {
+            "type": "string"
+          },
+          "logprob": {
+            "type": "number"
+          },
+          "bytes": {
+            "items": {
+              "type": "integer"
+            },
+            "type": "array"
+          }
+        },
+        "type": "object",
+        "required": [
+          "token",
+          "logprob",
+          "bytes"
+        ],
+        "title": "Top log probability",
+        "description": "The top log probability of a token."
+      },
+      "BetaAnnotation": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/BetaFileCitationBody"
+          },
+          {
+            "$ref": "#/components/schemas/BetaUrlCitationBody"
+          },
+          {
+            "$ref": "#/components/schemas/BetaContainerFileCitationBody"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFilePath"
+          }
+        ],
+        "description": "An annotation that applies to a span of output text.",
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "BetaFilePath": {
+        "type": "object",
+        "title": "File path",
+        "description": "A path to a file.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the file path. Always `file_path`.\n",
+            "enum": [
+              "file_path"
+            ],
+            "x-stainless-const": true
+          },
+          "file_id": {
+            "type": "string",
+            "description": "The ID of the file.\n"
+          },
+          "index": {
+            "type": "integer",
+            "description": "The index of the file in the list of files.\n"
+          }
+        },
+        "required": [
+          "type",
+          "file_id",
+          "index"
+        ]
+      },
+      "BetaContainerFileCitationBody": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "container_file_citation"
+            ],
+            "description": "The type of the container file citation. Always `container_file_citation`.",
+            "default": "container_file_citation",
+            "x-stainless-const": true
+          },
+          "container_id": {
+            "type": "string",
+            "description": "The ID of the container file."
+          },
+          "file_id": {
+            "type": "string",
+            "description": "The ID of the file."
+          },
+          "start_index": {
+            "type": "integer",
+            "description": "The index of the first character of the container file citation in the message."
+          },
+          "end_index": {
+            "type": "integer",
+            "description": "The index of the last character of the container file citation in the message."
+          },
+          "filename": {
+            "type": "string",
+            "description": "The filename of the container file cited."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "container_id",
+          "file_id",
+          "start_index",
+          "end_index",
+          "filename"
+        ],
+        "title": "Container file citation",
+        "description": "A citation for a container file used to generate a model response."
+      },
+      "BetaUrlCitationBody": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "url_citation"
+            ],
+            "description": "The type of the URL citation. Always `url_citation`.",
+            "default": "url_citation",
+            "x-stainless-const": true
+          },
+          "url": {
+            "type": "string",
+            "format": "uri",
+            "description": "The URL of the web resource."
+          },
+          "start_index": {
+            "type": "integer",
+            "description": "The index of the first character of the URL citation in the message."
+          },
+          "end_index": {
+            "type": "integer",
+            "description": "The index of the last character of the URL citation in the message."
+          },
+          "title": {
+            "type": "string",
+            "description": "The title of the web resource."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "url",
+          "start_index",
+          "end_index",
+          "title"
+        ],
+        "title": "URL citation",
+        "description": "A citation for a web resource used to generate a model response."
+      },
+      "BetaFileCitationBody": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "file_citation"
+            ],
+            "description": "The type of the file citation. Always `file_citation`.",
+            "default": "file_citation",
+            "x-stainless-const": true
+          },
+          "file_id": {
+            "type": "string",
+            "description": "The ID of the file."
+          },
+          "index": {
+            "type": "integer",
+            "description": "The index of the file in the list of files."
+          },
+          "filename": {
+            "type": "string",
+            "description": "The filename of the file cited."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "file_id",
+          "index",
+          "filename"
+        ],
+        "title": "File citation",
+        "description": "A citation to a file."
+      },
+      "BetaInputMessage": {
+        "type": "object",
+        "title": "Input message",
+        "description": "A message input to the model with a role indicating instruction following\nhierarchy. Instructions given with the `developer` or `system` role take\nprecedence over instructions given with the `user` role.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the message input. Always set to `message`.\n",
+            "enum": [
+              "message"
+            ],
+            "x-stainless-const": true
+          },
+          "role": {
+            "type": "string",
+            "description": "The role of the message input. One of `user`, `system`, or `developer`.\n",
+            "enum": [
+              "user",
+              "system",
+              "developer"
+            ]
+          },
+          "status": {
+            "type": "string",
+            "description": "The status of item. One of `in_progress`, `completed`, or\n`incomplete`. Populated when items are returned via API.\n",
+            "enum": [
+              "in_progress",
+              "completed",
+              "incomplete"
+            ]
+          },
+          "content": {
+            "$ref": "#/components/schemas/BetaInputMessageContentList"
+          }
+        },
+        "required": [
+          "role",
+          "content"
+        ]
+      },
+      "BetaInputMessageContentList": {
+        "type": "array",
+        "title": "Input item content list",
+        "description": "A list of one or many input items to the model, containing different content \ntypes.\n",
+        "items": {
+          "$ref": "#/components/schemas/BetaInputContent"
+        }
+      },
+      "BetaInputContent": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/BetaInputTextContent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaInputImageContent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaInputFileContent"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "BetaEasyInputMessage": {
+        "type": "object",
+        "title": "Input message",
+        "description": "A message input to the model with a role indicating instruction following\nhierarchy. Instructions given with the `developer` or `system` role take\nprecedence over instructions given with the `user` role. Messages with the\n`assistant` role are presumed to have been generated by the model in previous\ninteractions.\n",
+        "properties": {
+          "role": {
+            "type": "string",
+            "description": "The role of the message input. One of `user`, `assistant`, `system`, or\n`developer`.\n",
+            "enum": [
+              "user",
+              "assistant",
+              "system",
+              "developer"
+            ]
+          },
+          "content": {
+            "description": "Text, image, or audio input to the model, used to generate a response.\nCan also contain previous assistant responses.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "title": "Text input",
+                "description": "A text input to the model.\n"
+              },
+              {
+                "$ref": "#/components/schemas/BetaInputMessageContentList"
+              }
+            ]
+          },
+          "phase": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaMessagePhase"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the message input. Always `message`.\n",
+            "enum": [
+              "message"
+            ],
+            "x-stainless-const": true
+          }
+        },
+        "required": [
+          "role",
+          "content"
+        ]
+      },
+      "BetaCompactResponseMethodPublicBody": {
+        "properties": {
+          "model": {
+            "$ref": "#/components/schemas/BetaModelIdsCompaction"
+          },
+          "input": {
+            "anyOf": [
+              {
+                "oneOf": [
+                  {
+                    "type": "string",
+                    "maxLength": 10485760,
+                    "description": "A text input to the model, equivalent to a text input with the `user` role."
+                  },
+                  {
+                    "items": {
+                      "$ref": "#/components/schemas/BetaInputItem"
+                    },
+                    "type": "array",
+                    "maxItems": 131072,
+                    "description": "A list of one or many input items to the model, containing different content types."
+                  }
+                ],
+                "description": "Text, image, or file inputs to the model, used to generate a response"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "previous_response_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](https://developers.openai.com/api/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`.",
+                "example": "resp_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "instructions": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "A system (or developer) message inserted into the model's context.\nWhen used along with `previous_response_id`, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "prompt_cache_key": {
+            "anyOf": [
+              {
+                "type": "string",
+                "maxLength": 64,
+                "description": "A key to use when reading from or writing to the prompt cache."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "prompt_cache_retention": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaPromptCacheRetentionEnum",
+                "description": "How long to retain a prompt cache entry created by this request.",
+                "deprecated": true
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "prompt_cache_options": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaPromptCacheOptionsParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "service_tier": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaServiceTierEnum",
+                "description": "Specifies the processing type used for serving the request.   - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.   - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.   - If set to '[flex](https://developers.openai.com/api/docs/guides/flex-processing)', then the request will be processed with the Flex Processing service tier.   - To opt-in to [Fast mode](https://developers.openai.com/api/docs/guides/fast-mode) at the request level, include the `service_tier=fast` or `service_tier=priority` parameter for Responses or Chat Completions. For models with a dedicated Fast tier, either value resolves to `service_tier=fast`; for other models, either value resolves to `service_tier=priority`.   - When not set, the default behavior is 'auto'.\n  When the `service_tier` parameter is set, the response body will include the `service_tier` value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "model"
+        ]
+      },
+      "BetaServiceTierEnum": {
+        "type": "string",
+        "enum": [
+          "auto",
+          "default",
+          "fast",
+          "flex",
+          "priority"
+        ]
+      },
+      "BetaPromptCacheOptionsParam": {
+        "properties": {
+          "ttl": {
+            "$ref": "#/components/schemas/BetaPromptCacheTTLEnum",
+            "description": "The minimum lifetime applied to every implicit and explicit cache breakpoint written by the request. Defaults to `30m`, which is currently the only supported value. The backend may retain cache entries for longer."
+          },
+          "mode": {
+            "$ref": "#/components/schemas/BetaPromptCacheModeEnum",
+            "description": "Controls whether OpenAI automatically creates an implicit cache breakpoint. Defaults to `implicit`. With `implicit`, OpenAI creates one implicit breakpoint and writes up to the latest three explicit breakpoints in the request. With `explicit`, OpenAI does not create an implicit breakpoint and writes up to the latest four explicit breakpoints. If there are no explicit breakpoints, the request does not use prompt caching."
+          }
+        },
+        "type": "object",
+        "required": [],
+        "title": "Prompt cache options",
+        "description": "Options for prompt caching. Supported for `gpt-5.6` and later models. By default, OpenAI automatically chooses one implicit cache breakpoint. You can add explicit breakpoints to content blocks with `prompt_cache_breakpoint`. Each request can write up to four breakpoints. For cache matching, OpenAI considers up to the latest 80 breakpoints in the conversation, without a content-block lookback limit. Set `mode` to `explicit` to disable the implicit breakpoint. The `ttl` defaults to `30m`, which is currently the only supported value. See the [prompt caching guide](https://developers.openai.com/api/docs/guides/prompt-caching) for current details."
+      },
+      "BetaPromptCacheModeEnum": {
+        "type": "string",
+        "enum": [
+          "implicit",
+          "explicit"
+        ]
+      },
+      "BetaPromptCacheTTLEnum": {
+        "type": "string",
+        "enum": [
+          "30m"
+        ]
+      },
+      "BetaPromptCacheRetentionEnum": {
+        "type": "string",
+        "enum": [
+          "in_memory",
+          "24h"
+        ]
+      },
+      "BetaModelIdsCompaction": {
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/BetaModelIdsResponses"
+          },
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "description": "Model ID used to generate the response, like `gpt-6-astra`. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the [model guide](https://developers.openai.com/api/docs/models) to browse and compare available models."
+      },
+      "BetaModelIdsResponses": {
+        "example": "gpt-6-astra",
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/BetaModelIdsShared"
+          },
+          {
+            "type": "string",
+            "title": "ResponsesOnlyModel",
+            "enum": [
+              "o1-pro",
+              "o1-pro-2025-03-19",
+              "o3-pro",
+              "o3-pro-2025-06-10",
+              "o3-deep-research",
+              "o3-deep-research-2025-06-26",
+              "o4-mini-deep-research",
+              "o4-mini-deep-research-2025-06-26",
+              "computer-use-preview",
+              "computer-use-preview-2025-03-11",
+              "gpt-5.5-pro",
+              "gpt-5.5-pro-2026-04-23",
+              "gpt-5-codex",
+              "gpt-5-pro",
+              "gpt-5-pro-2025-10-06",
+              "gpt-5.1-codex-max",
+              "gpt-daybreak-blue-latest",
+              "gpt-daybreak-red-latest",
+              "gpt-5.6-cyber"
+            ]
+          }
+        ]
+      },
+      "BetaModelIdsShared": {
+        "example": "gpt-6-astra",
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "string",
+            "enum": [
+              "gpt-6-astra",
+              "gpt-5.6-sol",
+              "gpt-5.6-terra",
+              "gpt-5.6-luna",
+              "gpt-5.5",
+              "gpt-5.5-2026-04-23",
+              "gpt-5.4",
+              "gpt-5.4-mini",
+              "gpt-5.4-nano",
+              "gpt-5.4-mini-2026-03-17",
+              "gpt-5.4-nano-2026-03-17",
+              "gpt-5.3-chat-latest",
+              "gpt-5.2",
+              "gpt-5.2-2025-12-11",
+              "gpt-5.2-chat-latest",
+              "gpt-5.2-pro",
+              "gpt-5.2-pro-2025-12-11",
+              "gpt-5.1",
+              "gpt-5.1-2025-11-13",
+              "gpt-5.1-codex",
+              "gpt-5.1-mini",
+              "gpt-5.1-chat-latest",
+              "gpt-5",
+              "gpt-5-mini",
+              "gpt-5-nano",
+              "gpt-5-2025-08-07",
+              "gpt-5-mini-2025-08-07",
+              "gpt-5-nano-2025-08-07",
+              "gpt-5-chat-latest",
+              "gpt-4.1",
+              "gpt-4.1-mini",
+              "gpt-4.1-nano",
+              "gpt-4.1-2025-04-14",
+              "gpt-4.1-mini-2025-04-14",
+              "gpt-4.1-nano-2025-04-14",
+              "o4-mini",
+              "o4-mini-2025-04-16",
+              "o3",
+              "o3-2025-04-16",
+              "o3-mini",
+              "o3-mini-2025-01-31",
+              "o1",
+              "o1-2024-12-17",
+              "o1-preview",
+              "o1-preview-2024-09-12",
+              "o1-mini",
+              "o1-mini-2024-09-12",
+              "gpt-4o",
+              "gpt-4o-2024-11-20",
+              "gpt-4o-2024-08-06",
+              "gpt-4o-2024-05-13",
+              "gpt-4o-audio-preview",
+              "gpt-4o-audio-preview-2024-10-01",
+              "gpt-4o-audio-preview-2024-12-17",
+              "gpt-4o-audio-preview-2025-06-03",
+              "gpt-4o-mini-audio-preview",
+              "gpt-4o-mini-audio-preview-2024-12-17",
+              "gpt-4o-search-preview",
+              "gpt-4o-mini-search-preview",
+              "gpt-4o-search-preview-2025-03-11",
+              "gpt-4o-mini-search-preview-2025-03-11",
+              "chatgpt-4o-latest",
+              "codex-mini-latest",
+              "gpt-4o-mini",
+              "gpt-4o-mini-2024-07-18",
+              "gpt-4-turbo",
+              "gpt-4-turbo-2024-04-09",
+              "gpt-4-0125-preview",
+              "gpt-4-turbo-preview",
+              "gpt-4-1106-preview",
+              "gpt-4-vision-preview",
+              "gpt-4",
+              "gpt-4-0314",
+              "gpt-4-0613",
+              "gpt-4-32k",
+              "gpt-4-32k-0314",
+              "gpt-4-32k-0613",
+              "gpt-3.5-turbo",
+              "gpt-3.5-turbo-16k",
+              "gpt-3.5-turbo-0301",
+              "gpt-3.5-turbo-0613",
+              "gpt-3.5-turbo-1106",
+              "gpt-3.5-turbo-0125",
+              "gpt-3.5-turbo-16k-0613"
+            ]
+          }
+        ]
+      },
+      "BetaError": {
+        "type": "object",
+        "properties": {
+          "code": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "message": {
+            "type": "string"
+          },
+          "param": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string"
+          },
+          "misalignment": {
+            "$ref": "#/components/schemas/BetaMisalignmentErrorDetailsResource"
+          }
+        },
+        "required": [
+          "type",
+          "message",
+          "param",
+          "code"
+        ]
+      },
+      "BetaMisalignmentErrorDetailsResource": {
+        "properties": {
+          "error_type": {
+            "$ref": "#/components/schemas/Beta_MisalignmentErrorType",
+            "description": "An optional classification; clients must accept additional values."
+          },
+          "detailed_explanation": {
+            "type": "string",
+            "description": "The public explanation for this block."
+          },
+          "steer": {
+            "$ref": "#/components/schemas/Beta_MisalignmentSteer",
+            "description": "An optional public continuation instruction."
+          }
+        },
+        "type": "object",
+        "required": []
+      },
+      "Beta_MisalignmentSteer": {
+        "properties": {
+          "message": {
+            "type": "string",
+            "description": "The public continuation instruction."
+          }
+        },
+        "type": "object",
+        "required": [
+          "message"
+        ]
+      },
+      "Beta_MisalignmentErrorType": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "string",
+            "enum": [
+              "potentially_unintended_data_transfer",
+              "potentially_unintended_data_access",
+              "potentially_unintended_destructive_activity",
+              "other"
+            ]
+          }
+        ]
+      },
+      "BetaResponseItemList": {
+        "type": "object",
+        "description": "A list of Response items.",
+        "properties": {
+          "object": {
+            "type": "string",
+            "description": "The type of object returned, must be `list`.",
+            "enum": [
+              "list"
+            ],
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "array",
+            "description": "A list of items used to generate this response.",
+            "items": {
+              "$ref": "#/components/schemas/BetaItemResource"
+            }
+          },
+          "has_more": {
+            "type": "boolean",
+            "description": "Whether there are more items available."
+          },
+          "first_id": {
+            "type": "string",
+            "description": "The ID of the first item in the list."
+          },
+          "last_id": {
+            "type": "string",
+            "description": "The ID of the last item in the list."
+          }
+        },
+        "required": [
+          "object",
+          "data",
+          "has_more",
+          "first_id",
+          "last_id"
+        ],
+        "x-oaiMeta": {
+          "name": "The input item list",
+          "group": "responses",
+          "example": "{\n  \"object\": \"list\",\n  \"data\": [\n    {\n      \"id\": \"msg_abc123\",\n      \"type\": \"message\",\n      \"role\": \"user\",\n      \"content\": [\n        {\n          \"type\": \"input_text\",\n          \"text\": \"Tell me a three sentence bedtime story about a unicorn.\"\n        }\n      ]\n    }\n  ],\n  \"first_id\": \"msg_abc123\",\n  \"last_id\": \"msg_abc123\",\n  \"has_more\": false\n}\n"
+        }
+      },
+      "BetaItemResource": {
+        "description": "Content item used to generate a response.\n",
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/BetaInputMessageResource"
+          },
+          {
+            "$ref": "#/components/schemas/BetaOutputMessage"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFileSearchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaComputerToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaComputerToolCallOutputResource"
+          },
+          {
+            "$ref": "#/components/schemas/BetaWebSearchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFunctionToolCallResource"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFunctionToolCallOutputResource"
+          },
+          {
+            "$ref": "#/components/schemas/BetaAgentMessage"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMultiAgentCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMultiAgentCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/BetaToolSearchCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaToolSearchOutput"
+          },
+          {
+            "$ref": "#/components/schemas/BetaAdditionalTools"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseConfigurationUpdate"
+          },
+          {
+            "$ref": "#/components/schemas/BetaReasoningItem"
+          },
+          {
+            "$ref": "#/components/schemas/BetaProgram"
+          },
+          {
+            "$ref": "#/components/schemas/BetaProgramOutput"
+          },
+          {
+            "$ref": "#/components/schemas/BetaCompactionBody"
+          },
+          {
+            "$ref": "#/components/schemas/BetaImageGenToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaCodeInterpreterToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaLocalShellToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaLocalShellToolCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFunctionShellCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFunctionShellCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/BetaApplyPatchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaApplyPatchToolCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMCPListTools"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMCPApprovalRequest"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMCPApprovalResponseResource"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMCPToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaCustomToolCallResource"
+          },
+          {
+            "$ref": "#/components/schemas/BetaCustomToolCallOutputResource"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "BetaCustomToolCallOutputResource": {
+        "title": "ResponseCustomToolCallOutputItem",
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/BetaCustomToolCallOutput"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the custom tool call output item.\n"
+              },
+              "status": {
+                "description": "The status of the item. One of `in_progress`, `completed`, or\n`incomplete`. Populated when items are returned via API.\n",
+                "$ref": "#/components/schemas/BetaFunctionCallOutputStatusEnum"
+              },
+              "created_by": {
+                "type": "string",
+                "description": "The identifier of the actor that created the item.\n"
+              }
+            },
+            "required": [
+              "id",
+              "status"
+            ]
+          }
+        ]
+      },
+      "BetaFunctionCallOutputStatusEnum": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed",
+          "incomplete"
+        ]
+      },
+      "BetaCustomToolCallResource": {
+        "title": "ResponseCustomToolCallItem",
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/BetaCustomToolCall"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the custom tool call item.\n"
+              },
+              "status": {
+                "description": "The status of the item. One of `in_progress`, `completed`, or\n`incomplete`. Populated when items are returned via API.\n",
+                "$ref": "#/components/schemas/BetaFunctionCallStatus"
+              },
+              "created_by": {
+                "type": "string",
+                "description": "The identifier of the actor that created the item.\n"
+              }
+            },
+            "required": [
+              "id",
+              "status"
+            ]
+          }
+        ]
+      },
+      "BetaFunctionCallStatus": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed",
+          "incomplete"
+        ]
+      },
+      "BetaMCPApprovalResponseResource": {
+        "type": "object",
+        "title": "MCP approval response",
+        "description": "A response to an MCP approval request.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "mcp_approval_response"
+            ],
+            "description": "The type of the item. Always `mcp_approval_response`.\n",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the approval response\n"
+          },
+          "approval_request_id": {
+            "type": "string",
+            "description": "The ID of the approval request being answered.\n"
+          },
+          "approve": {
+            "type": "boolean",
+            "description": "Whether the request was approved.\n"
+          },
+          "reason": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Optional reason for the decision.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "id",
+          "request_id",
+          "approve",
+          "approval_request_id"
+        ]
+      },
+      "BetaApplyPatchToolCallOutput": {
+        "properties": {
+          "agent": {
+            "$ref": "#/components/schemas/BetaAgentTag",
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "apply_patch_call_output"
+            ],
+            "description": "The type of the item. Always `apply_patch_call_output`.",
+            "default": "apply_patch_call_output",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the apply patch tool call output. Populated when this item is returned via API."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The unique ID of the apply patch tool call generated by the model."
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaToolCallCaller",
+                "description": "The execution context that produced this tool call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "$ref": "#/components/schemas/BetaApplyPatchCallOutputStatus",
+            "description": "The status of the apply patch tool call output. One of `completed` or `failed`."
+          },
+          "output": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "Optional textual output returned by the apply patch tool."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "created_by": {
+            "type": "string",
+            "description": "The ID of the entity that created this tool call output."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "status"
+        ],
+        "title": "Apply patch tool call output",
+        "description": "The output emitted by an apply patch tool call."
+      },
+      "BetaApplyPatchCallOutputStatus": {
+        "type": "string",
+        "enum": [
+          "completed",
+          "failed"
+        ]
+      },
+      "BetaApplyPatchToolCall": {
+        "properties": {
+          "agent": {
+            "$ref": "#/components/schemas/BetaAgentTag",
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "apply_patch_call"
+            ],
+            "description": "The type of the item. Always `apply_patch_call`.",
+            "default": "apply_patch_call",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the apply patch tool call. Populated when this item is returned via API."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The unique ID of the apply patch tool call generated by the model."
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaToolCallCaller",
+                "description": "The execution context that produced this tool call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "$ref": "#/components/schemas/BetaApplyPatchCallStatus",
+            "description": "The status of the apply patch tool call. One of `in_progress` or `completed`."
+          },
+          "operation": {
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/BetaApplyPatchCreateFileOperation"
+              },
+              {
+                "$ref": "#/components/schemas/BetaApplyPatchDeleteFileOperation"
+              },
+              {
+                "$ref": "#/components/schemas/BetaApplyPatchUpdateFileOperation"
+              }
+            ],
+            "title": "Apply patch operation",
+            "description": "One of the create_file, delete_file, or update_file operations applied via apply_patch.",
+            "discriminator": {
+              "propertyName": "type"
+            }
+          },
+          "created_by": {
+            "type": "string",
+            "description": "The ID of the entity that created this tool call."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "status",
+          "operation"
+        ],
+        "title": "Apply patch tool call",
+        "description": "A tool call that applies file diffs by creating, deleting, or updating files."
+      },
+      "BetaApplyPatchUpdateFileOperation": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "update_file"
+            ],
+            "description": "Update an existing file with the provided diff.",
+            "default": "update_file",
+            "x-stainless-const": true
+          },
+          "path": {
+            "type": "string",
+            "description": "Path of the file to update."
+          },
+          "diff": {
+            "type": "string",
+            "description": "Diff to apply."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "path",
+          "diff"
+        ],
+        "title": "Apply patch update file operation",
+        "description": "Instruction describing how to update a file via the apply_patch tool."
+      },
+      "BetaApplyPatchDeleteFileOperation": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "delete_file"
+            ],
+            "description": "Delete the specified file.",
+            "default": "delete_file",
+            "x-stainless-const": true
+          },
+          "path": {
+            "type": "string",
+            "description": "Path of the file to delete."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "path"
+        ],
+        "title": "Apply patch delete file operation",
+        "description": "Instruction describing how to delete a file via the apply_patch tool."
+      },
+      "BetaApplyPatchCreateFileOperation": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "create_file"
+            ],
+            "description": "Create a new file with the provided diff.",
+            "default": "create_file",
+            "x-stainless-const": true
+          },
+          "path": {
+            "type": "string",
+            "description": "Path of the file to create."
+          },
+          "diff": {
+            "type": "string",
+            "description": "Diff to apply."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "path",
+          "diff"
+        ],
+        "title": "Apply patch create file operation",
+        "description": "Instruction describing how to create a file via the apply_patch tool."
+      },
+      "BetaApplyPatchCallStatus": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed"
+        ]
+      },
+      "BetaFunctionShellCallOutput": {
+        "properties": {
+          "agent": {
+            "$ref": "#/components/schemas/BetaAgentTag",
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "shell_call_output"
+            ],
+            "description": "The type of the shell call output. Always `shell_call_output`.",
+            "default": "shell_call_output",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the shell call output. Populated when this item is returned via API."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The unique ID of the shell tool call generated by the model."
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaToolCallCaller",
+                "description": "The execution context that produced this tool call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "$ref": "#/components/schemas/BetaFunctionShellCallOutputStatusEnum",
+            "description": "The status of the shell call output. One of `in_progress`, `completed`, or `incomplete`."
+          },
+          "output": {
+            "items": {
+              "$ref": "#/components/schemas/BetaFunctionShellCallOutputContent"
+            },
+            "type": "array",
+            "description": "An array of shell call output contents"
+          },
+          "max_output_length": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "created_by": {
+            "type": "string",
+            "description": "The identifier of the actor that created the item."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "status",
+          "output",
+          "max_output_length"
+        ],
+        "title": "Shell call output",
+        "description": "The output of a shell tool call that was emitted."
+      },
+      "BetaFunctionShellCallOutputContent": {
+        "properties": {
+          "stdout": {
+            "type": "string",
+            "description": "The standard output that was captured."
+          },
+          "stderr": {
+            "type": "string",
+            "description": "The standard error output that was captured."
+          },
+          "outcome": {
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/BetaFunctionShellCallOutputTimeoutOutcome"
+              },
+              {
+                "$ref": "#/components/schemas/BetaFunctionShellCallOutputExitOutcome"
+              }
+            ],
+            "title": "Shell call outcome",
+            "description": "Represents either an exit outcome (with an exit code) or a timeout outcome for a shell call output chunk.",
+            "discriminator": {
+              "propertyName": "type"
+            }
+          },
+          "created_by": {
+            "type": "string",
+            "description": "The identifier of the actor that created the item."
+          }
+        },
+        "type": "object",
+        "required": [
+          "stdout",
+          "stderr",
+          "outcome"
+        ],
+        "title": "Shell call output content",
+        "description": "The content of a shell tool call output that was emitted."
+      },
+      "BetaFunctionShellCallOutputExitOutcome": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "exit"
+            ],
+            "description": "The outcome type. Always `exit`.",
+            "default": "exit",
+            "x-stainless-const": true
+          },
+          "exit_code": {
+            "type": "integer",
+            "description": "Exit code from the shell process."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "exit_code"
+        ],
+        "title": "Shell call exit outcome",
+        "description": "Indicates that the shell commands finished and returned an exit code."
+      },
+      "BetaFunctionShellCallOutputTimeoutOutcome": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "timeout"
+            ],
+            "description": "The outcome type. Always `timeout`.",
+            "default": "timeout",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Shell call timeout outcome",
+        "description": "Indicates that the shell call exceeded its configured time limit."
+      },
+      "BetaFunctionShellCallOutputStatusEnum": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed",
+          "incomplete"
+        ]
+      },
+      "BetaFunctionShellCall": {
+        "properties": {
+          "agent": {
+            "$ref": "#/components/schemas/BetaAgentTag",
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "shell_call"
+            ],
+            "description": "The type of the item. Always `shell_call`.",
+            "default": "shell_call",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the shell tool call. Populated when this item is returned via API."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The unique ID of the shell tool call generated by the model."
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaToolCallCaller",
+                "description": "The execution context that produced this tool call."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "action": {
+            "$ref": "#/components/schemas/BetaFunctionShellAction",
+            "description": "The shell commands and limits that describe how to run the tool call."
+          },
+          "status": {
+            "$ref": "#/components/schemas/BetaFunctionShellCallStatus",
+            "description": "The status of the shell call. One of `in_progress`, `completed`, or `incomplete`."
+          },
+          "environment": {
+            "anyOf": [
+              {
+                "oneOf": [
+                  {
+                    "$ref": "#/components/schemas/BetaLocalEnvironmentResource"
+                  },
+                  {
+                    "$ref": "#/components/schemas/BetaContainerReferenceResource"
+                  }
+                ],
+                "discriminator": {
+                  "propertyName": "type"
+                }
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "created_by": {
+            "type": "string",
+            "description": "The ID of the entity that created this tool call."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "action",
+          "status",
+          "environment"
+        ],
+        "title": "Shell tool call",
+        "description": "A tool call that executes one or more shell commands in a managed environment."
+      },
+      "BetaContainerReferenceResource": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "container_reference"
+            ],
+            "description": "The environment type. Always `container_reference`.",
+            "default": "container_reference",
+            "x-stainless-const": true
+          },
+          "container_id": {
+            "type": "string"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "container_id"
+        ],
+        "title": "Container Reference",
+        "description": "Represents a container created with /v1/containers."
+      },
+      "BetaLocalEnvironmentResource": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "local"
+            ],
+            "description": "The environment type. Always `local`.",
+            "default": "local",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ],
+        "title": "Local Environment",
+        "description": "Represents the use of a local environment to perform shell actions."
+      },
+      "BetaFunctionShellCallStatus": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed",
+          "incomplete"
+        ]
+      },
+      "BetaFunctionShellAction": {
+        "properties": {
+          "commands": {
+            "items": {
+              "type": "string",
+              "description": "A list of commands to run."
+            },
+            "type": "array"
+          },
+          "timeout_ms": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "Optional timeout in milliseconds for the commands."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "max_output_length": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "description": "Optional maximum number of characters to return from each command."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "commands",
+          "timeout_ms",
+          "max_output_length"
+        ],
+        "title": "Shell exec action",
+        "description": "Execute a shell command."
+      },
+      "BetaCompactionBody": {
+        "properties": {
+          "agent": {
+            "$ref": "#/components/schemas/BetaAgentTag",
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "compaction"
+            ],
+            "description": "The type of the item. Always `compaction`.",
+            "default": "compaction",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the compaction item."
+          },
+          "encrypted_content": {
+            "type": "string",
+            "description": "The encrypted content that was produced by compaction."
+          },
+          "created_by": {
+            "type": "string",
+            "description": "The identifier of the actor that created the item."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "encrypted_content"
+        ],
+        "title": "Compaction item",
+        "description": "A compaction item generated by the [`v1/responses/compact` API](https://developers.openai.com/api/reference/resources/responses/methods/compact)."
+      },
+      "BetaProgramOutput": {
+        "properties": {
+          "agent": {
+            "$ref": "#/components/schemas/BetaAgentTag",
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "program_output"
+            ],
+            "description": "The type of the item. Always `program_output`.",
+            "default": "program_output",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the program output item."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The call ID of the program item."
+          },
+          "result": {
+            "type": "string",
+            "description": "The result produced by the program item."
+          },
+          "status": {
+            "$ref": "#/components/schemas/BetaProgramOutputStatus",
+            "description": "The terminal status of the program output item."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "result",
+          "status"
+        ]
+      },
+      "BetaProgramOutputStatus": {
+        "type": "string",
+        "enum": [
+          "completed",
+          "incomplete"
+        ]
+      },
+      "BetaProgram": {
+        "properties": {
+          "agent": {
+            "$ref": "#/components/schemas/BetaAgentTag",
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "program"
+            ],
+            "description": "The type of the item. Always `program`.",
+            "default": "program",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the program item."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The stable call ID of the program item."
+          },
+          "code": {
+            "type": "string",
+            "description": "The JavaScript source executed by programmatic tool calling."
+          },
+          "fingerprint": {
+            "type": "string",
+            "description": "Opaque program replay fingerprint that must be round-tripped."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "code",
+          "fingerprint"
+        ]
+      },
+      "BetaResponseConfigurationUpdate": {
+        "type": "object",
+        "description": "A configuration update that applies to subsequent responses until it is\nreplaced by another configuration update.\n",
+        "properties": {
+          "agent": {
+            "$ref": "#/components/schemas/BetaAgentTag",
+            "description": "The agent that produced this item."
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the configuration update item.",
+            "example": "cnfu_123"
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "configuration_update"
+            ],
+            "description": "The item type. Always `configuration_update`.",
+            "default": "configuration_update",
+            "x-stainless-const": true
+          },
+          "reasoning": {
+            "type": "object",
+            "description": "The reasoning configuration applied by this update.",
+            "properties": {
+              "effort": {
+                "$ref": "#/components/schemas/BetaReasoningEffort",
+                "description": "The reasoning effort used for subsequent responses until another\nconfiguration update replaces it.\n"
+              }
+            }
+          }
+        },
+        "required": [
+          "id",
+          "type"
+        ]
+      },
+      "BetaAdditionalTools": {
+        "properties": {
+          "agent": {
+            "$ref": "#/components/schemas/BetaAgentTag",
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "additional_tools"
+            ],
+            "description": "The type of the item. Always `additional_tools`.",
+            "default": "additional_tools",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the additional tools item."
+          },
+          "role": {
+            "$ref": "#/components/schemas/BetaMessageRole",
+            "description": "The role that provided the additional tools."
+          },
+          "tools": {
+            "items": {
+              "$ref": "#/components/schemas/BetaTool"
+            },
+            "type": "array",
+            "description": "The additional tool definitions made available at this item."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "role",
+          "tools"
+        ]
+      },
+      "BetaMessageRole": {
+        "type": "string",
+        "enum": [
+          "unknown",
+          "user",
+          "assistant",
+          "system",
+          "critic",
+          "discriminator",
+          "developer",
+          "tool"
+        ]
+      },
+      "BetaToolSearchOutput": {
+        "properties": {
+          "agent": {
+            "$ref": "#/components/schemas/BetaAgentTag",
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "tool_search_output"
+            ],
+            "description": "The type of the item. Always `tool_search_output`.",
+            "default": "tool_search_output",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the tool search output item."
+          },
+          "call_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the tool search call generated by the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "execution": {
+            "$ref": "#/components/schemas/BetaToolSearchExecutionType",
+            "description": "Whether tool search was executed by the server or by the client."
+          },
+          "tools": {
+            "items": {
+              "$ref": "#/components/schemas/BetaTool"
+            },
+            "type": "array",
+            "description": "The loaded tool definitions returned by tool search."
+          },
+          "status": {
+            "$ref": "#/components/schemas/BetaFunctionCallOutputStatusEnum",
+            "description": "The status of the tool search output item that was recorded."
+          },
+          "created_by": {
+            "type": "string",
+            "description": "The identifier of the actor that created the item."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "execution",
+          "tools",
+          "status"
+        ]
+      },
+      "BetaToolSearchCall": {
+        "properties": {
+          "agent": {
+            "$ref": "#/components/schemas/BetaAgentTag",
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "tool_search_call"
+            ],
+            "description": "The type of the item. Always `tool_search_call`.",
+            "default": "tool_search_call",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the tool search call item."
+          },
+          "call_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the tool search call generated by the model."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "execution": {
+            "$ref": "#/components/schemas/BetaToolSearchExecutionType",
+            "description": "Whether tool search was executed by the server or by the client."
+          },
+          "arguments": {
+            "description": "Arguments used for the tool search call."
+          },
+          "status": {
+            "$ref": "#/components/schemas/BetaFunctionCallStatus",
+            "description": "The status of the tool search call item that was recorded."
+          },
+          "created_by": {
+            "type": "string",
+            "description": "The identifier of the actor that created the item."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "execution",
+          "arguments",
+          "status"
+        ]
+      },
+      "BetaMultiAgentCallOutput": {
+        "properties": {
+          "agent": {
+            "$ref": "#/components/schemas/BetaAgentTag",
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "multi_agent_call_output"
+            ],
+            "description": "The type of the multi-agent result. Always `multi_agent_call_output`.",
+            "default": "multi_agent_call_output",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the multi-agent call output item."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The unique ID of the multi-agent call."
+          },
+          "action": {
+            "$ref": "#/components/schemas/BetaMultiAgentAction",
+            "description": "The multi-agent action that produced this result."
+          },
+          "output": {
+            "items": {
+              "$ref": "#/components/schemas/BetaOutputTextContent"
+            },
+            "type": "array",
+            "description": "Text output returned by the multi-agent action."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "action",
+          "output"
+        ],
+        "x-oai-beta": "responses_multi_agent=v1"
+      },
+      "BetaMultiAgentAction": {
+        "type": "string",
+        "enum": [
+          "spawn_agent",
+          "interrupt_agent",
+          "list_agents",
+          "send_message",
+          "followup_task",
+          "wait_agent"
+        ]
+      },
+      "BetaMultiAgentCall": {
+        "properties": {
+          "agent": {
+            "$ref": "#/components/schemas/BetaAgentTag",
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "multi_agent_call"
+            ],
+            "description": "The type of the multi-agent call. Always `multi_agent_call`.",
+            "default": "multi_agent_call",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the multi-agent call item."
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The unique ID linking this call to its output."
+          },
+          "action": {
+            "$ref": "#/components/schemas/BetaMultiAgentAction",
+            "description": "The multi-agent action to execute."
+          },
+          "arguments": {
+            "type": "string",
+            "description": "The JSON string of arguments generated for the action."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "call_id",
+          "action",
+          "arguments"
+        ],
+        "x-oai-beta": "responses_multi_agent=v1"
+      },
+      "BetaAgentMessage": {
+        "properties": {
+          "agent": {
+            "$ref": "#/components/schemas/BetaAgentTag",
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "agent_message"
+            ],
+            "description": "The type of the item. Always `agent_message`.",
+            "default": "agent_message",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the agent message."
+          },
+          "author": {
+            "type": "string",
+            "description": "The sending agent identity."
+          },
+          "recipient": {
+            "type": "string",
+            "description": "The destination agent identity."
+          },
+          "content": {
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/BetaInputTextContent"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaOutputTextContent"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaTextContent"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaSummaryTextContent"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaReasoningTextContent"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaRefusalContent"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaInputImageContent"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaComputerScreenshotContent"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaInputFileContent"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaEncryptedContent"
+                }
+              ],
+              "description": "A content part that makes up an input or output item.",
+              "discriminator": {
+                "propertyName": "type"
+              }
+            },
+            "type": "array",
+            "description": "Encrypted content sent between agents."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "author",
+          "recipient",
+          "content"
+        ],
+        "x-oai-beta": "responses_multi_agent=v1"
+      },
+      "BetaEncryptedContent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "encrypted_content"
+            ],
+            "description": "The type of the input item. Always `encrypted_content`.",
+            "default": "encrypted_content",
+            "x-stainless-const": true
+          },
+          "encrypted_content": {
+            "type": "string",
+            "description": "Opaque encrypted content."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "encrypted_content"
+        ],
+        "title": "Encrypted content",
+        "description": "Opaque encrypted content that Responses API decrypts inside trusted model execution.",
+        "x-oai-beta": "responses_multi_agent=v1"
+      },
+      "BetaComputerScreenshotContent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "computer_screenshot"
+            ],
+            "description": "Specifies the event type. For a computer screenshot, this property is always set to `computer_screenshot`.",
+            "default": "computer_screenshot",
+            "x-stainless-const": true
+          },
+          "image_url": {
+            "anyOf": [
+              {
+                "type": "string",
+                "format": "uri",
+                "description": "The URL of the screenshot image."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "file_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The identifier of an uploaded file that contains the screenshot."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "detail": {
+            "$ref": "#/components/schemas/BetaImageDetail",
+            "description": "The detail level of the screenshot image to be sent to the model. One of `high`, `low`, `auto`, or `original`. Defaults to `auto`."
+          },
+          "prompt_cache_breakpoint": {
+            "$ref": "#/components/schemas/BetaPromptCacheBreakpointConfig"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "image_url",
+          "file_id",
+          "detail"
+        ],
+        "title": "Computer screenshot",
+        "description": "A screenshot of a computer."
+      },
+      "BetaTextContent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "text"
+            ],
+            "default": "text",
+            "x-stainless-const": true
+          },
+          "text": {
+            "type": "string"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "text"
+        ],
+        "title": "Text Content",
+        "description": "A text content."
+      },
+      "BetaFunctionToolCallOutputResource": {
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/BetaFunctionToolCallOutput"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the function call tool output.\n"
+              },
+              "status": {
+                "description": "The status of the item. One of `in_progress`, `completed`, or\n`incomplete`. Populated when items are returned via API.\n",
+                "$ref": "#/components/schemas/BetaFunctionCallOutputStatusEnum"
+              },
+              "created_by": {
+                "type": "string",
+                "description": "The identifier of the actor that created the item.\n"
+              }
+            },
+            "required": [
+              "id",
+              "status"
+            ]
+          }
+        ]
+      },
+      "BetaFunctionToolCallOutput": {
+        "type": "object",
+        "title": "Function tool call output",
+        "description": "The output of a function tool call.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that produced this item."
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the function tool call output. Populated when this item\nis returned via API.\n"
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "function_call_output"
+            ],
+            "description": "The type of the function tool call output. Always `function_call_output`.\n",
+            "x-stainless-const": true
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The unique ID of the function tool call generated by the model.\n"
+          },
+          "name": {
+            "type": "string",
+            "description": "The name of the tool that produced the output.\n"
+          },
+          "namespace": {
+            "type": "string",
+            "description": "The namespace of the tool that produced the output.\n"
+          },
+          "caller": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaToolCallCallerParam"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "output": {
+            "description": "The output from the function call generated by your code.\nCan be a string or an list of output content.\n",
+            "oneOf": [
+              {
+                "type": "string",
+                "description": "A string of the output of the function call.\n",
+                "title": "string output"
+              },
+              {
+                "type": "array",
+                "items": {
+                  "$ref": "#/components/schemas/BetaFunctionAndCustomToolCallOutput"
+                },
+                "title": "output content list",
+                "description": "Text, image, or file output of the function call.\n"
+              }
+            ]
+          },
+          "status": {
+            "type": "string",
+            "description": "The status of the item. One of `in_progress`, `completed`, or\n`incomplete`. Populated when items are returned via API.\n",
+            "enum": [
+              "in_progress",
+              "completed",
+              "incomplete"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "output"
+        ]
+      },
+      "BetaFunctionToolCallResource": {
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/BetaFunctionToolCall"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the function tool call.\n"
+              },
+              "status": {
+                "description": "The status of the item. One of `in_progress`, `completed`, or\n`incomplete`. Populated when items are returned via API.\n",
+                "$ref": "#/components/schemas/BetaFunctionCallStatus"
+              },
+              "created_by": {
+                "type": "string",
+                "description": "The identifier of the actor that created the item.\n"
+              }
+            },
+            "required": [
+              "id",
+              "status"
+            ]
+          }
+        ]
+      },
+      "BetaComputerToolCallOutputResource": {
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/BetaComputerToolCallOutput"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the computer call tool output.\n"
+              },
+              "status": {
+                "description": "The status of the message input. One of `in_progress`, `completed`, or\n`incomplete`. Populated when input items are returned via API.\n",
+                "$ref": "#/components/schemas/BetaComputerCallOutputStatus"
+              },
+              "created_by": {
+                "type": "string",
+                "description": "The identifier of the actor that created the item.\n"
+              }
+            },
+            "required": [
+              "id",
+              "status"
+            ]
+          }
+        ]
+      },
+      "BetaComputerCallOutputStatus": {
+        "type": "string",
+        "enum": [
+          "completed",
+          "incomplete",
+          "failed"
+        ]
+      },
+      "BetaComputerToolCallOutput": {
+        "type": "object",
+        "title": "Computer tool call output",
+        "description": "The output of a computer tool call.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the computer tool call output. Always `computer_call_output`.\n",
+            "enum": [
+              "computer_call_output"
+            ],
+            "default": "computer_call_output",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The ID of the computer tool call output.\n"
+          },
+          "call_id": {
+            "type": "string",
+            "description": "The ID of the computer tool call that produced the output.\n"
+          },
+          "acknowledged_safety_checks": {
+            "type": "array",
+            "description": "The safety checks reported by the API that have been acknowledged by the\ndeveloper.\n",
+            "items": {
+              "$ref": "#/components/schemas/BetaComputerCallSafetyCheckParam"
+            }
+          },
+          "output": {
+            "$ref": "#/components/schemas/BetaComputerScreenshotImage"
+          },
+          "status": {
+            "type": "string",
+            "description": "The status of the message input. One of `in_progress`, `completed`, or\n`incomplete`. Populated when input items are returned via API.\n",
+            "enum": [
+              "in_progress",
+              "completed",
+              "incomplete"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "call_id",
+          "output"
+        ]
+      },
+      "BetaInputMessageResource": {
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/BetaInputMessage"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique ID of the message input.\n"
+              }
+            },
+            "required": [
+              "id",
+              "type"
+            ]
+          }
+        ]
+      },
+      "BetaCompactResource": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique identifier for the compacted response."
+          },
+          "object": {
+            "type": "string",
+            "enum": [
+              "response.compaction"
+            ],
+            "description": "The object type. Always `response.compaction`.",
+            "default": "response.compaction",
+            "x-stainless-const": true
+          },
+          "output": {
+            "items": {
+              "$ref": "#/components/schemas/BetaItemField"
+            },
+            "type": "array",
+            "description": "The compacted list of output items."
+          },
+          "created_at": {
+            "type": "integer",
+            "format": "unixtime",
+            "description": "Unix timestamp (in seconds) when the compacted conversation was created."
+          },
+          "usage": {
+            "$ref": "#/components/schemas/BetaResponseUsage",
+            "description": "Token accounting for the compaction pass, including cached, reasoning, and total tokens."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "object",
+          "output",
+          "created_at",
+          "usage"
+        ],
+        "title": "The compacted response object",
+        "example": {
+          "id": "resp_001",
+          "object": "response.compaction",
+          "output": [
+            {
+              "type": "message",
+              "role": "user",
+              "content": [
+                {
+                  "type": "input_text",
+                  "text": "Summarize our launch checklist from last week."
+                }
+              ]
+            },
+            {
+              "type": "message",
+              "role": "user",
+              "content": [
+                {
+                  "type": "input_text",
+                  "text": "You are performing a CONTEXT CHECKPOINT COMPACTION..."
+                }
+              ]
+            },
+            {
+              "type": "compaction",
+              "id": "cmp_001",
+              "encrypted_content": "encrypted-summary"
+            }
+          ],
+          "created_at": 1731459200,
+          "usage": {
+            "input_tokens": 42897,
+            "output_tokens": 12000,
+            "total_tokens": 54912
+          }
+        }
+      },
+      "BetaResponseUsage": {
+        "type": "object",
+        "description": "Represents token usage details including input tokens, output tokens,\na breakdown of output tokens, and the total tokens used.\n",
+        "properties": {
+          "input_tokens": {
+            "type": "integer",
+            "description": "The number of input tokens."
+          },
+          "input_tokens_details": {
+            "type": "object",
+            "description": "A detailed breakdown of the input tokens.",
+            "properties": {
+              "cached_tokens": {
+                "type": "integer",
+                "description": "The number of tokens that were retrieved from the cache.\n[More on prompt caching](https://developers.openai.com/api/docs/guides/prompt-caching).\n"
+              },
+              "cache_write_tokens": {
+                "type": "integer",
+                "description": "The number of input tokens that were written to the cache."
+              }
+            },
+            "required": [
+              "cached_tokens",
+              "cache_write_tokens"
+            ]
+          },
+          "output_tokens": {
+            "type": "integer",
+            "description": "The number of output tokens."
+          },
+          "output_tokens_details": {
+            "type": "object",
+            "description": "A detailed breakdown of the output tokens.",
+            "properties": {
+              "reasoning_tokens": {
+                "type": "integer",
+                "description": "The number of reasoning tokens."
+              }
+            },
+            "required": [
+              "reasoning_tokens"
+            ]
+          },
+          "total_tokens": {
+            "type": "integer",
+            "description": "The total number of tokens used."
+          }
+        },
+        "required": [
+          "input_tokens",
+          "input_tokens_details",
+          "output_tokens",
+          "output_tokens_details",
+          "total_tokens"
+        ]
+      },
+      "BetaItemField": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/BetaMessage"
+          },
+          {
+            "$ref": "#/components/schemas/BetaProgram"
+          },
+          {
+            "$ref": "#/components/schemas/BetaProgramOutput"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFunctionToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMultiAgentCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMultiAgentCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/BetaToolSearchCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaToolSearchOutput"
+          },
+          {
+            "$ref": "#/components/schemas/BetaAdditionalTools"
+          },
+          {
+            "$ref": "#/components/schemas/BetaAgentMessage"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFunctionToolCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFileSearchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaWebSearchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaImageGenToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaComputerToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaComputerToolCallOutputResource"
+          },
+          {
+            "$ref": "#/components/schemas/BetaReasoningItem"
+          },
+          {
+            "$ref": "#/components/schemas/BetaCompactionBody"
+          },
+          {
+            "$ref": "#/components/schemas/BetaCodeInterpreterToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaLocalShellToolCall",
+            "deprecated": true
+          },
+          {
+            "$ref": "#/components/schemas/BetaLocalShellToolCallOutput",
+            "deprecated": true
+          },
+          {
+            "$ref": "#/components/schemas/BetaFunctionShellCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFunctionShellCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/BetaApplyPatchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaApplyPatchToolCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMCPListTools"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMCPApprovalRequest"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMCPApprovalResponseResource"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMCPToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaCustomToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaCustomToolCallOutput"
+          }
+        ],
+        "description": "An item representing a message, tool call, tool output, reasoning, or other response element.",
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "BetaMessage": {
+        "properties": {
+          "agent": {
+            "$ref": "#/components/schemas/BetaAgentTag",
+            "description": "The agent that produced this item."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "message"
+            ],
+            "description": "The type of the message. Always set to `message`.",
+            "default": "message",
+            "x-stainless-const": true
+          },
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the message."
+          },
+          "status": {
+            "$ref": "#/components/schemas/BetaMessageStatus",
+            "description": "The status of item. One of `in_progress`, `completed`, or `incomplete`. Populated when items are returned via API."
+          },
+          "role": {
+            "$ref": "#/components/schemas/BetaMessageRole",
+            "description": "The role of the message. One of `unknown`, `user`, `assistant`, `system`, `critic`, `discriminator`, `developer`, or `tool`."
+          },
+          "content": {
+            "items": {
+              "oneOf": [
+                {
+                  "$ref": "#/components/schemas/BetaInputTextContent"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaOutputTextContent"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaTextContent"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaSummaryTextContent"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaReasoningTextContent"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaRefusalContent"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaInputImageContent"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaComputerScreenshotContent"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaInputFileContent"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaEncryptedContent"
+                }
+              ],
+              "description": "A content part that makes up an input or output item.",
+              "discriminator": {
+                "propertyName": "type"
+              }
+            },
+            "type": "array",
+            "description": "The content of the message"
+          },
+          "phase": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaMessagePhase-2",
+                "description": "Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "id",
+          "status",
+          "role",
+          "content"
+        ],
+        "title": "Message",
+        "description": "A message to or from the model."
+      },
+      "BetaMessagePhase-2": {
+        "type": "string",
+        "enum": [
+          "commentary",
+          "final_answer"
+        ]
+      },
+      "BetaMessageStatus": {
+        "type": "string",
+        "enum": [
+          "in_progress",
+          "completed",
+          "incomplete"
+        ]
+      },
+      "BetaResponseCustomToolCallInputDoneEvent": {
+        "title": "ResponseCustomToolCallInputDone",
+        "type": "object",
+        "description": "Event indicating that input for a custom tool call is complete.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.custom_tool_call_input.done"
+            ],
+            "description": "The event type identifier.",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output this event applies to."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "Unique identifier for the API item associated with this event."
+          },
+          "input": {
+            "type": "string",
+            "description": "The complete input data for the custom tool call."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "input",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.custom_tool_call_input.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.custom_tool_call_input.done\",\n  \"output_index\": 0,\n  \"item_id\": \"ctc_1234567890abcdef\",\n  \"input\": \"final complete input text\"\n}\n"
+        }
+      },
+      "BetaResponseCustomToolCallInputDeltaEvent": {
+        "title": "ResponseCustomToolCallInputDelta",
+        "type": "object",
+        "description": "Event representing a delta (partial update) to the input of a custom tool call.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.custom_tool_call_input.delta"
+            ],
+            "description": "The event type identifier.",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output this delta applies to."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "Unique identifier for the API item associated with this event."
+          },
+          "delta": {
+            "type": "string",
+            "description": "The incremental input data (delta) for the custom tool call."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "delta",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.custom_tool_call_input.delta",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.custom_tool_call_input.delta\",\n  \"output_index\": 0,\n  \"item_id\": \"ctc_1234567890abcdef\",\n  \"delta\": \"partial input text\"\n}\n"
+        }
+      },
+      "BetaResponseQueuedEvent": {
+        "type": "object",
+        "title": "ResponseQueuedEvent",
+        "description": "Emitted when a response is queued and waiting to be processed.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.queued"
+            ],
+            "description": "The type of the event. Always 'response.queued'.",
+            "x-stainless-const": true
+          },
+          "response": {
+            "$ref": "#/components/schemas/BetaResponse",
+            "description": "The full response object that is queued."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number for this event."
+          }
+        },
+        "required": [
+          "type",
+          "response",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.queued",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.queued\",\n  \"response\": {\n    \"id\": \"res_123\",\n    \"status\": \"queued\",\n    \"created_at\": \"2021-01-01T00:00:00Z\",\n    \"updated_at\": \"2021-01-01T00:00:00Z\"\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponse": {
+        "title": "The response object",
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/BetaModelResponseProperties"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseProperties"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "service_tier": {
+                "$ref": "#/components/schemas/BetaServiceTierResponses"
+              },
+              "truncation": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "The truncation strategy to use for the model response.\n- `auto`: If the input to this Response exceeds\n  the model's context window size, the model will truncate the\n  response to fit the context window by dropping items from the beginning of the conversation.\n- `disabled` (default): If the input size will exceed the context window\n  size for a model, the request will fail with a 400 error.\n",
+                    "enum": [
+                      "auto",
+                      "disabled"
+                    ],
+                    "default": "disabled"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "id": {
+                "type": "string",
+                "description": "Unique identifier for this Response.\n"
+              },
+              "object": {
+                "type": "string",
+                "description": "The object type of this resource - always set to `response`.\n",
+                "enum": [
+                  "response"
+                ],
+                "x-stainless-const": true
+              },
+              "status": {
+                "type": "string",
+                "description": "The status of the response generation. One of `completed`, `failed`,\n`in_progress`, `cancelled`, `queued`, or `incomplete`.\n",
+                "enum": [
+                  "completed",
+                  "failed",
+                  "in_progress",
+                  "cancelled",
+                  "queued",
+                  "incomplete"
+                ]
+              },
+              "created_at": {
+                "type": "number",
+                "format": "unixtime",
+                "description": "Unix timestamp (in seconds) of when this Response was created.\n"
+              },
+              "completed_at": {
+                "anyOf": [
+                  {
+                    "type": "number",
+                    "format": "unixtime",
+                    "description": "Unix timestamp (in seconds) of when this Response was completed.\nOnly present when the status is `completed`.\n"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "error": {
+                "$ref": "#/components/schemas/BetaResponseError"
+              },
+              "incomplete_details": {
+                "anyOf": [
+                  {
+                    "type": "object",
+                    "description": "Details about why the response is incomplete.\n",
+                    "properties": {
+                      "reason": {
+                        "type": "string",
+                        "description": "The reason why the response is incomplete. `steered` means\nthe response stopped at a safe output boundary after a\nWebSocket `response.steer` event. The server can then create\na successor response automatically with the queued input.\n",
+                        "enum": [
+                          "max_output_tokens",
+                          "max_messages",
+                          "content_filter",
+                          "steered"
+                        ]
+                      }
+                    }
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "output": {
+                "type": "array",
+                "description": "An array of content items generated by the model.\n\n- The length and order of items in the `output` array is dependent\n  on the model's response.\n- Rather than accessing the first item in the `output` array and\n  assuming it's an `assistant` message with the content generated by\n  the model, you might consider using the `output_text` property where\n  supported in SDKs.\n",
+                "items": {
+                  "$ref": "#/components/schemas/BetaOutputItem"
+                }
+              },
+              "reasoning": {
+                "anyOf": [
+                  {
+                    "$ref": "#/components/schemas/BetaReasoning"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "instructions": {
+                "anyOf": [
+                  {
+                    "description": "A system (or developer) message inserted into the model's context.\n\nWhen using along with `previous_response_id`, the instructions from a previous\nresponse will not be carried over to the next response. This makes it simple\nto swap out system (or developer) messages in new responses.\n",
+                    "oneOf": [
+                      {
+                        "type": "string",
+                        "description": "A text input to the model, equivalent to a text input with the\n`developer` role.\n"
+                      },
+                      {
+                        "type": "array",
+                        "title": "Input item list",
+                        "description": "A list of one or many input items to the model, containing\ndifferent content types.\n",
+                        "items": {
+                          "$ref": "#/components/schemas/BetaInputItem"
+                        }
+                      }
+                    ]
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "output_text": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "SDK-only convenience property that contains the aggregated text output\nfrom all `output_text` items in the `output` array, if any are present.\nSupported in the Python and JavaScript SDKs.\n",
+                    "x-oaiSupportedSDKs": [
+                      "python",
+                      "javascript"
+                    ]
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "usage": {
+                "$ref": "#/components/schemas/BetaResponseUsage"
+              },
+              "prompt_cache_options": {
+                "$ref": "#/components/schemas/BetaPromptCacheOptions"
+              },
+              "prompt_cache_diagnostics": {
+                "$ref": "#/components/schemas/BetaPromptCacheDiagnostics"
+              },
+              "moderation": {
+                "anyOf": [
+                  {
+                    "$ref": "#/components/schemas/BetaModeration",
+                    "description": "Moderation results for the response input and output, if moderated completions were requested.\n"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "parallel_tool_calls": {
+                "type": "boolean",
+                "description": "Whether to allow the model to run tool calls in parallel.\n",
+                "default": true
+              },
+              "conversation": {
+                "anyOf": [
+                  {
+                    "default": null,
+                    "$ref": "#/components/schemas/BetaResponseConversation"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "max_output_tokens": {
+                "anyOf": [
+                  {
+                    "description": "An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](https://developers.openai.com/api/docs/guides/reasoning).\n",
+                    "type": "integer"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              }
+            },
+            "required": [
+              "id",
+              "object",
+              "created_at",
+              "error",
+              "incomplete_details",
+              "instructions",
+              "model",
+              "tools",
+              "output",
+              "parallel_tool_calls",
+              "metadata",
+              "tool_choice",
+              "temperature",
+              "top_p"
+            ]
+          }
+        ],
+        "example": {
+          "id": "resp_67ccd3a9da748190baa7f1570fe91ac604becb25c45c1d41",
+          "object": "response",
+          "created_at": 1741476777,
+          "status": "completed",
+          "completed_at": 1741476778,
+          "error": null,
+          "incomplete_details": null,
+          "instructions": null,
+          "max_output_tokens": null,
+          "model": "gpt-6-astra",
+          "output": [
+            {
+              "type": "message",
+              "id": "msg_67ccd3acc8d48190a77525dc6de64b4104becb25c45c1d41",
+              "status": "completed",
+              "role": "assistant",
+              "content": [
+                {
+                  "type": "output_text",
+                  "text": "The image depicts a scenic landscape with a wooden boardwalk or pathway leading through lush, green grass under a blue sky with some clouds. The setting suggests a peaceful natural area, possibly a park or nature reserve. There are trees and shrubs in the background.",
+                  "annotations": []
+                }
+              ]
+            }
+          ],
+          "parallel_tool_calls": true,
+          "previous_response_id": null,
+          "reasoning": {
+            "effort": null,
+            "summary": null,
+            "context": null
+          },
+          "store": true,
+          "temperature": 1,
+          "text": {
+            "format": {
+              "type": "text"
+            }
+          },
+          "tool_choice": "auto",
+          "tools": [],
+          "top_p": 1,
+          "truncation": "disabled",
+          "usage": {
+            "input_tokens": 328,
+            "input_tokens_details": {
+              "cached_tokens": 0,
+              "cache_write_tokens": 0
+            },
+            "output_tokens": 52,
+            "output_tokens_details": {
+              "reasoning_tokens": 0
+            },
+            "total_tokens": 380
+          },
+          "user": null,
+          "metadata": {}
+        }
+      },
+      "BetaResponseConversation": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The unique ID of the conversation that this response was associated with."
+          }
+        },
+        "type": "object",
+        "required": [
+          "id"
+        ],
+        "title": "Conversation",
+        "description": "The conversation that this response belonged to. Input items and output items from this response were automatically added to this conversation."
+      },
+      "BetaModeration": {
+        "properties": {
+          "input": {
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/BetaModerationResultBody"
+              },
+              {
+                "$ref": "#/components/schemas/BetaModerationErrorBody"
+              }
+            ],
+            "description": "Moderation for the response input.",
+            "discriminator": {
+              "propertyName": "type"
+            }
+          },
+          "output": {
+            "oneOf": [
+              {
+                "$ref": "#/components/schemas/BetaModerationResultBody"
+              },
+              {
+                "$ref": "#/components/schemas/BetaModerationErrorBody"
+              }
+            ],
+            "description": "Moderation for the response output.",
+            "discriminator": {
+              "propertyName": "type"
+            }
+          }
+        },
+        "type": "object",
+        "required": [
+          "input",
+          "output"
+        ],
+        "title": "Moderation",
+        "description": "Moderation results or errors for the response input and output."
+      },
+      "BetaModerationErrorBody": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "error"
+            ],
+            "description": "The object type, which was always `error` for moderation failures.",
+            "default": "error",
+            "x-stainless-const": true
+          },
+          "code": {
+            "type": "string",
+            "description": "The error code."
+          },
+          "message": {
+            "type": "string",
+            "description": "The error message."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "code",
+          "message"
+        ],
+        "title": "Moderation error",
+        "description": "An error produced while attempting moderation for the response input or output."
+      },
+      "BetaModerationResultBody": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "moderation_result"
+            ],
+            "description": "The object type, which was always `moderation_result` for successful moderation results.",
+            "default": "moderation_result",
+            "x-stainless-const": true
+          },
+          "model": {
+            "type": "string",
+            "description": "The moderation model that produced this result."
+          },
+          "flagged": {
+            "type": "boolean",
+            "description": "A boolean indicating whether the content was flagged by any category."
+          },
+          "categories": {
+            "additionalProperties": {
+              "type": "boolean"
+            },
+            "type": "object",
+            "description": "A dictionary of moderation categories to booleans, True if the input is flagged under this category.",
+            "x-oaiTypeLabel": "map"
+          },
+          "category_scores": {
+            "additionalProperties": {
+              "type": "number"
+            },
+            "type": "object",
+            "description": "A dictionary of moderation categories to scores.",
+            "x-oaiTypeLabel": "map"
+          },
+          "category_applied_input_types": {
+            "additionalProperties": {
+              "items": {
+                "$ref": "#/components/schemas/BetaModerationInputType"
+              },
+              "type": "array"
+            },
+            "type": "object",
+            "description": "Which modalities of input are reflected by the score for each category.",
+            "x-oaiTypeLabel": "map"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "model",
+          "flagged",
+          "categories",
+          "category_scores",
+          "category_applied_input_types"
+        ],
+        "title": "Moderation result",
+        "description": "A moderation result produced for the response input or output."
+      },
+      "BetaModerationInputType": {
+        "type": "string",
+        "enum": [
+          "text",
+          "image"
+        ]
+      },
+      "BetaPromptCacheDiagnostics": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/BetaPromptCacheMissDiagnosticsBody"
+          },
+          {
+            "$ref": "#/components/schemas/BetaPromptCacheHitDiagnosticsBody"
+          },
+          {
+            "$ref": "#/components/schemas/BetaPromptCacheComparisonResponseNotFoundDiagnosticsBody"
+          },
+          {
+            "$ref": "#/components/schemas/BetaPromptCacheUnavailableDiagnosticsBody"
+          }
+        ],
+        "description": "Prompt cache diagnostics requested for this response.",
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "BetaPromptCacheUnavailableDiagnosticsBody": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "unavailable"
+            ],
+            "default": "unavailable",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "BetaPromptCacheComparisonResponseNotFoundDiagnosticsBody": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "comparison_response_not_found"
+            ],
+            "default": "comparison_response_not_found",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "BetaPromptCacheHitDiagnosticsBody": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "cache_hit"
+            ],
+            "default": "cache_hit",
+            "x-stainless-const": true
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "BetaPromptCacheMissDiagnosticsBody": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "cache_miss"
+            ],
+            "default": "cache_miss",
+            "x-stainless-const": true
+          },
+          "reason": {
+            "$ref": "#/components/schemas/BetaCacheMissReasonTypeEnum",
+            "description": "The reason prompt cache reuse did not occur."
+          },
+          "cache_missed_tokens": {
+            "type": "integer",
+            "description": "The estimated number of input tokens affected after the first detected divergence."
+          },
+          "comparison_reusable_tokens": {
+            "type": "integer",
+            "description": "The raw token count of the reusable prefix in the compared response."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "reason",
+          "cache_missed_tokens"
+        ]
+      },
+      "BetaCacheMissReasonTypeEnum": {
+        "type": "string",
+        "enum": [
+          "model_changed",
+          "prompt_cache_key_changed",
+          "tools_changed",
+          "text_format_changed",
+          "reasoning_effort_changed",
+          "verbosity_changed",
+          "context_compacted",
+          "input_changed",
+          "service_tier_changed"
+        ]
+      },
+      "BetaPromptCacheOptions": {
+        "properties": {
+          "ttl": {
+            "$ref": "#/components/schemas/BetaPromptCacheTTLEnum",
+            "description": "The minimum lifetime applied to each cache breakpoint."
+          },
+          "mode": {
+            "$ref": "#/components/schemas/BetaPromptCacheModeEnum",
+            "description": "Whether implicit prompt-cache breakpoints were enabled."
+          },
+          "comparison_response_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The response ID supplied as the prompt cache diagnostics comparison."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "ttl",
+          "mode"
+        ],
+        "title": "Prompt cache options",
+        "description": "The prompt-caching options that were applied to the response. Supported for `gpt-5.6` and later models."
+      },
+      "BetaOutputItem": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/BetaOutputMessage"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFileSearchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFunctionToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFunctionToolCallOutputResource"
+          },
+          {
+            "$ref": "#/components/schemas/BetaAgentMessage"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMultiAgentCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMultiAgentCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/BetaWebSearchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaComputerToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaComputerToolCallOutputResource"
+          },
+          {
+            "$ref": "#/components/schemas/BetaReasoningItem"
+          },
+          {
+            "$ref": "#/components/schemas/BetaProgram"
+          },
+          {
+            "$ref": "#/components/schemas/BetaProgramOutput"
+          },
+          {
+            "$ref": "#/components/schemas/BetaToolSearchCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaToolSearchOutput"
+          },
+          {
+            "$ref": "#/components/schemas/BetaAdditionalTools"
+          },
+          {
+            "$ref": "#/components/schemas/BetaCompactionBody"
+          },
+          {
+            "$ref": "#/components/schemas/BetaImageGenToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaCodeInterpreterToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaLocalShellToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaLocalShellToolCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFunctionShellCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFunctionShellCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/BetaApplyPatchToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaApplyPatchToolCallOutput"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMCPToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMCPListTools"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMCPApprovalRequest"
+          },
+          {
+            "$ref": "#/components/schemas/BetaMCPApprovalResponseResource"
+          },
+          {
+            "$ref": "#/components/schemas/BetaCustomToolCall"
+          },
+          {
+            "$ref": "#/components/schemas/BetaCustomToolCallOutputResource"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "BetaResponseError": {
+        "anyOf": [
+          {
+            "type": "object",
+            "description": "An error object returned when the model fails to generate a Response.\n",
+            "properties": {
+              "code": {
+                "$ref": "#/components/schemas/BetaResponseErrorCode"
+              },
+              "message": {
+                "type": "string",
+                "description": "A human-readable description of the error.\n"
+              },
+              "misalignment": {
+                "$ref": "#/components/schemas/BetaMisalignmentErrorDetailsResource"
+              }
+            },
+            "required": [
+              "code",
+              "message"
+            ]
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "BetaResponseErrorCode": {
+        "type": "string",
+        "description": "The error code for the response.\n",
+        "enum": [
+          "server_error",
+          "rate_limit_exceeded",
+          "invalid_prompt",
+          "data_residency_mismatch",
+          "bio_policy",
+          "misalignment_policy_violation",
+          "vector_store_timeout",
+          "invalid_image",
+          "invalid_image_format",
+          "invalid_base64_image",
+          "invalid_image_url",
+          "image_too_large",
+          "image_too_small",
+          "image_parse_error",
+          "image_content_policy_violation",
+          "invalid_image_mode",
+          "image_file_too_large",
+          "unsupported_image_media_type",
+          "empty_image_file",
+          "failed_to_download_image",
+          "image_file_not_found"
+        ]
+      },
+      "BetaServiceTierResponses": {
+        "anyOf": [
+          {
+            "type": "string",
+            "description": "Specifies the processing type used for serving the request.\n  - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.\n  - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.\n  - If set to '[flex](https://developers.openai.com/api/docs/guides/flex-processing)', then the request will be processed with the Flex Processing service tier.\n  - To opt-in to [Fast mode](https://developers.openai.com/api/docs/guides/fast-mode) at the request level, include the `service_tier=fast` or `service_tier=priority` parameter for Responses or Chat Completions. The response will show `service_tier=priority` regardless of if you specify `service_tier=fast` or `priority` in your request.\n  - If set to 'ultrafast', then the request will be processed with the access-controlled Ultrafast Processing service tier. This tier is currently available for `gpt-5.6-sol`; a response served through it will show `service_tier=ultrafast`.\n  - When not set, the default behavior is 'auto'.\n\n  When the `service_tier` parameter is set, the response body will include the `service_tier` value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.\n",
+            "enum": [
+              "auto",
+              "default",
+              "flex",
+              "scale",
+              "priority",
+              "fast",
+              "ultrafast"
+            ],
+            "default": "auto"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "BetaResponseProperties": {
+        "type": "object",
+        "properties": {
+          "previous_response_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of the previous response to the model. Use this to\ncreate multi-turn conversations. Learn more about\n[conversation state](https://developers.openai.com/api/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "model": {
+            "description": "Model ID used to generate the response, like `gpt-6-astra`. OpenAI\noffers a wide range of models with different capabilities, performance\ncharacteristics, and price points. Refer to the [model guide](https://developers.openai.com/api/docs/models)\nto browse and compare available models.\n",
+            "$ref": "#/components/schemas/BetaModelIdsResponses"
+          },
+          "background": {
+            "anyOf": [
+              {
+                "type": "boolean",
+                "description": "Whether to run the model response in the background.\n[Learn more](https://developers.openai.com/api/docs/guides/background).\n",
+                "default": false
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "max_tool_calls": {
+            "anyOf": [
+              {
+                "description": "The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.\n",
+                "type": "integer"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "text": {
+            "$ref": "#/components/schemas/BetaResponseTextParam"
+          },
+          "tools": {
+            "$ref": "#/components/schemas/BetaToolsArray"
+          },
+          "tool_choice": {
+            "$ref": "#/components/schemas/BetaToolChoiceParam"
+          },
+          "prompt": {
+            "$ref": "#/components/schemas/BetaPrompt"
+          }
+        }
+      },
+      "BetaPrompt": {
+        "anyOf": [
+          {
+            "type": "object",
+            "description": "Reference to a prompt template and its variables.\n[Learn more](https://developers.openai.com/api/docs/guides/text?api-mode=responses#version-prompts-in-code).\n",
+            "required": [
+              "id"
+            ],
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The unique identifier of the prompt template to use."
+              },
+              "version": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "Optional version of the prompt template."
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "variables": {
+                "$ref": "#/components/schemas/BetaResponsePromptVariables"
+              }
+            }
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "BetaResponsePromptVariables": {
+        "anyOf": [
+          {
+            "type": "object",
+            "title": "Prompt Variables",
+            "description": "Optional map of values to substitute in for variables in your\nprompt. The substitution values can either be strings, or other\nResponse input types like images or files.\n",
+            "x-oaiExpandable": true,
+            "x-oaiTypeLabel": "map",
+            "additionalProperties": {
+              "x-oaiExpandable": true,
+              "x-oaiTypeLabel": "map",
+              "oneOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaInputTextContent"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaInputImageContent"
+                },
+                {
+                  "$ref": "#/components/schemas/BetaInputFileContent"
+                }
+              ]
+            }
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "BetaToolsArray": {
+        "type": "array",
+        "description": "An array of tools the model may call while generating a response. You\ncan specify which tool to use by setting the `tool_choice` parameter.\n\nWe support the following categories of tools:\n- **Built-in tools**: Tools that are provided by OpenAI that extend the\n  model's capabilities, like [web search](https://developers.openai.com/api/docs/guides/tools-web-search)\n  or [file search](https://developers.openai.com/api/docs/guides/tools-file-search). Learn more about\n  [built-in tools](https://developers.openai.com/api/docs/guides/tools).\n- **MCP Tools**: Integrations with third-party systems via custom MCP servers\n  or predefined connectors such as Google Drive and SharePoint. Learn more about\n  [MCP Tools](https://developers.openai.com/api/docs/guides/tools-connectors-mcp).\n- **Function calls (custom tools)**: Functions that are defined by you,\n  enabling the model to call your own code with strongly typed arguments\n  and outputs. Learn more about\n  [function calling](https://developers.openai.com/api/docs/guides/function-calling). You can also use\n  custom tools to call your own code.\n",
+        "items": {
+          "$ref": "#/components/schemas/BetaTool"
+        }
+      },
+      "BetaModelResponseProperties": {
+        "type": "object",
+        "properties": {
+          "metadata": {
+            "$ref": "#/components/schemas/BetaMetadata"
+          },
+          "top_logprobs": {
+            "anyOf": [
+              {
+                "description": "An integer between 0 and 20 specifying the maximum number of most likely\ntokens to return at each token position, each with an associated log\nprobability. In some cases, the number of returned tokens may be fewer than\nrequested.\n",
+                "type": "integer",
+                "minimum": 0,
+                "maximum": 20
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "temperature": {
+            "anyOf": [
+              {
+                "type": "number",
+                "minimum": 0,
+                "maximum": 2,
+                "default": 1,
+                "example": 1,
+                "description": "What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.\nWe generally recommend altering this or `top_p` but not both.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "top_p": {
+            "anyOf": [
+              {
+                "type": "number",
+                "minimum": 0,
+                "maximum": 1,
+                "default": 1,
+                "example": 1,
+                "description": "An alternative to sampling with temperature, called nucleus sampling,\nwhere the model considers the results of the tokens with top_p probability\nmass. So 0.1 means only the tokens comprising the top 10% probability mass\nare considered.\n\nWe generally recommend altering this or `temperature` but not both.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "user": {
+            "type": "string",
+            "example": "user-1234",
+            "deprecated": true,
+            "description": "This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations.\nA stable identifier for your end-users.\nUsed to boost cache hit rates by better bucketing similar requests and  to help OpenAI detect and prevent abuse. [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers).\n"
+          },
+          "safety_identifier": {
+            "anyOf": [
+              {
+                "type": "string",
+                "maxLength": 64,
+                "example": "safety-identifier-1234",
+                "description": "A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies.\nThe IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers).\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "prompt_cache_key": {
+            "anyOf": [
+              {
+                "type": "string",
+                "example": "prompt-cache-key-1234",
+                "description": "Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](https://developers.openai.com/api/docs/guides/prompt-caching).\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "prompt_cache_retention": {
+            "deprecated": true,
+            "anyOf": [
+              {
+                "type": "string",
+                "enum": [
+                  "in_memory",
+                  "24h"
+                ],
+                "description": "Deprecated. Use `prompt_cache_options.ttl` instead.\n\nThe retention policy for the prompt cache. Set to `24h` to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. [Learn more](https://developers.openai.com/api/docs/guides/prompt-caching#prompt-cache-retention).\nThis field expresses a maximum retention policy, while\n`prompt_cache_options.ttl` expresses a minimum cache lifetime. The two\nfields are independent and do not interact.\nFor `gpt-5.5`, `gpt-5.5-pro`, and future models, only `24h` is supported.\n\nFor older models that support both `in_memory` and `24h`, the default depends on your organization's data retention policy:\n  - Organizations without ZDR enabled default to `24h`.\n  - Organizations with ZDR enabled default to `in_memory` when `prompt_cache_retention` is not specified.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        }
+      },
+      "BetaMetadata": {
+        "anyOf": [
+          {
+            "type": "object",
+            "description": "Set of 16 key-value pairs that can be attached to an object. This can be\nuseful for storing additional information about the object in a structured\nformat, and querying for objects via API or the dashboard.\n\nKeys are strings with a maximum length of 64 characters. Values are strings\nwith a maximum length of 512 characters.\n",
+            "additionalProperties": {
+              "type": "string"
+            },
+            "x-oaiTypeLabel": "map"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "BetaResponseOutputTextAnnotationAddedEvent": {
+        "type": "object",
+        "title": "ResponseOutputTextAnnotationAddedEvent",
+        "description": "Emitted when an annotation is added to output text content.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.output_text.annotation.added"
+            ],
+            "description": "The type of the event. Always 'response.output_text.annotation.added'.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the item to which the annotation is being added."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response's output array."
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part within the output item."
+          },
+          "annotation_index": {
+            "type": "integer",
+            "description": "The index of the annotation within the content part."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          },
+          "annotation": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAnnotation"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The annotation object being added. (See annotation schema for details.)"
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "content_index",
+          "annotation_index",
+          "annotation",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_text.annotation.added",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.output_text.annotation.added\",\n  \"item_id\": \"item-abc\",\n  \"output_index\": 0,\n  \"content_index\": 0,\n  \"annotation_index\": 0,\n  \"annotation\": {\n    \"type\": \"file_citation\",\n    \"file_id\": \"file-abc\",\n    \"index\": 0,\n    \"filename\": \"example.txt\"\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseMCPListToolsInProgressEvent": {
+        "type": "object",
+        "title": "ResponseMCPListToolsInProgressEvent",
+        "description": "Emitted when the system is in the process of retrieving the list of available MCP tools.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_list_tools.in_progress"
+            ],
+            "description": "The type of the event. Always 'response.mcp_list_tools.in_progress'.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP tool call item that is being processed."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that is being processed."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_list_tools.in_progress",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.mcp_list_tools.in_progress\",\n  \"sequence_number\": 1,\n  \"output_index\": 0,\n  \"item_id\": \"mcpl_682d4379df088191886b70f4ec39f90403937d5f622d7a90\"\n}\n"
+        }
+      },
+      "BetaResponseMCPListToolsFailedEvent": {
+        "type": "object",
+        "title": "ResponseMCPListToolsFailedEvent",
+        "description": "Emitted when the attempt to list available MCP tools has failed.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_list_tools.failed"
+            ],
+            "description": "The type of the event. Always 'response.mcp_list_tools.failed'.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP tool call item that failed."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that failed."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_list_tools.failed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.mcp_list_tools.failed\",\n  \"sequence_number\": 1,\n  \"output_index\": 0,\n  \"item_id\": \"mcpl_682d4379df088191886b70f4ec39f90403937d5f622d7a90\"\n}\n"
+        }
+      },
+      "BetaResponseMCPListToolsCompletedEvent": {
+        "type": "object",
+        "title": "ResponseMCPListToolsCompletedEvent",
+        "description": "Emitted when the list of available MCP tools has been successfully retrieved.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_list_tools.completed"
+            ],
+            "description": "The type of the event. Always 'response.mcp_list_tools.completed'.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP tool call item that produced this output."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that was processed."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_list_tools.completed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.mcp_list_tools.completed\",\n  \"sequence_number\": 1,\n  \"output_index\": 0,\n  \"item_id\": \"mcpl_682d4379df088191886b70f4ec39f90403937d5f622d7a90\"\n}\n"
+        }
+      },
+      "BetaResponseMCPCallInProgressEvent": {
+        "type": "object",
+        "title": "ResponseMCPCallInProgressEvent",
+        "description": "Emitted when an MCP  tool call is in progress.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_call.in_progress"
+            ],
+            "description": "The type of the event. Always 'response.mcp_call.in_progress'.",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response's output array."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the MCP tool call item being processed."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_call.in_progress",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.mcp_call.in_progress\",\n  \"sequence_number\": 1,\n  \"output_index\": 0,\n  \"item_id\": \"mcp_682d437d90a88191bf88cd03aae0c3e503937d5f622d7a90\"\n}\n"
+        }
+      },
+      "BetaResponseMCPCallFailedEvent": {
+        "type": "object",
+        "title": "ResponseMCPCallFailedEvent",
+        "description": "Emitted when an MCP  tool call has failed.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_call.failed"
+            ],
+            "description": "The type of the event. Always 'response.mcp_call.failed'.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP tool call item that failed."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that failed."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_call.failed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.mcp_call.failed\",\n  \"sequence_number\": 1,\n  \"item_id\": \"mcp_682d437d90a88191bf88cd03aae0c3e503937d5f622d7a90\",\n  \"output_index\": 0\n}\n"
+        }
+      },
+      "BetaResponseMCPCallCompletedEvent": {
+        "type": "object",
+        "title": "ResponseMCPCallCompletedEvent",
+        "description": "Emitted when an MCP  tool call has completed successfully.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_call.completed"
+            ],
+            "description": "The type of the event. Always 'response.mcp_call.completed'.",
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the MCP tool call item that completed."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that completed."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_call.completed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.mcp_call.completed\",\n  \"sequence_number\": 1,\n  \"item_id\": \"mcp_682d437d90a88191bf88cd03aae0c3e503937d5f622d7a90\",\n  \"output_index\": 0\n}\n"
+        }
+      },
+      "BetaResponseMCPCallArgumentsDoneEvent": {
+        "type": "object",
+        "title": "ResponseMCPCallArgumentsDoneEvent",
+        "description": "Emitted when the arguments for an MCP tool call are finalized.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_call_arguments.done"
+            ],
+            "description": "The type of the event. Always 'response.mcp_call_arguments.done'.",
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response's output array."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the MCP tool call item being processed."
+          },
+          "arguments": {
+            "type": "string",
+            "description": "A JSON string containing the finalized arguments for the MCP tool call.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "arguments",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_call_arguments.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.mcp_call_arguments.done\",\n  \"output_index\": 0,\n  \"item_id\": \"item-abc\",\n  \"arguments\": \"{\\\"arg1\\\": \\\"value1\\\", \\\"arg2\\\": \\\"value2\\\"}\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseMCPCallArgumentsDeltaEvent": {
+        "type": "object",
+        "title": "ResponseMCPCallArgumentsDeltaEvent",
+        "description": "Emitted when there is a delta (partial update) to the arguments of an MCP tool call.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.mcp_call_arguments.delta"
+            ],
+            "description": "The type of the event. Always 'response.mcp_call_arguments.delta'.",
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response's output array."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the MCP tool call item being processed."
+          },
+          "delta": {
+            "type": "string",
+            "description": "A JSON string containing the partial update to the arguments for the MCP tool call.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "delta",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.mcp_call_arguments.delta",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.mcp_call_arguments.delta\",\n  \"output_index\": 0,\n  \"item_id\": \"item-abc\",\n  \"delta\": \"{\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseImageGenCallPartialImageEvent": {
+        "type": "object",
+        "title": "ResponseImageGenCallPartialImageEvent",
+        "description": "Emitted when a partial image is available during image generation streaming.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.image_generation_call.partial_image"
+            ],
+            "description": "The type of the event. Always 'response.image_generation_call.partial_image'.",
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response's output array."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the image generation item being processed."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the image generation item being processed."
+          },
+          "partial_image_index": {
+            "type": "integer",
+            "description": "0-based index for the partial image (backend is 1-based, but this is 0-based for the user)."
+          },
+          "partial_image_b64": {
+            "type": "string",
+            "description": "Base64-encoded partial image data, suitable for rendering as an image."
+          },
+          "size": {
+            "type": "string",
+            "description": "The image size that was used."
+          },
+          "quality": {
+            "type": "string",
+            "description": "The image quality that was used."
+          },
+          "background": {
+            "type": "string",
+            "description": "The background setting that was used."
+          },
+          "output_format": {
+            "type": "string",
+            "description": "The output format that was used."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number",
+          "partial_image_index",
+          "partial_image_b64"
+        ],
+        "x-oaiMeta": {
+          "name": "response.image_generation_call.partial_image",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.image_generation_call.partial_image\",\n  \"output_index\": 0,\n  \"item_id\": \"item-123\",\n  \"sequence_number\": 0,\n  \"partial_image_index\": 0,\n  \"partial_image_b64\": \"...\"\n}\n"
+        }
+      },
+      "BetaResponseImageGenCallInProgressEvent": {
+        "type": "object",
+        "title": "ResponseImageGenCallInProgressEvent",
+        "description": "Emitted when an image generation tool call is in progress.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.image_generation_call.in_progress"
+            ],
+            "description": "The type of the event. Always 'response.image_generation_call.in_progress'.",
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response's output array."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the image generation item being processed."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the image generation item being processed."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.image_generation_call.in_progress",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.image_generation_call.in_progress\",\n  \"output_index\": 0,\n  \"item_id\": \"item-123\",\n  \"sequence_number\": 0\n}\n"
+        }
+      },
+      "BetaResponseImageGenCallGeneratingEvent": {
+        "type": "object",
+        "title": "ResponseImageGenCallGeneratingEvent",
+        "description": "Emitted when an image generation tool call is actively generating an image (intermediate state).\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.image_generation_call.generating"
+            ],
+            "description": "The type of the event. Always 'response.image_generation_call.generating'.",
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response's output array."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the image generation item being processed."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the image generation item being processed."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.image_generation_call.generating",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.image_generation_call.generating\",\n  \"output_index\": 0,\n  \"item_id\": \"item-123\",\n  \"sequence_number\": 0\n}\n"
+        }
+      },
+      "BetaResponseImageGenCallCompletedEvent": {
+        "type": "object",
+        "title": "ResponseImageGenCallCompletedEvent",
+        "description": "Emitted when an image generation tool call has completed and the final image is available.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.image_generation_call.completed"
+            ],
+            "description": "The type of the event. Always 'response.image_generation_call.completed'.",
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response's output array."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the image generation item being processed."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.image_generation_call.completed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.image_generation_call.completed\",\n  \"output_index\": 0,\n  \"item_id\": \"item-123\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseReasoningTextDoneEvent": {
+        "type": "object",
+        "description": "Emitted when a reasoning text is completed.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.reasoning_text.done`.\n",
+            "enum": [
+              "response.reasoning_text.done"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item this reasoning text is associated with.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item this reasoning text is associated with.\n"
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the reasoning content part.\n"
+          },
+          "text": {
+            "type": "string",
+            "description": "The full text of the completed reasoning content.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event.\n"
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "content_index",
+          "text",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.reasoning_text.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.reasoning_text.done\",\n  \"item_id\": \"rs_123\",\n  \"output_index\": 0,\n  \"content_index\": 0,\n  \"text\": \"The user is asking...\",\n  \"sequence_number\": 4\n}\n"
+        }
+      },
+      "BetaResponseReasoningTextDeltaEvent": {
+        "type": "object",
+        "description": "Emitted when a delta is added to a reasoning text.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.reasoning_text.delta`.\n",
+            "enum": [
+              "response.reasoning_text.delta"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item this reasoning text delta is associated with.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item this reasoning text delta is associated with.\n"
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the reasoning content part this delta is associated with.\n"
+          },
+          "delta": {
+            "type": "string",
+            "description": "The text delta that was added to the reasoning content.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event.\n"
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "content_index",
+          "delta",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.reasoning_text.delta",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.reasoning_text.delta\",\n  \"item_id\": \"rs_123\",\n  \"output_index\": 0,\n  \"content_index\": 0,\n  \"delta\": \"The\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseReasoningSummaryTextDoneEvent": {
+        "type": "object",
+        "description": "Emitted when a reasoning summary text is completed.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.reasoning_summary_text.done`.\n",
+            "enum": [
+              "response.reasoning_summary_text.done"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item this summary text is associated with.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item this summary text is associated with.\n"
+          },
+          "summary_index": {
+            "type": "integer",
+            "description": "The index of the summary part within the reasoning summary.\n"
+          },
+          "text": {
+            "type": "string",
+            "description": "The full text of the completed reasoning summary.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event.\n"
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "summary_index",
+          "text",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.reasoning_summary_text.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.reasoning_summary_text.done\",\n  \"item_id\": \"rs_6806bfca0b2481918a5748308061a2600d3ce51bdffd5476\",\n  \"output_index\": 0,\n  \"summary_index\": 0,\n  \"text\": \"**Responding to a greeting**\\n\\nThe user just said, \\\"Hello!\\\" So, it seems I need to engage. I'll greet them back and offer help since they're looking to chat. I could say something like, \\\"Hello! How can I assist you today?\\\" That feels friendly and open. They didn't ask a specific question, so this approach will work well for starting a conversation. Let's see where it goes from there!\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseReasoningSummaryTextDeltaEvent": {
+        "type": "object",
+        "description": "Emitted when a delta is added to a reasoning summary text.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.reasoning_summary_text.delta`.\n",
+            "enum": [
+              "response.reasoning_summary_text.delta"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item this summary text delta is associated with.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item this summary text delta is associated with.\n"
+          },
+          "summary_index": {
+            "type": "integer",
+            "description": "The index of the summary part within the reasoning summary.\n"
+          },
+          "delta": {
+            "type": "string",
+            "description": "The text delta that was added to the summary.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event.\n"
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "summary_index",
+          "delta",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.reasoning_summary_text.delta",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.reasoning_summary_text.delta\",\n  \"item_id\": \"rs_6806bfca0b2481918a5748308061a2600d3ce51bdffd5476\",\n  \"output_index\": 0,\n  \"summary_index\": 0,\n  \"delta\": \"**Responding to a greeting**\\n\\nThe user just said, \\\"Hello!\\\" So, it seems I need to engage. I'll greet them back and offer help since they're looking to chat. I could say something like, \\\"Hello! How can I assist you today?\\\" That feels friendly and open. They didn't ask a specific question, so this approach will work well for starting a conversation. Let's see where it goes from there!\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseReasoningSummaryPartDoneEvent": {
+        "type": "object",
+        "description": "Emitted when a reasoning summary part is completed.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.reasoning_summary_part.done`.\n",
+            "enum": [
+              "response.reasoning_summary_part.done"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item this summary part is associated with.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item this summary part is associated with.\n"
+          },
+          "summary_index": {
+            "type": "integer",
+            "description": "The index of the summary part within the reasoning summary.\n"
+          },
+          "status": {
+            "type": "string",
+            "description": "The completion status of the summary part. Omitted when the part completed\nnormally and set to `incomplete` when generation was interrupted.\n",
+            "enum": [
+              "incomplete"
+            ]
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event.\n"
+          },
+          "part": {
+            "type": "object",
+            "description": "The completed summary part.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "description": "The type of the summary part. Always `summary_text`.",
+                "enum": [
+                  "summary_text"
+                ],
+                "x-stainless-const": true
+              },
+              "text": {
+                "type": "string",
+                "description": "The text of the summary part."
+              }
+            },
+            "required": [
+              "type",
+              "text"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "summary_index",
+          "part",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.reasoning_summary_part.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.reasoning_summary_part.done\",\n  \"item_id\": \"rs_6806bfca0b2481918a5748308061a2600d3ce51bdffd5476\",\n  \"output_index\": 0,\n  \"summary_index\": 0,\n  \"part\": {\n    \"type\": \"summary_text\",\n    \"text\": \"**Responding to a greeting**\\n\\nThe user just said, \\\"Hello!\\\" So, it seems I need to engage. I'll greet them back and offer help since they're looking to chat. I could say something like, \\\"Hello! How can I assist you today?\\\" That feels friendly and open. They didn't ask a specific question, so this approach will work well for starting a conversation. Let's see where it goes from there!\"\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseReasoningSummaryPartAddedEvent": {
+        "type": "object",
+        "description": "Emitted when a new reasoning summary part is added.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.reasoning_summary_part.added`.\n",
+            "enum": [
+              "response.reasoning_summary_part.added"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item this summary part is associated with.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item this summary part is associated with.\n"
+          },
+          "summary_index": {
+            "type": "integer",
+            "description": "The index of the summary part within the reasoning summary.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event.\n"
+          },
+          "part": {
+            "type": "object",
+            "description": "The summary part that was added.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "description": "The type of the summary part. Always `summary_text`.",
+                "enum": [
+                  "summary_text"
+                ],
+                "x-stainless-const": true
+              },
+              "text": {
+                "type": "string",
+                "description": "The text of the summary part."
+              }
+            },
+            "required": [
+              "type",
+              "text"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "summary_index",
+          "part",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.reasoning_summary_part.added",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.reasoning_summary_part.added\",\n  \"item_id\": \"rs_6806bfca0b2481918a5748308061a2600d3ce51bdffd5476\",\n  \"output_index\": 0,\n  \"summary_index\": 0,\n  \"part\": {\n    \"type\": \"summary_text\",\n    \"text\": \"\"\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseTextDoneEvent": {
+        "type": "object",
+        "description": "Emitted when text content is finalized.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.output_text.done`.\n",
+            "enum": [
+              "response.output_text.done"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that the text content is finalized.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the text content is finalized.\n"
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part that the text content is finalized.\n"
+          },
+          "text": {
+            "type": "string",
+            "description": "The text content that is finalized.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number for this event."
+          },
+          "logprobs": {
+            "type": "array",
+            "description": "The log probabilities of the tokens in the delta.\n",
+            "items": {
+              "$ref": "#/components/schemas/BetaResponseLogProb"
+            }
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "content_index",
+          "text",
+          "sequence_number",
+          "logprobs"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_text.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.output_text.done\",\n  \"item_id\": \"msg_123\",\n  \"output_index\": 0,\n  \"content_index\": 0,\n  \"text\": \"In a shimmering forest under a sky full of stars, a lonely unicorn named Lila discovered a hidden pond that glowed with moonlight. Every night, she would leave sparkling, magical flowers by the water's edge, hoping to share her beauty with others. One enchanting evening, she woke to find a group of friendly animals gathered around, eager to be friends and share in her magic.\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseLogProb": {
+        "type": "object",
+        "description": "A logprob is the logarithmic probability that the model assigns to producing \na particular token at a given position in the sequence. Less-negative (higher) \nlogprob values indicate greater model confidence in that token choice.\n",
+        "properties": {
+          "token": {
+            "description": "A possible text token.",
+            "type": "string"
+          },
+          "logprob": {
+            "description": "The log probability of this token.\n",
+            "type": "number"
+          },
+          "top_logprobs": {
+            "description": "The log probabilities of up to 20 of the most likely tokens.\n",
+            "type": "array",
+            "items": {
+              "type": "object",
+              "properties": {
+                "token": {
+                  "description": "A possible text token.",
+                  "type": "string"
+                },
+                "logprob": {
+                  "description": "The log probability of this token.",
+                  "type": "number"
+                }
+              }
+            }
+          }
+        },
+        "required": [
+          "token",
+          "logprob"
+        ]
+      },
+      "BetaResponseTextDeltaEvent": {
+        "type": "object",
+        "description": "Emitted when there is an additional text delta.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.output_text.delta`.\n",
+            "enum": [
+              "response.output_text.delta"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that the text delta was added to.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the text delta was added to.\n"
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part that the text delta was added to.\n"
+          },
+          "delta": {
+            "type": "string",
+            "description": "The text delta that was added.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number for this event."
+          },
+          "logprobs": {
+            "type": "array",
+            "description": "The log probabilities of the tokens in the delta.\n",
+            "items": {
+              "$ref": "#/components/schemas/BetaResponseLogProb"
+            }
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "content_index",
+          "delta",
+          "sequence_number",
+          "logprobs"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_text.delta",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.output_text.delta\",\n  \"item_id\": \"msg_123\",\n  \"output_index\": 0,\n  \"content_index\": 0,\n  \"delta\": \"In\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseRefusalDoneEvent": {
+        "type": "object",
+        "description": "Emitted when refusal text is finalized.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.refusal.done`.\n",
+            "enum": [
+              "response.refusal.done"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that the refusal text is finalized.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the refusal text is finalized.\n"
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part that the refusal text is finalized.\n"
+          },
+          "refusal": {
+            "type": "string",
+            "description": "The refusal text that is finalized.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event.\n"
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "content_index",
+          "refusal",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.refusal.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.refusal.done\",\n  \"item_id\": \"item-abc\",\n  \"output_index\": 1,\n  \"content_index\": 2,\n  \"refusal\": \"final refusal text\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseRefusalDeltaEvent": {
+        "type": "object",
+        "description": "Emitted when there is a partial refusal text.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.refusal.delta`.\n",
+            "enum": [
+              "response.refusal.delta"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that the refusal text is added to.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the refusal text is added to.\n"
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part that the refusal text is added to.\n"
+          },
+          "delta": {
+            "type": "string",
+            "description": "The refusal text that is added.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event.\n"
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "content_index",
+          "delta",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.refusal.delta",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.refusal.delta\",\n  \"item_id\": \"msg_123\",\n  \"output_index\": 0,\n  \"content_index\": 0,\n  \"delta\": \"refusal text so far\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseOutputItemDoneEvent": {
+        "type": "object",
+        "description": "Emitted when an output item is marked done.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.output_item.done`.\n",
+            "enum": [
+              "response.output_item.done"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that was marked done.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event.\n"
+          },
+          "item": {
+            "$ref": "#/components/schemas/BetaOutputItem",
+            "description": "The output item that was marked done.\n"
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_item.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.output_item.done\",\n  \"output_index\": 0,\n  \"item\": {\n    \"id\": \"msg_123\",\n    \"status\": \"completed\",\n    \"type\": \"message\",\n    \"role\": \"assistant\",\n    \"content\": [\n      {\n        \"type\": \"output_text\",\n        \"text\": \"In a shimmering forest under a sky full of stars, a lonely unicorn named Lila discovered a hidden pond that glowed with moonlight. Every night, she would leave sparkling, magical flowers by the water's edge, hoping to share her beauty with others. One enchanting evening, she woke to find a group of friendly animals gathered around, eager to be friends and share in her magic.\",\n        \"annotations\": []\n      }\n    ]\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseOutputItemAddedEvent": {
+        "type": "object",
+        "description": "Emitted when a new output item is added.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.output_item.added`.\n",
+            "enum": [
+              "response.output_item.added"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that was added.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event.\n"
+          },
+          "item": {
+            "$ref": "#/components/schemas/BetaOutputItem",
+            "description": "The output item that was added. For reasoning items, `encrypted_content`\nmay be incomplete while the item is in progress. Use the reasoning item\nfrom the corresponding `response.output_item.done` event when passing it\nas input to a subsequent request.\n"
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.output_item.added",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.output_item.added\",\n  \"output_index\": 0,\n  \"item\": {\n    \"id\": \"msg_123\",\n    \"status\": \"in_progress\",\n    \"type\": \"message\",\n    \"role\": \"assistant\",\n    \"content\": []\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseInProgressEvent": {
+        "type": "object",
+        "description": "Emitted when the response is in progress.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.in_progress`.\n",
+            "enum": [
+              "response.in_progress"
+            ],
+            "x-stainless-const": true
+          },
+          "response": {
+            "$ref": "#/components/schemas/BetaResponse",
+            "description": "The response that is in progress.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "response",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.in_progress",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.in_progress\",\n  \"response\": {\n    \"id\": \"resp_67ccfcdd16748190a91872c75d38539e09e4d4aac714747c\",\n    \"object\": \"response\",\n    \"created_at\": 1741487325,\n    \"status\": \"in_progress\",\n    \"completed_at\": null,\n    \"error\": null,\n    \"incomplete_details\": null,\n    \"instructions\": null,\n    \"max_output_tokens\": null,\n    \"model\": \"gpt-6-astra\",\n    \"output\": [],\n    \"parallel_tool_calls\": true,\n    \"previous_response_id\": null,\n    \"reasoning\": {\n      \"effort\": null,\n      \"summary\": null\n    },\n    \"store\": true,\n    \"temperature\": 1,\n    \"text\": {\n      \"format\": {\n        \"type\": \"text\"\n      }\n    },\n    \"tool_choice\": \"auto\",\n    \"tools\": [],\n    \"top_p\": 1,\n    \"truncation\": \"disabled\",\n    \"usage\": null,\n    \"user\": null,\n    \"metadata\": {}\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseShellCallOutputContentDoneStreamingEvent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.shell_call_output_content.done"
+            ],
+            "description": "The type of the event, always `response.shell_call_output_content.done`.",
+            "default": "response.shell_call_output_content.done",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the event that was emitted."
+          },
+          "agent": {
+            "$ref": "#/components/schemas/BetaAgentTag",
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that was updated."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that was updated."
+          },
+          "command_index": {
+            "type": "integer",
+            "description": "The index of the shell command that produced output."
+          },
+          "output": {
+            "items": {
+              "$ref": "#/components/schemas/BetaFunctionShellCallOutputContent"
+            },
+            "type": "array",
+            "description": "The output contents emitted for the shell command."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "sequence_number",
+          "item_id",
+          "output_index",
+          "command_index",
+          "output"
+        ],
+        "title": "Response shell call output content done event",
+        "description": "A streaming event that indicated shell call output was completed."
+      },
+      "BetaResponseShellCallOutputContentDeltaStreamingEvent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.shell_call_output_content.delta"
+            ],
+            "description": "The type of the event, always `response.shell_call_output_content.delta`.",
+            "default": "response.shell_call_output_content.delta",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the event that was emitted."
+          },
+          "agent": {
+            "$ref": "#/components/schemas/BetaAgentTag",
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that was updated."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that was updated."
+          },
+          "command_index": {
+            "type": "integer",
+            "description": "The index of the shell command that produced output."
+          },
+          "delta": {
+            "$ref": "#/components/schemas/BetaShellCallOutputDelta",
+            "description": "The stdout/stderr delta that was emitted."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "sequence_number",
+          "item_id",
+          "output_index",
+          "command_index",
+          "delta"
+        ],
+        "title": "Response shell call output content delta event",
+        "description": "A streaming event that indicated shell call output was incrementally added."
+      },
+      "BetaShellCallOutputDelta": {
+        "properties": {
+          "stdout": {
+            "type": "string",
+            "description": "The stdout delta that was emitted."
+          },
+          "stderr": {
+            "type": "string",
+            "description": "The stderr delta that was emitted."
+          }
+        },
+        "type": "object",
+        "required": [],
+        "title": "Shell call output delta",
+        "description": "A delta of stdout/stderr emitted while a shell call was running."
+      },
+      "BetaResponseShellCallCommandDoneStreamingEvent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.shell_call_command.done"
+            ],
+            "description": "The type of the event, always `response.shell_call_command.done`.",
+            "default": "response.shell_call_command.done",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the event that was emitted."
+          },
+          "agent": {
+            "$ref": "#/components/schemas/BetaAgentTag",
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that was updated."
+          },
+          "command_index": {
+            "type": "integer",
+            "description": "The index of the shell command that was completed."
+          },
+          "command": {
+            "type": "string",
+            "description": "The final shell command that was emitted."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "sequence_number",
+          "output_index",
+          "command_index",
+          "command"
+        ],
+        "title": "Response shell command done event",
+        "description": "A streaming event that indicated a shell command was completed."
+      },
+      "BetaResponseShellCallCommandDeltaStreamingEvent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.shell_call_command.delta"
+            ],
+            "description": "The type of the event, always `response.shell_call_command.delta`.",
+            "default": "response.shell_call_command.delta",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the event that was emitted."
+          },
+          "agent": {
+            "$ref": "#/components/schemas/BetaAgentTag",
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that was updated."
+          },
+          "command_index": {
+            "type": "integer",
+            "description": "The index of the shell command that was updated."
+          },
+          "delta": {
+            "type": "string",
+            "description": "The shell command delta that was appended."
+          },
+          "obfuscation": {
+            "type": "string",
+            "description": "An obfuscation string that was added to pad the event payload."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "sequence_number",
+          "output_index",
+          "command_index",
+          "delta"
+        ],
+        "title": "Response shell command delta event",
+        "description": "A streaming event that indicated a shell command was incrementally updated."
+      },
+      "BetaResponseShellCallCommandAddedStreamingEvent": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.shell_call_command.added"
+            ],
+            "description": "The type of the event, always `response.shell_call_command.added`.",
+            "default": "response.shell_call_command.added",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the event that was emitted."
+          },
+          "agent": {
+            "$ref": "#/components/schemas/BetaAgentTag",
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that was updated."
+          },
+          "command_index": {
+            "type": "integer",
+            "description": "The index of the shell command that was added."
+          },
+          "command": {
+            "type": "string",
+            "description": "The shell command that was added."
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "sequence_number",
+          "output_index",
+          "command_index",
+          "command"
+        ],
+        "title": "Response shell command added event",
+        "description": "A streaming event that indicated a shell command was added to a tool call."
+      },
+      "BetaResponseFunctionCallArgumentsDoneEvent": {
+        "type": "object",
+        "description": "Emitted when function-call arguments are finalized.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.function_call_arguments.done"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the item."
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          },
+          "arguments": {
+            "type": "string",
+            "description": "The function-call arguments."
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "arguments",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.function_call_arguments.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.function_call_arguments.done\",\n  \"item_id\": \"item-abc\",\n  \"output_index\": 1,\n  \"arguments\": \"{ \\\"arg\\\": 123 }\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseFunctionCallArgumentsDeltaEvent": {
+        "type": "object",
+        "description": "Emitted when there is a partial function-call arguments delta.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.function_call_arguments.delta`.\n",
+            "enum": [
+              "response.function_call_arguments.delta"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that the function-call arguments delta is added to.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the function-call arguments delta is added to.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          },
+          "delta": {
+            "type": "string",
+            "description": "The function-call arguments delta that is added.\n"
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "delta",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.function_call_arguments.delta",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.function_call_arguments.delta\",\n  \"item_id\": \"item-abc\",\n  \"output_index\": 0,\n  \"delta\": \"{ \\\"arg\\\":\"\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseFileSearchCallSearchingEvent": {
+        "type": "object",
+        "description": "Emitted when a file search is currently searching.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.file_search_call.searching`.\n",
+            "enum": [
+              "response.file_search_call.searching"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the file search call is searching.\n"
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that the file search call is initiated.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.file_search_call.searching",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.file_search_call.searching\",\n  \"output_index\": 0,\n  \"item_id\": \"fs_123\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseFileSearchCallInProgressEvent": {
+        "type": "object",
+        "description": "Emitted when a file search call is initiated.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.file_search_call.in_progress`.\n",
+            "enum": [
+              "response.file_search_call.in_progress"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the file search call is initiated.\n"
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that the file search call is initiated.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.file_search_call.in_progress",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.file_search_call.in_progress\",\n  \"output_index\": 0,\n  \"item_id\": \"fs_123\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseFileSearchCallCompletedEvent": {
+        "type": "object",
+        "description": "Emitted when a file search call is completed (results found).",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.file_search_call.completed`.\n",
+            "enum": [
+              "response.file_search_call.completed"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the file search call is initiated.\n"
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that the file search call is initiated.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.file_search_call.completed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.file_search_call.completed\",\n  \"output_index\": 0,\n  \"item_id\": \"fs_123\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseErrorEvent": {
+        "type": "object",
+        "description": "Emitted when an error occurs.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `error`.\n",
+            "enum": [
+              "error"
+            ],
+            "x-stainless-const": true
+          },
+          "code": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The error code.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "message": {
+            "type": "string",
+            "description": "The error message.\n"
+          },
+          "param": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The error parameter.\n"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "code",
+          "message",
+          "param",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "error",
+          "group": "responses",
+          "example": "{\n  \"type\": \"error\",\n  \"code\": \"ERR_SOMETHING\",\n  \"message\": \"Something went wrong\",\n  \"param\": null,\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseCreatedEvent": {
+        "type": "object",
+        "description": "An event that is emitted when a response is created.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.created`.\n",
+            "enum": [
+              "response.created"
+            ],
+            "x-stainless-const": true
+          },
+          "response": {
+            "$ref": "#/components/schemas/BetaResponse",
+            "description": "The response that was created.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number for this event."
+          }
+        },
+        "required": [
+          "type",
+          "response",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.created",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.created\",\n  \"response\": {\n    \"id\": \"resp_67ccfcdd16748190a91872c75d38539e09e4d4aac714747c\",\n    \"object\": \"response\",\n    \"created_at\": 1741487325,\n    \"status\": \"in_progress\",\n    \"completed_at\": null,\n    \"error\": null,\n    \"incomplete_details\": null,\n    \"instructions\": null,\n    \"max_output_tokens\": null,\n    \"model\": \"gpt-6-astra\",\n    \"output\": [],\n    \"parallel_tool_calls\": true,\n    \"previous_response_id\": null,\n    \"reasoning\": {\n      \"effort\": null,\n      \"summary\": null\n    },\n    \"store\": true,\n    \"temperature\": 1,\n    \"text\": {\n      \"format\": {\n        \"type\": \"text\"\n      }\n    },\n    \"tool_choice\": \"auto\",\n    \"tools\": [],\n    \"top_p\": 1,\n    \"truncation\": \"disabled\",\n    \"usage\": null,\n    \"user\": null,\n    \"metadata\": {}\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseContentPartDoneEvent": {
+        "type": "object",
+        "description": "Emitted when a content part is done.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.content_part.done`.\n",
+            "enum": [
+              "response.content_part.done"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that the content part was added to.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the content part was added to.\n"
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part that is done.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          },
+          "part": {
+            "$ref": "#/components/schemas/BetaOutputContent",
+            "description": "The content part that is done.\n"
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "content_index",
+          "part",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.content_part.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.content_part.done\",\n  \"item_id\": \"msg_123\",\n  \"output_index\": 0,\n  \"content_index\": 0,\n  \"sequence_number\": 1,\n  \"part\": {\n    \"type\": \"output_text\",\n    \"text\": \"In a shimmering forest under a sky full of stars, a lonely unicorn named Lila discovered a hidden pond that glowed with moonlight. Every night, she would leave sparkling, magical flowers by the water's edge, hoping to share her beauty with others. One enchanting evening, she woke to find a group of friendly animals gathered around, eager to be friends and share in her magic.\",\n    \"annotations\": []\n  }\n}\n"
+        }
+      },
+      "BetaOutputContent": {
+        "oneOf": [
+          {
+            "$ref": "#/components/schemas/BetaOutputTextContent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaRefusalContent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaReasoningTextContent"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "BetaResponseContentPartAddedEvent": {
+        "type": "object",
+        "description": "Emitted when a new content part is added.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.content_part.added`.\n",
+            "enum": [
+              "response.content_part.added"
+            ],
+            "x-stainless-const": true
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The ID of the output item that the content part was added to.\n"
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the content part was added to.\n"
+          },
+          "content_index": {
+            "type": "integer",
+            "description": "The index of the content part that was added.\n"
+          },
+          "part": {
+            "$ref": "#/components/schemas/BetaOutputContent",
+            "description": "The content part that was added.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "item_id",
+          "output_index",
+          "content_index",
+          "part",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.content_part.added",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.content_part.added\",\n  \"item_id\": \"msg_123\",\n  \"output_index\": 0,\n  \"content_index\": 0,\n  \"part\": {\n    \"type\": \"output_text\",\n    \"text\": \"\",\n    \"annotations\": []\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseCompletedEvent": {
+        "type": "object",
+        "description": "Emitted when the model response is complete.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.completed`.\n",
+            "enum": [
+              "response.completed"
+            ],
+            "x-stainless-const": true
+          },
+          "response": {
+            "$ref": "#/components/schemas/BetaResponse",
+            "description": "Properties of the completed response.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number for this event."
+          }
+        },
+        "required": [
+          "type",
+          "response",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.completed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.completed\",\n  \"response\": {\n    \"id\": \"resp_123\",\n    \"object\": \"response\",\n    \"created_at\": 1740855869,\n    \"status\": \"completed\",\n    \"completed_at\": 1740855870,\n    \"error\": null,\n    \"incomplete_details\": null,\n    \"input\": [],\n    \"instructions\": null,\n    \"max_output_tokens\": null,\n    \"model\": \"gpt-6-astra\",\n    \"output\": [\n      {\n        \"id\": \"msg_123\",\n        \"type\": \"message\",\n        \"role\": \"assistant\",\n        \"content\": [\n          {\n            \"type\": \"output_text\",\n            \"text\": \"In a shimmering forest under a sky full of stars, a lonely unicorn named Lila discovered a hidden pond that glowed with moonlight. Every night, she would leave sparkling, magical flowers by the water's edge, hoping to share her beauty with others. One enchanting evening, she woke to find a group of friendly animals gathered around, eager to be friends and share in her magic.\",\n            \"annotations\": []\n          }\n        ]\n      }\n    ],\n    \"previous_response_id\": null,\n    \"reasoning_effort\": null,\n    \"store\": false,\n    \"temperature\": 1,\n    \"text\": {\n      \"format\": {\n        \"type\": \"text\"\n      }\n    },\n    \"tool_choice\": \"auto\",\n    \"tools\": [],\n    \"top_p\": 1,\n    \"truncation\": \"disabled\",\n    \"usage\": {\n      \"input_tokens\": 0,\n      \"output_tokens\": 0,\n      \"output_tokens_details\": {\n        \"reasoning_tokens\": 0\n      },\n      \"total_tokens\": 0\n    },\n    \"user\": null,\n    \"metadata\": {}\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseCodeInterpreterCallInterpretingEvent": {
+        "type": "object",
+        "description": "Emitted when the code interpreter is actively interpreting the code snippet.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.code_interpreter_call.interpreting`.",
+            "enum": [
+              "response.code_interpreter_call.interpreting"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response for which the code interpreter is interpreting code."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the code interpreter tool call item."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event, used to order streaming events."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.code_interpreter_call.interpreting",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.code_interpreter_call.interpreting\",\n  \"output_index\": 4,\n  \"item_id\": \"ci_12345\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseCodeInterpreterCallInProgressEvent": {
+        "type": "object",
+        "description": "Emitted when a code interpreter call is in progress.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.code_interpreter_call.in_progress`.",
+            "enum": [
+              "response.code_interpreter_call.in_progress"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response for which the code interpreter call is in progress."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the code interpreter tool call item."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event, used to order streaming events."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.code_interpreter_call.in_progress",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.code_interpreter_call.in_progress\",\n  \"output_index\": 0,\n  \"item_id\": \"ci_12345\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseCodeInterpreterCallCompletedEvent": {
+        "type": "object",
+        "description": "Emitted when the code interpreter call is completed.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.code_interpreter_call.completed`.",
+            "enum": [
+              "response.code_interpreter_call.completed"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response for which the code interpreter call is completed."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the code interpreter tool call item."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event, used to order streaming events."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.code_interpreter_call.completed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.code_interpreter_call.completed\",\n  \"output_index\": 5,\n  \"item_id\": \"ci_12345\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseCodeInterpreterCallCodeDoneEvent": {
+        "type": "object",
+        "description": "Emitted when the code snippet is finalized by the code interpreter.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.code_interpreter_call_code.done`.",
+            "enum": [
+              "response.code_interpreter_call_code.done"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response for which the code is finalized."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the code interpreter tool call item."
+          },
+          "code": {
+            "type": "string",
+            "description": "The final code snippet output by the code interpreter."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event, used to order streaming events."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "code",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.code_interpreter_call_code.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.code_interpreter_call_code.done\",\n  \"output_index\": 3,\n  \"item_id\": \"ci_12345\",\n  \"code\": \"print('done')\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseCodeInterpreterCallCodeDeltaEvent": {
+        "type": "object",
+        "description": "Emitted when a partial code snippet is streamed by the code interpreter.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.code_interpreter_call_code.delta`.",
+            "enum": [
+              "response.code_interpreter_call_code.delta"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item in the response for which the code is being streamed."
+          },
+          "item_id": {
+            "type": "string",
+            "description": "The unique identifier of the code interpreter tool call item."
+          },
+          "delta": {
+            "type": "string",
+            "description": "The partial code snippet being streamed by the code interpreter."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event, used to order streaming events."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "delta",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.code_interpreter_call_code.delta",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.code_interpreter_call_code.delta\",\n  \"output_index\": 0,\n  \"item_id\": \"ci_12345\",\n  \"delta\": \"print('Hello, world')\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseAudioTranscriptDoneEvent": {
+        "type": "object",
+        "description": "Emitted when the full audio transcript is completed.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.audio.transcript.done`.\n",
+            "enum": [
+              "response.audio.transcript.done"
+            ],
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "response_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.audio.transcript.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.audio.transcript.done\",\n  \"response_id\": \"resp_123\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseAudioTranscriptDeltaEvent": {
+        "type": "object",
+        "description": "Emitted when there is a partial transcript of audio.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.audio.transcript.delta`.\n",
+            "enum": [
+              "response.audio.transcript.delta"
+            ],
+            "x-stainless-const": true
+          },
+          "delta": {
+            "type": "string",
+            "description": "The partial transcript of the audio response.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "response_id",
+          "delta",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.audio.transcript.delta",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.audio.transcript.delta\",\n  \"response_id\": \"resp_123\",\n  \"delta\": \" ... partial transcript ... \",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseAudioDoneEvent": {
+        "type": "object",
+        "description": "Emitted when the audio response is complete.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.audio.done`.\n",
+            "enum": [
+              "response.audio.done"
+            ],
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the delta.\n"
+          }
+        },
+        "required": [
+          "type",
+          "sequence_number",
+          "response_id"
+        ],
+        "x-oaiMeta": {
+          "name": "response.audio.done",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.audio.done\",\n  \"response_id\": \"resp-123\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseAudioDeltaEvent": {
+        "type": "object",
+        "description": "Emitted when there is a partial audio response.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.audio.delta`.\n",
+            "enum": [
+              "response.audio.delta"
+            ],
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "A sequence number for this chunk of the stream response.\n"
+          },
+          "delta": {
+            "type": "string",
+            "description": "A chunk of Base64 encoded response audio bytes.\n"
+          }
+        },
+        "required": [
+          "type",
+          "delta",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.audio.delta",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.audio.delta\",\n  \"response_id\": \"resp_123\",\n  \"delta\": \"base64encoded...\",\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseIncompleteEvent": {
+        "type": "object",
+        "description": "An event that is emitted when a response finishes as incomplete.\n\nOver WebSocket, steering can finish a response with\n`response.incomplete_details.reason` set to `steered`, followed automatically\nby a successor `response.created` that commits the queued steering input.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.incomplete`.\n",
+            "enum": [
+              "response.incomplete"
+            ],
+            "x-stainless-const": true
+          },
+          "response": {
+            "$ref": "#/components/schemas/BetaResponse",
+            "description": "The response that was incomplete.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          }
+        },
+        "required": [
+          "type",
+          "response",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.incomplete",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.incomplete\",\n  \"response\": {\n    \"id\": \"resp_123\",\n    \"object\": \"response\",\n    \"created_at\": 1740855869,\n    \"status\": \"incomplete\",\n    \"completed_at\": null,\n    \"error\": null,\n    \"incomplete_details\": {\n      \"reason\": \"max_tokens\"\n    },\n    \"instructions\": null,\n    \"max_output_tokens\": null,\n    \"model\": \"gpt-6-astra\",\n    \"output\": [],\n    \"previous_response_id\": null,\n    \"reasoning_effort\": null,\n    \"store\": false,\n    \"temperature\": 1,\n    \"text\": {\n      \"format\": {\n        \"type\": \"text\"\n      }\n    },\n    \"tool_choice\": \"auto\",\n    \"tools\": [],\n    \"top_p\": 1,\n    \"truncation\": \"disabled\",\n    \"usage\": null,\n    \"user\": null,\n    \"metadata\": {}\n  },\n  \"sequence_number\": 1\n}\n"
+        }
+      },
+      "BetaResponseFailedEvent": {
+        "type": "object",
+        "description": "An event that is emitted when a response fails.\n",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.failed`.\n",
+            "enum": [
+              "response.failed"
+            ],
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of this event."
+          },
+          "response": {
+            "$ref": "#/components/schemas/BetaResponse",
+            "description": "The response that failed.\n"
+          }
+        },
+        "required": [
+          "type",
+          "response",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.failed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.failed\",\n  \"response\": {\n    \"id\": \"resp_123\",\n    \"object\": \"response\",\n    \"created_at\": 1740855869,\n    \"status\": \"failed\",\n    \"completed_at\": null,\n    \"error\": {\n      \"code\": \"server_error\",\n      \"message\": \"The model failed to generate a response.\"\n    },\n    \"incomplete_details\": null,\n    \"instructions\": null,\n    \"max_output_tokens\": null,\n    \"model\": \"gpt-6-astra\",\n    \"output\": [],\n    \"previous_response_id\": null,\n    \"reasoning_effort\": null,\n    \"store\": false,\n    \"temperature\": 1,\n    \"text\": {\n      \"format\": {\n        \"type\": \"text\"\n      }\n    },\n    \"tool_choice\": \"auto\",\n    \"tools\": [],\n    \"top_p\": 1,\n    \"truncation\": \"disabled\",\n    \"usage\": null,\n    \"user\": null,\n    \"metadata\": {}\n  }\n}\n"
+        }
+      },
+      "BetaResponseWebSearchCallCompletedEvent": {
+        "type": "object",
+        "description": "Emitted when a web search call is completed.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.web_search_call.completed`.\n",
+            "enum": [
+              "response.web_search_call.completed"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the web search call is associated with.\n"
+          },
+          "item_id": {
+            "type": "string",
+            "description": "Unique ID for the output item associated with the web search call.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the web search call being processed."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.web_search_call.completed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.web_search_call.completed\",\n  \"output_index\": 0,\n  \"item_id\": \"ws_123\",\n  \"sequence_number\": 0\n}\n"
+        }
+      },
+      "BetaResponseWebSearchCallSearchingEvent": {
+        "type": "object",
+        "description": "Emitted when a web search call is executing.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.web_search_call.searching`.\n",
+            "enum": [
+              "response.web_search_call.searching"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the web search call is associated with.\n"
+          },
+          "item_id": {
+            "type": "string",
+            "description": "Unique ID for the output item associated with the web search call.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the web search call being processed."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.web_search_call.searching",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.web_search_call.searching\",\n  \"output_index\": 0,\n  \"item_id\": \"ws_123\",\n  \"sequence_number\": 0\n}\n"
+        }
+      },
+      "BetaResponseWebSearchCallInProgressEvent": {
+        "type": "object",
+        "description": "Emitted when a web search call is initiated.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `response.web_search_call.in_progress`.\n",
+            "enum": [
+              "response.web_search_call.in_progress"
+            ],
+            "x-stainless-const": true
+          },
+          "output_index": {
+            "type": "integer",
+            "description": "The index of the output item that the web search call is associated with.\n"
+          },
+          "item_id": {
+            "type": "string",
+            "description": "Unique ID for the output item associated with the web search call.\n"
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of the web search call being processed."
+          }
+        },
+        "required": [
+          "type",
+          "output_index",
+          "item_id",
+          "sequence_number"
+        ],
+        "x-oaiMeta": {
+          "name": "response.web_search_call.in_progress",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.web_search_call.in_progress\",\n  \"output_index\": 0,\n  \"item_id\": \"ws_123\",\n  \"sequence_number\": 0\n}\n"
+        }
+      },
+      "BetaResponseSteerFailedEvent": {
+        "type": "object",
+        "title": "ResponseSteerFailedEvent",
+        "description": "Emitted when steering input is rejected or cannot be committed to a\nsuccessor response. Returns the original, uncommitted input so the client\ncan carry it into `response.create` when appropriate. Invalid input must\nbe corrected before retrying.\n\nFailures after acceptance include the same steering ID. Failures before an\nID is allocated omit `steer.id`. A lost connection or missing acknowledgement\nleaves the outcome unknown; it is not proof that the input was rejected.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.steer.failed"
+            ],
+            "description": "The event discriminator. Always `response.steer.failed`.",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number for this event."
+          },
+          "steer": {
+            "type": "object",
+            "description": "The steering submission that could not be committed.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID assigned to the steering submission, if one was allocated.\n"
+              },
+              "previous_response_id": {
+                "type": "string",
+                "description": "The ID of the response that was targeted for steering."
+              },
+              "input": {
+                "$ref": "#/components/schemas/BetaResponseSteerInput"
+              }
+            },
+            "required": [
+              "previous_response_id",
+              "input"
+            ]
+          },
+          "error": {
+            "type": "object",
+            "description": "Information about why the input could not be committed.",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "invalid_request_error"
+                ],
+                "description": "The error type. Always `invalid_request_error`.",
+                "x-stainless-const": true
+              },
+              "code": {
+                "$ref": "#/components/schemas/BetaResponseSteerErrorCode"
+              },
+              "message": {
+                "type": "string",
+                "description": "A human-readable description of the error."
+              }
+            },
+            "required": [
+              "type",
+              "code",
+              "message"
+            ]
+          },
+          "stream_id": {
+            "type": "string",
+            "description": "The WebSocket lane that emitted this event, when the target response is\navailable and its `response.create` event supplied a `stream_id`.\n"
+          }
+        },
+        "required": [
+          "type",
+          "sequence_number",
+          "steer",
+          "error"
+        ],
+        "x-oaiMeta": {
+          "name": "response.steer.failed",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.steer.failed\",\n  \"sequence_number\": 5,\n  \"steer\": {\n    \"id\": \"steer_456\",\n    \"previous_response_id\": \"resp_123\",\n    \"input\": [\n      {\n        \"type\": \"message\",\n        \"role\": \"user\",\n        \"content\": [\n          {\n            \"type\": \"input_text\",\n            \"text\": \"Prioritize the database rollout.\"\n          }\n        ]\n      }\n    ]\n  },\n  \"error\": {\n    \"type\": \"invalid_request_error\",\n    \"code\": \"successor_creation_failed\",\n    \"message\": \"We couldn't start the next response. Send this steering input again with response.create.\"\n  }\n}\n"
+        }
+      },
+      "BetaResponseSteerErrorCode": {
+        "title": "ResponseSteerErrorCode",
+        "description": "A machine-readable steering error code. Clients should handle unknown\nvalues because additional codes may be introduced. Known values include:\n- `response_not_found`: The target response is not available on this connection.\n- `invalid_input`: The event or input failed validation.\n- `steering_not_supported`: The model or response execution mode does not support steering.\n- `too_many_pending_steers`: Too much steering input is pending for the response.\n- `response_already_completed`: The response completed and is no longer accepting steering input.\n- `response_not_active`: The response is no longer accepting steering input.\n- `successor_creation_failed`: The successor response could not be created.\n",
+        "anyOf": [
+          {
+            "type": "string",
+            "enum": [
+              "response_not_found",
+              "invalid_input",
+              "steering_not_supported",
+              "too_many_pending_steers",
+              "response_already_completed",
+              "response_not_active",
+              "successor_creation_failed"
+            ]
+          },
+          {
+            "type": "string"
+          }
+        ]
+      },
+      "BetaResponseSteerInput": {
+        "title": "ResponseSteerInput",
+        "description": "Input to queue for a continuation of the response. Uses the same string or\ninput-item shape as `response.create.input`, with a non-empty array when\nsupplying input items.\n\nSteering accepts only messages with the `user` role. Each message may\ncontain only `type`, `role`, and `content`, with `content` as a string or an\narray of `input_text`, `input_image`, and `input_file` parts. The optional\n`type` must be `message`. Other roles, tool outputs, and item types are not\nsupported for steering.\n",
+        "oneOf": [
+          {
+            "type": "string",
+            "title": "Text input",
+            "description": "A text input, equivalent to a message with the `user` role."
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseSteerInputItemList"
+          }
+        ]
+      },
+      "BetaResponseSteerInputItemList": {
+        "type": "array",
+        "title": "Response steer input item list",
+        "description": "A non-empty list of message inputs to queue for the response.",
+        "minItems": 1,
+        "items": {
+          "$ref": "#/components/schemas/BetaResponseSteerInputItem"
+        }
+      },
+      "BetaResponseSteerInputItem": {
+        "title": "Response steer input item",
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/BetaUserMessageItemParam"
+          },
+          {
+            "$ref": "#/components/schemas/BetaFunctionCallOutputItemParam"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "BetaUserMessageItemParam": {
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/Beta_AgentTagParam",
+                "description": "The agent that produced this item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The unique ID of this message item.",
+                "example": "msg_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "type": {
+            "type": "string",
+            "enum": [
+              "message"
+            ],
+            "description": "The item type. Always `message`.",
+            "default": "message",
+            "x-stainless-const": true
+          },
+          "role": {
+            "type": "string",
+            "enum": [
+              "user"
+            ],
+            "description": "The message role. Always `user`.",
+            "default": "user",
+            "x-stainless-const": true
+          },
+          "content": {
+            "oneOf": [
+              {
+                "items": {
+                  "oneOf": [
+                    {
+                      "$ref": "#/components/schemas/BetaInputTextContentParam"
+                    },
+                    {
+                      "$ref": "#/components/schemas/BetaInputImageContentParamAutoParam"
+                    },
+                    {
+                      "$ref": "#/components/schemas/BetaInputFileContentParam"
+                    }
+                  ],
+                  "description": "A piece of message content, such as text, an image, or a file.",
+                  "discriminator": {
+                    "propertyName": "type"
+                  }
+                },
+                "type": "array"
+              },
+              {
+                "type": "string",
+                "maxLength": 10485760,
+                "description": "The message content, as a single string."
+              }
+            ],
+            "description": "The message content, as an array of content parts."
+          },
+          "status": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The status of the message item."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "role",
+          "content"
+        ]
+      },
+      "BetaResponseSteerPendingEvent": {
+        "type": "object",
+        "title": "ResponseSteerPendingEvent",
+        "description": "Emitted when accepted steering input remains queued after the target\nresponse completes. The server still owns the input. Do not resend it.\nThe successor's `response.created` event is the commit point.\n\nWhen `reason` is `waiting_for_required_input`, this event follows\n`response.completed` while the response waits for the tool results or\napproval decisions identified by `required_input`. Copy those stubs, fill\ntheir result fields using the ordinary `response.create` input schemas,\nand submit one continuation per parent with the same `previous_response_id`\nand WebSocket lane. Use saved results without rerunning tools. The queued\nsteering input is prepended in submission order to the continuation's\ninput. That explicit request retains its own settings.\n\nThis notification is emitted at most once per steering submission. Multiple\nsubmissions for the same parent can report the same required inputs; they\ndo not each require a separate continuation.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.steer.pending"
+            ],
+            "description": "The event discriminator. Always `response.steer.pending`.",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number for this event."
+          },
+          "steer": {
+            "type": "object",
+            "description": "The steering submission that remains queued.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID assigned to the steering submission."
+              },
+              "previous_response_id": {
+                "type": "string",
+                "description": "The ID of the response being steered."
+              }
+            },
+            "required": [
+              "id",
+              "previous_response_id"
+            ]
+          },
+          "reason": {
+            "$ref": "#/components/schemas/BetaResponseSteerPendingReason"
+          },
+          "required_input": {
+            "type": "array",
+            "minItems": 1,
+            "description": "Input stubs identifying outstanding client-owned tool results or\napproval decisions. Each stub contains identifying fields only; the\nclient supplies the result before including it in `response.create`.\n",
+            "items": {
+              "$ref": "#/components/schemas/BetaResponseSteerRequiredInput"
+            }
+          },
+          "stream_id": {
+            "type": "string",
+            "description": "The WebSocket lane that emitted this event. This field is present when\nthe target response's `response.create` event supplied a `stream_id`.\n"
+          }
+        },
+        "required": [
+          "type",
+          "sequence_number",
+          "steer",
+          "reason",
+          "required_input"
+        ],
+        "x-oaiMeta": {
+          "name": "response.steer.pending",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.steer.pending\",\n  \"sequence_number\": 10,\n  \"steer\": {\n    \"id\": \"steer_456\",\n    \"previous_response_id\": \"resp_123\"\n  },\n  \"reason\": \"waiting_for_required_input\",\n  \"required_input\": [\n    {\n      \"type\": \"function_call_output\",\n      \"call_id\": \"call_789\",\n      \"name\": \"lookup\"\n    }\n  ]\n}\n"
+        }
+      },
+      "BetaResponseSteerRequiredInput": {
+        "title": "ResponseSteerRequiredInput",
+        "description": "An input stub identifying an outstanding client-owned tool result or\napproval decision. Copy the stub and fill the result fields using the\ncorresponding `response.create` input schema. Use saved results without\nrerunning the tool. The server does not supply results, approval decisions,\nor safety acknowledgements in these stubs.\n",
+        "oneOf": [
+          {
+            "type": "object",
+            "title": "Required function tool call output",
+            "additionalProperties": false,
+            "description": "Supply `output` using the function tool call output input schema.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "function_call_output"
+                ],
+                "x-stainless-const": true
+              },
+              "call_id": {
+                "type": "string"
+              },
+              "name": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "type",
+              "call_id",
+              "name"
+            ]
+          },
+          {
+            "type": "object",
+            "title": "Required custom tool call output",
+            "additionalProperties": false,
+            "description": "Supply `output` using the custom tool call output input schema. The\noriginal custom tool call supplies the tool's name.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "custom_tool_call_output"
+                ],
+                "x-stainless-const": true
+              },
+              "call_id": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "type",
+              "call_id"
+            ]
+          },
+          {
+            "type": "object",
+            "title": "Required computer tool call output",
+            "additionalProperties": false,
+            "description": "Supply `output` using the computer tool call output input schema,\nincluding any required `acknowledged_safety_checks`.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "computer_call_output"
+                ],
+                "x-stainless-const": true
+              },
+              "call_id": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "type",
+              "call_id"
+            ]
+          },
+          {
+            "type": "object",
+            "title": "Required shell tool call output",
+            "additionalProperties": false,
+            "description": "Supply `output` using the shell tool call output input schema. Each\noutput entry includes `stdout`, `stderr`, and `outcome`.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "shell_call_output"
+                ],
+                "x-stainless-const": true
+              },
+              "call_id": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "type",
+              "call_id"
+            ]
+          },
+          {
+            "type": "object",
+            "title": "Required apply patch tool call output",
+            "additionalProperties": false,
+            "description": "Supply `status` and optional `output` using the apply patch tool call\noutput input schema.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "apply_patch_call_output"
+                ],
+                "x-stainless-const": true
+              },
+              "call_id": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "type",
+              "call_id"
+            ]
+          },
+          {
+            "type": "object",
+            "title": "Required tool search output",
+            "additionalProperties": false,
+            "description": "Supply `tools` using the tool search output input schema, retaining\n`execution: \"client\"`.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "tool_search_output"
+                ],
+                "x-stainless-const": true
+              },
+              "call_id": {
+                "type": "string"
+              },
+              "execution": {
+                "type": "string",
+                "enum": [
+                  "client"
+                ],
+                "x-stainless-const": true
+              }
+            },
+            "required": [
+              "type",
+              "call_id",
+              "execution"
+            ]
+          },
+          {
+            "type": "object",
+            "title": "Required MCP approval response",
+            "additionalProperties": false,
+            "description": "Supply `approve` using the MCP approval response input schema. An\noptional `reason` can be supplied when denying the request. The original\napproval request identifies the tool and server.\n",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "mcp_approval_response"
+                ],
+                "x-stainless-const": true
+              },
+              "approval_request_id": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "type",
+              "approval_request_id"
+            ]
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      },
+      "BetaResponseSteerPendingReason": {
+        "title": "ResponseSteerPendingReason",
+        "description": "An extensible enum describing why accepted steering input is still queued.\nClients should handle unknown values because additional reasons may be\nintroduced. Known values include:\n- `waiting_for_required_input`: The response is waiting for the tool results or approval decisions identified by `required_input`.\n",
+        "anyOf": [
+          {
+            "type": "string",
+            "enum": [
+              "waiting_for_required_input"
+            ]
+          },
+          {
+            "type": "string"
+          }
+        ]
+      },
+      "BetaResponseSteerAcceptedEvent": {
+        "type": "object",
+        "title": "ResponseSteerAcceptedEvent",
+        "description": "Emitted when steering input has been validated and queued. Acceptance means\nthe server owns the input, not that it has been applied. The successor's\n`response.created` event is the commit point. If accepted input cannot be\ncommitted, `response.steer.failed` returns it with the same steering ID.\n\nWhen the response stops for client-owned tool output or approval, the input\nremains queued and `response.steer.pending` is emitted after\n`response.completed`. Fill the pending event's `required_input` stubs with\nsaved results and send one matching explicit `response.create` per parent.\nDo not resend accepted input while it is still queued.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.steer.accepted"
+            ],
+            "description": "The event discriminator. Always `response.steer.accepted`.",
+            "x-stainless-const": true
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number for this event."
+          },
+          "steer": {
+            "type": "object",
+            "description": "The accepted steering submission.",
+            "properties": {
+              "id": {
+                "type": "string",
+                "description": "The ID assigned to the steering submission."
+              },
+              "previous_response_id": {
+                "type": "string",
+                "description": "The ID of the response being steered."
+              }
+            },
+            "required": [
+              "id",
+              "previous_response_id"
+            ]
+          },
+          "stream_id": {
+            "type": "string",
+            "description": "The WebSocket lane that emitted this event. This field is present when\nthe target response's `response.create` event supplied a `stream_id`.\n"
+          }
+        },
+        "required": [
+          "type",
+          "sequence_number",
+          "steer"
+        ],
+        "x-oaiMeta": {
+          "name": "response.steer.accepted",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.steer.accepted\",\n  \"sequence_number\": 2,\n  \"steer\": {\n    \"id\": \"steer_456\",\n    \"previous_response_id\": \"resp_123\"\n  }\n}\n"
+        }
+      },
+      "BetaResponseSteerEvent": {
+        "type": "object",
+        "title": "ResponseSteerEvent",
+        "additionalProperties": false,
+        "description": "Queues user input to steer a response on this WebSocket connection. Input\ncan contain text, images, and files. Steering is supported only for\nsingle-agent responses on models and execution modes that support steering.\nResponses bound to a conversation or using automatic compaction do not\nsupport steering.\n\nA `response.steer.accepted` event acknowledges that the server owns the\nqueued input, not that it has been applied. The successor's `response.created`\nevent is the commit point. Input that cannot be committed is returned in\n`response.steer.failed`.\n\nSteering may cause the active response to finish at a safe output boundary\nwith `response.incomplete` and `incomplete_details.reason` set to `steered`,\nfollowed automatically by a successor `response.created`. Normal completion\ncan also be followed by an automatic successor. Automatic successors inherit\nthe previous response's settings and continue from it with the queued input.\n\nIf the response stops for client-owned tool output or approval, accepted\nsteering input remains queued and `response.steer.pending` is emitted after\n`response.completed`. Fill the `required_input` stubs from that event with\nsaved tool results or approval decisions, and send one explicit\n`response.create` per parent with the same `previous_response_id` and\nWebSocket lane. Do not rerun tools or resend accepted steering input. The\nqueued input is prepended in submission order to that request's input, and\nthe explicit request retains its own settings.\n\nThis event accepts only `type`, `previous_response_id`, and `input`. Do not\nsend `stream_id`; the target response determines the WebSocket lane.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.steer"
+            ],
+            "description": "The event discriminator. Always `response.steer`.",
+            "x-stainless-const": true
+          },
+          "previous_response_id": {
+            "type": "string",
+            "description": "The ID of the response to steer on this WebSocket connection."
+          },
+          "input": {
+            "$ref": "#/components/schemas/BetaResponseSteerInput"
+          }
+        },
+        "required": [
+          "type",
+          "previous_response_id",
+          "input"
+        ],
+        "x-oaiMeta": {
+          "name": "response.steer",
+          "group": "responses",
+          "example": "{\n  \"type\": \"response.steer\",\n  \"previous_response_id\": \"resp_123\",\n  \"input\": [\n    {\n      \"type\": \"message\",\n      \"role\": \"user\",\n      \"content\": [\n        {\n          \"type\": \"input_text\",\n          \"text\": \"Prioritize the database rollout.\"\n        }\n      ]\n    }\n  ]\n}\n"
+        }
+      },
+      "BetaOutputAudio": {
+        "type": "object",
+        "title": "Output audio",
+        "description": "An audio output from the model.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the output audio. Always `output_audio`.\n",
+            "enum": [
+              "output_audio"
+            ],
+            "x-stainless-const": true
+          },
+          "data": {
+            "type": "string",
+            "description": "Base64-encoded audio data from the model.\n"
+          },
+          "transcript": {
+            "type": "string",
+            "description": "The transcript of the audio data from the model.\n"
+          }
+        },
+        "required": [
+          "type",
+          "data",
+          "transcript"
+        ]
+      },
+      "BetaInputAudio": {
+        "type": "object",
+        "title": "Input audio",
+        "description": "An audio input to the model.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The type of the input item. Always `input_audio`.\n",
+            "enum": [
+              "input_audio"
+            ],
+            "x-stainless-const": true
+          },
+          "input_audio": {
+            "type": "object",
+            "properties": {
+              "data": {
+                "type": "string",
+                "description": "Base64-encoded audio data.\n"
+              },
+              "format": {
+                "type": "string",
+                "description": "The format of the audio data. Currently supported formats are `mp3` and\n`wav`.\n",
+                "enum": [
+                  "mp3",
+                  "wav"
+                ]
+              }
+            },
+            "required": [
+              "data",
+              "format"
+            ]
+          }
+        },
+        "required": [
+          "type",
+          "input_audio"
+        ]
+      },
+      "BetaInputParam": {
+        "description": "Text, image, or file inputs to the model, used to generate a response.\n\nLearn more:\n- [Text inputs and outputs](https://developers.openai.com/api/docs/guides/text)\n- [Image inputs](https://developers.openai.com/api/docs/guides/images-vision)\n- [File inputs](https://developers.openai.com/api/docs/guides/file-inputs)\n- [Conversation state](https://developers.openai.com/api/docs/guides/conversation-state)\n- [Function calling](https://developers.openai.com/api/docs/guides/function-calling)\n",
+        "oneOf": [
+          {
+            "type": "string",
+            "title": "Text input",
+            "description": "A text input to the model, equivalent to a text input with the\n`user` role.\n"
+          },
+          {
+            "type": "array",
+            "title": "Input item list",
+            "description": "A list of one or many input items to the model, containing\ndifferent content types.\n",
+            "items": {
+              "$ref": "#/components/schemas/BetaInputItem"
+            }
+          }
+        ]
+      },
+      "BetaContent": {
+        "description": "Multi-modal input and output contents.\n",
+        "oneOf": [
+          {
+            "title": "Input content types",
+            "$ref": "#/components/schemas/BetaInputContent"
+          },
+          {
+            "title": "Output content types",
+            "$ref": "#/components/schemas/BetaOutputContent"
+          }
+        ]
+      },
+      "BetaIncludeEnum": {
+        "type": "string",
+        "enum": [
+          "file_search_call.results",
+          "web_search_call.results",
+          "web_search_call.action.sources",
+          "message.input_image.image_url",
+          "computer_call_output.output.image_url",
+          "code_interpreter_call.outputs",
+          "reasoning.encrypted_content",
+          "message.output_text.logprobs"
+        ],
+        "description": "Specify additional output data to include in the model response. Currently supported values are:\n- `web_search_call.results`: Include the search results of the web search tool call.\n- `web_search_call.action.sources`: Include the sources of the web search tool call.\n- `code_interpreter_call.outputs`: Includes the outputs of python code execution in code interpreter tool call items.\n- `computer_call_output.output.image_url`: Include image urls from the computer call output.\n- `file_search_call.results`: Include the search results of the file search tool call.\n- `message.input_image.image_url`: Include image urls from the input message.\n- `message.output_text.logprobs`: Include logprobs with assistant messages.\n- `reasoning.encrypted_content`: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when the `store` parameter is set to `false`, or when an organization is enrolled in the zero data retention program)."
+      },
+      "BetaResponsesServerEvent": {
+        "discriminator": {
+          "propertyName": "type"
+        },
+        "description": "Server events emitted by the Responses WebSocket server.\n",
+        "anyOf": [
+          {
+            "title": "BetaResponseAudioWsDelta",
+            "description": "Emitted when there is a partial audio response.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseAudioDeltaEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseAudioWsDone",
+            "description": "Emitted when the audio response is complete.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseAudioDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseAudioTranscriptWsDelta",
+            "description": "Emitted when there is a partial transcript of audio.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseAudioTranscriptDeltaEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseAudioTranscriptWsDone",
+            "description": "Emitted when the full audio transcript is completed.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseAudioTranscriptDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseCodeInterpreterCallCodeWsDelta",
+            "description": "Emitted when a partial code snippet is streamed by the code interpreter.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseCodeInterpreterCallCodeDeltaEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseCodeInterpreterCallCodeWsDone",
+            "description": "Emitted when the code snippet is finalized by the code interpreter.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseCodeInterpreterCallCodeDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseCodeInterpreterCallWsCompleted",
+            "description": "Emitted when the code interpreter call is completed.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseCodeInterpreterCallCompletedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseCodeInterpreterCallInWsProgress",
+            "description": "Emitted when a code interpreter call is in progress.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseCodeInterpreterCallInProgressEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseCodeInterpreterCallWsInterpreting",
+            "description": "Emitted when the code interpreter is actively interpreting the code snippet.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseCodeInterpreterCallInterpretingEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseWsCompleted",
+            "description": "Emitted when the model response is complete.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseCompletedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseContentPartWsAdded",
+            "description": "Emitted when a new content part is added.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseContentPartAddedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseContentPartWsDone",
+            "description": "Emitted when a content part is done.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseContentPartDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseWsCreated",
+            "description": "An event that is emitted when a response is created.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseCreatedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseFileSearchCallWsCompleted",
+            "description": "Emitted when a file search call is completed (results found).",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseFileSearchCallCompletedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseFileSearchCallInWsProgress",
+            "description": "Emitted when a file search call is initiated.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseFileSearchCallInProgressEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseFileSearchCallWsSearching",
+            "description": "Emitted when a file search is currently searching.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseFileSearchCallSearchingEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseFunctionCallArgumentsWsDelta",
+            "description": "Emitted when there is a partial function-call arguments delta.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseFunctionCallArgumentsDeltaEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseFunctionCallArgumentsWsDone",
+            "description": "Emitted when function-call arguments are finalized.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseFunctionCallArgumentsDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseShellCallCommandWsAdded",
+            "description": "A streaming event that indicated a shell command was added to a tool call.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseShellCallCommandAddedStreamingEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseShellCallCommandWsDelta",
+            "description": "A streaming event that indicated a shell command was incrementally updated.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseShellCallCommandDeltaStreamingEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseShellCallCommandWsDone",
+            "description": "A streaming event that indicated a shell command was completed.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseShellCallCommandDoneStreamingEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseShellCallOutputContentWsDelta",
+            "description": "A streaming event that indicated shell call output was incrementally added.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseShellCallOutputContentDeltaStreamingEvent",
+                "x-stainless-skip": [
+                  "go"
+                ]
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseShellCallOutputContentWsDone",
+            "description": "A streaming event that indicated shell call output was completed.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseShellCallOutputContentDoneStreamingEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseInWsProgress",
+            "description": "Emitted when the response is in progress.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseInProgressEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseWsFailed",
+            "description": "An event that is emitted when a response fails.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseFailedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseWsIncomplete",
+            "description": "An event that is emitted when a response finishes as incomplete.\n\nOver WebSocket, steering can finish a response with\n`response.incomplete_details.reason` set to `steered`, followed automatically\nby a successor `response.created` that commits the queued steering input.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseIncompleteEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseOutputItemWsAdded",
+            "description": "Emitted when a new output item is added.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseOutputItemAddedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseOutputItemWsDone",
+            "description": "Emitted when an output item is marked done.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseOutputItemDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseReasoningSummaryPartWsAdded",
+            "description": "Emitted when a new reasoning summary part is added.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseReasoningSummaryPartAddedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseReasoningSummaryPartWsDone",
+            "description": "Emitted when a reasoning summary part is completed.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseReasoningSummaryPartDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseReasoningSummaryTextWsDelta",
+            "description": "Emitted when a delta is added to a reasoning summary text.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseReasoningSummaryTextDeltaEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseReasoningSummaryTextWsDone",
+            "description": "Emitted when a reasoning summary text is completed.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseReasoningSummaryTextDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseReasoningTextWsDelta",
+            "description": "Emitted when a delta is added to a reasoning text.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseReasoningTextDeltaEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseReasoningTextWsDone",
+            "description": "Emitted when a reasoning text is completed.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseReasoningTextDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseRefusalWsDelta",
+            "description": "Emitted when there is a partial refusal text.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseRefusalDeltaEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseRefusalWsDone",
+            "description": "Emitted when refusal text is finalized.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseRefusalDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseTextWsDelta",
+            "description": "Emitted when there is an additional text delta.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseTextDeltaEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseTextWsDone",
+            "description": "Emitted when text content is finalized.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseTextDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseWebSearchCallWsCompleted",
+            "description": "Emitted when a web search call is completed.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseWebSearchCallCompletedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseWebSearchCallInWsProgress",
+            "description": "Emitted when a web search call is initiated.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseWebSearchCallInProgressEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseWebSearchCallWsSearching",
+            "description": "Emitted when a web search call is executing.",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseWebSearchCallSearchingEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseImageGenCallWsCompleted",
+            "description": "Emitted when an image generation tool call has completed and the final image is available.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseImageGenCallCompletedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseImageGenCallWsGenerating",
+            "description": "Emitted when an image generation tool call is actively generating an image (intermediate state).\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseImageGenCallGeneratingEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseImageGenCallInWsProgress",
+            "description": "Emitted when an image generation tool call is in progress.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseImageGenCallInProgressEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseImageGenCallPartialWsImage",
+            "description": "Emitted when a partial image is available during image generation streaming.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseImageGenCallPartialImageEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseMcpCallArgumentsWsDelta",
+            "description": "Emitted when there is a delta (partial update) to the arguments of an MCP tool call.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseMCPCallArgumentsDeltaEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseMcpCallArgumentsWsDone",
+            "description": "Emitted when the arguments for an MCP tool call are finalized.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseMCPCallArgumentsDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseMcpCallWsCompleted",
+            "description": "Emitted when an MCP  tool call has completed successfully.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseMCPCallCompletedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseMcpCallWsFailed",
+            "description": "Emitted when an MCP  tool call has failed.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseMCPCallFailedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseMcpCallInWsProgress",
+            "description": "Emitted when an MCP  tool call is in progress.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseMCPCallInProgressEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseMcpListToolsWsCompleted",
+            "description": "Emitted when the list of available MCP tools has been successfully retrieved.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseMCPListToolsCompletedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseMcpListToolsWsFailed",
+            "description": "Emitted when the attempt to list available MCP tools has failed.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseMCPListToolsFailedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseMcpListToolsInWsProgress",
+            "description": "Emitted when the system is in the process of retrieving the list of available MCP tools.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseMCPListToolsInProgressEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseOutputTextAnnotationWsAdded",
+            "description": "Emitted when an annotation is added to output text content.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseOutputTextAnnotationAddedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseWsQueued",
+            "description": "Emitted when a response is queued and waiting to be processed.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseQueuedEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseCustomToolCallInputWsDelta",
+            "description": "Event representing a delta (partial update) to the input of a custom tool call.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseCustomToolCallInputDeltaEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "title": "BetaResponseCustomToolCallInputWsDone",
+            "description": "Event indicating that input for a custom tool call is complete.\n",
+            "allOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseCustomToolCallInputDoneEvent"
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "stream_id": {
+                    "type": "string",
+                    "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+                  }
+                }
+              }
+            ]
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseWsError"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseSteerAcceptedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseSteerPendingEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseSteerFailedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseInjectCreatedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseInjectFailedEvent"
+          }
+        ]
+      },
+      "BetaResponseInjectFailedEvent": {
+        "type": "object",
+        "title": "ResponseInjectFailedEvent",
+        "description": "Emitted when injected input could not be committed to a response. The event\nreturns the uncommitted raw input so the client can retry it in another\nresponse when appropriate.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.inject.failed"
+            ],
+            "description": "The event discriminator. Always `response.inject.failed`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response that rejected the input."
+          },
+          "input": {
+            "type": "array",
+            "description": "The raw input items that were not committed.",
+            "items": {
+              "$ref": "#/components/schemas/BetaInputItem"
+            }
+          },
+          "error": {
+            "type": "object",
+            "description": "Information about why the input was not committed.",
+            "properties": {
+              "code": {
+                "type": "string",
+                "enum": [
+                  "response_already_completed",
+                  "response_not_found"
+                ],
+                "description": "A machine-readable error code."
+              },
+              "message": {
+                "type": "string",
+                "description": "A human-readable description of the error."
+              }
+            },
+            "required": [
+              "code",
+              "message"
+            ]
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number for this event."
+          },
+          "stream_id": {
+            "type": "string",
+            "description": "The multiplexed WebSocket stream that emitted the event. This field is\npresent only when WebSocket multiplexing is enabled separately.\n"
+          }
+        },
+        "required": [
+          "type",
+          "response_id",
+          "input",
+          "error",
+          "sequence_number"
+        ],
+        "x-oai-beta": "responses_multi_agent=v1",
+        "x-oaiMeta": {
+          "example": "{\n  \"type\": \"response.inject.failed\",\n  \"response_id\": \"resp_123\",\n  \"input\": [\n    {\n      \"type\": \"function_call_output\",\n      \"call_id\": \"call_123\",\n      \"output\": \"{\\\"temperature\\\":72}\"\n    }\n  ],\n  \"error\": {\n    \"code\": \"response_already_completed\",\n    \"message\": \"Response 'resp_123' has already completed.\"\n  },\n  \"sequence_number\": 9\n}\n"
+        }
+      },
+      "BetaResponseInjectCreatedEvent": {
+        "type": "object",
+        "title": "ResponseInjectCreatedEvent",
+        "description": "Emitted when all injected input items were validated and committed to the\nactive response.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.inject.created"
+            ],
+            "description": "The event discriminator. Always `response.inject.created`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the response that accepted the input."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number for this event."
+          },
+          "stream_id": {
+            "type": "string",
+            "description": "The multiplexed WebSocket stream that emitted the event. This field is\npresent only when WebSocket multiplexing is enabled separately.\n"
+          }
+        },
+        "required": [
+          "type",
+          "response_id",
+          "sequence_number"
+        ],
+        "x-oai-beta": "responses_multi_agent=v1",
+        "x-oaiMeta": {
+          "example": "{\n  \"type\": \"response.inject.created\",\n  \"response_id\": \"resp_123\",\n  \"sequence_number\": 8\n}\n"
+        }
+      },
+      "BetaResponseWsError": {
+        "type": "object",
+        "title": "ResponseWsError",
+        "description": "Emitted when an error occurs while processing a Responses WebSocket request.",
+        "properties": {
+          "agent": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaAgentTag"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "The agent that owns this multi-agent streaming event."
+          },
+          "type": {
+            "type": "string",
+            "description": "The type of the event. Always `error`.",
+            "enum": [
+              "error"
+            ],
+            "x-stainless-const": true
+          },
+          "status": {
+            "type": "integer",
+            "description": "The HTTP status code associated with a WebSocket protocol error."
+          },
+          "sequence_number": {
+            "type": "integer",
+            "description": "The sequence number of an error emitted by the response stream."
+          },
+          "error": {
+            "$ref": "#/components/schemas/BetaErrorPayload",
+            "description": "Details about the error."
+          },
+          "stream_id": {
+            "type": "string",
+            "description": "The WebSocket lane that emitted this event. This field is present when the\noriginating `response.create` event supplied a `stream_id`.\n"
+          }
+        },
+        "required": [
+          "type",
+          "error"
+        ],
+        "x-oaiMeta": {
+          "name": "error",
+          "group": "responses",
+          "example": "{\n  \"type\": \"error\",\n  \"status\": 400,\n  \"stream_id\": \"agent_1\",\n  \"error\": {\n    \"type\": \"invalid_request_error\",\n    \"code\": \"websocket_stream_limit_reached\",\n    \"message\": \"This WebSocket connection has reached its stream limit.\",\n    \"param\": \"stream_id\"\n  }\n}\n"
+        }
+      },
+      "BetaErrorPayload": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The error type that was emitted."
+          },
+          "code": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The error code that was emitted, if any."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "message": {
+            "type": "string",
+            "description": "The human-readable error message that was emitted."
+          },
+          "param": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The parameter name that was associated with the error, if any."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "headers": {
+            "additionalProperties": {
+              "type": "string",
+              "description": "The header value that was emitted."
+            },
+            "type": "object",
+            "description": "The response headers that were emitted with the error, if any.",
+            "x-oaiTypeLabel": "map"
+          },
+          "misalignment": {
+            "$ref": "#/components/schemas/BetaMisalignmentErrorDetailsResource"
+          }
+        },
+        "type": "object",
+        "required": [
+          "type",
+          "code",
+          "message",
+          "param"
+        ],
+        "title": "Error payload",
+        "description": "An error payload that was emitted for a streaming error event."
+      },
+      "BetaResponsesWebSocketStreamEvent": {
+        "allOf": [
+          {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaResponseAudioDeltaEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseAudioDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseAudioTranscriptDeltaEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseAudioTranscriptDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseCodeInterpreterCallCodeDeltaEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseCodeInterpreterCallCodeDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseCodeInterpreterCallCompletedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseCodeInterpreterCallInProgressEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseCodeInterpreterCallInterpretingEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseCompletedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseContentPartAddedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseContentPartDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseCreatedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseFileSearchCallCompletedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseFileSearchCallInProgressEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseFileSearchCallSearchingEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseFunctionCallArgumentsDeltaEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseFunctionCallArgumentsDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseShellCallCommandAddedStreamingEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseShellCallCommandDeltaStreamingEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseShellCallCommandDoneStreamingEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseShellCallOutputContentDeltaStreamingEvent",
+                "x-stainless-skip": [
+                  "go"
+                ]
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseShellCallOutputContentDoneStreamingEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseInProgressEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseFailedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseIncompleteEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseOutputItemAddedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseOutputItemDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseReasoningSummaryPartAddedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseReasoningSummaryPartDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseReasoningSummaryTextDeltaEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseReasoningSummaryTextDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseReasoningTextDeltaEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseReasoningTextDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseRefusalDeltaEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseRefusalDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseTextDeltaEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseTextDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseWebSearchCallCompletedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseWebSearchCallInProgressEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseWebSearchCallSearchingEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseImageGenCallCompletedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseImageGenCallGeneratingEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseImageGenCallInProgressEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseImageGenCallPartialImageEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseMCPCallArgumentsDeltaEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseMCPCallArgumentsDoneEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseMCPCallCompletedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseMCPCallFailedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseMCPCallInProgressEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseMCPListToolsCompletedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseMCPListToolsFailedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseMCPListToolsInProgressEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseOutputTextAnnotationAddedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseQueuedEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseCustomToolCallInputDeltaEvent"
+              },
+              {
+                "$ref": "#/components/schemas/BetaResponseCustomToolCallInputDoneEvent"
+              }
+            ]
+          },
+          {
+            "type": "object",
+            "properties": {
+              "stream_id": {
+                "type": "string",
+                "description": "The WebSocket lane that emitted this event. This field is present\nwhen the originating `response.create` event supplied a\n`stream_id`.\n"
+              }
+            }
+          }
+        ]
+      },
+      "BetaResponsesClientEvent": {
+        "discriminator": {
+          "propertyName": "type"
+        },
+        "description": "Client events accepted by the Responses WebSocket server.\n",
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/BetaResponsesClientEventResponseCreate"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseSteerEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseInjectEvent"
+          }
+        ]
+      },
+      "BetaResponseInjectEvent": {
+        "type": "object",
+        "title": "ResponseInjectEvent",
+        "description": "Injects input items into an active response over a WebSocket connection.\nThe items are validated and committed atomically. Currently, the server\naccepts client-owned tool outputs that resume a waiting agent.\n",
+        "properties": {
+          "type": {
+            "type": "string",
+            "enum": [
+              "response.inject"
+            ],
+            "description": "The event discriminator. Always `response.inject`.",
+            "x-stainless-const": true
+          },
+          "response_id": {
+            "type": "string",
+            "description": "The ID of the active response that should receive the input."
+          },
+          "input": {
+            "type": "array",
+            "maxItems": 16384,
+            "description": "Input items to inject into the active response.",
+            "items": {
+              "$ref": "#/components/schemas/BetaInputItem"
+            }
+          }
+        },
+        "required": [
+          "type",
+          "response_id",
+          "input"
+        ],
+        "x-oai-beta": "responses_multi_agent=v1",
+        "x-oaiMeta": {
+          "example": "{\n  \"type\": \"response.inject\",\n  \"response_id\": \"resp_123\",\n  \"input\": [\n    {\n      \"type\": \"function_call_output\",\n      \"call_id\": \"call_123\",\n      \"output\": \"{\\\"temperature\\\":72}\"\n    }\n  ]\n}\n"
+        }
+      },
+      "BetaResponsesClientEventResponseCreate": {
+        "allOf": [
+          {
+            "type": "object",
+            "properties": {
+              "type": {
+                "type": "string",
+                "enum": [
+                  "response.create"
+                ],
+                "description": "The type of the client event. Always `response.create`.\n",
+                "x-stainless-const": true
+              },
+              "stream_id": {
+                "type": "string",
+                "minLength": 1,
+                "maxLength": 256,
+                "pattern": "^[A-Za-z0-9_.-]+$",
+                "description": "The WebSocket lane for this response. Requests with the same\n`stream_id` are processed FIFO, and events for the response echo the\nsame `stream_id`.\n\n`stream_id` controls routing; `previous_response_id` controls\nconversation lineage, so a new lane can fork from a response created\non another lane.\n"
+              }
+            },
+            "required": [
+              "type"
+            ]
+          },
+          {
+            "$ref": "#/components/schemas/BetaCreateResponse"
+          }
+        ],
+        "description": "Client event for creating a response over a persistent WebSocket connection.\nThis payload uses the same top-level fields as `POST /v1/responses`, plus\nWebSocket-only envelope metadata.\n\nNotes:\n- `stream` is implicit over WebSocket and should not be sent.\n- `background` is not supported over WebSocket.\n- `stream_id` is WebSocket-only and is not part of `POST /v1/responses`.\n",
+        "x-oaiMeta": {
+          "example": "{\n  \"type\": \"response.create\",\n  \"stream_id\": \"agent_1\",\n  \"model\": \"gpt-6-astra\",\n  \"input\": \"Say hello.\"\n}\n"
+        }
+      },
+      "BetaCreateResponse": {
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/BetaCreateModelResponseProperties"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseProperties"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "prompt_cache_options": {
+                "$ref": "#/components/schemas/BetaResponsePromptCacheOptionsParam"
+              },
+              "service_tier": {
+                "$ref": "#/components/schemas/BetaServiceTierResponses"
+              },
+              "truncation": {
+                "deprecated": true,
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "The truncation strategy to use for the model response.\n- `auto`: If the input to this Response exceeds\n  the model's context window size, the model will truncate the\n  response to fit the context window by dropping items from the beginning of the conversation.\n- `disabled` (default): If the input size will exceed the context window\n  size for a model, the request will fail with a 400 error.\n",
+                    "enum": [
+                      "auto",
+                      "disabled"
+                    ],
+                    "default": "disabled"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "reasoning": {
+                "anyOf": [
+                  {
+                    "$ref": "#/components/schemas/BetaReasoning"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "input": {
+                "$ref": "#/components/schemas/BetaInputParam"
+              },
+              "include": {
+                "anyOf": [
+                  {
+                    "type": "array",
+                    "description": "Specify additional output data to include in the model response. Currently supported values are:\n- `web_search_call.action.sources`: Include the sources of the web search tool call.\n- `code_interpreter_call.outputs`: Includes the outputs of python code execution in code interpreter tool call items.\n- `computer_call_output.output.image_url`: Include image urls from the computer call output.\n- `file_search_call.results`: Include the search results of the file search tool call.\n- `message.input_image.image_url`: Include image urls from the input message.\n- `message.output_text.logprobs`: Include logprobs with assistant messages.\n- `reasoning.encrypted_content`: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when the `store` parameter is set to `false`, or when an organization is enrolled in the zero data retention program).",
+                    "items": {
+                      "$ref": "#/components/schemas/BetaIncludeEnum"
+                    }
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "parallel_tool_calls": {
+                "anyOf": [
+                  {
+                    "type": "boolean",
+                    "description": "Whether to allow the model to run tool calls in parallel.\n",
+                    "default": true
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "store": {
+                "anyOf": [
+                  {
+                    "type": "boolean",
+                    "description": "Whether to store the generated model response for later retrieval via\nAPI.\nDefaults to true when omitted.\nIf set to true, response data will be stored for at least 30 days, subject to the [data retention exceptions](https://developers.openai.com/api/docs/guides/your-data#v1responses).\n",
+                    "default": true
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "instructions": {
+                "anyOf": [
+                  {
+                    "type": "string",
+                    "description": "A system (or developer) message inserted into the model's context.\n\nWhen using along with `previous_response_id`, the instructions from a previous\nresponse will not be carried over to the next response. This makes it simple\nto swap out system (or developer) messages in new responses.\n"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "moderation": {
+                "anyOf": [
+                  {
+                    "$ref": "#/components/schemas/BetaModerationParam",
+                    "description": "Configuration for running moderation on the input and output of this response.\n"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "stream": {
+                "anyOf": [
+                  {
+                    "description": "If set to true, the model response data will be streamed to the client\nas it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).\nSee the [Streaming section below](https://developers.openai.com/api/reference/resources/responses/streaming-events)\nfor more information.\n",
+                    "type": "boolean",
+                    "default": false
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "stream_options": {
+                "$ref": "#/components/schemas/BetaResponseStreamOptions"
+              },
+              "conversation": {
+                "anyOf": [
+                  {
+                    "$ref": "#/components/schemas/BetaConversationParam"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "context_management": {
+                "anyOf": [
+                  {
+                    "type": "array",
+                    "description": "Context management configuration for this request.\n",
+                    "minItems": 1,
+                    "items": {
+                      "$ref": "#/components/schemas/BetaContextManagementParam"
+                    }
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "max_output_tokens": {
+                "anyOf": [
+                  {
+                    "description": "An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](https://developers.openai.com/api/docs/guides/reasoning).\n",
+                    "type": "integer",
+                    "minimum": 16
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "multi_agent": {
+                "anyOf": [
+                  {
+                    "$ref": "#/components/schemas/BetaMultiAgentParam",
+                    "description": "Configuration for server-hosted multi-agent execution."
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              }
+            }
+          }
+        ]
+      },
+      "BetaMultiAgentParam": {
+        "properties": {
+          "enabled": {
+            "type": "boolean",
+            "description": "Whether to enable server-hosted multi-agent execution for this response."
+          },
+          "max_concurrent_subagents": {
+            "type": "integer",
+            "minimum": 1,
+            "description": "`max_concurrent_subagents` sets the maximum number of subagents that can be active simultaneously across the entire agent tree. It includes all descendants—children, grandchildren, and deeper subagents—but excludes the root agent.\nThe API does not impose a fixed upper bound on this setting. The default is `3`, which is recommended for most workloads. Multi-agent runs also have no fixed limit on tree depth or the total number of subagents created during a run."
+          }
+        },
+        "type": "object",
+        "required": [
+          "enabled"
+        ],
+        "description": "Configuration for server-hosted multi-agent execution.",
+        "x-oai-beta": "responses_multi_agent=v1"
+      },
+      "BetaContextManagementParam": {
+        "properties": {
+          "type": {
+            "type": "string",
+            "description": "The context management entry type. Currently only 'compaction' is supported."
+          },
+          "compact_threshold": {
+            "anyOf": [
+              {
+                "type": "integer",
+                "minimum": 1000,
+                "description": "Token threshold at which compaction should be triggered for this entry."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "type"
+        ]
+      },
+      "BetaResponseStreamOptions": {
+        "anyOf": [
+          {
+            "description": "Options for streaming responses. Only set this when you set `stream: true`.\n",
+            "type": "object",
+            "default": null,
+            "properties": {
+              "include_obfuscation": {
+                "type": "boolean",
+                "description": "When true, stream obfuscation will be enabled. Stream obfuscation adds\nrandom characters to an `obfuscation` field on streaming delta events to\nnormalize payload sizes as a mitigation to certain side-channel attacks.\nThese obfuscation fields are included by default, but add a small amount\nof overhead to the data stream. You can set `include_obfuscation` to\nfalse to optimize for bandwidth if you trust the network links between\nyour application and the OpenAI API.\n"
+              }
+            }
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "BetaModerationParam": {
+        "properties": {
+          "model": {
+            "type": "string",
+            "description": "The moderation model to use for moderated completions, e.g. 'omni-moderation-latest'."
+          },
+          "policy": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaModerationPolicyParam",
+                "description": "The policy to apply to moderated response input and output."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [
+          "model"
+        ],
+        "description": "Configuration for running moderation on the input and output of this response."
+      },
+      "BetaModerationPolicyParam": {
+        "properties": {
+          "input": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaModerationConfigParam",
+                "description": "The moderation policy for the response input."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "output": {
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/BetaModerationConfigParam",
+                "description": "The moderation policy for the response output."
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [],
+        "description": "The policy to apply to moderated response input and output."
+      },
+      "BetaModerationConfigParam": {
+        "properties": {
+          "mode": {
+            "$ref": "#/components/schemas/BetaModerationMode"
+          }
+        },
+        "type": "object",
+        "required": [
+          "mode"
+        ],
+        "description": "The moderation policy for the response input."
+      },
+      "BetaModerationMode": {
+        "type": "string",
+        "enum": [
+          "score",
+          "block"
+        ]
+      },
+      "BetaResponsePromptCacheOptionsParam": {
+        "properties": {
+          "ttl": {
+            "$ref": "#/components/schemas/BetaPromptCacheTTLEnum",
+            "description": "The minimum lifetime applied to every implicit and explicit cache breakpoint written by the request. Defaults to `30m`, which is currently the only supported value. The backend may retain cache entries for longer."
+          },
+          "mode": {
+            "$ref": "#/components/schemas/BetaPromptCacheModeEnum",
+            "description": "Controls whether OpenAI automatically creates an implicit cache breakpoint. Defaults to `implicit`. With `implicit`, OpenAI creates one implicit breakpoint and writes up to the latest three explicit breakpoints in the request. With `explicit`, OpenAI does not create an implicit breakpoint and writes up to the latest four explicit breakpoints. If there are no explicit breakpoints, the request does not use prompt caching."
+          },
+          "comparison_response_id": {
+            "anyOf": [
+              {
+                "type": "string",
+                "description": "The ID of a response to compare when diagnosing prompt cache reuse. Supplying this field requests prompt cache diagnostics when the feature is enabled.",
+                "example": "resp_123"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          }
+        },
+        "type": "object",
+        "required": [],
+        "title": "Prompt cache options",
+        "description": "Options for prompt caching. Supported for `gpt-5.6` and later models. By default, OpenAI automatically chooses one implicit cache breakpoint. You can add explicit breakpoints to content blocks with `prompt_cache_breakpoint`. Each request can write up to four breakpoints. For cache matching, OpenAI considers up to the latest 80 breakpoints in the conversation, without a content-block lookback limit. Set `mode` to `explicit` to disable the implicit breakpoint. The `ttl` defaults to `30m`, which is currently the only supported value. See the [prompt caching guide](https://developers.openai.com/api/docs/guides/prompt-caching) for current details."
+      },
+      "BetaCreateModelResponseProperties": {
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/BetaModelResponseProperties"
+          },
+          {
+            "type": "object",
+            "properties": {
+              "prompt_cache_options": {
+                "$ref": "#/components/schemas/BetaPromptCacheOptionsParam"
+              },
+              "top_logprobs": {
+                "description": "An integer between 0 and 20 specifying the maximum number of most likely\ntokens to return at each token position, each with an associated log\nprobability. In some cases, the number of returned tokens may be fewer than\nrequested.\n",
+                "type": "integer",
+                "minimum": 0,
+                "maximum": 20
+              }
+            }
+          }
+        ]
+      },
+      "BetaResponseStreamEvent": {
+        "description": "Event emitted while a response is streamed.",
+        "anyOf": [
+          {
+            "$ref": "#/components/schemas/BetaResponseAudioDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseAudioDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseAudioTranscriptDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseAudioTranscriptDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseCodeInterpreterCallCodeDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseCodeInterpreterCallCodeDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseCodeInterpreterCallCompletedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseCodeInterpreterCallInProgressEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseCodeInterpreterCallInterpretingEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseCompletedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseContentPartAddedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseContentPartDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseCreatedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseErrorEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseFileSearchCallCompletedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseFileSearchCallInProgressEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseFileSearchCallSearchingEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseFunctionCallArgumentsDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseFunctionCallArgumentsDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseShellCallCommandAddedStreamingEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseShellCallCommandDeltaStreamingEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseShellCallCommandDoneStreamingEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseShellCallOutputContentDeltaStreamingEvent",
+            "x-stainless-skip": [
+              "go"
+            ]
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseShellCallOutputContentDoneStreamingEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseInProgressEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseFailedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseIncompleteEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseOutputItemAddedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseOutputItemDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseReasoningSummaryPartAddedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseReasoningSummaryPartDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseReasoningSummaryTextDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseReasoningSummaryTextDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseReasoningTextDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseReasoningTextDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseRefusalDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseRefusalDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseTextDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseTextDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseWebSearchCallCompletedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseWebSearchCallInProgressEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseWebSearchCallSearchingEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseImageGenCallCompletedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseImageGenCallGeneratingEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseImageGenCallInProgressEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseImageGenCallPartialImageEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseMCPCallArgumentsDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseMCPCallArgumentsDoneEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseMCPCallCompletedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseMCPCallFailedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseMCPCallInProgressEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseMCPListToolsCompletedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseMCPListToolsFailedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseMCPListToolsInProgressEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseOutputTextAnnotationAddedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseQueuedEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseCustomToolCallInputDeltaEvent"
+          },
+          {
+            "$ref": "#/components/schemas/BetaResponseCustomToolCallInputDoneEvent"
+          }
+        ],
+        "discriminator": {
+          "propertyName": "type"
+        }
+      }
+    },
+    "responses": {
+      "TooManyRequests": {
+        "description": "The request was rejected because a rate limit was exceeded.",
+        "headers": {
+          "Retry-After": {
+            "description": "The minimum number of seconds to wait before retrying. This header is returned when the server has computed a retry delay and may be omitted for 429 responses that require user action.",
+            "schema": {
+              "type": "integer",
+              "minimum": 1
+            }
+          }
+        },
+        "content": {
+          "application/json": {
+            "schema": {
+              "$ref": "#/components/schemas/ErrorResponse"
+            }
+          }
+        }
+      },
+      "InferenceRateLimited": {
+        "description": "The request was rejected because a rate limit was exceeded. A slow_down error means traffic increased too quickly; reduce your request rate, then increase it gradually.",
+        "headers": {
+          "Retry-After": {
+            "description": "The minimum number of seconds to wait before retrying. This header is returned when the server has computed a retry delay and may be omitted.",
+            "schema": {
+              "type": "integer",
+              "minimum": 1
+            }
+          }
+        },
+        "content": {
+          "application/json": {
+            "schema": {
+              "$ref": "#/components/schemas/ErrorResponse"
+            },
+            "examples": {
+              "slowDown": {
+                "summary": "Traffic increased too quickly",
+                "value": {
+                  "error": {
+                    "message": "Your request rate increased too quickly. Please reduce the request rate and gradually increase it again.",
+                    "type": "rate_limit_error",
+                    "param": null,
+                    "code": "slow_down"
+                  }
+                }
+              }
+            }
+          }
+        }
+      },
+      "InferenceServiceUnavailable": {
+        "description": "The service is temporarily unavailable. A server_is_overloaded error means the requested model is temporarily overloaded; retry after a brief delay.",
+        "headers": {
+          "Retry-After": {
+            "description": "The minimum number of seconds to wait before retrying. This header is returned when the server has computed a retry delay and may be omitted.",
+            "schema": {
+              "type": "integer",
+              "minimum": 1
+            }
+          }
+        },
+        "content": {
+          "application/json": {
+            "schema": {
+              "$ref": "#/components/schemas/ErrorResponse"
+            },
+            "examples": {
+              "serverOverloaded": {
+                "summary": "The requested model is temporarily overloaded",
+                "value": {
+                  "error": {
+                    "message": "The model is temporarily overloaded. Please retry your request after a brief delay.",
+                    "type": "service_unavailable_error",
+                    "param": null,
+                    "code": "server_is_overloaded"
+                  }
+                }
+              }
+            }
+          }
+        }
+      }
+    },
+    "securitySchemes": {
+      "ApiKeyAuth": {
+        "type": "http",
+        "scheme": "bearer"
+      },
+      "AdminApiKeyAuth": {
+        "type": "http",
+        "scheme": "bearer"
+      }
+    }
+  },
+  "x-oaiMeta": {
+    "navigationGroups": [
+      {
+        "id": "responses",
+        "title": "Responses API"
+      },
+      {
+        "id": "webhooks",
+        "title": "Webhooks"
+      },
+      {
+        "id": "endpoints",
+        "title": "Platform APIs"
+      },
+      {
+        "id": "vector_stores",
+        "title": "Vector stores"
+      },
+      {
+        "id": "chatkit",
+        "title": "ChatKit",
+        "beta": true
+      },
+      {
+        "id": "containers",
+        "title": "Containers"
+      },
+      {
+        "id": "live",
+        "title": "Live (alpha)"
+      },
+      {
+        "id": "realtime",
+        "title": "Realtime"
+      },
+      {
+        "id": "chat",
+        "title": "Chat Completions"
+      },
+      {
+        "id": "assistants",
+        "title": "Assistants",
+        "deprecated": true
+      },
+      {
+        "id": "administration",
+        "title": "Administration"
+      },
+      {
+        "id": "legacy",
+        "title": "Legacy"
+      }
+    ],
+    "groups": [
+      {
+        "id": "responses-streaming",
+        "title": "Streaming events",
+        "description": "When you [create a Response](https://developers.openai.com/api/reference/resources/responses/methods/create) with\n`stream` set to `true`, the server will emit server-sent events to the\nclient as the Response is generated. This section contains the events that\nare emitted by the server.\n\n[Learn more about streaming responses](https://developers.openai.com/api/docs/guides/streaming-responses).\n",
+        "navigationGroup": "responses",
+        "sections": [
+          {
+            "type": "object",
+            "key": "ResponseCreatedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFailedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseIncompleteEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseOutputItemAddedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseOutputItemDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseContentPartAddedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseContentPartDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseTextDeltaEvent",
+            "path": "response/output_text/delta"
+          },
+          {
+            "type": "object",
+            "key": "ResponseTextDoneEvent",
+            "path": "response/output_text/done"
+          },
+          {
+            "type": "object",
+            "key": "ResponseRefusalDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseRefusalDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFunctionCallArgumentsDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFunctionCallArgumentsDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFileSearchCallInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFileSearchCallSearchingEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFileSearchCallCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseWebSearchCallInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseWebSearchCallSearchingEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseWebSearchCallCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningSummaryPartAddedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningSummaryPartDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningSummaryTextDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningSummaryTextDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningTextDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningTextDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseImageGenCallCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseImageGenCallGeneratingEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseImageGenCallInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseImageGenCallPartialImageEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPCallArgumentsDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPCallArgumentsDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPCallCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPCallFailedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPCallInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPListToolsCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPListToolsFailedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPListToolsInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCodeInterpreterCallInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCodeInterpreterCallInterpretingEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCodeInterpreterCallCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCodeInterpreterCallCodeDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCodeInterpreterCallCodeDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseOutputTextAnnotationAddedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseQueuedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCustomToolCallInputDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCustomToolCallInputDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseErrorEvent",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "responses-websocket-client-events",
+        "title": "Client events",
+        "description": "Events sent by the client over a Responses API WebSocket connection.\n",
+        "navigationGroup": "responses",
+        "sections": [
+          {
+            "type": "object",
+            "key": "ResponsesClientEventResponseCreate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseSteerEvent",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "responses-websocket-server-events",
+        "title": "Server events (WebSocket only)",
+        "description": "Events emitted only over a Responses API WebSocket connection.\n",
+        "navigationGroup": "responses",
+        "sections": [
+          {
+            "type": "object",
+            "key": "ResponseSteerAcceptedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseSteerPendingEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseSteerFailedEvent",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "responses-websocket-shared-events",
+        "title": "Server events",
+        "description": "These events use the same payloads over WebSocket and\n[HTTP streaming](https://developers.openai.com/api/reference/resources/responses/streaming-events).\n",
+        "navigationGroup": "responses",
+        "sections": [
+          {
+            "type": "object",
+            "key": "ResponseCreatedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFailedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseIncompleteEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseOutputItemAddedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseOutputItemDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseContentPartAddedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseContentPartDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseTextDeltaEvent",
+            "path": "response/output_text/delta"
+          },
+          {
+            "type": "object",
+            "key": "ResponseTextDoneEvent",
+            "path": "response/output_text/done"
+          },
+          {
+            "type": "object",
+            "key": "ResponseRefusalDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseRefusalDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFunctionCallArgumentsDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFunctionCallArgumentsDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFileSearchCallInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFileSearchCallSearchingEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseFileSearchCallCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseWebSearchCallInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseWebSearchCallSearchingEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseWebSearchCallCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningSummaryPartAddedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningSummaryPartDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningSummaryTextDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningSummaryTextDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningTextDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseReasoningTextDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseImageGenCallCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseImageGenCallGeneratingEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseImageGenCallInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseImageGenCallPartialImageEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPCallArgumentsDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPCallArgumentsDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPCallCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPCallFailedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPCallInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPListToolsCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPListToolsFailedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseMCPListToolsInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCodeInterpreterCallInProgressEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCodeInterpreterCallInterpretingEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCodeInterpreterCallCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCodeInterpreterCallCodeDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCodeInterpreterCallCodeDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseOutputTextAnnotationAddedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseQueuedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCustomToolCallInputDeltaEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseCustomToolCallInputDoneEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ResponseErrorEvent",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "safety-alerts",
+        "title": "Safety Alerts",
+        "description": "Retrieve approved safety alerts with an API key. Project keys require\n`api.safety.alerts.read` and can read alerts from their project.\n",
+        "navigationGroup": "endpoints",
+        "sections": [
+          {
+            "type": "endpoint",
+            "key": "Getprojectsafetyalert",
+            "path": "retrieve"
+          },
+          {
+            "type": "object",
+            "key": "SafetyAlertResource",
+            "path": "object"
+          }
+        ]
+      },
+      {
+        "id": "webhook-events",
+        "title": "Webhook Events",
+        "description": "Webhooks are HTTP requests sent by OpenAI to a URL you specify when certain\nevents happen during the course of API usage.\n\n[Learn more about webhooks](https://developers.openai.com/api/docs/guides/webhooks).\n",
+        "navigationGroup": "webhooks",
+        "sections": [
+          {
+            "type": "object",
+            "key": "WebhookResponseCompleted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookResponseCancelled",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookResponseFailed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookResponseIncomplete",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookBatchCompleted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookBatchCancelled",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookBatchExpired",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookBatchFailed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookFineTuningJobSucceeded",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookFineTuningJobFailed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookFineTuningJobCancelled",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookEvalRunSucceeded",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookEvalRunFailed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookEvalRunCanceled",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookRealtimeCallIncoming",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookLiveCallIncoming",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookLiveTransportIncoming",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookSafetyAlertCreated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "WebhookSafetyOrgAlertCreated",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "images-streaming",
+        "title": "Image Streaming",
+        "description": "Stream image generation and editing in real time with server-sent events.\n[Learn more about image streaming](https://developers.openai.com/api/docs/guides/image-generation).\n",
+        "navigationGroup": "endpoints",
+        "sections": [
+          {
+            "type": "object",
+            "key": "ImageGenPartialImageEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ImageGenCompletedEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ImageEditPartialImageEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "ImageEditCompletedEvent",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "realtime-client-events",
+        "title": "Client events",
+        "description": "These are events that the OpenAI Realtime WebSocket server will accept from the client.\n",
+        "navigationGroup": "realtime",
+        "sections": [
+          {
+            "type": "object",
+            "key": "RealtimeClientEventSessionUpdate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeClientEventInputAudioBufferAppend",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeClientEventInputAudioBufferCommit",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeClientEventInputAudioBufferClear",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeClientEventConversationItemCreate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeClientEventConversationItemRetrieve",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeClientEventConversationItemTruncate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeClientEventConversationItemDelete",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeClientEventResponseCreate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeClientEventResponseCancel",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeClientEventOutputAudioBufferClear",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "realtime-server-events",
+        "title": "Server events",
+        "description": "These are events emitted from the OpenAI Realtime WebSocket server to the client.\n",
+        "navigationGroup": "realtime",
+        "sections": [
+          {
+            "type": "object",
+            "key": "RealtimeServerEventError",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventSessionCreated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventSessionUpdated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventConversationItemAdded",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventConversationItemDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventConversationItemRetrieved",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventConversationItemInputAudioTranscriptionCompleted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventConversationItemInputAudioTranscriptionDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventConversationItemInputAudioTranscriptionSegment",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventConversationItemInputAudioTranscriptionFailed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventConversationItemTruncated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventConversationItemDeleted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventInputAudioBufferCommitted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventInputAudioBufferDtmfEventReceived",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventInputAudioBufferCleared",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventInputAudioBufferSpeechStarted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventInputAudioBufferSpeechStopped",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventInputAudioBufferTimeoutTriggered",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventOutputAudioBufferStarted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventOutputAudioBufferStopped",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventOutputAudioBufferCleared",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseCreated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseOutputItemAdded",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseOutputItemDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseContentPartAdded",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseContentPartDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseTextDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseTextDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseAudioTranscriptDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseAudioTranscriptDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseAudioDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseAudioDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseFunctionCallArgumentsDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseFunctionCallArgumentsDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseMCPCallArgumentsDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseMCPCallArgumentsDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseMCPCallInProgress",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseMCPCallCompleted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventResponseMCPCallFailed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventMCPListToolsInProgress",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventMCPListToolsCompleted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventMCPListToolsFailed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventRateLimitsUpdated",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "realtime-translation-client-events",
+        "title": "Translation client events",
+        "description": "These are events that the OpenAI Realtime Translation WebSocket server will accept from the client.\n",
+        "navigationGroup": "realtime",
+        "sections": [
+          {
+            "type": "object",
+            "key": "RealtimeTranslationClientEventSessionUpdate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeTranslationClientEventInputAudioBufferAppend",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeTranslationClientEventSessionClose",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "realtime-translation-server-events",
+        "title": "Translation server events",
+        "description": "These are events emitted from the OpenAI Realtime Translation WebSocket server to the client.\n",
+        "navigationGroup": "realtime",
+        "sections": [
+          {
+            "type": "object",
+            "key": "RealtimeServerEventError",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeTranslationServerEventSessionCreated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeTranslationServerEventSessionUpdated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeTranslationServerEventSessionClosed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeTranslationServerEventSessionInputTranscriptDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeTranslationServerEventSessionOutputTranscriptDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeTranslationServerEventSessionOutputAudioDelta",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "chat-streaming",
+        "title": "Streaming",
+        "description": "Stream Chat Completions in real time. Receive chunks of completions\nreturned from the model using server-sent events.\n[Learn more](https://developers.openai.com/api/docs/guides/streaming-responses).\n",
+        "navigationGroup": "chat",
+        "sections": [
+          {
+            "type": "object",
+            "key": "CreateChatCompletionStreamResponse",
+            "path": "streaming"
+          }
+        ]
+      },
+      {
+        "id": "assistants-streaming",
+        "title": "Streaming",
+        "beta": true,
+        "description": "Stream the result of executing a Run or resuming a Run after submitting tool outputs.\nYou can stream events from the [Create Thread and Run](https://developers.openai.com/api/docs/assistants/migration),\n[Create Run](https://developers.openai.com/api/docs/assistants/migration), and [Submit Tool Outputs](https://developers.openai.com/api/docs/assistants/migration)\nendpoints by passing `\"stream\": true`. The response will be a [Server-Sent events](https://html.spec.whatwg.org/multipage/server-sent-events.html#server-sent-events) stream.\nOur Node and Python SDKs provide helpful utilities to make streaming easy. Reference the\n[Assistants API quickstart](https://developers.openai.com/api/docs/assistants/migration) to learn more.\n",
+        "navigationGroup": "assistants",
+        "sections": [
+          {
+            "type": "object",
+            "key": "AssistantStreamEvent",
+            "path": "events"
+          }
+        ]
+      },
+      {
+        "id": "realtime-beta-client-events",
+        "title": "Realtime Beta client events",
+        "description": "These are events that the OpenAI Realtime WebSocket server will accept from the client.\n",
+        "navigationGroup": "legacy",
+        "sections": [
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventSessionUpdate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventInputAudioBufferAppend",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventInputAudioBufferCommit",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventInputAudioBufferClear",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventConversationItemCreate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventConversationItemRetrieve",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventConversationItemTruncate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventConversationItemDelete",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventResponseCreate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventResponseCancel",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventTranscriptionSessionUpdate",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaClientEventOutputAudioBufferClear",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "realtime-beta-server-events",
+        "title": "Realtime Beta server events",
+        "description": "These are events emitted from the OpenAI Realtime WebSocket server to the client.\n",
+        "navigationGroup": "legacy",
+        "sections": [
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventError",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventSessionCreated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventSessionUpdated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventTranscriptionSessionCreated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventTranscriptionSessionUpdated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventConversationItemCreated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventConversationItemRetrieved",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventConversationItemInputAudioTranscriptionCompleted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventConversationItemInputAudioTranscriptionDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventConversationItemInputAudioTranscriptionSegment",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventConversationItemInputAudioTranscriptionFailed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventConversationItemTruncated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventConversationItemDeleted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventInputAudioBufferCommitted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventInputAudioBufferCleared",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventInputAudioBufferSpeechStarted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventInputAudioBufferSpeechStopped",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeServerEventInputAudioBufferTimeoutTriggered",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseCreated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseOutputItemAdded",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseOutputItemDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseContentPartAdded",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseContentPartDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseTextDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseTextDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseAudioTranscriptDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseAudioTranscriptDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseAudioDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseAudioDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseFunctionCallArgumentsDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseFunctionCallArgumentsDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseMCPCallArgumentsDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseMCPCallArgumentsDone",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseMCPCallInProgress",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseMCPCallCompleted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventResponseMCPCallFailed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventMCPListToolsInProgress",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventMCPListToolsCompleted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventMCPListToolsFailed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "RealtimeBetaServerEventRateLimitsUpdated",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "live-client-events",
+        "title": "Client events",
+        "description": "Initialize a primary WebSocket with session.start and wait for session.started before sending other events. WebRTC creation starts the session for you. Start with the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) to design frontend instructions and delegation policy; see [backend prompting](https://developers.openai.com/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt) for tools and business rules.",
+        "navigationGroup": "live",
+        "sections": [
+          {
+            "type": "object",
+            "key": "LiveSessionStartEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveForkSessionStartEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveSessionUpdateParam",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveInputAudioAppendEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveInputAudioMuteParam",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveInputAudioUnmuteParam",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveInstructionsAppendParam",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveThinkingAppendParam",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveCommentaryAppendParam",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveResponseItemCreateParam",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveResponseCreateParam",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveSessionCloseParam",
+            "path": "<auto>"
+          }
+        ]
+      },
+      {
+        "id": "live-server-events",
+        "title": "Server events",
+        "description": "Live server events. Responses delegation lifecycle events arrive inside response.event, not as top-level response events. Start with the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) to design frontend instructions and delegation policy; see [backend prompting](https://developers.openai.com/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt) for tools and business rules.",
+        "navigationGroup": "live",
+        "sections": [
+          {
+            "type": "object",
+            "key": "LiveSessionStarted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveSessionUpdated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveInputAudioMuted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveInputAudioUnmuted",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveInstructionsAppended",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveThinkingAppended",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveCommentaryAppended",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveOutputAudioDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveInputTranscriptDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveOutputTranscriptDelta",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveDelegationCreated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveResponseEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveSessionUsageUpdated",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveSessionClosed",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveErrorEvent",
+            "path": "<auto>"
+          },
+          {
+            "type": "object",
+            "key": "LiveInfoEvent",
+            "path": "<auto>"
+          }
+        ]
+      }
+    ]
+  }
+}
diff --git a/contracts/agents-api/v1/agents.go b/contracts/agents-api/v1/agents.go
index 17cda82d6..fc4a18a0c 100644
--- a/contracts/agents-api/v1/agents.go
+++ b/contracts/agents-api/v1/agents.go
@@ -2,73 +2,6 @@ package v1
 
 import "encoding/json"
 
-// CreateAgentRequest describes reusable configuration, not an execution request.
-// MCP/web-search tools and model-derived reasoning defaults remain incomplete.
-type CreateAgentRequest struct {
-	XAgentsCore  *SavedAgentCoreInput `json:"x_agents_core,omitempty" extensions:"x-nullable"`
-	Model        *string              `json:"model" binding:"required"`
-	Name         *string              `json:"name,omitempty" extensions:"x-nullable" maxLength:"128"`
-	Instructions *string              `json:"instructions,omitempty" extensions:"x-nullable"`
-	Metadata     map[string]*string   `json:"metadata,omitempty" swaggertype:"object,string" extensions:"x-nullable"`
-	MultiAgent   json.RawMessage      `json:"multi_agent,omitempty" swaggertype:"object" extensions:"x-nullable"`
-	Reasoning    *Reasoning           `json:"reasoning,omitempty" extensions:"x-nullable"`
-	ServiceTier  *string              `json:"service_tier,omitempty" enums:"auto,default,flex,priority,fast" extensions:"x-nullable"`
-	Text         *SavedAgentTextInput `json:"text,omitempty" extensions:"x-nullable"`
-	Tools        []json.RawMessage    `json:"tools,omitempty" swaggertype:"array,object" extensions:"x-nullable"`
-}
-
-// UpdateAgentRequest replaces supplied fields and preserves omitted fields.
-type UpdateAgentRequest struct {
-	XAgentsCore  *SavedAgentCoreInput `json:"x_agents_core,omitempty" extensions:"x-nullable"`
-	Model        *string              `json:"model,omitempty"`
-	Name         *string              `json:"name,omitempty" extensions:"x-nullable" maxLength:"128"`
-	Instructions *string              `json:"instructions,omitempty" extensions:"x-nullable"`
-	Metadata     map[string]*string   `json:"metadata,omitempty" swaggertype:"object,string" extensions:"x-nullable"`
-	MultiAgent   json.RawMessage      `json:"multi_agent,omitempty" swaggertype:"object" extensions:"x-nullable"`
-	Reasoning    *Reasoning           `json:"reasoning,omitempty" extensions:"x-nullable"`
-	ServiceTier  *string              `json:"service_tier,omitempty" enums:"auto,default,flex,priority,fast" extensions:"x-nullable"`
-	Text         *SavedAgentTextInput `json:"text,omitempty" extensions:"x-nullable"`
-	Tools        []json.RawMessage    `json:"tools,omitempty" swaggertype:"array,object" extensions:"x-nullable"`
-}
-
-type SavedAgentTextInput struct {
-	Format    json.RawMessage `json:"format,omitempty" swaggertype:"object" extensions:"x-nullable"`
-	Verbosity *string         `json:"verbosity,omitempty" enums:"low,medium,high" extensions:"x-nullable"`
-}
-
-type SavedAgentText struct {
-	Format    SavedAgentTextFormat `json:"format" binding:"required"`
-	Verbosity string               `json:"verbosity" binding:"required" enums:"low,medium,high"`
-}
-
-type SavedAgentTextFormat struct {
-	Type   string          `json:"type" binding:"required" enums:"text,json_schema"`
-	Schema json.RawMessage `json:"schema,omitempty" swaggertype:"object"`
-}
-
-// SavedAgentConfiguration excludes resource identity and mutable metadata. It is
-// not the immutable effective configuration of an execution Session.
-type SavedAgentConfiguration struct {
-	XAgentsCore  *SavedAgentCore   `json:"x_agents_core,omitempty" extensions:"x-nullable"`
-	Model        string            `json:"model" binding:"required"`
-	Name         *string           `json:"name" extensions:"x-nullable"`
-	Instructions *string           `json:"instructions" extensions:"x-nullable"`
-	MultiAgent   MultiAgentConfig  `json:"multi_agent" binding:"required"`
-	Reasoning    Reasoning         `json:"reasoning" binding:"required"`
-	ServiceTier  string            `json:"service_tier" binding:"required" enums:"auto,default,flex,priority,fast"`
-	Text         SavedAgentText    `json:"text" binding:"required"`
-	Tools        []json.RawMessage `json:"tools" binding:"required" swaggertype:"array,object"`
-}
-
-type SavedAgent struct {
-	SavedAgentConfiguration
-	ID        string            `json:"id" binding:"required"`
-	Object    string            `json:"object" binding:"required" enums:"agent"`
-	Metadata  map[string]string `json:"metadata" binding:"required"`
-	CreatedAt int64             `json:"created_at" binding:"required"`
-	UpdatedAt int64             `json:"updated_at" binding:"required"`
-}
-
 // MarshalJSON renders reasoning with explicit null keys. The stored
 // SavedAgentConfiguration keeps its original encoding.
 func (a SavedAgent) MarshalJSON() ([]byte, error) {
@@ -78,18 +11,3 @@ func (a SavedAgent) MarshalJSON() ([]byte, error) {
 		Reasoning reasoningResponse `json:"reasoning"`
 	}{wire(a), reasoningResponse(a.Reasoning)})
 }
-
-type SavedAgentList struct {
-	Object  string       `json:"object" binding:"required" enums:"list"`
-	Data    []SavedAgent `json:"data" binding:"required"`
-	HasMore bool         `json:"has_more" binding:"required"`
-	FirstID *string      `json:"first_id" extensions:"x-nullable"`
-	LastID  *string      `json:"last_id" extensions:"x-nullable"`
-}
-
-// AgentDeleted is the pinned successful saved-resource deletion response.
-type AgentDeleted struct {
-	ID      string `json:"id" binding:"required"`
-	Object  string `json:"object" binding:"required" enums:"agent.deleted"`
-	Deleted bool   `json:"deleted" binding:"required" enums:"true"`
-}
diff --git a/contracts/agents-api/v1/credentials.go b/contracts/agents-api/v1/credentials.go
index e5360ad68..1d1a443d6 100644
--- a/contracts/agents-api/v1/credentials.go
+++ b/contracts/agents-api/v1/credentials.go
@@ -2,81 +2,6 @@ package v1
 
 import "encoding/json"
 
-// CredentialAuthInput represents the pinned create union. The API validates each
-// discriminator separately so fields cannot cross authentication variants.
-type CredentialAuthInput struct {
-	Type         string                       `json:"type" binding:"required" enums:"static_bearer,mcp_oauth"`
-	MCPServerURL *string                      `json:"mcp_server_url" binding:"required"`
-	Token        *string                      `json:"token,omitempty" minLength:"1"`
-	AccessToken  *string                      `json:"access_token,omitempty" minLength:"1"`
-	ExpiresAt    *string                      `json:"expires_at,omitempty" extensions:"x-nullable"`
-	Refresh      *OAuthCredentialRefreshInput `json:"refresh,omitempty" extensions:"x-nullable"`
-}
-
-type CreateCredentialRequest struct {
-	Name *string              `json:"name" binding:"required"`
-	Auth *CredentialAuthInput `json:"auth" binding:"required"`
-}
-
-type OAuthCredentialRefreshInput struct {
-	ClientID          *string                 `json:"client_id" binding:"required"`
-	RefreshToken      *string                 `json:"refresh_token" binding:"required"`
-	TokenEndpoint     *string                 `json:"token_endpoint" binding:"required"`
-	TokenEndpointAuth *OAuthEndpointAuthInput `json:"token_endpoint_auth" binding:"required"`
-	Resource          *string                 `json:"resource,omitempty" extensions:"x-nullable"`
-	Scope             *string                 `json:"scope,omitempty" extensions:"x-nullable"`
-}
-
-type OAuthEndpointAuthInput struct {
-	Type         string  `json:"type" binding:"required" enums:"none,client_secret_basic,client_secret_post"`
-	ClientSecret *string `json:"client_secret,omitempty"`
-}
-
-type UpdateCredentialRequest struct {
-	Auth *CredentialAuthReplacement `json:"auth" binding:"required"`
-}
-
-// Raw nullable fields retain omission separately from explicit null.
-type CredentialAuthReplacement struct {
-	Type        string                             `json:"type" binding:"required" enums:"static_bearer,mcp_oauth"`
-	Token       *string                            `json:"token,omitempty" minLength:"1"`
-	AccessToken *string                            `json:"access_token,omitempty" extensions:"x-nullable" minLength:"1"`
-	ExpiresAt   json.RawMessage                    `json:"expires_at,omitempty" swaggertype:"string" extensions:"x-nullable"`
-	Refresh     *OAuthCredentialRefreshReplacement `json:"refresh,omitempty" extensions:"x-nullable"`
-}
-
-type OAuthCredentialRefreshReplacement struct {
-	RefreshToken      *string                       `json:"refresh_token,omitempty" extensions:"x-nullable"`
-	Scope             json.RawMessage               `json:"scope,omitempty" swaggertype:"string" extensions:"x-nullable"`
-	TokenEndpointAuth *OAuthEndpointAuthReplacement `json:"token_endpoint_auth,omitempty" extensions:"x-nullable"`
-}
-
-type OAuthEndpointAuthReplacement struct {
-	Type         string  `json:"type" binding:"required" enums:"client_secret_basic,client_secret_post"`
-	ClientSecret *string `json:"client_secret,omitempty" extensions:"x-nullable"`
-}
-
-// CredentialAuth contains safe metadata only. OAuth nullable fields are emitted
-// for OAuth credentials and excluded entirely from static bearer resources.
-type CredentialAuth struct {
-	Type         string                  `json:"type" binding:"required" enums:"static_bearer,mcp_oauth"`
-	MCPServerURL string                  `json:"mcp_server_url" binding:"required"`
-	ExpiresAt    *string                 `json:"expires_at" extensions:"x-nullable"`
-	Refresh      *OAuthCredentialRefresh `json:"refresh" extensions:"x-nullable"`
-}
-
-type OAuthCredentialRefresh struct {
-	ClientID          string            `json:"client_id" binding:"required"`
-	TokenEndpoint     string            `json:"token_endpoint" binding:"required"`
-	TokenEndpointAuth OAuthEndpointAuth `json:"token_endpoint_auth" binding:"required"`
-	Resource          *string           `json:"resource" extensions:"x-nullable"`
-	Scope             *string           `json:"scope" extensions:"x-nullable"`
-}
-
-type OAuthEndpointAuth struct {
-	Type string `json:"type" binding:"required" enums:"none,client_secret_basic,client_secret_post"`
-}
-
 func (a CredentialAuth) MarshalJSON() ([]byte, error) {
 	if a.Type == "static_bearer" {
 		return json.Marshal(struct {
@@ -87,27 +12,3 @@ func (a CredentialAuth) MarshalJSON() ([]byte, error) {
 	type resource CredentialAuth
 	return json.Marshal(resource(a))
 }
-
-type Credential struct {
-	ID        string         `json:"id" binding:"required"`
-	VaultID   string         `json:"vault_id" binding:"required"`
-	Name      string         `json:"name" binding:"required"`
-	Object    string         `json:"object" binding:"required" enums:"vault.credential"`
-	Auth      CredentialAuth `json:"auth" binding:"required"`
-	CreatedAt int64          `json:"created_at" binding:"required"`
-	UpdatedAt int64          `json:"updated_at" binding:"required"`
-}
-
-type CredentialList struct {
-	Object  string       `json:"object" binding:"required" enums:"list"`
-	Data    []Credential `json:"data" binding:"required"`
-	HasMore bool         `json:"has_more" binding:"required"`
-	FirstID *string      `json:"first_id" extensions:"x-nullable"`
-	LastID  *string      `json:"last_id" extensions:"x-nullable"`
-}
-
-type CredentialDeleted struct {
-	ID      string `json:"id" binding:"required"`
-	Deleted bool   `json:"deleted" binding:"required"`
-	Object  string `json:"object" binding:"required" enums:"vault.credential.deleted"`
-}
diff --git a/contracts/agents-api/v1/environment_events.go b/contracts/agents-api/v1/environment_events.go
deleted file mode 100644
index e7808b836..000000000
--- a/contracts/agents-api/v1/environment_events.go
+++ /dev/null
@@ -1,10 +0,0 @@
-package v1
-
-// SessionEnvironmentState is the pinned event snapshot, not EnvironmentInfo.
-// The event vocabulary includes ready; the resource vocabulary instead includes expired.
-type SessionEnvironmentState struct {
-	ID     string       `json:"id" binding:"required"`
-	Type   string       `json:"type" binding:"required"`
-	Status string       `json:"status" enums:"pending,ready,connected,disconnected,failed" binding:"required"`
-	Error  *StreamError `json:"error" extensions:"x-nullable"`
-}
diff --git a/contracts/agents-api/v1/environment_files.go b/contracts/agents-api/v1/environment_files.go
deleted file mode 100644
index 4427a565d..000000000
--- a/contracts/agents-api/v1/environment_files.go
+++ /dev/null
@@ -1,25 +0,0 @@
-package v1
-
-// EnvironmentFileCreateRequest represents the pinned inline/file_id union.
-type EnvironmentFileCreateRequest struct {
-	Type   string  `json:"type" binding:"required" enums:"inline,file_id"`
-	Data   *string `json:"data,omitempty"`
-	FileID *string `json:"file_id,omitempty"`
-	Path   *string `json:"path" binding:"required"`
-}
-
-type EnvironmentFile struct {
-	EnvironmentID string `json:"environment_id" binding:"required"`
-	Object        string `json:"object" binding:"required" enums:"agent.environment.file"`
-	Path          string `json:"path" binding:"required"`
-	SizeBytes     int64  `json:"size_bytes" binding:"required" minimum:"0"`
-}
-
-// EnvironmentFileList is the official token page: has_more is true exactly
-// when next carries a continuation token.
-type EnvironmentFileList struct {
-	Object  string            `json:"object" binding:"required" enums:"page"`
-	Data    []EnvironmentFile `json:"data" binding:"required"`
-	Next    *string           `json:"next" extensions:"x-nullable"`
-	HasMore bool              `json:"has_more" binding:"required"`
-}
diff --git a/contracts/agents-api/v1/environment_templates.go b/contracts/agents-api/v1/environment_templates.go
deleted file mode 100644
index d325ef476..000000000
--- a/contracts/agents-api/v1/environment_templates.go
+++ /dev/null
@@ -1,52 +0,0 @@
-package v1
-
-import "encoding/json"
-
-// EnvironmentTemplateRequest exposes pinned input fields; only qualified installations execute.
-type EnvironmentTemplateRequest struct {
-	Name                  *string                   `json:"name,omitempty" extensions:"x-nullable"`
-	Network               *EnvironmentNetworkInput  `json:"network,omitempty" extensions:"x-nullable"`
-	CapabilityDirectories []string                  `json:"capability_directories,omitempty" extensions:"x-nullable"`
-	Env                   map[string]string         `json:"env,omitempty" extensions:"x-nullable"`
-	Files                 []json.RawMessage         `json:"files,omitempty" extensions:"x-nullable" swaggertype:"array,object"`
-	Packages              *EnvironmentPackagesInput `json:"packages,omitempty" extensions:"x-nullable"`
-	Plugins               []json.RawMessage         `json:"plugins,omitempty" extensions:"x-nullable" swaggertype:"array,object"`
-	Skills                []json.RawMessage         `json:"skills,omitempty" extensions:"x-nullable" swaggertype:"array,object"`
-	SetupCommands         []json.RawMessage         `json:"setup_commands,omitempty" extensions:"x-nullable" swaggertype:"array,object"`
-}
-
-// EnvironmentPackagesInput keeps optional nullable request defaults separate from
-// the complete package lists returned by resource responses.
-type EnvironmentPackagesInput struct {
-	NPM    []string `json:"npm,omitempty" extensions:"x-nullable"`
-	Python []string `json:"python,omitempty" extensions:"x-nullable"`
-}
-
-// EnvironmentTemplate returns safe configuration metadata only.
-type EnvironmentTemplate struct {
-	ID                    string                      `json:"id" binding:"required"`
-	Object                string                      `json:"object" binding:"required" enums:"agent.environment.template"`
-	Name                  *string                     `json:"name" extensions:"x-nullable"`
-	CreatedAt             int64                       `json:"created_at" binding:"required"`
-	UpdatedAt             int64                       `json:"updated_at" binding:"required"`
-	CapabilityDirectories []string                    `json:"capability_directories" binding:"required"`
-	Network               EnvironmentNetwork          `json:"network" binding:"required"`
-	Packages              EnvironmentPackagesResponse `json:"packages" binding:"required"`
-	Files                 []json.RawMessage           `json:"files" binding:"required" swaggertype:"array,object"`
-	Plugins               []json.RawMessage           `json:"plugins" binding:"required" swaggertype:"array,object"`
-	Skills                []json.RawMessage           `json:"skills" binding:"required" swaggertype:"array,object"`
-}
-
-type EnvironmentTemplateList struct {
-	Object  string                `json:"object" binding:"required" enums:"list"`
-	Data    []EnvironmentTemplate `json:"data" binding:"required"`
-	HasMore bool                  `json:"has_more" binding:"required"`
-	FirstID *string               `json:"first_id" extensions:"x-nullable"`
-	LastID  *string               `json:"last_id" extensions:"x-nullable"`
-}
-
-type EnvironmentTemplateDeleted struct {
-	ID      string `json:"id" binding:"required"`
-	Object  string `json:"object" binding:"required" enums:"agent.environment.template.deleted"`
-	Deleted bool   `json:"deleted" binding:"required"`
-}
diff --git a/contracts/agents-api/v1/environments.go b/contracts/agents-api/v1/environments.go
deleted file mode 100644
index fc4e4a1de..000000000
--- a/contracts/agents-api/v1/environments.go
+++ /dev/null
@@ -1,39 +0,0 @@
-package v1
-
-import "encoding/json"
-
-// EnvironmentInfo contains safe installed metadata; populated installation variants remain unsupported.
-type EnvironmentInfo struct {
-	ID      string            `json:"id" binding:"required"`
-	Object  string            `json:"object" binding:"required" enums:"agent.environment"`
-	Type    string            `json:"type" binding:"required" enums:"openai_hosted,self_hosted"`
-	Status  string            `json:"status" binding:"required" enums:"pending,connected,disconnected,expired,failed"`
-	Files   []json.RawMessage `json:"files" binding:"required" swaggertype:"array,object"`
-	Plugins []json.RawMessage `json:"plugins" binding:"required" swaggertype:"array,object"`
-	Skills  []json.RawMessage `json:"skills" binding:"required" swaggertype:"array,object"`
-}
-
-// EnvironmentNetwork is the effective hosted network policy.
-type EnvironmentNetwork struct {
-	Access         string   `json:"access" binding:"required" enums:"enabled,disabled,restricted"`
-	AllowedDomains []string `json:"allowed_domains" binding:"required"`
-}
-
-// EnvironmentNetworkInput preserves the optional request domain list.
-type EnvironmentNetworkInput struct {
-	Access         string   `json:"access" binding:"required" enums:"enabled,disabled,restricted"`
-	AllowedDomains []string `json:"allowed_domains,omitempty" extensions:"x-nullable"`
-}
-
-type EnvironmentPackages struct {
-	NPM    []string `json:"npm" binding:"required"`
-	Python []string `json:"python" binding:"required"`
-}
-
-// EnvironmentPackagesResponse preserves the official response schema. System is
-// always empty: Runtime system-package requests are unsupported.
-type EnvironmentPackagesResponse struct {
-	NPM    []string `json:"npm" binding:"required"`
-	Python []string `json:"python" binding:"required"`
-	System []string `json:"system" binding:"required"`
-}
diff --git a/contracts/agents-api/v1/events.go b/contracts/agents-api/v1/events.go
index d344623d0..dc2441bc5 100644
--- a/contracts/agents-api/v1/events.go
+++ b/contracts/agents-api/v1/events.go
@@ -2,39 +2,6 @@ package v1
 
 import "encoding/json"
 
-// SessionEvent contains the supported live event variants of the pinned protocol.
-type SessionEvent struct {
-	Subagent     *Subagent                `json:"subagent,omitempty"`
-	Type         string                   `json:"type" binding:"required"`
-	EventID      string                   `json:"event_id" binding:"required"`
-	SessionID    string                   `json:"session_id,omitempty"`
-	TurnID       string                   `json:"turn_id,omitempty"`
-	Session      *Session                 `json:"session,omitempty"`
-	Turn         *Turn                    `json:"turn,omitempty"`
-	Item         *Item                    `json:"item,omitempty"`
-	ItemID       string                   `json:"item_id,omitempty"`
-	OutputIndex  *int32                   `json:"output_index,omitempty" extensions:"x-nullable"`
-	ContentIndex *int                     `json:"content_index,omitempty"`
-	Part         *ItemContent             `json:"part,omitempty"`
-	Delta        *string                  `json:"delta,omitempty"`
-	Text         *string                  `json:"text,omitempty"`
-	Error        *StreamError             `json:"error,omitempty"`
-	Environment  *SessionEnvironmentState `json:"environment,omitempty"`
-	// Usage is present only on terminal Turn events, where it mirrors the Turn
-	// snapshot and is null when unknown. Other events omit it.
-	Usage *TokenUsage `json:"usage,omitempty" extensions:"x-nullable"`
-}
-
-type StreamError struct {
-	Code    string `json:"code"`
-	Type    string `json:"type"`
-	Message string `json:"message"`
-	// Param is the pinned SessionError field. An error SessionEvent always
-	// carries it, null when unset; Environment state errors and Core's own
-	// stream_interrupted frame omit it.
-	Param *string `json:"param,omitempty" extensions:"x-nullable"`
-}
-
 // TerminalTurnEvent reports whether an event type settles a Turn.
 func TerminalTurnEvent(eventType string) bool {
 	switch eventType {
@@ -49,15 +16,6 @@ func itemEvent(eventType string) bool {
 	return eventType == "agent.session.turn.item.added" || eventType == "agent.session.turn.item.done"
 }
 
-// sessionError is the pinned SessionError of a top-level error event, whose
-// param is present and null when unset (HI-01).
-type sessionError struct {
-	Code    string  `json:"code"`
-	Type    string  `json:"type"`
-	Message string  `json:"message"`
-	Param   *string `json:"param"`
-}
-
 // MarshalJSON keeps the nullable top-level usage on terminal Turn events only,
 // a nullable output_index on every Item event (EVT-09) and a nullable error
 // param on error events.
diff --git a/contracts/agents-api/v1/function_actions.go b/contracts/agents-api/v1/function_actions.go
deleted file mode 100644
index 4d90bfc50..000000000
--- a/contracts/agents-api/v1/function_actions.go
+++ /dev/null
@@ -1,10 +0,0 @@
-package v1
-
-// FunctionCallAction is the supported function-call variant of required_actions.
-type FunctionCallAction struct {
-	Arguments any    `json:"arguments" binding:"required"`
-	CallID    string `json:"call_id" binding:"required"`
-	Name      string `json:"name" binding:"required"`
-	TurnID    string `json:"turn_id" binding:"required"`
-	Type      string `json:"type" enums:"function_call" binding:"required"`
-}
diff --git a/contracts/agents-api/v1/function_tools.go b/contracts/agents-api/v1/function_tools.go
deleted file mode 100644
index ad5aea81e..000000000
--- a/contracts/agents-api/v1/function_tools.go
+++ /dev/null
@@ -1,12 +0,0 @@
-package v1
-
-import "encoding/json"
-
-// FunctionToolInput is the supported application-defined tool configuration.
-type FunctionToolInput struct {
-	Type         string          `json:"type" enums:"function" binding:"required"`
-	Name         *string         `json:"name" binding:"required"`
-	Description  *string         `json:"description" binding:"required"`
-	Parameters   json.RawMessage `json:"parameters" swaggertype:"object" binding:"required"`
-	DeferLoading json.RawMessage `json:"defer_loading,omitempty" swaggertype:"boolean"`
-}
diff --git a/contracts/agents-api/v1/inputs.go b/contracts/agents-api/v1/inputs.go
deleted file mode 100644
index 2fd8600c5..000000000
--- a/contracts/agents-api/v1/inputs.go
+++ /dev/null
@@ -1,30 +0,0 @@
-package v1
-
-import "encoding/json"
-
-// SessionInput contains the message, cancellation and function-result event variants.
-type SessionInput struct {
-	Type    string          `json:"type" enums:"agent.session.input.message,agent.session.input.cancel,agent.session.input.tool_result" binding:"required"`
-	Input   []InputMessage  `json:"input,omitempty"`
-	CallID  string          `json:"call_id,omitempty"`
-	TurnID  string          `json:"turn_id,omitempty"`
-	Success *bool           `json:"success,omitempty"`
-	Error   json.RawMessage `json:"error,omitempty" swaggertype:"string" extensions:"x-nullable"`
-	Output  any             `json:"output,omitempty" extensions:"x-nullable"`
-}
-
-type InputMessage struct {
-	Type    string         `json:"type,omitempty" enums:"message"`
-	Role    string         `json:"role" enums:"user" binding:"required"`
-	Content []InputContent `json:"content" binding:"required"`
-}
-
-type InputContent struct {
-	Type     string  `json:"type" enums:"input_text,input_image" binding:"required"`
-	Text     *string `json:"text,omitempty"`
-	ImageURL *string `json:"image_url,omitempty"`
-}
-
-type CreateEventsRequest struct {
-	Events []SessionInput `json:"events" binding:"required"`
-}
diff --git a/contracts/agents-api/v1/items.go b/contracts/agents-api/v1/items.go
index c004bcf4c..18813fab3 100644
--- a/contracts/agents-api/v1/items.go
+++ b/contracts/agents-api/v1/items.go
@@ -5,58 +5,6 @@ import (
 	"encoding/json"
 )
 
-// Item contains the supported variants of the pinned Session Item union.
-type Item struct {
-	ID                string           `json:"id" binding:"required"`
-	TurnID            string           `json:"turn_id" binding:"required"`
-	Type              string           `json:"type" binding:"required" enums:"message,command_execution,mcp_call,function_call,function_call_output,web_search_call,reasoning,agent_message,create_subagent_call,send_subagent_input_call,resume_subagent_call,wait_for_subagents_call,interrupt_subagent_call,close_subagent_call"`
-	Status            string           `json:"status" enums:"in_progress,completed,failed,incomplete"`
-	Role              string           `json:"role,omitempty" enums:"user,assistant"`
-	Phase             string           `json:"phase,omitempty" enums:"commentary,final_answer" extensions:"x-nullable"`
-	Content           []ItemContent    `json:"content,omitempty"`
-	Command           string           `json:"command,omitempty"`
-	Cwd               *string          `json:"cwd,omitempty"`
-	DurationMS        *int64           `json:"duration_ms,omitempty"`
-	ExitCode          *int64           `json:"exit_code,omitempty"`
-	Name              string           `json:"name,omitempty"`
-	CallID            string           `json:"call_id,omitempty"`
-	ServerLabel       string           `json:"server_label,omitempty"`
-	Arguments         any              `json:"arguments,omitempty"`
-	Output            any              `json:"output,omitempty"`
-	Error             any              `json:"error,omitempty"`
-	Action            *WebSearchAction `json:"action,omitempty"`
-	AgentID           string           `json:"agent_id,omitempty"`
-	SenderAgentID     string           `json:"sender_agent_id,omitempty"`
-	RecipientAgentID  string           `json:"recipient_agent_id,omitempty"`
-	RecipientAgentIDs []string         `json:"recipient_agent_ids,omitempty"`
-	Model             *string          `json:"model,omitempty"`
-	ReasoningEffort   *string          `json:"reasoning_effort,omitempty"`
-	Summary           []SummaryText    `json:"summary,omitempty"`
-}
-
-type ItemContent struct {
-	Type             string  `json:"type" binding:"required" enums:"input_text,output_text,input_image,encrypted_content"`
-	Text             *string `json:"text,omitempty"`
-	ImageURL         string  `json:"image_url,omitempty"`
-	EncryptedContent *string `json:"encrypted_content,omitempty"`
-}
-
-type WebSearchAction struct {
-	Type    string   `json:"type" binding:"required" enums:"search,open_page,find_in_page,other"`
-	Query   *string  `json:"query,omitempty"`
-	Queries []string `json:"queries,omitempty"`
-	URL     *string  `json:"url,omitempty"`
-	Pattern *string  `json:"pattern,omitempty"`
-}
-
-type ItemList struct {
-	Object  string  `json:"object" enums:"list" binding:"required"`
-	FirstID *string `json:"first_id" extensions:"x-nullable"`
-	LastID  *string `json:"last_id" extensions:"x-nullable"`
-	Data    []Item  `json:"data" binding:"required"`
-	HasMore bool    `json:"has_more" binding:"required"`
-}
-
 // UnmarshalJSON preserves integer precision in tool arguments and structured results.
 func (i *Item) UnmarshalJSON(raw []byte) error {
 	type wire Item
diff --git a/contracts/agents-api/v1/items_test.go b/contracts/agents-api/v1/items_test.go
index 5de654118..5e5c154e9 100644
--- a/contracts/agents-api/v1/items_test.go
+++ b/contracts/agents-api/v1/items_test.go
@@ -155,3 +155,38 @@ func TestReasoningResponsesCarryBothKeys(t *testing.T) {
 	}{Agent{ID: "agent", Reasoning: Reasoning{Effort: &low}}})
 	expectField(t, fields(t, stored["agent"]), "reasoning", `{"effort":"low"}`)
 }
+
+func TestStoredSearchItemRoundTripPreservesPayload(t *testing.T) {
+	for _, raw := range []string{
+		`{"id":"search","turn_id":"turn","type":"web_search_call","status":"completed","action":{"type":"search","query":"reference"}}`,
+		`{"id":"search","turn_id":"turn","type":"web_search_call","status":"completed","action":{"type":"search"}}`,
+		`{"id":"search","turn_id":"turn","type":"web_search_call","status":"in_progress"}`,
+	} {
+		var item Item
+		if err := json.Unmarshal([]byte(raw), &item); err != nil {
+			t.Fatal(err)
+		}
+		stored, err := item.MarshalStored()
+		if err != nil {
+			t.Fatal(err)
+		}
+		if string(stored) != raw {
+			t.Fatalf("stored replay changed: %s, want %s", stored, raw)
+		}
+		wire := fields(t, item)
+		if item.Action == nil {
+			expectField(t, wire, "action", "null")
+		} else {
+			var action map[string]json.RawMessage
+			if err := json.Unmarshal(wire["action"], &action); err != nil {
+				t.Fatal(err)
+			}
+			if _, ok := action["query"]; !ok {
+				t.Fatal("wire query is missing")
+			}
+			if _, ok := action["queries"]; !ok {
+				t.Fatal("wire queries is missing")
+			}
+		}
+	}
+}
diff --git a/contracts/agents-api/v1/mcp_tools.go b/contracts/agents-api/v1/mcp_tools.go
deleted file mode 100644
index c8cd2adf7..000000000
--- a/contracts/agents-api/v1/mcp_tools.go
+++ /dev/null
@@ -1,34 +0,0 @@
-package v1
-
-import "encoding/json"
-
-// MCPToolInput preserves presence for the pinned MCP configuration union.
-type MCPToolInput struct {
-	Type             string          `json:"type"`
-	ServerLabel      *string         `json:"server_label"`
-	Transport        json.RawMessage `json:"transport"`
-	AllowedTools     json.RawMessage `json:"allowed_tools"`
-	ConnectionOrigin *string         `json:"connection_origin"`
-	CredentialID     *string         `json:"credential_id"`
-	RequestMetadata  json.RawMessage `json:"request_metadata"`
-	Required         json.RawMessage `json:"required"`
-}
-
-// MCPTool is the supported HTTP resource shape. Headers belong only to saved
-// configuration; effective Session transports expose type and server_url.
-type MCPTool struct {
-	Type             string                     `json:"type"`
-	ServerLabel      string                     `json:"server_label"`
-	Transport        MCPHTTPTransport           `json:"transport"`
-	AllowedTools     *[]string                  `json:"allowed_tools"`
-	ConnectionOrigin string                     `json:"connection_origin"`
-	CredentialID     *string                    `json:"credential_id"`
-	RequestMetadata  map[string]json.RawMessage `json:"request_metadata"`
-	Required         bool                       `json:"required"`
-}
-
-type MCPHTTPTransport struct {
-	Type      string             `json:"type"`
-	ServerURL string             `json:"server_url"`
-	Headers   *map[string]string `json:"headers,omitempty"`
-}
diff --git a/contracts/agents-api/v1/model_execution.go b/contracts/agents-api/v1/model_execution.go
index 5babd6861..9d52bcb28 100644
--- a/contracts/agents-api/v1/model_execution.go
+++ b/contracts/agents-api/v1/model_execution.go
@@ -88,7 +88,3 @@ func (p *ModelProviderInput) ValidateHarnessWithRegistry(harness string, registr
 	}
 	return nil
 }
-
-func ValidateModelProtocol(protocol, harness string) error {
-	return builtin.Registry().ValidateProtocol(harness, protocol)
-}
diff --git a/contracts/agents-api/v1/official.gen.go b/contracts/agents-api/v1/official.gen.go
new file mode 100644
index 000000000..1cc7b4653
--- /dev/null
+++ b/contracts/agents-api/v1/official.gen.go
@@ -0,0 +1,932 @@
+// Code generated by scripts/generate-public-api.py; DO NOT EDIT.
+package v1
+
+import "encoding/json"
+
+import "fmt"
+
+// APIError projects Error.
+type APIError struct {
+	Message      string          `json:"message" binding:"required"`
+	Type         string          `json:"type" binding:"required"`
+	Code         *string         `json:"code" binding:"required" extensions:"x-nullable"`
+	Param        *string         `json:"param" binding:"required" extensions:"x-nullable"`
+	Misalignment json.RawMessage `json:"misalignment,omitempty" swaggertype:"object"`
+}
+
+// Agent projects SessionAgentResource.
+type Agent struct {
+	XAgentsCore  *AgentsCore       `json:"x_agents_core,omitempty"`
+	ID           string            `json:"id" binding:"required"`
+	Instructions *string           `json:"instructions" binding:"required" extensions:"x-nullable"`
+	Model        string            `json:"model" binding:"required"`
+	MultiAgent   MultiAgentConfig  `json:"multi_agent" binding:"required"`
+	Name         *string           `json:"name" binding:"required" extensions:"x-nullable"`
+	Reasoning    Reasoning         `json:"reasoning" binding:"required"`
+	ServiceTier  string            `json:"service_tier" binding:"required" enums:"auto,default,flex,priority,fast"`
+	Text         TextConfig        `json:"text" binding:"required"`
+	Tools        []json.RawMessage `json:"tools" binding:"required" swaggertype:"array,object"`
+}
+
+// AgentContent projects AgentContentResource.
+type AgentContent struct {
+	Type             string  `json:"type" binding:"required" enums:"output_text,encrypted_content"`
+	Text             *string `json:"text,omitempty"`
+	EncryptedContent *string `json:"encrypted_content,omitempty"`
+}
+
+// AgentDeleted projects DeletedAgentResource.
+type AgentDeleted struct {
+	ID      string `json:"id" binding:"required"`
+	Object  string `json:"object" binding:"required" enums:"agent.deleted"`
+	Deleted bool   `json:"deleted" binding:"required"`
+}
+
+// AgentMessageItem projects AgentMessageItemResource.
+type AgentMessageItem struct {
+	ID               string         `json:"id" binding:"required"`
+	TurnID           string         `json:"turn_id" binding:"required"`
+	Type             string         `json:"type" binding:"required" enums:"agent_message"`
+	SenderAgentID    string         `json:"sender_agent_id" binding:"required"`
+	RecipientAgentID string         `json:"recipient_agent_id" binding:"required"`
+	Content          []AgentContent `json:"content" binding:"required"`
+}
+
+// CreateAgentRequest projects CreateAgentParams.
+type CreateAgentRequest struct {
+	XAgentsCore  *SavedAgentCoreInput `json:"x_agents_core,omitempty"`
+	Model        *string              `json:"model" binding:"required"`
+	Name         *string              `json:"name,omitempty" extensions:"x-nullable"`
+	Instructions *string              `json:"instructions,omitempty" extensions:"x-nullable"`
+	Metadata     map[string]*string   `json:"metadata,omitempty" extensions:"x-nullable"`
+	MultiAgent   json.RawMessage      `json:"multi_agent,omitempty" extensions:"x-nullable" swaggertype:"object"`
+	Reasoning    *Reasoning           `json:"reasoning,omitempty" extensions:"x-nullable"`
+	ServiceTier  *string              `json:"service_tier,omitempty" extensions:"x-nullable" enums:"auto,default,flex,priority,fast"`
+	Text         *TextConfigInput     `json:"text,omitempty" extensions:"x-nullable"`
+	Tools        []json.RawMessage    `json:"tools,omitempty" extensions:"x-nullable" swaggertype:"array,object"`
+}
+
+// CreateSessionRequest projects CreateAgentSessionParams.
+type CreateSessionRequest struct {
+	XAgentsCore *SessionExecutionInput `json:"x_agents_core,omitempty"`
+	Agent       *InlineAgent           `json:"agent,omitempty"`
+	AgentID     *string                `json:"agent_id,omitempty"`
+	Environment *Environment           `json:"environment" binding:"required"`
+	Input       any                    `json:"input,omitempty" extensions:"x-nullable"`
+	Metadata    map[string]string      `json:"metadata,omitempty" extensions:"x-nullable"`
+	Stream      bool                   `json:"stream,omitempty"`
+	VaultIDs    []string               `json:"vault_ids,omitempty" extensions:"x-nullable"`
+}
+
+// CreateSubagentCallItem projects CreateSubagentCallItemResource.
+type CreateSubagentCallItem struct {
+	ID              string         `json:"id" binding:"required"`
+	TurnID          string         `json:"turn_id" binding:"required"`
+	Type            string         `json:"type" binding:"required" enums:"create_subagent_call"`
+	Status          string         `json:"status" binding:"required" enums:"in_progress,completed,failed,incomplete"`
+	AgentID         string         `json:"agent_id" binding:"required"`
+	Content         []AgentContent `json:"content" binding:"required"`
+	Model           *string        `json:"model" binding:"required" extensions:"x-nullable"`
+	ReasoningEffort *string        `json:"reasoning_effort" binding:"required" extensions:"x-nullable"`
+}
+
+// Credential projects VaultCredentialResource.
+type Credential struct {
+	ID        string         `json:"id" binding:"required"`
+	VaultID   string         `json:"vault_id" binding:"required"`
+	Name      string         `json:"name" binding:"required"`
+	Object    string         `json:"object" binding:"required" enums:"vault.credential"`
+	Auth      CredentialAuth `json:"auth" binding:"required"`
+	CreatedAt int64          `json:"created_at" binding:"required"`
+	UpdatedAt int64          `json:"updated_at" binding:"required"`
+}
+
+// CredentialAuth projects VaultCredentialAuthResource.
+type CredentialAuth struct {
+	Type         string                  `json:"type" binding:"required" enums:"mcp_oauth,static_bearer"`
+	MCPServerURL string                  `json:"mcp_server_url" binding:"required"`
+	ExpiresAt    *string                 `json:"expires_at" extensions:"x-nullable"`
+	Refresh      *OAuthCredentialRefresh `json:"refresh" extensions:"x-nullable"`
+}
+
+// CredentialAuthInput projects CreateVaultCredentialAuthParam.
+type CredentialAuthInput struct {
+	Type         string                       `json:"type" binding:"required" enums:"mcp_oauth,static_bearer"`
+	MCPServerURL *string                      `json:"mcp_server_url" binding:"required"`
+	Token        *string                      `json:"token,omitempty"`
+	AccessToken  *string                      `json:"access_token,omitempty"`
+	ExpiresAt    *string                      `json:"expires_at,omitempty" extensions:"x-nullable"`
+	Refresh      *OAuthCredentialRefreshInput `json:"refresh,omitempty" extensions:"x-nullable"`
+}
+
+// CredentialAuthReplacement projects RotateVaultCredentialAuthParam.
+type CredentialAuthReplacement struct {
+	Type        string                             `json:"type" binding:"required" enums:"mcp_oauth,static_bearer"`
+	Token       *string                            `json:"token,omitempty"`
+	AccessToken *string                            `json:"access_token,omitempty" extensions:"x-nullable"`
+	ExpiresAt   json.RawMessage                    `json:"expires_at,omitempty" extensions:"x-nullable" swaggertype:"object"`
+	Refresh     *OAuthCredentialRefreshReplacement `json:"refresh,omitempty" extensions:"x-nullable"`
+}
+
+// CredentialDeleted projects DeletedVaultCredentialResource.
+type CredentialDeleted struct {
+	ID      string `json:"id" binding:"required"`
+	Deleted bool   `json:"deleted" binding:"required"`
+	Object  string `json:"object" binding:"required" enums:"vault.credential.deleted"`
+}
+
+// CredentialList projects VaultCredentialListResource.
+type CredentialList struct {
+	Object  string       `json:"object" binding:"required" enums:"list"`
+	Data    []Credential `json:"data" binding:"required"`
+	HasMore bool         `json:"has_more" binding:"required"`
+	FirstID *string      `json:"first_id" binding:"required" extensions:"x-nullable"`
+	LastID  *string      `json:"last_id" binding:"required" extensions:"x-nullable"`
+}
+
+// Environment projects EnvironmentParam.
+type Environment struct {
+	Plugins               []json.RawMessage        `json:"plugins,omitempty" extensions:"x-nullable" swaggertype:"array,object"`
+	Skills                []json.RawMessage        `json:"skills,omitempty" extensions:"x-nullable" swaggertype:"array,object"`
+	Env                   map[string]string        `json:"env,omitempty" extensions:"x-nullable"`
+	SetupCommands         []json.RawMessage        `json:"setup_commands,omitempty" extensions:"x-nullable" swaggertype:"array,object"`
+	Packages              *EnvironmentPackages     `json:"packages,omitempty" extensions:"x-nullable"`
+	Files                 []json.RawMessage        `json:"files,omitempty" extensions:"x-nullable" swaggertype:"array,object"`
+	EnvironmentTemplateID string                   `json:"environment_template_id,omitempty"`
+	Type                  string                   `json:"type" binding:"required" enums:"none,openai_hosted,self_hosted"`
+	WorkspaceDirectory    string                   `json:"workspace_directory,omitempty"`
+	CapabilityDirectories []string                 `json:"capability_directories,omitempty" extensions:"x-nullable"`
+	Network               *EnvironmentNetworkInput `json:"network,omitempty" extensions:"x-nullable"`
+}
+
+// EnvironmentConnectionAction projects SessionRequiredActionResourceEnvironmentConnection.
+type EnvironmentConnectionAction struct {
+	EnvironmentID string `json:"environment_id" binding:"required"`
+	Type          string `json:"type" binding:"required" enums:"environment_connection"`
+}
+
+// EnvironmentFile projects EnvironmentFileResource.
+type EnvironmentFile struct {
+	EnvironmentID string `json:"environment_id" binding:"required"`
+	Object        string `json:"object" binding:"required" enums:"agent.environment.file"`
+	Path          string `json:"path" binding:"required"`
+	SizeBytes     int64  `json:"size_bytes" binding:"required"`
+}
+
+// EnvironmentFileCreateRequest projects HostedEnvironmentFileParam.
+type EnvironmentFileCreateRequest struct {
+	Type   string  `json:"type" binding:"required" enums:"file_id,inline"`
+	Data   *string `json:"data,omitempty"`
+	FileID *string `json:"file_id,omitempty"`
+	Path   *string `json:"path" binding:"required"`
+}
+
+// EnvironmentFileList projects EnvironmentFileListResource.
+type EnvironmentFileList struct {
+	Object  string            `json:"object" binding:"required" enums:"page"`
+	Data    []EnvironmentFile `json:"data" binding:"required"`
+	Next    *string           `json:"next" binding:"required" extensions:"x-nullable"`
+	HasMore bool              `json:"has_more" binding:"required"`
+}
+
+// EnvironmentInfo projects PublicEnvironmentResource.
+type EnvironmentInfo struct {
+	ID      string            `json:"id" binding:"required"`
+	Object  string            `json:"object" binding:"required" enums:"agent.environment"`
+	Type    string            `json:"type" binding:"required" enums:"openai_hosted,self_hosted"`
+	Status  string            `json:"status" binding:"required" enums:"pending,connected,disconnected,expired,failed"`
+	Files   []json.RawMessage `json:"files" binding:"required" swaggertype:"array,object"`
+	Plugins []json.RawMessage `json:"plugins" binding:"required" swaggertype:"array,object"`
+	Skills  []json.RawMessage `json:"skills" binding:"required" swaggertype:"array,object"`
+}
+
+// EnvironmentNetwork projects NetworkPolicyResource.
+type EnvironmentNetwork struct {
+	Access         string   `json:"access" binding:"required" enums:"enabled,disabled,restricted"`
+	AllowedDomains []string `json:"allowed_domains" binding:"required"`
+}
+
+// EnvironmentNetworkInput projects NetworkPolicyParam.
+type EnvironmentNetworkInput struct {
+	Access         string   `json:"access" binding:"required" enums:"enabled,disabled,restricted"`
+	AllowedDomains []string `json:"allowed_domains,omitempty" extensions:"x-nullable"`
+}
+
+// EnvironmentPackages projects EnvironmentPackagesParam.
+type EnvironmentPackages struct {
+	NPM    []string `json:"npm" extensions:"x-nullable"`
+	Python []string `json:"python" extensions:"x-nullable"`
+}
+
+// EnvironmentPackagesResponse projects EnvironmentPackagesResource.
+type EnvironmentPackagesResponse struct {
+	NPM    []string `json:"npm" binding:"required"`
+	Python []string `json:"python" binding:"required"`
+	System []string `json:"system" binding:"required"`
+}
+
+// EnvironmentTemplate projects EnvironmentTemplateResource.
+type EnvironmentTemplate struct {
+	ID                    string                      `json:"id" binding:"required"`
+	Object                string                      `json:"object" binding:"required" enums:"agent.environment.template"`
+	Name                  *string                     `json:"name" binding:"required" extensions:"x-nullable"`
+	CreatedAt             int64                       `json:"created_at" binding:"required"`
+	UpdatedAt             int64                       `json:"updated_at" binding:"required"`
+	CapabilityDirectories []string                    `json:"capability_directories" binding:"required"`
+	Network               EnvironmentNetwork          `json:"network" binding:"required"`
+	Packages              EnvironmentPackagesResponse `json:"packages" binding:"required"`
+	Files                 []json.RawMessage           `json:"files" binding:"required" swaggertype:"array,object"`
+	Plugins               []json.RawMessage           `json:"plugins" binding:"required" swaggertype:"array,object"`
+	Skills                []json.RawMessage           `json:"skills" binding:"required" swaggertype:"array,object"`
+}
+
+// EnvironmentTemplateDeleted projects DeletedEnvironmentTemplateResource.
+type EnvironmentTemplateDeleted struct {
+	ID      string `json:"id" binding:"required"`
+	Object  string `json:"object" binding:"required" enums:"agent.environment.template.deleted"`
+	Deleted bool   `json:"deleted" binding:"required"`
+}
+
+// EnvironmentTemplateList projects EnvironmentTemplateListResource.
+type EnvironmentTemplateList struct {
+	Object  string                `json:"object" binding:"required" enums:"list"`
+	Data    []EnvironmentTemplate `json:"data" binding:"required"`
+	HasMore bool                  `json:"has_more" binding:"required"`
+	FirstID *string               `json:"first_id" binding:"required" extensions:"x-nullable"`
+	LastID  *string               `json:"last_id" binding:"required" extensions:"x-nullable"`
+}
+
+// ErrorResponse projects ErrorResponse-2.
+type ErrorResponse struct {
+	Error APIError `json:"error" binding:"required"`
+}
+
+// FunctionCallAction projects SessionRequiredActionResourceFunctionCall.
+type FunctionCallAction struct {
+	Arguments any    `json:"arguments" binding:"required"`
+	CallID    string `json:"call_id" binding:"required"`
+	Name      string `json:"name" binding:"required"`
+	TurnID    string `json:"turn_id" binding:"required"`
+	Type      string `json:"type" binding:"required" enums:"function_call"`
+}
+
+// FunctionToolInput projects AgentToolConfigParamFunction.
+type FunctionToolInput struct {
+	Type         string          `json:"type" binding:"required" enums:"function"`
+	Name         *string         `json:"name" binding:"required"`
+	Description  *string         `json:"description" binding:"required"`
+	Parameters   json.RawMessage `json:"parameters" binding:"required" swaggertype:"object"`
+	DeferLoading json.RawMessage `json:"defer_loading,omitempty" swaggertype:"object"`
+}
+
+// InlineAgent projects SessionAgentConfigParam.
+type InlineAgent struct {
+	XAgentsCore  *AgentsCore       `json:"x_agents_core,omitempty"`
+	Model        *string           `json:"model,omitempty"`
+	Instructions *string           `json:"instructions,omitempty" extensions:"x-nullable"`
+	MultiAgent   json.RawMessage   `json:"multi_agent,omitempty" extensions:"x-nullable" swaggertype:"object"`
+	Reasoning    *Reasoning        `json:"reasoning,omitempty" extensions:"x-nullable"`
+	ServiceTier  *string           `json:"service_tier,omitempty" extensions:"x-nullable" enums:"auto,default,flex,priority,fast"`
+	Text         *TextConfigInput  `json:"text,omitempty" extensions:"x-nullable"`
+	Tools        []json.RawMessage `json:"tools,omitempty" extensions:"x-nullable" swaggertype:"array,object"`
+}
+
+// InputContent projects InputContentParam.
+type InputContent struct {
+	Type     string  `json:"type" binding:"required" enums:"input_text,input_image"`
+	Text     *string `json:"text,omitempty"`
+	ImageURL *string `json:"image_url,omitempty"`
+}
+
+// InputMessage projects InputMessageParam.
+type InputMessage struct {
+	Type    string         `json:"type,omitempty" enums:"message"`
+	Role    string         `json:"role" binding:"required" enums:"user"`
+	Content []InputContent `json:"content" binding:"required"`
+}
+
+// InputTokenDetails projects InputTokensDetailsResource.
+type InputTokenDetails struct {
+	CachedTokens int64 `json:"cached_tokens" binding:"required"`
+}
+
+// Item projects SessionTurnItemResource.
+type Item struct {
+	ID                string           `json:"id" binding:"required" extensions:"x-nullable"`
+	TurnID            string           `json:"turn_id" binding:"required"`
+	Type              string           `json:"type" binding:"required" enums:"message,reasoning,function_call,function_call_output,agent_message,mcp_call,web_search_call,command_execution,create_subagent_call,send_subagent_input_call,resume_subagent_call,wait_for_subagents_call,interrupt_subagent_call,close_subagent_call"`
+	Status            string           `json:"status" extensions:"x-nullable" enums:"in_progress,completed,incomplete,failed"`
+	Role              string           `json:"role,omitempty" enums:"user,assistant"`
+	Phase             string           `json:"phase,omitempty" extensions:"x-nullable" enums:"commentary,final_answer"`
+	Content           []ItemContent    `json:"content,omitempty"`
+	Command           string           `json:"command,omitempty"`
+	Cwd               *string          `json:"cwd,omitempty" extensions:"x-nullable"`
+	DurationMS        *int64           `json:"duration_ms,omitempty" extensions:"x-nullable"`
+	ExitCode          *int64           `json:"exit_code,omitempty" extensions:"x-nullable"`
+	Name              string           `json:"name,omitempty"`
+	CallID            string           `json:"call_id,omitempty"`
+	ServerLabel       string           `json:"server_label,omitempty"`
+	Arguments         any              `json:"arguments,omitempty"`
+	Output            any              `json:"output,omitempty" extensions:"x-nullable"`
+	Error             any              `json:"error,omitempty" extensions:"x-nullable"`
+	Action            *WebSearchAction `json:"action,omitempty" extensions:"x-nullable"`
+	AgentID           string           `json:"agent_id,omitempty"`
+	SenderAgentID     string           `json:"sender_agent_id,omitempty"`
+	RecipientAgentID  string           `json:"recipient_agent_id,omitempty"`
+	RecipientAgentIDs []string         `json:"recipient_agent_ids,omitempty"`
+	Model             *string          `json:"model,omitempty" extensions:"x-nullable"`
+	ReasoningEffort   *string          `json:"reasoning_effort,omitempty" extensions:"x-nullable"`
+	Summary           []SummaryText    `json:"summary,omitempty"`
+}
+
+// ItemContent projects MessageContentResource, EncryptedContentResource.
+type ItemContent struct {
+	Type             string  `json:"type" binding:"required" enums:"input_text,input_image,output_text,encrypted_content"`
+	Text             *string `json:"text,omitempty"`
+	ImageURL         string  `json:"image_url,omitempty"`
+	EncryptedContent *string `json:"encrypted_content,omitempty"`
+}
+
+// ItemList projects SessionItemListResource.
+type ItemList struct {
+	Object  string  `json:"object" binding:"required" enums:"list"`
+	FirstID *string `json:"first_id" binding:"required" extensions:"x-nullable"`
+	LastID  *string `json:"last_id" binding:"required" extensions:"x-nullable"`
+	Data    []Item  `json:"data" binding:"required"`
+	HasMore bool    `json:"has_more" binding:"required"`
+}
+
+// MCPHTTPTransport projects PersistedMcpTransportConfigParamHttp.
+type MCPHTTPTransport struct {
+	Type      string             `json:"type" binding:"required" enums:"http"`
+	ServerURL string             `json:"server_url" binding:"required"`
+	Headers   *map[string]string `json:"headers,omitempty" extensions:"x-nullable"`
+}
+
+// MCPTool projects AgentToolResourceMcp.
+type MCPTool struct {
+	Type             string                     `json:"type" binding:"required" enums:"mcp"`
+	ServerLabel      string                     `json:"server_label" binding:"required"`
+	Transport        MCPHTTPTransport           `json:"transport" binding:"required"`
+	AllowedTools     *[]string                  `json:"allowed_tools" binding:"required" extensions:"x-nullable"`
+	ConnectionOrigin string                     `json:"connection_origin" binding:"required" enums:"service,environment"`
+	CredentialID     *string                    `json:"credential_id" binding:"required" extensions:"x-nullable"`
+	RequestMetadata  map[string]json.RawMessage `json:"request_metadata" binding:"required" swaggertype:"object"`
+	Required         bool                       `json:"required" binding:"required"`
+}
+
+// MCPToolInput projects AgentToolConfigParamMcp.
+type MCPToolInput struct {
+	Type             string          `json:"type" binding:"required" enums:"mcp"`
+	ServerLabel      *string         `json:"server_label" binding:"required"`
+	Transport        json.RawMessage `json:"transport" binding:"required" swaggertype:"object"`
+	AllowedTools     json.RawMessage `json:"allowed_tools" extensions:"x-nullable" swaggertype:"object"`
+	ConnectionOrigin *string         `json:"connection_origin" extensions:"x-nullable" enums:"service,environment"`
+	CredentialID     *string         `json:"credential_id" extensions:"x-nullable"`
+	RequestMetadata  json.RawMessage `json:"request_metadata" extensions:"x-nullable" swaggertype:"object"`
+	Required         json.RawMessage `json:"required" swaggertype:"object"`
+}
+
+// MultiAgentConfig projects MultiAgentConfigResource.
+type MultiAgentConfig struct {
+	Enabled                bool `json:"enabled" binding:"required"`
+	MaxConcurrentSubagents *int `json:"max_concurrent_subagents" binding:"required" extensions:"x-nullable"`
+}
+
+// OAuthCredentialRefresh projects McpOauthRefreshResource.
+type OAuthCredentialRefresh struct {
+	ClientID          string            `json:"client_id" binding:"required"`
+	TokenEndpoint     string            `json:"token_endpoint" binding:"required"`
+	TokenEndpointAuth OAuthEndpointAuth `json:"token_endpoint_auth" binding:"required"`
+	Resource          *string           `json:"resource" binding:"required" extensions:"x-nullable"`
+	Scope             *string           `json:"scope" binding:"required" extensions:"x-nullable"`
+}
+
+// OAuthCredentialRefreshInput projects CreateMcpOauthRefreshParam.
+type OAuthCredentialRefreshInput struct {
+	ClientID          *string                 `json:"client_id" binding:"required"`
+	RefreshToken      *string                 `json:"refresh_token" binding:"required"`
+	TokenEndpoint     *string                 `json:"token_endpoint" binding:"required"`
+	TokenEndpointAuth *OAuthEndpointAuthInput `json:"token_endpoint_auth" binding:"required"`
+	Resource          *string                 `json:"resource,omitempty" extensions:"x-nullable"`
+	Scope             *string                 `json:"scope,omitempty" extensions:"x-nullable"`
+}
+
+// OAuthCredentialRefreshReplacement projects RotateMcpOauthRefreshParam.
+type OAuthCredentialRefreshReplacement struct {
+	RefreshToken      *string                       `json:"refresh_token,omitempty" extensions:"x-nullable"`
+	Scope             json.RawMessage               `json:"scope,omitempty" extensions:"x-nullable" swaggertype:"object"`
+	TokenEndpointAuth *OAuthEndpointAuthReplacement `json:"token_endpoint_auth,omitempty" extensions:"x-nullable"`
+}
+
+// OAuthEndpointAuth projects McpOauthTokenEndpointAuthResource.
+type OAuthEndpointAuth struct {
+	Type string `json:"type" binding:"required" enums:"none,client_secret_basic,client_secret_post"`
+}
+
+// OAuthEndpointAuthInput projects CreateMcpOauthTokenEndpointAuthParam.
+type OAuthEndpointAuthInput struct {
+	Type         string  `json:"type" binding:"required" enums:"none,client_secret_basic,client_secret_post"`
+	ClientSecret *string `json:"client_secret,omitempty"`
+}
+
+// OAuthEndpointAuthReplacement projects RotateMcpOauthTokenEndpointAuthParam.
+type OAuthEndpointAuthReplacement struct {
+	Type         string  `json:"type" binding:"required" enums:"client_secret_basic,client_secret_post"`
+	ClientSecret *string `json:"client_secret,omitempty" extensions:"x-nullable"`
+}
+
+// OutputTokenDetails projects OutputTokensDetailsResource.
+type OutputTokenDetails struct {
+	ReasoningTokens int64 `json:"reasoning_tokens" binding:"required"`
+}
+
+// Reasoning projects ReasoningParam.
+type Reasoning struct {
+	Effort  *string `json:"effort,omitempty" extensions:"x-nullable" enums:"none,minimal,low,medium,high,xhigh,max"`
+	Summary *string `json:"summary,omitempty" extensions:"x-nullable" enums:"concise,detailed,auto"`
+}
+
+// ReasoningItem projects ReasoningItemResource.
+type ReasoningItem struct {
+	ID      string        `json:"id" binding:"required"`
+	TurnID  string        `json:"turn_id" binding:"required"`
+	Type    string        `json:"type" binding:"required" enums:"reasoning"`
+	Status  *string       `json:"status" binding:"required" extensions:"x-nullable" enums:"in_progress,completed,incomplete"`
+	Summary []SummaryText `json:"summary" binding:"required"`
+}
+
+// RequiredAction projects SessionRequiredActionResource.
+type RequiredAction struct {
+	Type          string `json:"type" binding:"required" enums:"function_call,environment_connection"`
+	Arguments     any    `json:"arguments,omitempty"`
+	CallID        string `json:"call_id,omitempty"`
+	Name          string `json:"name,omitempty"`
+	TurnID        string `json:"turn_id,omitempty"`
+	EnvironmentID string `json:"environment_id,omitempty"`
+}
+
+// SavedAgent projects AgentResource.
+type SavedAgent struct {
+	SavedAgentConfiguration
+	ID        string            `json:"id" binding:"required"`
+	Object    string            `json:"object" binding:"required" enums:"agent"`
+	Metadata  map[string]string `json:"metadata" binding:"required"`
+	CreatedAt int64             `json:"created_at" binding:"required"`
+	UpdatedAt int64             `json:"updated_at" binding:"required"`
+}
+
+// SavedAgentConfiguration projects AgentResource.
+type SavedAgentConfiguration struct {
+	XAgentsCore  *SavedAgentCore   `json:"x_agents_core,omitempty"`
+	Model        string            `json:"model" binding:"required"`
+	Name         *string           `json:"name" binding:"required" extensions:"x-nullable"`
+	Instructions *string           `json:"instructions" binding:"required" extensions:"x-nullable"`
+	MultiAgent   MultiAgentConfig  `json:"multi_agent" binding:"required"`
+	Reasoning    Reasoning         `json:"reasoning" binding:"required"`
+	ServiceTier  string            `json:"service_tier" binding:"required" enums:"auto,default,flex,priority,fast"`
+	Text         TextConfig        `json:"text" binding:"required"`
+	Tools        []json.RawMessage `json:"tools" binding:"required" swaggertype:"array,object"`
+}
+
+// SavedAgentList projects AgentListResource.
+type SavedAgentList struct {
+	Object  string       `json:"object" binding:"required" enums:"list"`
+	Data    []SavedAgent `json:"data" binding:"required"`
+	HasMore bool         `json:"has_more" binding:"required"`
+	FirstID *string      `json:"first_id" binding:"required" extensions:"x-nullable"`
+	LastID  *string      `json:"last_id" binding:"required" extensions:"x-nullable"`
+}
+
+// SendSubagentInputCallItem projects SendSubagentInputCallItemResource.
+type SendSubagentInputCallItem struct {
+	ID               string         `json:"id" binding:"required"`
+	TurnID           string         `json:"turn_id" binding:"required"`
+	Type             string         `json:"type" binding:"required" enums:"send_subagent_input_call"`
+	Status           string         `json:"status" binding:"required" enums:"in_progress,completed,failed,incomplete"`
+	SenderAgentID    string         `json:"sender_agent_id" binding:"required"`
+	RecipientAgentID string         `json:"recipient_agent_id" binding:"required"`
+	Content          []AgentContent `json:"content" binding:"required"`
+}
+
+// Session projects SessionResource.
+type Session struct {
+	XAgentsCore     *SessionCore       `json:"x_agents_core,omitempty"`
+	ID              string             `json:"id" binding:"required"`
+	Agent           Agent              `json:"agent" binding:"required"`
+	CreatedAt       int64              `json:"created_at" binding:"required"`
+	Environment     SessionEnvironment `json:"environment" binding:"required"`
+	Error           *string            `json:"error" binding:"required" extensions:"x-nullable"`
+	LastActiveAt    int64              `json:"last_active_at" binding:"required"`
+	Metadata        map[string]string  `json:"metadata" binding:"required"`
+	Object          string             `json:"object" binding:"required" enums:"agent.session"`
+	RequiredActions []RequiredAction   `json:"required_actions" binding:"required"`
+	Status          string             `json:"status" binding:"required" enums:"idle,in_progress,requires_action,failed"`
+	Usage           *TokenUsage        `json:"usage" binding:"required" extensions:"x-nullable"`
+	VaultIDs        []string           `json:"vault_ids" binding:"required"`
+}
+
+// SessionArtifact projects SessionArtifactResource.
+type SessionArtifact struct {
+	ID            string `json:"id" binding:"required"`
+	CreatedAt     int64  `json:"created_at" binding:"required"`
+	EnvironmentID string `json:"environment_id" binding:"required"`
+	Object        string `json:"object" binding:"required" enums:"agent.session.artifact"`
+	Path          string `json:"path" binding:"required"`
+	SessionID     string `json:"session_id" binding:"required"`
+	SizeBytes     int64  `json:"size_bytes" binding:"required"`
+	TurnID        string `json:"turn_id" binding:"required"`
+}
+
+// SessionArtifactDeleted projects DeletedSessionArtifactResource.
+type SessionArtifactDeleted struct {
+	ID      string `json:"id" binding:"required"`
+	Object  string `json:"object" binding:"required" enums:"agent.session.artifact.deleted"`
+	Deleted bool   `json:"deleted" binding:"required"`
+}
+
+// SessionArtifactList projects SessionArtifactListResource.
+type SessionArtifactList struct {
+	Object  string            `json:"object" binding:"required" enums:"list"`
+	FirstID *string           `json:"first_id" binding:"required" extensions:"x-nullable"`
+	LastID  *string           `json:"last_id" binding:"required" extensions:"x-nullable"`
+	Data    []SessionArtifact `json:"data" binding:"required"`
+	HasMore bool              `json:"has_more" binding:"required"`
+}
+
+// SessionDeleted projects DeletedSessionResource.
+type SessionDeleted struct {
+	ID      string `json:"id" binding:"required"`
+	Deleted bool   `json:"deleted" binding:"required"`
+	Object  string `json:"object" binding:"required" enums:"agent.session.deleted"`
+}
+
+// SessionEnvironment projects EnvironmentResource.
+type SessionEnvironment struct {
+	Type                  string                       `json:"type" binding:"required" enums:"none,openai_hosted,self_hosted"`
+	ID                    string                       `json:"id,omitempty"`
+	CapabilityDirectories *[]string                    `json:"capability_directories,omitempty"`
+	RemoteURL             string                       `json:"remote_url,omitempty"`
+	WorkspaceDirectory    string                       `json:"workspace_directory,omitempty"`
+	Network               *EnvironmentNetwork          `json:"network,omitempty"`
+	Packages              *EnvironmentPackagesResponse `json:"packages,omitempty"`
+	Files                 *[]json.RawMessage           `json:"files,omitempty" swaggertype:"array,object"`
+	Plugins               *[]json.RawMessage           `json:"plugins,omitempty" swaggertype:"array,object"`
+	Skills                *[]json.RawMessage           `json:"skills,omitempty" swaggertype:"array,object"`
+}
+
+// SessionEnvironmentState projects SessionEnvironmentStateResource.
+type SessionEnvironmentState struct {
+	ID     string       `json:"id" binding:"required"`
+	Type   string       `json:"type" binding:"required"`
+	Status string       `json:"status" binding:"required" enums:"pending,ready,connected,disconnected,failed"`
+	Error  *StreamError `json:"error" binding:"required" extensions:"x-nullable"`
+}
+
+// SessionEvent projects SessionEvent.
+type SessionEvent struct {
+	Subagent     *Subagent                `json:"subagent,omitempty"`
+	Type         string                   `json:"type" binding:"required" enums:"error,agent.session.environment.ready,agent.output.command_execution_output.delta,agent.session.created,agent.session.turn.created,agent.session.turn.in_progress,agent.session.turn.completed,agent.session.turn.failed,agent.session.turn.cancelled,agent.session.turn.item.added,agent.session.idle,agent.session.in_progress,agent.session.requires_action,agent.session.failed,agent.session.environment.pending,agent.session.environment.connected,agent.session.environment.disconnected,agent.session.environment.failed,agent.session.subagent.created,agent.session.subagent.active,agent.session.subagent.closed,agent.session.turn.item.done,agent.session.turn.content_part.added,agent.session.turn.content_part.done,agent.session.turn.output_text.delta,agent.session.turn.output_text.done,agent.session.turn.reasoning_summary_part.added,agent.session.turn.reasoning_summary_part.done,agent.session.turn.reasoning_summary_text.delta,agent.session.turn.reasoning_summary_text.done"`
+	EventID      string                   `json:"event_id" binding:"required"`
+	SessionID    string                   `json:"session_id,omitempty"`
+	TurnID       string                   `json:"turn_id,omitempty" extensions:"x-nullable"`
+	Session      *Session                 `json:"session,omitempty"`
+	Turn         *Turn                    `json:"turn,omitempty"`
+	Item         *Item                    `json:"item,omitempty"`
+	ItemID       string                   `json:"item_id,omitempty"`
+	OutputIndex  *int32                   `json:"output_index,omitempty" extensions:"x-nullable"`
+	ContentIndex *int                     `json:"content_index,omitempty"`
+	Part         *ItemContent             `json:"part,omitempty"`
+	Delta        *string                  `json:"delta,omitempty"`
+	Text         *string                  `json:"text,omitempty"`
+	Error        *StreamError             `json:"error,omitempty"`
+	Environment  *SessionEnvironmentState `json:"environment,omitempty"`
+	Usage        *TokenUsage              `json:"usage,omitempty" extensions:"x-nullable"`
+	SummaryIndex *int64                   `json:"summary_index,omitempty"`
+	Status       *string                  `json:"status,omitempty" extensions:"x-nullable" enums:"incomplete"`
+}
+
+// SessionInput projects SessionInputParam.
+type SessionInput struct {
+	Type    string          `json:"type" binding:"required" enums:"agent.session.input.message,agent.session.input.cancel,agent.session.input.tool_result"`
+	Input   []InputMessage  `json:"input,omitempty"`
+	CallID  string          `json:"call_id,omitempty"`
+	TurnID  string          `json:"turn_id,omitempty"`
+	Success *bool           `json:"success,omitempty"`
+	Error   json.RawMessage `json:"error,omitempty" extensions:"x-nullable" swaggertype:"object"`
+	Output  any             `json:"output,omitempty" extensions:"x-nullable"`
+}
+
+// SessionList projects SessionListResource.
+type SessionList struct {
+	Object  string    `json:"object" binding:"required" enums:"list"`
+	FirstID *string   `json:"first_id" binding:"required" extensions:"x-nullable"`
+	LastID  *string   `json:"last_id" binding:"required" extensions:"x-nullable"`
+	Data    []Session `json:"data" binding:"required"`
+	HasMore bool      `json:"has_more" binding:"required"`
+}
+
+// Skill projects SkillResource.
+type Skill struct {
+	ID             string `json:"id" binding:"required"`
+	Object         string `json:"object" binding:"required" enums:"skill"`
+	CreatedAt      int64  `json:"created_at" binding:"required"`
+	Name           string `json:"name" binding:"required"`
+	Description    string `json:"description" binding:"required"`
+	DefaultVersion string `json:"default_version" binding:"required"`
+	LatestVersion  string `json:"latest_version" binding:"required"`
+}
+
+// SkillDeleted projects DeletedSkillResource.
+type SkillDeleted struct {
+	ID      string `json:"id" binding:"required"`
+	Object  string `json:"object" binding:"required" enums:"skill.deleted"`
+	Deleted bool   `json:"deleted" binding:"required"`
+}
+
+// SkillList projects SkillListResource.
+type SkillList struct {
+	Object  string  `json:"object" binding:"required" enums:"list"`
+	Data    []Skill `json:"data" binding:"required"`
+	FirstID *string `json:"first_id" binding:"required" extensions:"x-nullable"`
+	LastID  *string `json:"last_id" binding:"required" extensions:"x-nullable"`
+	HasMore bool    `json:"has_more" binding:"required"`
+}
+
+// SkillUpdateRequest projects SetDefaultSkillVersionBody.
+type SkillUpdateRequest struct {
+	DefaultVersion string `json:"default_version" binding:"required"`
+}
+
+// SkillVersion projects SkillVersionResource.
+type SkillVersion struct {
+	ID          string `json:"id" binding:"required"`
+	Object      string `json:"object" binding:"required" enums:"skill.version"`
+	CreatedAt   int64  `json:"created_at" binding:"required"`
+	SkillID     string `json:"skill_id" binding:"required"`
+	Version     string `json:"version" binding:"required"`
+	Name        string `json:"name" binding:"required"`
+	Description string `json:"description" binding:"required"`
+}
+
+// SkillVersionDeleted projects DeletedSkillVersionResource.
+type SkillVersionDeleted struct {
+	ID      string `json:"id" binding:"required"`
+	Object  string `json:"object" binding:"required" enums:"skill.version.deleted"`
+	Version string `json:"version" binding:"required"`
+	Deleted bool   `json:"deleted" binding:"required"`
+}
+
+// SkillVersionList projects SkillVersionListResource.
+type SkillVersionList struct {
+	Object  string         `json:"object" binding:"required" enums:"list"`
+	Data    []SkillVersion `json:"data" binding:"required"`
+	FirstID *string        `json:"first_id" binding:"required" extensions:"x-nullable"`
+	LastID  *string        `json:"last_id" binding:"required" extensions:"x-nullable"`
+	HasMore bool           `json:"has_more" binding:"required"`
+}
+
+// SourceFile projects OpenAIFile.
+type SourceFile struct {
+	ID            string  `json:"id" binding:"required"`
+	Object        string  `json:"object" binding:"required" enums:"file"`
+	Bytes         int64   `json:"bytes" binding:"required"`
+	CreatedAt     int64   `json:"created_at" binding:"required"`
+	Filename      string  `json:"filename" binding:"required"`
+	Purpose       string  `json:"purpose" binding:"required" enums:"assistants,assistants_output,batch,batch_output,fine-tune,fine-tune-results,vision,user_data"`
+	Status        string  `json:"status" binding:"required" enums:"uploaded,processed,error"`
+	ExpiresAt     *int64  `json:"expires_at"`
+	StatusDetails *string `json:"status_details"`
+}
+
+// SourceFileDeleted projects DeleteFileResponse.
+type SourceFileDeleted struct {
+	ID      string `json:"id" binding:"required"`
+	Object  string `json:"object" binding:"required" enums:"file"`
+	Deleted bool   `json:"deleted" binding:"required"`
+}
+
+// SourceFileList projects ListFilesResponse.
+type SourceFileList struct {
+	Object  string       `json:"object" binding:"required"`
+	Data    []SourceFile `json:"data" binding:"required"`
+	HasMore bool         `json:"has_more" binding:"required"`
+	FirstID *string      `json:"first_id" binding:"required"`
+	LastID  *string      `json:"last_id" binding:"required"`
+}
+
+// StreamError projects SessionErrorResource.
+type StreamError struct {
+	Code    string  `json:"code" binding:"required" extensions:"x-nullable"`
+	Type    string  `json:"type" binding:"required"`
+	Message string  `json:"message" binding:"required"`
+	Param   *string `json:"param,omitempty" binding:"required" extensions:"x-nullable"`
+}
+
+// Subagent projects SubagentResource.
+type Subagent struct {
+	ID            string         `json:"id" binding:"required"`
+	Object        string         `json:"object" binding:"required" enums:"agent.session.subagent"`
+	SessionID     string         `json:"session_id" binding:"required"`
+	ParentAgentID string         `json:"parent_agent_id" binding:"required"`
+	OpenedAt      int64          `json:"opened_at" binding:"required"`
+	ClosedAt      *int64         `json:"closed_at" binding:"required" extensions:"x-nullable"`
+	Name          *string        `json:"name" binding:"required" extensions:"x-nullable"`
+	Instructions  []AgentContent `json:"instructions" binding:"required" extensions:"x-nullable"`
+	Status        string         `json:"status" binding:"required" enums:"active,closed"`
+}
+
+// SubagentControlCallItem projects ResumeSubagentCallItemResource, InterruptSubagentCallItemResource, CloseSubagentCallItemResource.
+type SubagentControlCallItem struct {
+	ID               string `json:"id" binding:"required"`
+	TurnID           string `json:"turn_id" binding:"required"`
+	Type             string `json:"type" binding:"required" enums:"resume_subagent_call,interrupt_subagent_call,close_subagent_call"`
+	Status           string `json:"status" binding:"required" enums:"in_progress,completed,failed,incomplete"`
+	SenderAgentID    string `json:"sender_agent_id" binding:"required"`
+	RecipientAgentID string `json:"recipient_agent_id" binding:"required"`
+}
+
+// SubagentList projects schema.
+type SubagentList struct {
+	Object  string     `json:"object" binding:"required" enums:"list"`
+	FirstID *string    `json:"first_id" binding:"required" extensions:"x-nullable"`
+	LastID  *string    `json:"last_id" binding:"required" extensions:"x-nullable"`
+	Data    []Subagent `json:"data" binding:"required"`
+	HasMore bool       `json:"has_more" binding:"required"`
+}
+
+// SummaryText projects SummaryTextResource.
+type SummaryText struct {
+	Type string `json:"type" binding:"required" enums:"summary_text"`
+	Text string `json:"text" binding:"required"`
+}
+
+// TextConfig projects TextResource.
+type TextConfig struct {
+	Format    TextFormat `json:"format" binding:"required"`
+	Verbosity string     `json:"verbosity" binding:"required" enums:"low,medium,high"`
+}
+
+// TextConfigInput projects TextParam.
+type TextConfigInput struct {
+	Format    json.RawMessage `json:"format,omitempty" extensions:"x-nullable" swaggertype:"object"`
+	Verbosity *string         `json:"verbosity,omitempty" extensions:"x-nullable" enums:"low,medium,high"`
+}
+
+// TextFormat projects TextFormatResource.
+type TextFormat struct {
+	Type   string          `json:"type" binding:"required" enums:"text,json_schema"`
+	Schema json.RawMessage `json:"schema,omitempty" swaggertype:"object"`
+}
+
+// TokenUsage projects TokenUsageResource.
+type TokenUsage struct {
+	InputTokens         int64              `json:"input_tokens" binding:"required"`
+	InputTokensDetails  InputTokenDetails  `json:"input_tokens_details" binding:"required"`
+	OutputTokens        int64              `json:"output_tokens" binding:"required"`
+	OutputTokensDetails OutputTokenDetails `json:"output_tokens_details" binding:"required"`
+	TotalTokens         int64              `json:"total_tokens" binding:"required"`
+}
+
+// Turn projects TurnResource.
+type Turn struct {
+	ID          string      `json:"id" binding:"required"`
+	AgentID     string      `json:"agent_id" binding:"required"`
+	SubagentID  *string     `json:"subagent_id" binding:"required" extensions:"x-nullable"`
+	SessionID   string      `json:"session_id" binding:"required"`
+	Object      string      `json:"object" binding:"required" enums:"agent.session.turn"`
+	Status      string      `json:"status" binding:"required" enums:"queued,in_progress,waiting,completed,failed,cancelled"`
+	CreatedAt   int64       `json:"created_at" binding:"required"`
+	StartedAt   *int64      `json:"started_at" binding:"required" extensions:"x-nullable"`
+	CompletedAt *int64      `json:"completed_at" binding:"required" extensions:"x-nullable"`
+	Error       *TurnError  `json:"error" binding:"required" extensions:"x-nullable"`
+	Usage       *TokenUsage `json:"usage" binding:"required" extensions:"x-nullable"`
+}
+
+// TurnError projects SessionTurnErrorResource.
+type TurnError struct {
+	Code    string `json:"code" binding:"required" enums:"context_length_exceeded,session_budget_exceeded,usage_limit_exceeded,rate_limit_exceeded,server_overloaded,cyber_policy,connection_failed,server_error,authentication_error,invalid_request,resource_not_found,sandbox_error,executor_version_incompatible,active_turn_not_steerable,request_timeout,internal_error"`
+	Message string `json:"message" binding:"required"`
+}
+
+// TurnList projects SessionTurnListResource.
+type TurnList struct {
+	Object  string  `json:"object" binding:"required" enums:"list"`
+	FirstID *string `json:"first_id" binding:"required" extensions:"x-nullable"`
+	LastID  *string `json:"last_id" binding:"required" extensions:"x-nullable"`
+	Data    []Turn  `json:"data" binding:"required"`
+	HasMore bool    `json:"has_more" binding:"required"`
+}
+
+// UpdateAgentRequest projects UpdateAgentParams.
+type UpdateAgentRequest struct {
+	XAgentsCore  *SavedAgentCoreInput `json:"x_agents_core,omitempty"`
+	Model        *string              `json:"model,omitempty"`
+	Name         *string              `json:"name,omitempty" extensions:"x-nullable"`
+	Instructions *string              `json:"instructions,omitempty" extensions:"x-nullable"`
+	Metadata     map[string]*string   `json:"metadata,omitempty" extensions:"x-nullable"`
+	MultiAgent   json.RawMessage      `json:"multi_agent,omitempty" extensions:"x-nullable" swaggertype:"object"`
+	Reasoning    *Reasoning           `json:"reasoning,omitempty" extensions:"x-nullable"`
+	ServiceTier  *string              `json:"service_tier,omitempty" extensions:"x-nullable" enums:"auto,default,flex,priority,fast"`
+	Text         *TextConfigInput     `json:"text,omitempty" extensions:"x-nullable"`
+	Tools        []json.RawMessage    `json:"tools,omitempty" extensions:"x-nullable" swaggertype:"array,object"`
+}
+
+// Vault projects VaultResource.
+type Vault struct {
+	ID        string            `json:"id" binding:"required"`
+	Object    string            `json:"object" binding:"required" enums:"vault"`
+	CreatedAt int64             `json:"created_at" binding:"required"`
+	Name      *string           `json:"name" binding:"required" extensions:"x-nullable"`
+	Metadata  map[string]string `json:"metadata" binding:"required"`
+}
+
+// VaultDeleted projects DeletedVaultResource.
+type VaultDeleted struct {
+	ID      string `json:"id" binding:"required"`
+	Deleted bool   `json:"deleted" binding:"required"`
+	Object  string `json:"object" binding:"required" enums:"vault.deleted"`
+}
+
+// VaultList projects VaultListResource.
+type VaultList struct {
+	Object  string  `json:"object" binding:"required" enums:"list"`
+	Data    []Vault `json:"data" binding:"required"`
+	HasMore bool    `json:"has_more" binding:"required"`
+	FirstID *string `json:"first_id" binding:"required" extensions:"x-nullable"`
+	LastID  *string `json:"last_id" binding:"required" extensions:"x-nullable"`
+}
+
+// WaitForSubagentsCallItem projects WaitForSubagentsCallItemResource.
+type WaitForSubagentsCallItem struct {
+	ID                string   `json:"id" binding:"required"`
+	TurnID            string   `json:"turn_id" binding:"required"`
+	Type              string   `json:"type" binding:"required" enums:"wait_for_subagents_call"`
+	Status            string   `json:"status" binding:"required" enums:"in_progress,completed,failed,incomplete"`
+	SenderAgentID     string   `json:"sender_agent_id" binding:"required"`
+	RecipientAgentIDs []string `json:"recipient_agent_ids" binding:"required"`
+}
+
+// WebSearchAction projects WebSearchActionResource.
+type WebSearchAction struct {
+	Type    string   `json:"type" binding:"required" enums:"search,open_page,find_in_page,other"`
+	Query   *string  `json:"query,omitempty" extensions:"x-nullable"`
+	Queries []string `json:"queries,omitempty" extensions:"x-nullable"`
+	URL     *string  `json:"url,omitempty" extensions:"x-nullable"`
+	Pattern *string  `json:"pattern,omitempty" extensions:"x-nullable"`
+}
+
+func (value WebSearchAction) MarshalJSON() ([]byte, error) {
+	switch value.Type {
+	case "search":
+		return json.Marshal(struct {
+			Type    string   `json:"type"`
+			Query   *string  `json:"query"`
+			Queries []string `json:"queries"`
+		}{
+			Type:    value.Type,
+			Query:   value.Query,
+			Queries: value.Queries,
+		})
+	case "open_page":
+		return json.Marshal(struct {
+			Type string  `json:"type"`
+			URL  *string `json:"url"`
+		}{
+			Type: value.Type,
+			URL:  value.URL,
+		})
+	case "find_in_page":
+		return json.Marshal(struct {
+			Type    string  `json:"type"`
+			URL     *string `json:"url"`
+			Pattern *string `json:"pattern"`
+		}{
+			Type:    value.Type,
+			URL:     value.URL,
+			Pattern: value.Pattern,
+		})
+	case "other":
+		return json.Marshal(struct {
+			Type string `json:"type"`
+		}{
+			Type: value.Type,
+		})
+	default:
+		return nil, fmt.Errorf("invalid WebSearchAction type %q", value.Type)
+	}
+}
+
+// reasoningResponse projects ReasoningResource.
+type reasoningResponse struct {
+	Effort  *string `json:"effort" binding:"required" extensions:"x-nullable" enums:"none,minimal,low,medium,high,xhigh,max"`
+	Summary *string `json:"summary" binding:"required" extensions:"x-nullable" enums:"concise,detailed,auto"`
+}
+
+// sessionError projects SessionErrorResource.
+type sessionError struct {
+	Code    string  `json:"code" binding:"required" extensions:"x-nullable"`
+	Type    string  `json:"type" binding:"required"`
+	Message string  `json:"message" binding:"required"`
+	Param   *string `json:"param" binding:"required" extensions:"x-nullable"`
+}
diff --git a/contracts/agents-api/v1/required_actions.go b/contracts/agents-api/v1/required_actions.go
index 1567b1a05..f6bcb18b3 100644
--- a/contracts/agents-api/v1/required_actions.go
+++ b/contracts/agents-api/v1/required_actions.go
@@ -6,21 +6,6 @@ import (
 	"errors"
 )
 
-// RequiredAction contains the supported variants of the Session action union.
-type RequiredAction struct {
-	Type          string `json:"type" enums:"function_call,environment_connection" binding:"required"`
-	Arguments     any    `json:"arguments,omitempty"`
-	CallID        string `json:"call_id,omitempty"`
-	Name          string `json:"name,omitempty"`
-	TurnID        string `json:"turn_id,omitempty"`
-	EnvironmentID string `json:"environment_id,omitempty"`
-}
-
-type EnvironmentConnectionAction struct {
-	EnvironmentID string `json:"environment_id" binding:"required"`
-	Type          string `json:"type" enums:"environment_connection" binding:"required"`
-}
-
 // MarshalJSON preserves required null function arguments without exposing function fields on connection actions.
 func (a RequiredAction) MarshalJSON() ([]byte, error) {
 	switch a.Type {
diff --git a/contracts/agents-api/v1/session_artifacts.go b/contracts/agents-api/v1/session_artifacts.go
deleted file mode 100644
index 77f68951d..000000000
--- a/contracts/agents-api/v1/session_artifacts.go
+++ /dev/null
@@ -1,26 +0,0 @@
-package v1
-
-type SessionArtifact struct {
-	ID            string `json:"id" binding:"required"`
-	CreatedAt     int64  `json:"created_at" binding:"required"`
-	EnvironmentID string `json:"environment_id" binding:"required"`
-	Object        string `json:"object" enums:"agent.session.artifact" binding:"required"`
-	Path          string `json:"path" binding:"required"`
-	SessionID     string `json:"session_id" binding:"required"`
-	SizeBytes     int64  `json:"size_bytes" binding:"required"`
-	TurnID        string `json:"turn_id" binding:"required"`
-}
-
-type SessionArtifactList struct {
-	Object  string            `json:"object" enums:"list" binding:"required"`
-	FirstID *string           `json:"first_id" extensions:"x-nullable"`
-	LastID  *string           `json:"last_id" extensions:"x-nullable"`
-	Data    []SessionArtifact `json:"data" binding:"required"`
-	HasMore bool              `json:"has_more" binding:"required"`
-}
-
-type SessionArtifactDeleted struct {
-	ID      string `json:"id" binding:"required"`
-	Object  string `json:"object" enums:"agent.session.artifact.deleted" binding:"required"`
-	Deleted bool   `json:"deleted" binding:"required"`
-}
diff --git a/contracts/agents-api/v1/session_deletion.go b/contracts/agents-api/v1/session_deletion.go
deleted file mode 100644
index f95bacc98..000000000
--- a/contracts/agents-api/v1/session_deletion.go
+++ /dev/null
@@ -1,7 +0,0 @@
-package v1
-
-type SessionDeleted struct {
-	ID      string `json:"id" binding:"required"`
-	Deleted bool   `json:"deleted" binding:"required"`
-	Object  string `json:"object" enums:"agent.session.deleted" binding:"required"`
-}
diff --git a/contracts/agents-api/v1/session_environment.go b/contracts/agents-api/v1/session_environment.go
deleted file mode 100644
index be8117520..000000000
--- a/contracts/agents-api/v1/session_environment.go
+++ /dev/null
@@ -1,17 +0,0 @@
-package v1
-
-import "encoding/json"
-
-// SessionEnvironment contains supported output variants, independently of request admission.
-type SessionEnvironment struct {
-	Type                  string                       `json:"type" enums:"none,self_hosted,openai_hosted" binding:"required"`
-	ID                    string                       `json:"id,omitempty"`
-	CapabilityDirectories *[]string                    `json:"capability_directories,omitempty"`
-	RemoteURL             string                       `json:"remote_url,omitempty"`
-	WorkspaceDirectory    string                       `json:"workspace_directory,omitempty"`
-	Network               *EnvironmentNetwork          `json:"network,omitempty"`
-	Packages              *EnvironmentPackagesResponse `json:"packages,omitempty"`
-	Files                 *[]json.RawMessage           `json:"files,omitempty" swaggertype:"array,object"`
-	Plugins               *[]json.RawMessage           `json:"plugins,omitempty" swaggertype:"array,object"`
-	Skills                *[]json.RawMessage           `json:"skills,omitempty" swaggertype:"array,object"`
-}
diff --git a/contracts/agents-api/v1/sessions.go b/contracts/agents-api/v1/sessions.go
index ac2400877..e165327d8 100644
--- a/contracts/agents-api/v1/sessions.go
+++ b/contracts/agents-api/v1/sessions.go
@@ -3,117 +3,6 @@ package v1
 
 import "encoding/json"
 
-// CreateSessionRequest supports inline configuration or a saved Agent reference.
-// Initial text input is accepted with ordinary or streaming responses.
-type CreateSessionRequest struct {
-	XAgentsCore *SessionExecutionInput `json:"x_agents_core,omitempty"`
-	Agent       *InlineAgent           `json:"agent,omitempty"`
-	AgentID     *string                `json:"agent_id,omitempty"`
-	Environment *Environment           `json:"environment" binding:"required"`
-	// Input accepts a string or an ordered array of user InputMessage objects.
-	// Required for none and streamed creation outside self_hosted; otherwise optional.
-	Input    any               `json:"input,omitempty" extensions:"x-nullable"`
-	Metadata map[string]string `json:"metadata,omitempty" extensions:"x-nullable"`
-	Stream   bool              `json:"stream,omitempty" default:"false"`
-	VaultIDs []string          `json:"vault_ids,omitempty"`
-}
-
-// UpdateSessionRequest requires metadata; null and an empty object clear it.
-type UpdateSessionRequest struct {
-	Metadata map[string]string `json:"metadata" extensions:"x-nullable" binding:"required"`
-}
-
-// InlineAgent supplies a complete inline configuration or per-Session overrides.
-// With agent_id, omitted fields inherit and supplied fields replace saved values.
-type InlineAgent struct {
-	XAgentsCore  *AgentsCore          `json:"x_agents_core,omitempty" extensions:"x-nullable"`
-	Model        *string              `json:"model,omitempty"`
-	Instructions *string              `json:"instructions,omitempty" extensions:"x-nullable"`
-	MultiAgent   json.RawMessage      `json:"multi_agent,omitempty" swaggertype:"object" extensions:"x-nullable"`
-	Reasoning    *Reasoning           `json:"reasoning,omitempty" extensions:"x-nullable"`
-	ServiceTier  *string              `json:"service_tier,omitempty" enums:"auto,default,flex,priority,fast" extensions:"x-nullable"`
-	Text         *SavedAgentTextInput `json:"text,omitempty" extensions:"x-nullable"`
-	Tools        []json.RawMessage    `json:"tools,omitempty" swaggertype:"array,object" extensions:"x-nullable"`
-}
-
-// Environment contains supported request variants; self-hosted creation requires a workspace directory.
-type Environment struct {
-	Plugins               []json.RawMessage        `json:"plugins,omitempty" swaggertype:"array,object" extensions:"x-nullable"`
-	Skills                []json.RawMessage        `json:"skills,omitempty" swaggertype:"array,object" extensions:"x-nullable"`
-	Env                   map[string]string        `json:"env,omitempty" extensions:"x-nullable"`
-	SetupCommands         []json.RawMessage        `json:"setup_commands,omitempty" extensions:"x-nullable" swaggertype:"array,object"`
-	Packages              *EnvironmentPackages     `json:"packages,omitempty" extensions:"x-nullable"`
-	Files                 []json.RawMessage        `json:"files,omitempty" swaggertype:"array,object" extensions:"x-nullable"`
-	EnvironmentTemplateID string                   `json:"environment_template_id,omitempty"`
-	Type                  string                   `json:"type" enums:"none,self_hosted,openai_hosted" binding:"required"`
-	WorkspaceDirectory    string                   `json:"workspace_directory,omitempty"`
-	CapabilityDirectories []string                 `json:"capability_directories,omitempty" extensions:"x-nullable"`
-	Network               *EnvironmentNetworkInput `json:"network,omitempty" extensions:"x-nullable"`
-}
-
-type Agent struct {
-	XAgentsCore  *AgentsCore       `json:"x_agents_core,omitempty" extensions:"x-nullable"`
-	ID           string            `json:"id" binding:"required"`
-	Instructions *string           `json:"instructions" extensions:"x-nullable"`
-	Model        string            `json:"model" binding:"required"`
-	MultiAgent   MultiAgentConfig  `json:"multi_agent" binding:"required"`
-	Name         *string           `json:"name" extensions:"x-nullable"`
-	Reasoning    Reasoning         `json:"reasoning" binding:"required"`
-	ServiceTier  string            `json:"service_tier" enums:"auto" binding:"required"`
-	Text         TextConfig        `json:"text" binding:"required"`
-	Tools        []json.RawMessage `json:"tools" swaggertype:"array,object" binding:"required"`
-}
-
-type MultiAgentConfig struct {
-	Enabled                bool `json:"enabled" binding:"required"`
-	MaxConcurrentSubagents *int `json:"max_concurrent_subagents" extensions:"x-nullable"`
-}
-
-type Reasoning struct {
-	Effort  *string `json:"effort,omitempty" extensions:"x-nullable"`
-	Summary *string `json:"summary,omitempty" extensions:"x-nullable"`
-}
-
-// reasoningResponse renders both reasoning keys, null when unset, as pinned
-// Agent and Session responses do (SES-23, VA-11). Requests and stored
-// configuration keep the omitting Reasoning encoding. It does not resolve a
-// model-derived default effort.
-type reasoningResponse struct {
-	Effort  *string `json:"effort"`
-	Summary *string `json:"summary"`
-}
-
-type TextConfigInput struct {
-	Format    *TextFormat `json:"format,omitempty" extensions:"x-nullable"`
-	Verbosity *string     `json:"verbosity,omitempty" enums:"low,medium,high" extensions:"x-nullable"`
-}
-
-type TextConfig struct {
-	Format    TextFormat `json:"format" binding:"required"`
-	Verbosity string     `json:"verbosity" enums:"low,medium,high" binding:"required"`
-}
-
-type TextFormat struct {
-	Type   string          `json:"type" enums:"text,json_schema" binding:"required"`
-	Schema json.RawMessage `json:"schema,omitempty" swaggertype:"object"`
-}
-
-type Session struct {
-	XAgentsCore     *SessionCore       `json:"x_agents_core,omitempty"`
-	ID              string             `json:"id" binding:"required"`
-	Agent           Agent              `json:"agent" binding:"required"`
-	CreatedAt       int64              `json:"created_at" binding:"required"`
-	Environment     SessionEnvironment `json:"environment" binding:"required"`
-	Error           *string            `json:"error" extensions:"x-nullable"`
-	LastActiveAt    int64              `json:"last_active_at" binding:"required"`
-	Metadata        map[string]string  `json:"metadata" binding:"required"`
-	Object          string             `json:"object" enums:"agent.session" binding:"required"`
-	RequiredActions []RequiredAction   `json:"required_actions" binding:"required"`
-	Status          string             `json:"status" enums:"idle,in_progress,requires_action,failed" binding:"required"`
-	Usage           *TokenUsage        `json:"usage" extensions:"x-nullable"`
-	VaultIDs        []string           `json:"vault_ids" binding:"required"`
-}
-
 type agentWire Agent
 
 // agentResponse renders a Session Agent with explicit reasoning keys.
@@ -131,22 +20,3 @@ func (s Session) MarshalJSON() ([]byte, error) {
 		Agent agentResponse `json:"agent"`
 	}{wire(s), agentResponse{agentWire(s.Agent), reasoningResponse(s.Agent.Reasoning)}})
 }
-
-type SessionList struct {
-	Object  string    `json:"object" enums:"list" binding:"required"`
-	FirstID *string   `json:"first_id" extensions:"x-nullable"`
-	LastID  *string   `json:"last_id" extensions:"x-nullable"`
-	Data    []Session `json:"data" binding:"required"`
-	HasMore bool      `json:"has_more" binding:"required"`
-}
-
-type ErrorResponse struct {
-	Error APIError `json:"error" binding:"required"`
-}
-
-type APIError struct {
-	Message string  `json:"message" binding:"required"`
-	Type    string  `json:"type" binding:"required"`
-	Code    *string `json:"code" extensions:"x-nullable"`
-	Param   *string `json:"param" extensions:"x-nullable"`
-}
diff --git a/contracts/agents-api/v1/skills.go b/contracts/agents-api/v1/skills.go
deleted file mode 100644
index 4820024e7..000000000
--- a/contracts/agents-api/v1/skills.go
+++ /dev/null
@@ -1,55 +0,0 @@
-package v1
-
-// Skill describes a tenant-owned, versioned bundle without exposing its contents.
-type Skill struct {
-	ID             string `json:"id" binding:"required"`
-	Object         string `json:"object" binding:"required" enums:"skill"`
-	CreatedAt      int64  `json:"created_at" binding:"required"`
-	Name           string `json:"name" binding:"required"`
-	Description    string `json:"description" binding:"required"`
-	DefaultVersion string `json:"default_version" binding:"required"`
-	LatestVersion  string `json:"latest_version" binding:"required"`
-}
-
-type SkillVersion struct {
-	ID          string `json:"id" binding:"required"`
-	Object      string `json:"object" binding:"required" enums:"skill.version"`
-	CreatedAt   int64  `json:"created_at" binding:"required"`
-	SkillID     string `json:"skill_id" binding:"required"`
-	Version     string `json:"version" binding:"required"`
-	Name        string `json:"name" binding:"required"`
-	Description string `json:"description" binding:"required"`
-}
-
-type SkillList struct {
-	Object  string  `json:"object" binding:"required" enums:"list"`
-	Data    []Skill `json:"data" binding:"required"`
-	FirstID *string `json:"first_id" extensions:"x-nullable"`
-	LastID  *string `json:"last_id" extensions:"x-nullable"`
-	HasMore bool    `json:"has_more" binding:"required"`
-}
-
-type SkillVersionList struct {
-	Object  string         `json:"object" binding:"required" enums:"list"`
-	Data    []SkillVersion `json:"data" binding:"required"`
-	FirstID *string        `json:"first_id" extensions:"x-nullable"`
-	LastID  *string        `json:"last_id" extensions:"x-nullable"`
-	HasMore bool           `json:"has_more" binding:"required"`
-}
-
-type SkillDeleted struct {
-	ID      string `json:"id" binding:"required"`
-	Object  string `json:"object" binding:"required" enums:"skill.deleted"`
-	Deleted bool   `json:"deleted" binding:"required"`
-}
-
-type SkillVersionDeleted struct {
-	ID      string `json:"id" binding:"required"`
-	Object  string `json:"object" binding:"required" enums:"skill.version.deleted"`
-	Version string `json:"version" binding:"required"`
-	Deleted bool   `json:"deleted" binding:"required"`
-}
-
-type SkillUpdateRequest struct {
-	DefaultVersion string `json:"default_version" binding:"required"`
-}
diff --git a/contracts/agents-api/v1/source_files.go b/contracts/agents-api/v1/source_files.go
deleted file mode 100644
index 09fcc9ac3..000000000
--- a/contracts/agents-api/v1/source_files.go
+++ /dev/null
@@ -1,27 +0,0 @@
-package v1
-
-type SourceFile struct {
-	ID            string  `json:"id" binding:"required"`
-	Object        string  `json:"object" binding:"required" enums:"file"`
-	Bytes         int64   `json:"bytes" binding:"required" minimum:"0"`
-	CreatedAt     int64   `json:"created_at" binding:"required"`
-	Filename      string  `json:"filename" binding:"required"`
-	Purpose       string  `json:"purpose" binding:"required" enums:"user_data"`
-	Status        string  `json:"status" binding:"required" enums:"processed"`
-	ExpiresAt     *int64  `json:"expires_at" extensions:"x-nullable"`
-	StatusDetails *string `json:"status_details" extensions:"x-nullable"`
-}
-
-type SourceFileList struct {
-	Object  string       `json:"object" binding:"required" enums:"list"`
-	Data    []SourceFile `json:"data" binding:"required"`
-	HasMore bool         `json:"has_more" binding:"required"`
-	FirstID *string      `json:"first_id" extensions:"x-nullable"`
-	LastID  *string      `json:"last_id" extensions:"x-nullable"`
-}
-
-type SourceFileDeleted struct {
-	ID      string `json:"id" binding:"required"`
-	Object  string `json:"object" binding:"required" enums:"file"`
-	Deleted bool   `json:"deleted" binding:"required"`
-}
diff --git a/contracts/agents-api/v1/subagent_items.go b/contracts/agents-api/v1/subagent_items.go
index 82a40d6a9..b9c4a1533 100644
--- a/contracts/agents-api/v1/subagent_items.go
+++ b/contracts/agents-api/v1/subagent_items.go
@@ -5,71 +5,9 @@ import (
 	"errors"
 )
 
-type CreateSubagentCallItem struct {
-	ID              string         `json:"id" binding:"required"`
-	TurnID          string         `json:"turn_id" binding:"required"`
-	Type            string         `json:"type" binding:"required" enums:"create_subagent_call"`
-	Status          string         `json:"status" binding:"required" enums:"in_progress,completed,failed,incomplete"`
-	AgentID         string         `json:"agent_id" binding:"required"`
-	Content         []AgentContent `json:"content" binding:"required"`
-	Model           *string        `json:"model" extensions:"x-nullable"`
-	ReasoningEffort *string        `json:"reasoning_effort" extensions:"x-nullable"`
-}
-
-type SendSubagentInputCallItem struct {
-	ID               string         `json:"id" binding:"required"`
-	TurnID           string         `json:"turn_id" binding:"required"`
-	Type             string         `json:"type" binding:"required" enums:"send_subagent_input_call"`
-	Status           string         `json:"status" binding:"required" enums:"in_progress,completed,failed,incomplete"`
-	SenderAgentID    string         `json:"sender_agent_id" binding:"required"`
-	RecipientAgentID string         `json:"recipient_agent_id" binding:"required"`
-	Content          []AgentContent `json:"content" binding:"required"`
-}
-
-// SubagentControlCallItem is the common wire shape of resume, interrupt and close calls.
-type SubagentControlCallItem struct {
-	ID               string `json:"id" binding:"required"`
-	TurnID           string `json:"turn_id" binding:"required"`
-	Type             string `json:"type" binding:"required" enums:"resume_subagent_call,interrupt_subagent_call,close_subagent_call"`
-	Status           string `json:"status" binding:"required" enums:"in_progress,completed,failed,incomplete"`
-	SenderAgentID    string `json:"sender_agent_id" binding:"required"`
-	RecipientAgentID string `json:"recipient_agent_id" binding:"required"`
-}
-
-type WaitForSubagentsCallItem struct {
-	ID                string   `json:"id" binding:"required"`
-	TurnID            string   `json:"turn_id" binding:"required"`
-	Type              string   `json:"type" binding:"required" enums:"wait_for_subagents_call"`
-	Status            string   `json:"status" binding:"required" enums:"in_progress,completed,failed,incomplete"`
-	SenderAgentID     string   `json:"sender_agent_id" binding:"required"`
-	RecipientAgentIDs []string `json:"recipient_agent_ids" binding:"required"`
-}
-
-type AgentMessageItem struct {
-	ID               string         `json:"id" binding:"required"`
-	TurnID           string         `json:"turn_id" binding:"required"`
-	Type             string         `json:"type" binding:"required" enums:"agent_message"`
-	SenderAgentID    string         `json:"sender_agent_id" binding:"required"`
-	RecipientAgentID string         `json:"recipient_agent_id" binding:"required"`
-	Content          []AgentContent `json:"content" binding:"required"`
-}
-
-type SummaryText struct {
-	Type string `json:"type" binding:"required" enums:"summary_text"`
-	Text string `json:"text" binding:"required"`
-}
-
-type ReasoningItem struct {
-	ID      string        `json:"id" binding:"required"`
-	TurnID  string        `json:"turn_id" binding:"required"`
-	Type    string        `json:"type" binding:"required" enums:"reasoning"`
-	Status  *string       `json:"status" extensions:"x-nullable" enums:"in_progress,completed,incomplete"`
-	Summary []SummaryText `json:"summary" binding:"required"`
-}
-
 // MarshalJSON renders the wire shape. Messages always carry content and a
-// nullable phase, and function results a nullable output and error, as in the
-// pinned responses (EVT-09, SES-25). Other variants use the stored encoding.
+// nullable phase, function results a nullable output and error, and web search
+// a nullable action. Other variants use the stored encoding.
 func (i Item) MarshalJSON() ([]byte, error) {
 	type wire Item
 	switch i.Type {
@@ -87,6 +25,11 @@ func (i Item) MarshalJSON() ([]byte, error) {
 			Phase   *string       `json:"phase"`
 			Content []ItemContent `json:"content"`
 		}{wire(i), phase, content})
+	case "web_search_call":
+		return json.Marshal(struct {
+			wire
+			Action *WebSearchAction `json:"action"`
+		}{wire(i), i.Action})
 	case "function_call_output":
 		return json.Marshal(struct {
 			wire
@@ -103,6 +46,13 @@ func (i Item) MarshalJSON() ([]byte, error) {
 // required fields and nulls in both forms.
 func (i Item) MarshalStored() ([]byte, error) {
 	switch i.Type {
+	case "web_search_call":
+		type wire Item
+		type storedAction WebSearchAction
+		return json.Marshal(struct {
+			wire
+			Action *storedAction `json:"action,omitempty"`
+		}{wire(i), (*storedAction)(i.Action)})
 	case "create_subagent_call", "send_subagent_input_call", "agent_message":
 		content, err := coordinationContent(i.Content)
 		if err != nil {
diff --git a/contracts/agents-api/v1/subagents.go b/contracts/agents-api/v1/subagents.go
deleted file mode 100644
index 1686b9c86..000000000
--- a/contracts/agents-api/v1/subagents.go
+++ /dev/null
@@ -1,28 +0,0 @@
-package v1
-
-// AgentContent is the pinned content union used for inter-agent instructions and messages.
-type AgentContent struct {
-	Type             string  `json:"type" binding:"required" enums:"output_text,encrypted_content"`
-	Text             *string `json:"text,omitempty"`
-	EncryptedContent *string `json:"encrypted_content,omitempty"`
-}
-
-type Subagent struct {
-	ID            string         `json:"id" binding:"required"`
-	Object        string         `json:"object" binding:"required" enums:"agent.session.subagent"`
-	SessionID     string         `json:"session_id" binding:"required"`
-	ParentAgentID string         `json:"parent_agent_id" binding:"required"`
-	OpenedAt      int64          `json:"opened_at" binding:"required"`
-	ClosedAt      *int64         `json:"closed_at" extensions:"x-nullable"`
-	Name          *string        `json:"name" extensions:"x-nullable"`
-	Instructions  []AgentContent `json:"instructions" extensions:"x-nullable"`
-	Status        string         `json:"status" binding:"required" enums:"active,closed"`
-}
-
-type SubagentList struct {
-	Object  string     `json:"object" enums:"list" binding:"required"`
-	FirstID *string    `json:"first_id" extensions:"x-nullable"`
-	LastID  *string    `json:"last_id" extensions:"x-nullable"`
-	Data    []Subagent `json:"data" binding:"required"`
-	HasMore bool       `json:"has_more" binding:"required"`
-}
diff --git a/contracts/agents-api/v1/turns.go b/contracts/agents-api/v1/turns.go
deleted file mode 100644
index 745953deb..000000000
--- a/contracts/agents-api/v1/turns.go
+++ /dev/null
@@ -1,28 +0,0 @@
-package v1
-
-type Turn struct {
-	ID          string      `json:"id" binding:"required"`
-	AgentID     string      `json:"agent_id" binding:"required"`
-	SubagentID  *string     `json:"subagent_id" extensions:"x-nullable"`
-	SessionID   string      `json:"session_id" binding:"required"`
-	Object      string      `json:"object" enums:"agent.session.turn" binding:"required"`
-	Status      string      `json:"status" enums:"queued,in_progress,waiting,completed,failed,cancelled" binding:"required"`
-	CreatedAt   int64       `json:"created_at" binding:"required"`
-	StartedAt   *int64      `json:"started_at" extensions:"x-nullable"`
-	CompletedAt *int64      `json:"completed_at" extensions:"x-nullable"`
-	Error       *TurnError  `json:"error" extensions:"x-nullable"`
-	Usage       *TokenUsage `json:"usage" extensions:"x-nullable"`
-}
-
-type TurnError struct {
-	Code    string `json:"code" enums:"context_length_exceeded,session_budget_exceeded,usage_limit_exceeded,rate_limit_exceeded,server_overloaded,cyber_policy,connection_failed,server_error,authentication_error,invalid_request,resource_not_found,sandbox_error,executor_version_incompatible,active_turn_not_steerable,request_timeout,internal_error" binding:"required"`
-	Message string `json:"message" binding:"required"`
-}
-
-type TurnList struct {
-	Object  string  `json:"object" enums:"list" binding:"required"`
-	FirstID *string `json:"first_id" extensions:"x-nullable"`
-	LastID  *string `json:"last_id" extensions:"x-nullable"`
-	Data    []Turn  `json:"data" binding:"required"`
-	HasMore bool    `json:"has_more" binding:"required"`
-}
diff --git a/contracts/agents-api/v1/upstream_contract_test.go b/contracts/agents-api/v1/upstream_contract_test.go
index 57b44bdd5..9be78a569 100644
--- a/contracts/agents-api/v1/upstream_contract_test.go
+++ b/contracts/agents-api/v1/upstream_contract_test.go
@@ -1,290 +1,109 @@
 package v1
 
 import (
+	"crypto/sha256"
+	"encoding/hex"
 	"encoding/json"
 	"os"
-	"regexp"
-	"slices"
-	"sort"
+	"reflect"
 	"strings"
 	"testing"
-
-	"gopkg.in/yaml.v3"
 )
 
-// upstream-routes.json and upstream-fields.json are produced from the pinned
-// SDK by scripts/extract-agents-api-upstream.py.
-
-var openAPIPathParameter = regexp.MustCompile(`\{[^}]*\}`)
-
-func readContractJSON(t *testing.T, name string, value any) {
+func contractDocument(t *testing.T, path string) map[string]any {
 	t.Helper()
-	raw, err := os.ReadFile("../" + name)
-	if err != nil {
-		t.Fatal(err)
-	}
-	if err := json.Unmarshal(raw, value); err != nil {
-		t.Fatalf("parse %s: %v", name, err)
-	}
-}
-
-// publicOperations indexes the public OpenAPI operations by "METHOD /path",
-// with path parameters normalised to {} like the pinned route set.
-func publicOperations(t *testing.T) (map[string]map[string]any, map[string]any) {
-	t.Helper()
-	raw, err := os.ReadFile("../openapi.yaml")
+	raw, err := os.ReadFile("../" + path)
 	if err != nil {
 		t.Fatal(err)
 	}
 	var document map[string]any
-	if err := yaml.Unmarshal(raw, &document); err != nil {
+	if err := json.Unmarshal(raw, &document); err != nil {
 		t.Fatal(err)
 	}
-	operations := map[string]map[string]any{}
-	for path, item := range openAPIMap(t, document, "paths") {
-		for method, operation := range item.(map[string]any) {
-			if method == "parameters" {
-				continue
-			}
-			operations[strings.ToUpper(method)+" "+openAPIPathParameter.ReplaceAllString(path, "{}")] = operation.(map[string]any)
-		}
-	}
-	return operations, openAPIMap(t, document, "definitions")
+	return document
 }
 
-func TestPublicOpenAPIRoutesMatchPinnedUpstream(t *testing.T) {
-	var pinned struct {
-		Routes []string `json:"routes"`
-	}
-	readContractJSON(t, "upstream-routes.json", &pinned)
-	operations, _ := publicOperations(t)
-	var missing, extra []string
-	for _, route := range pinned.Routes {
-		if operations[route] == nil {
-			missing = append(missing, route)
-		}
-	}
-	for route := range operations {
-		if !slices.Contains(pinned.Routes, route) {
-			extra = append(extra, route)
-		}
+func TestOfficialSchemaPin(t *testing.T) {
+	pin := contractDocument(t, "upstream.json")["openapi"].(map[string]any)
+	raw, err := os.ReadFile("../upstream/openapi.json")
+	if err != nil {
+		t.Fatal(err)
 	}
-	sort.Strings(extra)
-	if len(pinned.Routes) == 0 || len(missing) != 0 || len(extra) != 0 {
-		t.Fatalf("public OpenAPI differs from the pinned SDK route set: missing %v, extra %v", missing, extra)
+	digest := sha256.Sum256(raw)
+	if hex.EncodeToString(digest[:]) != pin["sha256"] {
+		t.Fatal("official schema differs from its pin")
 	}
 }
 
-// fieldPlacementPending temporarily lists properties that are neither in the
-// pinned SDK type nor inside x_agents_core, keyed by schema.property. Each one
-// awaits a decision: remove it, move it into x_agents_core or rename it to the
-// official field. Remove an entry once it is resolved; stale entries fail.
-var fieldPlacementPending = map[string]string{
-	// Naming mismatch, not an extension: v1.ItemContent is shared by Item
-	// content, where these fields are official, and the content_part and
-	// reasoning_summary_part event parts, whose official types have only text
-	// and type.
-	"v1.ItemContent.encrypted_content": "shared with Item content; not on official event parts",
-	"v1.ItemContent.image_url":         "shared with Item content; not on official event parts",
-	// Naming mismatch, not an extension: v1.StreamError is shared by error
-	// events (official SessionError.param) and Environment state errors, whose
-	// official type has no param; Core omits it there.
-	"v1.StreamError.param": "shared with error events; not on official Environment state errors",
-}
-
-// Official list pages also carry object, first_id and last_id (recorded in
-// wire-semantics.md#lists), which the SDK's hand-written page classes
-// do not declare.
-var listEnvelopeFields = []string{"object", "first_id", "last_id"}
-
-// Core fields live only inside x_agents_core on these Agent and Session
-// definitions, and only as these members.
-var (
-	coreExtensionOwners  = []string{"v1.Agent", "v1.InlineAgent", "v1.SavedAgent", "v1.CreateAgentRequest", "v1.UpdateAgentRequest", "v1.Session", "v1.CreateSessionRequest"}
-	coreExtensionMembers = []string{"harness", "model_provider", "harness_config", "environment"}
-)
-
-type upstreamFields struct {
-	Operations map[string]struct{ Request, Query, Response []string } `json:"operations"`
-	Types      map[string]map[string][]string                         `json:"types"`
-}
-
-type fieldAudit struct {
-	definitions map[string]any
-	types       map[string]map[string][]string
-	visited     map[string]bool
-	violations  map[string][]string
-}
-
-// auditPublicFields returns every public property, query parameter or
-// extension member that the pinned SDK types do not have, keyed by schema.field.
-func auditPublicFields(operations map[string]map[string]any, definitions map[string]any, pinned upstreamFields) map[string][]string {
-	audit := fieldAudit{definitions: definitions, types: pinned.Types, visited: map[string]bool{}, violations: map[string][]string{}}
-	for route, operation := range operations {
-		official, ok := pinned.Operations[route]
-		if !ok {
-			continue // The route set test reports it.
+func TestPublicSchemaPreservesOfficialDefinitions(t *testing.T) {
+	source := contractDocument(t, "upstream/openapi.json")
+	public := contractDocument(t, "openapi.yaml")
+	if public["openapi"] != "3.1.0" {
+		t.Fatal("public contract must retain OpenAPI 3.1")
+	}
+	upstream := source["components"].(map[string]any)["schemas"].(map[string]any)
+	schemas := public["components"].(map[string]any)["schemas"].(map[string]any)
+	owners := map[string]bool{"AgentResource": true, "CreateAgentParams": true, "UpdateAgentParams": true, "SessionAgentConfigParam": true, "SessionAgentResource": true, "CreateAgentSessionParams": true, "SessionResource": true}
+	for name, value := range schemas {
+		if strings.HasPrefix(name, "v1.") {
+			continue
 		}
-		form, query := map[string]any{}, map[string]any{}
-		for _, parameter := range asSlice(operation["parameters"]) {
-			parameter := parameter.(map[string]any)
-			switch parameter["in"] {
-			case "body":
-				audit.compare(route+" body", parameter["schema"].(map[string]any), official.Request)
-			case "formData":
-				form[parameter["name"].(string)] = map[string]any{}
-			case "query":
-				// The SDK sends list parameters with brackets, as status[].
-				query[strings.TrimSuffix(parameter["name"].(string), "[]")] = map[string]any{}
+		schema := value.(map[string]any)
+		properties, _ := schema["properties"].(map[string]any)
+		if _, exists := properties["x_agents_core"]; exists {
+			if !owners[name] {
+				t.Errorf("extension on unexpected resource %s", name)
 			}
+			delete(properties, "x_agents_core")
+			delete(owners, name)
 		}
-		if len(form) != 0 {
-			audit.compare(route+" form", map[string]any{"properties": form}, official.Request)
-		}
-		if len(query) != 0 {
-			audit.compare(route+" query", map[string]any{"properties": query}, official.Query)
+		if !reflect.DeepEqual(schema, upstream[name]) {
+			t.Errorf("official definition %s was changed", name)
 		}
-		for code, response := range asMap(operation["responses"]) {
-			if schema, ok := asMap(response)["schema"].(map[string]any); ok && strings.HasPrefix(code, "2") {
-				audit.compare(route+" response", schema, official.Response)
-			}
-		}
-	}
-	return audit.violations
-}
-
-func TestPublicOpenAPIFieldsAreOfficialOrCoreExtensions(t *testing.T) {
-	var pinned upstreamFields
-	readContractJSON(t, "upstream-fields.json", &pinned)
-	var routes struct {
-		Routes []string `json:"routes"`
-	}
-	readContractJSON(t, "upstream-routes.json", &routes)
-	var extracted []string
-	for route := range pinned.Operations {
-		extracted = append(extracted, route)
 	}
-	sort.Strings(extracted)
-	if !slices.Equal(extracted, routes.Routes) {
-		t.Fatalf("upstream-fields.json operations %v differ from the pinned routes %v", extracted, routes.Routes)
-	}
-	operations, definitions := publicOperations(t)
-	violations := auditPublicFields(operations, definitions, pinned)
-	for field, sources := range violations {
-		if _, ok := fieldPlacementPending[field]; !ok {
-			t.Errorf("%s is not an official field of %v; put Core-only fields inside x_agents_core", field, sources)
-		}
-	}
-	for field := range fieldPlacementPending {
-		if violations[field] == nil {
-			t.Errorf("resolved field %s is still listed in fieldPlacementPending", field)
-		}
+	if len(owners) != 0 {
+		t.Errorf("missing extension owners: %v", owners)
 	}
 }
 
-// The audit rejects a Core field outside x_agents_core, a new x_agents_core
-// member and x_agents_core on another resource.
-func TestPublicFieldAuditRejectsMisplacedCoreFields(t *testing.T) {
-	var pinned upstreamFields
-	readContractJSON(t, "upstream-fields.json", &pinned)
-	for _, test := range []struct {
-		definition, property, want string
-	}{
-		{"v1.SessionExecutionInput", "sandbox_node_id", "v1.CreateSessionRequest.x_agents_core.sandbox_node_id"},
-		{"v1.AgentsCore", "sandbox_node_id", "v1.Agent.x_agents_core.sandbox_node_id"},
-		{"v1.Vault", "x_agents_core", "v1.Vault.x_agents_core"},
-	} {
-		operations, definitions := publicOperations(t)
-		asMap(asMap(definitions[test.definition])["properties"])[test.property] = map[string]any{"type": "string"}
-		if violations := auditPublicFields(operations, definitions, pinned); violations[test.want] == nil {
-			t.Errorf("%s.%s was not reported as %s; got %v", test.definition, test.property, test.want, violations)
+func TestPublicOperationsPreserveOfficialContract(t *testing.T) {
+	source := contractDocument(t, "upstream/openapi.json")["paths"].(map[string]any)
+	published := contractDocument(t, "openapi.yaml")["paths"].(map[string]any)
+	count := 0
+	for path, item := range source {
+		if !(strings.HasPrefix(path, "/agents") || strings.HasPrefix(path, "/files") || strings.HasPrefix(path, "/skills") || strings.HasPrefix(path, "/vaults")) {
+			continue
 		}
-	}
-}
-
-// compare checks one of our schemas against the union of the official types
-// that describe the same value, following nested official models.
-func (a *fieldAudit) compare(name string, schema map[string]any, official []string) {
-	name, schema = a.resolve(name, schema)
-	key := name + "|" + strings.Join(official, ",")
-	if schema == nil || a.visited[key] {
-		return
-	}
-	a.visited[key] = true
-	for property, value := range a.properties(schema) {
-		var children []string
-		known := false
-		for _, typeName := range official {
-			if nested, ok := a.types[typeName][property]; ok {
-				known = true
-				for _, child := range nested {
-					if !slices.Contains(children, child) {
-						children = append(children, child)
-					}
-				}
-			}
+		actual, ok := published[path].(map[string]any)
+		if !ok {
+			t.Errorf("missing official path %s", path)
+			continue
 		}
-		switch {
-		case known && len(children) != 0:
-			sort.Strings(children)
-			a.compare(name+"."+property, value, children)
-		case known:
-		case property == "x_agents_core" && slices.Contains(coreExtensionOwners, name):
-			_, extension := a.resolve(name+"."+property, value)
-			for member := range a.properties(extension) {
-				if name == "v1.Session" && member == "installation" {
-					continue
+		for method, raw := range item.(map[string]any) {
+			expected := raw.(map[string]any)
+			operation := actual[method].(map[string]any)
+			if strings.HasPrefix(path, "/agents") || strings.HasPrefix(path, "/vaults") {
+				params := operation["parameters"].([]any)
+				beta := params[len(params)-1].(map[string]any)
+				if beta["name"] != "OpenAI-Beta" || beta["required"] != true {
+					t.Errorf("missing Beta header on %s %s", method, path)
 				}
-				if !slices.Contains(coreExtensionMembers, member) {
-					a.violations[name+".x_agents_core."+member] = coreExtensionMembers
+				if _, present := expected["parameters"]; len(params) == 1 && !present {
+					delete(operation, "parameters")
+				} else {
+					operation["parameters"] = params[:len(params)-1]
 				}
 			}
-		case slices.Contains(listEnvelopeFields, property) && slices.ContainsFunc(official, func(typeName string) bool { return strings.HasPrefix(typeName, "pagination.") }):
-		default:
-			a.violations[name+"."+property] = official
-		}
-	}
-}
 
-// resolve follows references, single allOf wrappers and arrays to the object
-// schema, naming it by its definition when it has one.
-func (a *fieldAudit) resolve(name string, schema map[string]any) (string, map[string]any) {
-	for schema != nil {
-		switch {
-		case schema["$ref"] != nil:
-			name = strings.TrimPrefix(schema["$ref"].(string), "#/definitions/")
-			schema = asMap(a.definitions[name])
-		case len(asSlice(schema["allOf"])) == 1:
-			schema = asMap(asSlice(schema["allOf"])[0])
-		case schema["items"] != nil:
-			schema = asMap(schema["items"])
-		default:
-			return name, schema
+			delete(expected, "security")
+			if !reflect.DeepEqual(operation, expected) {
+				t.Errorf("official operation changed: %s %s", method, path)
+			}
+			count++
 		}
+		delete(published, path)
 	}
-	return name, nil
-}
-
-func (a *fieldAudit) properties(schema map[string]any) map[string]map[string]any {
-	result := map[string]map[string]any{}
-	for property, value := range asMap(schema["properties"]) {
-		result[property] = asMap(value)
-	}
-	for _, part := range asSlice(schema["allOf"]) {
-		_, resolved := a.resolve("", asMap(part))
-		for property, value := range a.properties(resolved) {
-			result[property] = value
-		}
+	if count != 58 || len(published) != 0 {
+		t.Fatalf("expected pinned 58 operations, got %d, extra paths %v", count, published)
 	}
-	return result
-}
-
-func asMap(value any) map[string]any {
-	result, _ := value.(map[string]any)
-	return result
-}
-
-func asSlice(value any) []any {
-	result, _ := value.([]any)
-	return result
 }
diff --git a/contracts/agents-api/v1/usage.go b/contracts/agents-api/v1/usage.go
deleted file mode 100644
index d74752ec0..000000000
--- a/contracts/agents-api/v1/usage.go
+++ /dev/null
@@ -1,15 +0,0 @@
-package v1
-
-type TokenUsage struct {
-	InputTokens         int64              `json:"input_tokens" binding:"required"`
-	InputTokensDetails  InputTokenDetails  `json:"input_tokens_details" binding:"required"`
-	OutputTokens        int64              `json:"output_tokens" binding:"required"`
-	OutputTokensDetails OutputTokenDetails `json:"output_tokens_details" binding:"required"`
-	TotalTokens         int64              `json:"total_tokens" binding:"required"`
-}
-type InputTokenDetails struct {
-	CachedTokens int64 `json:"cached_tokens" binding:"required"`
-}
-type OutputTokenDetails struct {
-	ReasoningTokens int64 `json:"reasoning_tokens" binding:"required"`
-}
diff --git a/contracts/agents-api/v1/vaults.go b/contracts/agents-api/v1/vaults.go
deleted file mode 100644
index 8ba62afc8..000000000
--- a/contracts/agents-api/v1/vaults.go
+++ /dev/null
@@ -1,30 +0,0 @@
-package v1
-
-// CreateVaultRequest creates a project-owned credential container. An omitted
-// name stays null; a supplied name must be a string with 1–256 UTF-8 bytes after trimming.
-type CreateVaultRequest struct {
-	Name     *string            `json:"name,omitempty"`
-	Metadata map[string]*string `json:"metadata,omitempty" swaggertype:"object,string" extensions:"x-nullable"`
-}
-
-type Vault struct {
-	ID        string            `json:"id" binding:"required"`
-	Object    string            `json:"object" binding:"required" enums:"vault"`
-	CreatedAt int64             `json:"created_at" binding:"required"`
-	Name      *string           `json:"name" extensions:"x-nullable"`
-	Metadata  map[string]string `json:"metadata" binding:"required"`
-}
-
-type VaultList struct {
-	Object  string  `json:"object" binding:"required" enums:"list"`
-	Data    []Vault `json:"data" binding:"required"`
-	HasMore bool    `json:"has_more" binding:"required"`
-	FirstID *string `json:"first_id" extensions:"x-nullable"`
-	LastID  *string `json:"last_id" extensions:"x-nullable"`
-}
-
-type VaultDeleted struct {
-	ID      string `json:"id" binding:"required"`
-	Deleted bool   `json:"deleted" binding:"required"`
-	Object  string `json:"object" binding:"required" enums:"vault.deleted"`
-}
diff --git a/contracts/agents-api/zh/core-errors.md b/contracts/agents-api/zh/core-errors.md
index d90ac52b0..c7bc4301b 100644
--- a/contracts/agents-api/zh/core-errors.md
+++ b/contracts/agents-api/zh/core-errors.md
@@ -1,7 +1,7 @@
 ---
 title: "Core 管理错误"
 source: contracts/agents-api/core-errors.md
-source_hash: d5c4450c0c74927115c79dca70d29372a7316d5d2591c7e18af688d08257a98c
+source_hash: 3d8e6a03d6a54c7dc86a27164749ffae963b5ef52cbede0e0da843c7da0216ba
 ---
 
 `/core/v1` 上的错误使用此封装结构。`message` 是安全的英文文本；`code` 和 `param` 可以为 null。客户端依据稳定的 `code` 和可选的 `param` 进行处理，对未知代码显示 `message`，绝不解析消息，也绝不自动重试被拒绝的写操作。
@@ -98,7 +98,7 @@ Web 的控制台服务器在 `/core` 路径上发生自身故障时使用此封
 | `execution_interrupted` | Core 执行被中断 |
 | `delivery_unconfirmed` | `delivery_unknown`、`input_outcome_unknown`、`cancel_unconfirmed`、`cancel_outcome_unavailable`、`function_result_unconfirmed` |
 | `input_rejected` | `invalid_input`、`input_not_applied`、`message_input_unsupported`，以及确切的 steering 结果 `input_invalid_input`、`input_run_inactive`、`input_input_conflict`、`input_input_limit`、`input_unsupported`、`input_rejected`、`input_not_ready`、`input_busy` |
-| `executor_protocol_error` | `invalid_executor_result`、`interaction_not_supported`、`execution_state_unavailable`、`execution_state_changed`、`function_call_invalid`、`function_result_invalid` |
+| `executor_protocol_error` | `invalid_executor_result`、`execution_state_unavailable`、`execution_state_changed`、`function_call_invalid`、`function_result_invalid` |
 | `core_storage_failed` | `event_persistence_failed`、`artifact_capture_failed` |
 | `internal_error` | 结果未知或格式错误；不返回原始值 |
 | `environment_connection_timeout` | 初始输入连接截止时间已过 |
diff --git a/contracts/agents-api/zh/harness-onboarding.md b/contracts/agents-api/zh/harness-onboarding.md
index fc0fccdca..5d7b26f55 100644
--- a/contracts/agents-api/zh/harness-onboarding.md
+++ b/contracts/agents-api/zh/harness-onboarding.md
@@ -1,7 +1,7 @@
 ---
 title: "将原生 Harness 添加到 OpenAgentCore"
 source: contracts/agents-api/harness-onboarding.md
-source_hash: 6a046c227cb9d0b3074a21c9257a408c126234fd127ad08f359d89891ee0f20b
+source_hash: 6c87f33d0ea60e0510c262b58aa92279852457bb85f0443b87a38bf2b0c3419c
 ---
 
 **Harness** 是一种运行模型和工具循环的原生代理引擎（Codex、Claude Code、MiniMax Code）。**Harness 适配器**将 Runtime 的 Executor 和 Turn 契约转换到该引擎的 SDK 或协议。本文档定义 Runtime–Harness 协议：适配器接口及其生命周期义务、注册、Core 资格认定和验收。[Harness capabilities](harness-capabilities.md) 记录了当前每个 Harness 支持的功能。
@@ -71,7 +71,6 @@ Environment 提供执行资源。受管 E2B、Docker 和 microsandbox 机器以
 | `DurableSteerer` | 每个 Turn 上真实实现 | 区分完整写入与原生应用回执；保留重试身份 |
 | `Steerer` | 明确实现或 Unsupported | 额外的非持久化活动 Turn 输入 |
 | `FunctionResultSubmitter` | 明确实现或 Unsupported | 匹配原生调用和结果身份，并确认应用 |
-| `PermissionResponder`、`UserChoiceResponder` | 明确实现或 Unsupported | 响应精确发出的身份；未知或已过期的交互与 Unsupported 保持区分 |
 | `WorkspaceDirectoryLister`、`WorkspaceWriter` | 在 Turn 和 Executor 所有者上明确实现 | 使用授权工作区，确认访问，提交或关闭，或者返回该操作的 Unsupported 错误 |
 | 中立消息、图像、MCP、结构化输出和 Subagent 观察 | 明确作出能力决策 | 保持每项操作的协议语义；在提交前拒绝不受支持的输入 |
 
@@ -85,7 +84,7 @@ func (s *Session) SubmitFunctionResult(context.Context, proto.FunctionResultPayl
 }
 ```
 
-原因必须是固定的安全字符串，绝不能是已提交内容、凭据或原始原生诊断信息。Unsupported 保证不会产生原生副作用，也不表示操作成功且为空。安装不可用、未知交互 ID、原生失败和不确定结果应保留各自的错误和所有权。nil `Turn` 仍表示没有提交任何输入，并且输出归调用方所有；绝不能将其用作 Unsupported 标记。
+原因必须是固定的安全字符串，绝不能是已提交内容、凭据或原始原生诊断信息。Unsupported 保证不会产生原生副作用，也不表示操作成功且为空。安装不可用、未知调用 ID、原生失败和不确定结果应保留各自的错误和所有权。nil `Turn` 仍表示没有提交任何输入，并且输出归调用方所有；绝不能将其用作 Unsupported 标记。
 
 线协议请求不携带工作目录。Runtime 将 `local_environment.workspace_directory` 与其绑定进行核对，并通过 `LocalEnvironment.WorkspaceRoot` 向 Harness 提供其绑定的工作区目录；必须在该目录中运行原生 Harness。
 
@@ -107,26 +106,26 @@ Session 在其已连接的 Runtime 中拥有一个可复用的 Executor；Turn 
 
 **绑定。** Runtime 将其 Executor 记录绑定到 Session、Environment、连接和不可变执行配置。恢复身份和先前 Turn 恢复标志是连续性断言，而不是配置更改。提供的原生身份必须与保留的所有者匹配；当需要现有历史时，恢复绝不能启动新的根。配置冲突属于错误，而不是热切换。连接丢失会让其所有者和句柄退役；旧计时器、输出和取消操作不能影响替代对象。
 
-**每 Turn 状态。** 每个 Turn 都会获得全新的包装器、输出通道和回执状态。引导、函数、权限和用户选择接口均属于该 Turn。原生回调必须在异步工作开始前捕获来源 Turn，因此迟到事件绝不会被归到当前活动的 Turn 上。原生进程、query 或传输连接、固定能力配置和原生 session 身份均属于 Executor。不要重置已完成的 `sync.Once` 值，也不要复用旧 Turn 对象。
+**每 Turn 状态。** 每个 Turn 都会获得全新的包装器、输出通道和回执状态。引导和函数接口均属于该 Turn。原生回调必须在异步工作开始前捕获来源 Turn，因此迟到事件绝不会被归到当前活动的 Turn 上。原生进程、query 或传输连接、固定能力配置和原生 session 身份均属于 Executor。不要重置已完成的 `sync.Once` 值，也不要复用旧 Turn 对象。
 
 **开始。** `StartTurn` 返回 nil Turn，保证没有提交任何原生输入，也没有保留输出通道；随后由 Runtime 关闭该通道。一旦输入可能已经提交，即使同时返回错误，也必须返回非 nil Turn：该 Turn 拥有恰好一次的输出关闭权，并在结算前持续接受跟踪。未知输入绝不能重放。明确的 `executor_unavailable` Start 拒绝允许进行一次通用恢复尝试，但只能在此前 Executor 已关闭且未提交输入之后进行；Runtime 会重新检查同一物理对端和当前授权。
 
-**取消和结算。** `Turn.Cancel` 仅以目标 Turn 为对象，不会关闭健康的 Executor。`AwaitSettlement` 同时适用于自然完成和取消。成功意味着输出已无法再写入，并且该 Turn 的原生事件、输入、函数、交互和子任务均已结算。原生完成或取消确认独立于资源退役：关闭传输层无法提供缺失的原生终态或操作回执。
+**取消和结算。** `Turn.Cancel` 仅以目标 Turn 为对象，不会关闭健康的 Executor。`AwaitSettlement` 同时适用于自然完成和取消。成功意味着输出已无法再写入，并且该 Turn 的原生事件、输入、函数和子任务均已结算。原生完成或取消确认独立于资源退役：关闭传输层无法提供缺失的原生终态或操作回执。
 
 - `Reusable=true` 还要确认原生所有者能够接受下一个 Turn。`Reusable=false` 要求提供原因，并在之后确认 Executor 已关闭。
 - 错误表示结算尚未确认，既不释放所有权，也不释放容量。调用方截止时间只会停止等待，不会停止受跟踪的清理。必须串行重试同一个清理目标；清理失败会阻止替换并保留其资源槽位。
 - `Executor.Close` 独立于 Turn 结果确认资源退役：不可变的 Turn 错误不得阻止在其工作和输出已经停止后关闭原生传输层。
 - 结算必须包含所属的后台工作，并在失败后保留精确的原生清理目标。原生终止由适配器负责；仅有批量清理确认并不能证明已达到静默状态。
-- 每个 `Session`（包括直接调用工厂的结果）都要声明 `CancellationOutcome`。`Turn` 继承该声明。快照保留已观察到的原生身份、Usage 和输出，并在取消后仍可读取。缺失的证据保持未设置；空的 `DonePayload` 表示未观察到任何内容，而不是表示取消成功或不受支持。读取快照不会等待结算。
-- 直接调用的 `Session.Cancel` 请求取消；输出关闭表示拆卸开始。Turn 结算仍需要 `AwaitSettlement` 和所需的任何 `Executor.Close`；取消请求成功或其快照都不能替代这些等待。
+- 每个 `Session` 都要声明 `CancellationOutcome`。`Turn` 继承该声明。快照保留已观察到的原生身份、Usage 和输出，并在取消后仍可读取。缺失的证据保持未设置；空的 `DonePayload` 表示未观察到任何内容，而不是表示取消成功或不受支持。读取快照不会等待结算。
+- `Session.Cancel` 请求取消；输出关闭表示拆卸开始。Turn 结算仍需要 `AwaitSettlement` 和所需的任何 `Executor.Close`；取消请求成功或其快照都不能替代这些等待。
 
-**Runtime 在 Turn 前后执行的工作。** 一个输出消费者会在原生 Start 之前启动，耗尽有界的 64 帧通道，并将终态观察保留到 Start 发布、Turn 结算和已准入操作回执完成为止。正常完成绝不调用 Cancel。输入、函数和交互准入会在结算前关闭；已准入的操作会持有其屏障，直至原生回执和出站确认完成。Runtime 会在等待该屏障之前向 Turn 发送取消，因为已写入的输入可能需要原生中断才能生成回执。Runtime 会汇合原生结算、所需的已确认 Executor 关闭、输出耗尽和所有已准入操作，然后应用确认或执行复用，之后才会转发 Done 或已应用的取消回执。Close 失败可以报告失败，同时保留同一 Run 和未完成操作以供重试；已关闭的调用方等待无法凭空生成已应用输入回执。Runtime 会在发布 Done 前提交原生连续性状态并释放旧 Run 的准入，因为接收方可能立即启动另一个 Turn；迟到的终态发送失败属于旧 Run，不能使已拥有 Executor 的后继对象失效。连接关闭负责传输丢失清理。结算等待时间为十秒，回执发送预算为五秒；超时不能证明已达到静默状态。
+**Runtime 在 Turn 前后执行的工作。** 一个输出消费者会在原生 Start 之前启动，耗尽有界的 64 帧通道，并将终态观察保留到 Start 发布、Turn 结算和已准入操作回执完成为止。正常完成绝不调用 Cancel。输入和函数准入会在结算前关闭；已准入的操作会持有其屏障，直至原生回执和出站确认完成。Runtime 会在等待该屏障之前向 Turn 发送取消，因为已写入的输入可能需要原生中断才能生成回执。Runtime 会汇合原生结算、所需的已确认 Executor 关闭、输出耗尽和所有已准入操作，然后应用确认或执行复用，之后才会转发 Done 或已应用的取消回执。Close 失败可以报告失败，同时保留同一 Run 和未完成操作以供重试；已关闭的调用方等待无法凭空生成已应用输入回执。Runtime 会在发布 Done 前提交原生连续性状态并释放旧 Run 的准入，因为接收方可能立即启动另一个 Turn；迟到的终态发送失败属于旧 Run，不能使已拥有 Executor 的后继对象失效。连接关闭负责传输丢失清理。结算等待时间为十秒，回执发送预算为五秒；超时不能证明已达到静默状态。
 
 ## 事件、输入和可选能力 {#events-inputs-and-optional-capabilities}
 
 使用 [`internal/agentdaemon/proto`](https://github.com/MiniMax-AI/OpenAgentCore/tree/main/internal/agentdaemon/proto) 处理中立请求、事件和回执。每个 Turn 只按顺序发出带有其 Run ID 的自身事件，并产生一个终态结果。原生 ID 和 usage 必须来自观察，绝不能虚构；缺失的度量值表示未知，而不是零。
 
-初始输入和引导使用有序的 `proto.MessageInput`。必须保持用户消息顺序和内容顺序。仅支持文本的适配器通过 `TextOnly()` 拒绝图像，而不是丢弃图像；图像适配器在原生环境中转换每个部分，并且只有在其所有消息均已应用后才确认活动批次。成功传输写入与确认原生应用是不同的事件。用户选择答案使用发出的问题 ID 和值数组；共享的 `PromptForUserChoiceDecisionPayload.AnswersFor` 会在消费待处理交互之前验证身份，因此绝不能按标头或位置映射答案。只能恢复绑定到 Session 的精确历史；缺失、含糊或外部历史会在新的模型输入之前导致失败。设备身份不代表原生 session 所有权。
+初始输入和引导使用有序的 `proto.MessageInput`。必须保持用户消息顺序和内容顺序。仅支持文本的适配器通过 `TextOnly()` 拒绝图像，而不是丢弃图像；图像适配器在原生环境中转换每个部分，并且只有在其所有消息均已应用后才确认活动批次。成功传输写入与确认原生应用是不同的事件。只能恢复绑定到 Session 的精确历史；缺失、含糊或外部历史会在新的模型输入之前导致失败。设备身份不代表原生 session 所有权。
 
 ### 必需操作和扩展操作 {#required-and-extension-operations}
 
@@ -150,23 +149,21 @@ MCP、公共函数、延迟函数发现、结构化输出、图像输入、详
 
 ## 注册适配器 {#register-the-adapter}
 
-注册是静态的，并且需要构建。从 `apps/daemon/internal/agent/<kind>/declaration.go` 导出一个 `agent.Declaration`，然后将其添加到 [`cli/agent_discovery.go`](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/apps/daemon/internal/cli/agent_discovery.go) 的 `harnessDeclarations` 中。声明包含 kind、完整能力描述符、共享模型 `Configuration` 和 `Discover` 函数。发现过程接收 profile 和诊断写入器，负责原生配置和可用性检查，并返回已安装的 `agent.Runtime` 及其描述符、session 工厂和 Executor 工厂。未配置适配器时返回 nil；已配置的前置条件失败时，返回不可用描述符和 session 工厂。将版本门控和工厂选择条件保留在适配器内部。
+注册是静态的，并且需要构建。从 `apps/daemon/internal/agent/<kind>/declaration.go` 导出一个 `agent.Declaration`，然后将其添加到 [`cli/agent_discovery.go`](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/apps/daemon/internal/cli/agent_discovery.go) 的 `harnessDeclarations` 中。声明包含 kind、完整能力描述符、共享模型 `Configuration` 和 `Discover` 函数。发现过程接收 profile 和诊断写入器，负责原生配置和可用性检查，并返回已安装的 `agent.Runtime` 及其描述符、Executor 工厂和视图声明。未配置适配器时返回 nil；已配置的前置条件失败时，返回不带 Executor 工厂和视图的不可用描述符。将版本门控和工厂选择条件保留在适配器内部。
 
-[`cli/agent_registration.go`](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/apps/daemon/internal/cli/agent_registration.go) 遍历已发现的 Runtime，并调用 `agent/harness.go` 中的 `Registry.Register`。它验证发现过程是否保留了声明的 kind，并按以下顺序安装工厂：
+[`cli/agent_registration.go`](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/apps/daemon/internal/cli/agent_registration.go) 遍历已发现的 Runtime，并调用 `agent/harness.go` 中的 `Registry.Register`。它验证发现过程是否保留了声明的 kind，并按以下顺序注册该 Runtime：
 
 | 顺序 | 方法 | 注册内容 |
 | --- | --- | --- |
-| 1 | `RegisterKind(proto.SupportedAgentKind, harnessconfig.Configuration, agent.Factory)` | Kind、可用性、版本、`AgentKindCapabilities`、模型配置声明和直接调用工厂。它会重置其他注册项，因此必须首先调用。 |
+| 1 | `RegisterKind(proto.SupportedAgentKind, harnessconfig.Configuration)` | Kind、可用性、版本、`AgentKindCapabilities` 和模型配置声明。它会重置其他注册项，因此必须首先调用。 |
 | 2 | `RegisterExecutor(kind, agent.ExecutorFactory)` | 执行所用的 Executor 和 Turn 生命周期；据此派生 `Preparation` 能力 |
 | 3 | `RegisterView(kind, agent.View)` | 可选：来自 `Runtime.View` 的 agent-host 视图声明。`View.Validate` 失败时以 `ErrInvalidView` panic。其 Executor 工厂像 `RegisterExecutor` 一样验证模型配置，并执行[网关规则](#endpoints-and-proxy)。 |
 
-直接调用的 `agent.Factory` 委托给同一个 Executor 实现。
-
 `Runtime.View` 声明 Harness 如何在 agent-host Session 视图中运行，详见[在 agent-host 视图中运行](#run-in-an-agent-host-view)。每个适配器都显式设置它；`View: nil` 表示 agent host 拒绝该 kind，`Registry.ResolveView` 返回包装 `ErrUnsupportedOperation` 的错误。`TestPublicHarnessContractDeclarations` 要求每个声明都包含该字段。
 
 每个 `proto.AgentKindCapabilities` 字段都必须显式设为 `proto.CapabilitySupported` 或 `proto.CapabilityUnsupported`，即使 Harness 不可用也是如此。`proto.CapabilityUnspecified` 无效：零值和省略字段绝不表示 Unsupported。安装探测可以使用 `proto.CapabilityFromBool` 设置单个字段；但不得填充未提及字段或未来字段。可用性通过 `SupportedAgentKind.Available` 单独表示。注册会在更改 registry 之前验证完整声明；线协议会为每个字段携带显式布尔值，因此省略字段和 null 字段均无效。添加新字段时，每个生产声明都必须作出决定。Runtime 使用者应调用 `IsSupported()`，并在原生操作前拒绝不受支持的请求；接口断言用于验证实现，绝不表示支持。每个声明都必须与针对该安装验证的行为一致；[Core–Runtime protocol](../../../docs/zh/runtime-protocol.md#capability-declarations) 负责声明的传输方式和冻结方式。
 
-准入映射是显式的。`Steering` 控制非持久化 `Steerer` 输入。`DurableInputReceipts` 控制 `DurableSteerer` 输入，并且还要求 Turn 结算契约；二者互不隐含，而且 Core 的公共文本 profile 要求同时具备二者。`Permissions` 一起认定权限响应和用户选择响应的资格，并要求两条原生响应路径均存在。工作区声明描述授权资源所有者，包括通用 Runtime 工作区实现。Runtime 注册不会授予 Core 资格；服务 profile 才会授予。
+准入映射是显式的。`Steering` 控制非持久化 `Steerer` 输入。`DurableInputReceipts` 控制 `DurableSteerer` 输入，并且还要求 Turn 结算契约；二者互不隐含，而且 Core 的公共文本 profile 要求同时具备二者。工作区声明描述授权资源所有者，包括通用 Runtime 工作区实现。`WorkspaceReadPreparation` 准入带 `workspace_read_only` 的 `execution_prepare`。Runtime 自行就绪该 preparation，并从绑定的本地工作区目录提供读取，不调用 Executor 工厂；因此仅当该 kind 的 Environment 工作区就是该本地目录时，adapter 才声明它。注册过程不会派生它。Runtime 注册不会授予 Core 资格；服务 profile 才会授予。
 
 可运行的仅测试示例 [`testdata/onboarding/main.go`](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/apps/daemon/testdata/onboarding/main.go) 会以 `mcode` 类型注册一个仅支持文本的合成 Harness，因为 Core 只接纳[目录](harness-catalog.md)中的 Harness。它展示 Session 所有的 Executor、全新的 Turn、持久化引导、取消和历史绑定，并且绝不会发布。
 
@@ -203,7 +200,7 @@ profile 是纯逻辑：它使用现有的公共类型和协议类型，声明受
 
 ## 原生模型配置 {#native-model-configuration}
 
-[`internal/harnessconfig/harness.go`](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/harnessconfig/harness.go) 负责共享配置声明和纯准备契约。每个适配器在 `internal/harnessconfig/<kind>` 中提供一个 `Configuration`，供 Core 组合和 Runtime 的 `RegisterKind` 使用。直接调用工厂和 Executor 路径都会在产生原生副作用之前通过该声明进行验证，而 Registry 包装器会将声明与工厂保留在一起。线协议对象是 `proto.HarnessConfig`。[Model execution](model-execution.md#native-model-parameters) 列出了每个 Harness 接受的字段。
+[`internal/harnessconfig/harness.go`](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/harnessconfig/harness.go) 负责共享配置声明和纯准备契约。每个适配器在 `internal/harnessconfig/<kind>` 中提供一个 `Configuration`，供 Core 组合和 Runtime 的 `RegisterKind` 使用。Executor 路径和视图路径都会在产生原生副作用之前通过该声明进行验证，而 Registry 包装器会将声明与工厂保留在一起。线协议对象是 `proto.HarnessConfig`。[Model execution](model-execution.md#native-model-parameters) 列出了每个 Harness 接受的字段。
 
 每个请求都指定非空的 `model` 和一个 `model_provider`；缺少任一项的请求，包括显式 null 或空值，都会在产生任何原生副作用之前被准备阶段拒绝。因此空声明不接受任何请求。未知协议格式和重复协议声明会导致注册失败。
 
@@ -214,7 +211,7 @@ profile 是纯逻辑：它使用现有的公共类型和协议类型，声明受
 开始前，记录操作集、预期结果、排除项和停止条件。当其声明的操作通过时，资格认定即结束；它不会扩展为匹配另一个 Harness 的功能列表。
 
 1. **契约测试。** 在名为 `TestSharedTextLifecycle` 的测试中，使用适配器准备好的 Executor 和确定性的原生夹具调用 `agent/contracttest.TextLifecycle`；`claudesdk/executor_test.go` 是参考实现。它检查独立的 Turn 流、原生所有者和历史连续性、持久化写入与应用回执、过期取消，以及取消后的健康继续执行。`make check-runtime-contract` 会将它与共享线协议、gateway、传输层和调度器测试、声明完整性检查以及每个适配器的 `TestUnsupportedExtensionsHaveNoNativeEffects` 一起运行。适配器测试还覆盖两个普通 Turn 共享一个原生进程或连接和历史、取消后执行另一个 Turn、过期取消和迟到事件、原生退出、清理失败、输入写入与应用回执、未知结果，以及每 Turn 新鲜的 usage、函数、输入和子项观察状态。必须说明夹具是受控夹具还是真实 Provider。
-2. **共享集成。** `TestThirdHarnessPublicOnboarding` 让合成 Harness 通过公共 Session 和输入准入、Worker 设备选择、真实 WebSocket gateway、daemon Registry 和 Router、中立事件以及持久化终态投影运行。它在与 API 处理程序和调度器相同的 `execution.Policy` 中使用自定义不可变 `engine.Catalog`，并检查已应用输入回执、已保存原生身份、继续执行、取消、不受支持的可选请求以及缺少强制 Runtime 支持。该夹具没有工作区、MCP、公共函数、权限或用户选择处理器，其注册仅保留在测试本地。它证明的是集成路径，而不是原生执行。
+2. **共享集成。** `TestThirdHarnessPublicOnboarding` 让合成 Harness 通过公共 Session 和输入准入、Worker 设备选择、真实 WebSocket gateway、daemon Registry 和 Router、中立事件以及持久化终态投影运行。它在与 API 处理程序和调度器相同的 `execution.Policy` 中使用自定义不可变 `engine.Catalog`，并检查已应用输入回执、已保存原生身份、继续执行、取消、不受支持的可选请求以及缺少强制 Runtime 支持。该夹具没有工作区、MCP 或公共函数，其注册仅保留在测试本地。它证明的是集成路径，而不是原生执行。
 3. **真实验收。** 使用锁定的官方 Python SDK 和针对 Core 的原始 HTTP、真实 Provider API、原生 Harness 以及专用数据库。验证初始执行、热后续执行、取消以及带继续执行的重启；记录原生所有者身份以及相同条件下的冷启动和热运行时间。对于工作区放置方式，还要验证 Files 和 Artifacts、工作区身份、公开响应中未出现凭据，以及外部历史会被拒绝。`services/core/tests/official_hosted_functions_native.py` 保存共享函数断言：成功和错误、原生文件输出和公共 Artifact 字节、重启后的同历史继续执行、外部结果拒绝以及待处理调用取消。合成运行或失败运行绝不计入。下面的选择性测试会在 `services/core/tests` 中针对真实 daemon 和模型运行锁定 SDK 夹具；设置 `OAC_TEST_OFFICIAL_SDK_PYTHON`、`OAC_TEST_NATIVE_DAEMON_BIN`、`OAC_TEST_NATIVE_PROOF_DIR` 及其私有选项文件后，每项测试才会运行。选项文件是一个 JSON 对象，恰好包含 `model` 和 `model_provider`（即 `x_agents_core.model_provider` 的字段）；测试会将其设置为部署默认模型 Provider，而夹具的 `environment: none` Session 会在创建时将其冻结。
 4. **回归。** 现有 Harness 必须继续正常工作。先运行定向测试，然后运行 `make check`；API 更改后运行 `make openapi`，查询更改后运行 `make sqlc-generate`。
 5. **审查。** 遵循 [blind review workflow](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/CONTRIBUTING.md#review)。
@@ -254,7 +251,7 @@ daemon 的 `clirunner` 让每个原生子进程在自己的 Unix 进程组中启
 
 所属输出管道在主进程退出后仍可读取。消费者在调用 `Wait` 之前耗尽 stdout 和 stderr；`Wait` 会汇合缓存的进程结果并关闭读取器。`Done` 报告主进程回收和进程组清理信号；它不是原生执行回执，也不是历史已持久化的证据。SDK 适配器会结算每个 Turn，并在发布完成状态前耗尽其观察结果；Executor 关闭还会关闭 Query 并等待原生子进程。进程组用于生命周期监管，而不是隔离或遏制离开进程组的后代进程。
 
-适配器以启动用户的权限无人值守运行原生工具：Codex 使用批准策略 `never` 和完全访问权限；Claude 通过适配器的工具回调，以原生 `default` 权限模式运行，并禁用 SDK sandbox；MiniMax 绕过权限并禁用 sandbox。不要添加权限 profile、bubblewrap 包装器或原生 sandbox 设置；每种 Environment 来源都只有一条执行路径。资源路径属于操作员配置，而不是权限边界。
+适配器以启动用户的权限无人值守运行原生工具，Harness 从不询问人类。Codex 使用批准策略 `never` 和完全访问权限，在该策略下 Codex 自行处理 MCP elicitation，不会发给客户端；适配器还禁用其阻塞式 `request_user_input` 工具。Claude 通过适配器的工具回调运行，回调直接允许或拒绝、不会询问，使用原生 `default` 权限模式并禁用 SDK sandbox。MiniMax 绕过权限并禁用 sandbox；适配器禁用 `askUser`、不声明 elicitation，并以 ACP `cancelled` 结果答复 `session/request_permission`，MiniMax 将其视为拒绝。原生权限或问题请求都不会到达 Core：需要人工介入时通过 function 工具完成，Session 读取 [`requires_action`](./sessions-events.md#session-status)，由应用提交 function 结果。不要添加权限 profile、bubblewrap 包装器或原生 sandbox 设置；每种 Environment 来源都只有一条执行路径。资源路径属于操作员配置，而不是权限边界。
 
 网络准入遵循 [Restricted network](environments.md#restricted-network)。
 
diff --git a/contracts/agents-api/zh/index.md b/contracts/agents-api/zh/index.md
index 2099ed5d7..c93f781f1 100644
--- a/contracts/agents-api/zh/index.md
+++ b/contracts/agents-api/zh/index.md
@@ -1,7 +1,7 @@
 ---
 title: "Agents API 覆盖台账"
 source: contracts/agents-api/index.md
-source_hash: 39137ce659092855b8d5f236b7d0be615af2b9dab9f397c9cdcee243c24da23c
+source_hash: abca1a568c1d5b58a35e4c3b17a488ca8f9805fa114b13e6692c25699a77a7f8
 ---
 
 Core 旨在以下方固定版本为准支持完整的 OpenAI Agents API（[public API rule](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/AGENTS.md#public-api)）。本台账记录 Core 对各项资源实现了哪些内容、哪些契约保存其详细信息，并列出相对于 OpenAI 服务的所有已知差异和所有未解决缺口。[API namespaces and credentials](../../../docs/zh/api/index.md) 说明谁调用哪些 API；[Agents API guide](../../../docs/zh/api/public-agent-api.md) 介绍使用方法。
@@ -11,10 +11,19 @@ Core 旨在以下方固定版本为准支持完整的 OpenAI Agents API（[publi
 | 文件 | 内容 |
 | --- | --- |
 | [upstream.json](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/contracts/agents-api/upstream.json) | 固定版本：提交 `d7c41ef` 时的 [openai-python](https://github.com/openai/openai-python/tree/d7c41efee1b0802b79f3f88a678ef2052b06e9ce/src/openai/resources/beta/agents) 3.13.0；资源位于 `beta/agents` 下；Beta 标头为 `agents=v1` |
-| [upstream-routes.json](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/contracts/agents-api/upstream-routes.json)、[upstream-fields.json](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/contracts/agents-api/upstream-fields.json) | 58 组方法与路径及其官方字段：`beta/agents` 下的 42 个操作、5 个 Files 操作和 11 个 Skills 操作。`scripts/extract-agents-api-upstream.py` 从固定版本的 SDK 中提取这些内容；安装该 SDK 后运行此脚本 |
-| [openapi.yaml](../openapi.yaml) | Core 的公共架构，由 `make openapi` 根据 `services/core/internal/api/` 中的路由注解以及 [`v1/`](https://github.com/MiniMax-AI/OpenAgentCore/tree/main/contracts/agents-api/v1) 中的传输类型生成 |
+| [upstream/openapi.json](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/contracts/agents-api/upstream/openapi.json) | 未修改的官方 OpenAPI 3.1，固定提交为 `046a2a0f325bf11f97966f2729219f27281ba71e`，发布于 2026-09-10。其中 58 个 Agents、Vaults、Files 和 Skills 操作与固定 SDK 的路由集合一致。`upstream.json` 记录 SHA-256 校验和 |
+| [upstream-routes.json](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/contracts/agents-api/upstream-routes.json) | 从官方 schema 生成的标准化方法和路径清单 |
+| [openapi.yaml](../openapi.yaml) | 官方公共契约，并在 Agent 和 Session 请求及响应对象上加入 Core 的 `x_agents_core` 扩展 |
+| [go-bindings.json](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/contracts/agents-api/go-bindings.json) | Go 名称、字段表示、编码顺序和存储投影；不定义官方字段集合、枚举或约束 |
+
+运行 `make openapi` 重新生成公共 Go 类型、路由清单和三个 OpenAPI 文档。`scripts/generate-public-api.py` 读取仓库内经过校验和验证的官方源文件，无需网络。它选择 Agents、Vaults、Files 和 Skills，并跟随 schema 引用，保留联合类型、可空性、必填字段和约束。Core 在 `v1/` 中的扩展类型继续由 Go 定义，在生成时加入公共 schema。内部 `/core/v1` 和 `/api/v1` 文档由处理函数注解生成。`make check-openapi` 检查生成结果是否最新并测试生成器；`make check-go` 也会运行此检查。
+
+公共契约是官方 API 加上 Core 扩展。标准字段生成到 `v1/official.gen.go`；`go-bindings.json` 只列出 Core 使用的类型，仅在已有存储或自定义 JSON 编码需要时覆盖 Go 表示或字段顺序。未覆盖的字段遵循官方 schema，相同结构复用同一个 Go 类型。部分带判别字段的联合类型也从 schema 生成 JSON 序列化代码，保留每个分支必需的可空字段。其他联合类型序列化、请求准入和状态转换仍由实现代码负责。契约测试验证公共 schema 保留官方定义、扩展位于 `x_agents_core` 中，且所有文档与注册路由一致。官方客户端和原始 HTTP 测试验证行为。生成 schema 不代表某个尚未实现的功能已经得到验证；下方缺口仍然适用。升级上游时，在比对和兼容性测试后一起更新 OpenAPI 和 SDK 固定版本。
+
+官方源文件与已有服务存在以下已记录的差异：Agents 鉴权错误的 `code` 可以为 null；Files 空页的 `first_id` 和 `last_id` 为 null；File 资源的 `expires_at` 和 `status_details` 可以为 null。源文件将这些字段声明为非空。官方客户端响应验证器只对这些指定字段允许 null，其余部分按 OpenAPI 3.1 响应 schema 验证。源文件中的 Files 和 Skills 操作未声明错误响应，因此这些错误体使用上游共享的 `ErrorResponse` schema。[传输语义](wire-semantics.md)和原始 HTTP 测试验证服务行为；发布的 schema 保留官方定义。
+
+Go 输入投影排除 `packages.system`，保留下方记录的明确拒绝行为。生成过程不会启用尚未支持的操作，也不会改变已存储安装配置的验证。
 
-契约测试确保 Core 符合固定版本：路由器和 `openapi.yaml` 提供的路由与固定版本完全一致（`services/core/internal/api/routing_test.go`、`v1/upstream_contract_test.go`），每个查询参数和字段都采用官方定义，而 Core 专有字段仅位于 Agents 和 Sessions 内部的 `x_agents_core` 中。Swagger 2.0 无法表达字符串或数组联合类型，因此 `openapi.yaml` 不对 Session 的 `input` 和函数结果的 `output` 施加约束；这些类型由固定版本的类型定义和 Core 的校验逻辑确定。晚于该固定版本的操作和字段需等待协议升级。
 
 各项状态的证据必须来自固定版本的官方 SDK，以及针对运行中服务发出的原始 HTTP 请求，正如 [CONTRIBUTING](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/CONTRIBUTING.md#compatibility-evidence) 所要求。
 
diff --git a/deploy/README.md b/deploy/README.md
index 716971334..20a61d2e4 100644
--- a/deploy/README.md
+++ b/deploy/README.md
@@ -2,18 +2,18 @@
 
 | Path | Contents |
 | --- | --- |
-| `install.sh` | Host installer published with each release |
+| `install.sh`, `install.ps1` | Native command launchers published with each release |
 | `compose/` | Compose template and its tests |
 | `distribution/` | Image Dockerfiles |
 | `node/` | [Node installer](node/README.md), packaged as `node-install.pyz` |
 
 ## Installation
 
-`install.sh` downloads its release's `compose.yaml`, checks it against `compose-sha256sums.txt`, writes `.env`, and starts Compose. Core applies database migrations when it starts. The host needs Linux amd64 and Docker Compose 2.26 or newer. [Configuration](../docs/configuration.md) owns the installation layout and settings.
+`install.sh` and `install.ps1` select a native `oac` release binary, verify its checksum and invoke `oac install`. That Go command owns the same installation lifecycle on Linux, macOS and Windows: validate Docker, verify release configuration, prepare `.env` and the host command, pull images, publish the installation directory, initialize the data volume and start Compose. [Installation](../docs/getting-started/install.md#prerequisites) owns platform prerequisites; [Configuration](../docs/configuration.md) owns settings and storage.
 
-The Core installer validates downloads and Compose in the private sibling `<install-dir>.staging` directory, and pulls all images before publishing the installation directory. A retry clears leftover staging only when its atomically created ownership link names this installation, including after the previous process was killed. An unrecognized nonempty staging directory is preserved. The staging log moves with the configuration and is removed on normal exit. Once published, failures retain configuration, containers and data. A retry verifies and starts that saved installation without replacing its Compose file, cached images or existing containers. Missing images are downloaded explicitly; Compose never pulls images implicitly. It refuses unrelated nonempty directories. `<install-dir>.install.lock` serializes directory preparation; `.oac.lock` serializes service changes with mutating `oac` commands. Both lock files remain after exit. Download failures have bounded retries and timeouts; service startup failures print Compose status and recent logs.
+Preparation happens in `<install-dir>.staging`. On entry, the installer removes an empty stage or one with the empty ownership directory `.oac-installer-<hash of the installation path>`; it preserves unrecognized directories. Ordinary failures remove owned staging immediately. The ownership marker is created atomically before downloading files. A killed process leaves staging for the next attempt. Publication happens only after downloads, checks and pulls succeed. Later failures preserve saved configuration, containers and the Docker data volume. Retries reuse those settings and cached images, pull missing images and start services with `--pull never --no-recreate`. `<install-dir>.lock` is a persistent lock directory shared by installation and mutating operator commands; the existing `runtimefs` platform adapter owns locking.
 
-`oac` is a Go command (`services/core/cmd/oac`) in the Core image and the ingress image. The host copy implements `apply`, `core-key` and `rotate-core-key`; `core-key --show` runs `oac-web core-key` in the Web container. Start, stop, logs and removal are `docker compose`. `apply` runs `oac-core check-config` before recreating services. The ingress image runs data initialization as `oac init`, verifies and copies its bundled node metadata without network access, and contains no Python. No service receives a Docker socket. Initialization writes structured logs to stderr for directory preparation, lock acquisition, existing-installation verification, bundled metadata verification and publication, credential generation or reuse, and receipt persistence. Each step records its start and completion; failures identify the current step, and completion records elapsed milliseconds. Credential values and digests are never logged. View these logs with `docker compose logs --timestamps init`.
+The host `oac` command also implements `apply`, `core-key` and `rotate-core-key`. `apply` checks Core configuration before recreating services. Reading the key executes `oac-web core-key` in Web. Rotation runs in the initialization container, where Linux file ownership is identical on every host, then restarts Core and Web. Start, stop, logs and removal use `docker compose`. The initialization image verifies and copies bundled node metadata without network access. Its receipt authenticates immutable metadata and credentials; the operator-rotatable Core key and its digest remain mutable. No service receives a Docker socket. Initialization emits structured step logs without credential values; view them with `docker compose logs --timestamps init`.
 
 Web serves the console and forwards `/v1` and `/api/v1` to Core, so it is the only published service. HTTPS is terminated by the operator's reverse proxy or hosting platform, which routes to `web:8080`; `OAC_PUBLIC_URL` records that origin.
 
diff --git a/deploy/compose/compose.yaml b/deploy/compose/compose.yaml
index 21ecceea9..6fe45a4db 100644
--- a/deploy/compose/compose.yaml
+++ b/deploy/compose/compose.yaml
@@ -1,24 +1,23 @@
 # Release template. The publisher pins the initialization image to this release.
 # Core and Web default to latest; OAC_IMAGE_* selects another reference.
-# Data is bind-mounted from ${OAC_DATA_DIR:-./data}.
+# Docker owns data permissions on every host platform.
 x-ingress-image: &ingress-image ${OAC_IMAGE_INGRESS:-__OAC_INIT_IMAGE__}
 services:
   init:
     image: *ingress-image
-    platform: linux/amd64
     restart: "no"
     security_opt: [no-new-privileges:true]
     command: [/usr/local/bin/oac, init]
     environment:
       OAC_REVISION: __OAC_REVISION__
     volumes:
-      - type: bind
-        source: ${OAC_DATA_DIR:-./data}
+      - type: volume
+        source: data
         target: /data
+        volume: {nocopy: true}
 
   database:
     image: postgres:16-alpine
-    platform: linux/amd64
     restart: unless-stopped
     depends_on:
       init: {condition: service_completed_successfully}
@@ -27,12 +26,14 @@ services:
       POSTGRES_DB: agents_api
       POSTGRES_PASSWORD_FILE: /run/database/password
     volumes:
-      - type: bind
-        source: ${OAC_DATA_DIR:-./data}/database
+      - type: volume
+        source: data
         target: /var/lib/postgresql/data
-      - type: bind
-        source: ${OAC_DATA_DIR:-./data}/secrets/database
+        volume: {nocopy: true, subpath: database}
+      - type: volume
+        source: data
         target: /run/database
+        volume: {nocopy: true, subpath: secrets/database}
         read_only: true
     healthcheck:
       test: [CMD-SHELL, "pg_isready -h 127.0.0.1 -U agents_api -d agents_api"]
@@ -42,7 +43,6 @@ services:
 
   core:
     image: ${OAC_IMAGE_CORE:-ghcr.io/minimax-ai/openagentcore/core:latest}
-    platform: linux/amd64
     user: "65532:65532"
     restart: unless-stopped
     read_only: true
@@ -70,23 +70,28 @@ services:
       OAC_LOG_ADD_SOURCE: ${OAC_LOG_ADD_SOURCE:-}
       OAC_HISTORY_SETTINGS_FILE: ${OAC_HISTORY_SETTINGS_FILE:-}
     volumes:
-      - type: bind
-        source: ${OAC_DATA_DIR:-./data}/secrets/core
+      - type: volume
+        source: data
         target: /run/oac
+        volume: {nocopy: true, subpath: secrets/core}
         read_only: true
-      - type: bind
-        source: ${OAC_DATA_DIR:-./data}/secrets/database
+      - type: volume
+        source: data
         target: /run/database
+        volume: {nocopy: true, subpath: secrets/database}
         read_only: true
-      - type: bind
-        source: ${OAC_DATA_DIR:-./data}/state
+      - type: volume
+        source: data
         target: /state
+        volume: {nocopy: true, subpath: state}
 
   web:
     ports:
-      - "${OAC_HOST:-127.0.0.1}:${OAC_WEB_PORT:-8080}:8080"
+      - target: 8080
+        published: "${OAC_WEB_PORT:-8080}"
+        host_ip: "${OAC_HOST:-127.0.0.1}"
+        protocol: tcp
     image: ${OAC_IMAGE_WEB:-ghcr.io/minimax-ai/openagentcore/web:latest}
-    platform: linux/amd64
     user: "65532:65532"
     restart: unless-stopped
     read_only: true
@@ -102,16 +107,21 @@ services:
       OAC_LOG_FORMAT: ${OAC_LOG_FORMAT:-}
       OAC_LOG_ADD_SOURCE: ${OAC_LOG_ADD_SOURCE:-}
     volumes:
-      - type: bind
-        source: ${OAC_DATA_DIR:-./data}/secrets/web
+      - type: volume
+        source: data
         target: /run/oac
+        volume: {nocopy: true, subpath: secrets/web}
         read_only: true
-      - type: bind
-        source: ${OAC_DATA_DIR:-./data}/node-payload
+      - type: volume
+        source: data
         target: /node-payload
+        volume: {nocopy: true, subpath: node-payload}
         read_only: true
     healthcheck:
       test: [CMD, /usr/local/bin/oac-web, healthcheck]
       interval: 5s
       timeout: 10s
       retries: 30
+
+volumes:
+  data:
diff --git a/deploy/compose/test_compose.py b/deploy/compose/test_compose.py
index 11f666e15..ce428f89a 100644
--- a/deploy/compose/test_compose.py
+++ b/deploy/compose/test_compose.py
@@ -61,7 +61,9 @@ def test_compose_uses_private_services_and_ordered_initialization(self):
             self.assertTrue(service['image'].endswith(':latest') or service['image'] == 'postgres:16-alpine' or service['image'].endswith('@sha256:' + 'e' * 64))
             for volume in service.get('volumes', []):
                 self.assertNotIn('docker.sock', json.dumps(volume))
-                self.assertEqual(volume['type'], 'bind')
+                self.assertEqual(volume['type'], 'volume')
+                self.assertEqual(volume['source'], 'data')
+            self.assertNotIn('platform', service)
         self.assertEqual({v['target'] for v in services['web']['volumes']}, {'/run/oac', '/node-payload'})
         self.assertIsNone(services['core']['command'])
         self.assertNotIn('OAC_WEB_INSTALLATION_SOCKET', services['web']['environment'])
@@ -95,6 +97,12 @@ def ports(config):
             ['docker', 'compose', '--env-file', os.devnull, '-f', str(self.compose_file),
              'config', '--format', 'json'], env=env))
         self.assertEqual(ports(configured), {'web': [('0.0.0.0', '9080')]})
+        env['OAC_HOST'] = '::1'
+        configured = json.loads(subprocess.check_output(
+            ['docker', 'compose', '--env-file', os.devnull, '-f', str(self.compose_file),
+             'config', '--format', 'json'], env=env))
+        self.assertEqual(ports(configured), {'web': [('::1', '9080')]})
+
 
     def test_platform_network_injection_keeps_the_file_valid(self):
         # Dokploy isolated deployments attach a project network to every service.
diff --git a/deploy/install.dev.sh b/deploy/install.dev.sh
index eada59aa3..7a3fb5135 100755
--- a/deploy/install.dev.sh
+++ b/deploy/install.dev.sh
@@ -47,8 +47,7 @@ if [[ "$install_dir" != /* ]]; then
   exit 1
 fi
 
-mkdir -p "$install_dir/data"
-chmod 700 "$install_dir/data"
+mkdir -p "$install_dir"
 build="$install_dir/image-build"
 rm -rf "$build"
 mkdir -p "$build"
@@ -115,7 +114,6 @@ PY
 umask 077
 cat >"$install_dir/.env" <<EOF
 COMPOSE_PROJECT_NAME=oac-local
-OAC_DATA_DIR=$install_dir/data
 OAC_HOST=$host_address
 OAC_WEB_PORT=$web_port
 OAC_IMAGE_CORE=$tag/core:dev
diff --git a/deploy/install.ps1 b/deploy/install.ps1
new file mode 100644
index 000000000..02d14975b
--- /dev/null
+++ b/deploy/install.ps1
@@ -0,0 +1,31 @@
+# The same native oac command owns installation on Windows.
+$ErrorActionPreference = 'Stop'
+$installArgs = $args
+$version = 'latest'
+for ($i = 0; $i -lt $installArgs.Count; $i++) {
+    if ($installArgs[$i] -eq '--version') {
+        if ($i + 1 -ge $installArgs.Count) { throw 'Missing release tag' }
+        $version = $installArgs[$i + 1]
+    }
+}
+$architecture = [System.Runtime.InteropServices.RuntimeInformation]::OSArchitecture.ToString().ToLowerInvariant()
+if ($architecture -ne 'x64') { throw 'Windows x64 is required.' }
+$repository = $env:OAC_REPOSITORY
+if (-not $repository) { $repository = 'MiniMax-AI/OpenAgentCore' }
+$base = "https://github.com/$repository/releases/latest/download"
+if ($version -ne 'latest') { $base = "https://github.com/$repository/releases/download/$version" }
+$directory = Join-Path ([IO.Path]::GetTempPath()) ([Guid]::NewGuid().ToString())
+New-Item -ItemType Directory -Path $directory | Out-Null
+try {
+    $asset = 'oac-windows-amd64.exe'
+    foreach ($name in @($asset, "$asset.sha256")) {
+        Invoke-WebRequest -UseBasicParsing -Uri "$base/$name" -OutFile (Join-Path $directory $name)
+    }
+    $binary = Join-Path $directory $asset
+    $actual = (Get-FileHash -Algorithm SHA256 $binary).Hash.ToLowerInvariant() + "  $asset"
+    if ($actual -cne (Get-Content -Raw (Join-Path $directory "$asset.sha256")).Trim()) { throw 'Installer checksum mismatch.' }
+    & $binary install @installArgs
+    if ($LASTEXITCODE -ne 0) { throw "Installation failed (exit $LASTEXITCODE). Fix the reported error and rerun." }
+} finally {
+    Remove-Item -Recurse -Force $directory
+}
diff --git a/deploy/install.sh b/deploy/install.sh
index 3746122fd..58ef0226c 100755
--- a/deploy/install.sh
+++ b/deploy/install.sh
@@ -1,230 +1,25 @@
 #!/usr/bin/env bash
-# Install Core and Web from one release's Compose file. The host needs Docker.
+# The native oac command owns installation on every platform.
 set -euo pipefail
-
-repository="${OAC_REPOSITORY:-MiniMax-AI/OpenAgentCore}"
-version="latest"
-install_dir="${OAC_INSTALL_DIR_DEFAULT:-$HOME/.oac/core}"
-public_url=""
-host_address="0.0.0.0"
-web_port="8080"
-stage=""
-published=0
-
-usage() {
-  cat <<'EOF'
-Usage: install.sh [--version TAG] [--install-dir DIR] [--public-url URL]
-                  [--host ADDRESS] [--web-port PORT]
-
-Installs Core, Web and PostgreSQL, and publishes Web on --web-port. Without
---public-url, a host published on all addresses with a private-network address
-is reached at http://<that address>:<web port>; otherwise only from this host.
-HTTPS is terminated by your reverse proxy or hosting platform.
-EOF
-}
-
+case "$(uname -s)" in Linux) os=linux;; Darwin) os=darwin;; *) echo 'Use install.ps1 on Windows.' >&2; exit 1;; esac
+case "$(uname -m)" in x86_64) arch=amd64;; arm64|aarch64) arch=arm64;; *) echo 'Unsupported CPU architecture.' >&2; exit 1;; esac
+version=latest
+args=("$@")
 while [[ $# -gt 0 ]]; do
-  case "$1" in
-    --version) version="${2:?}"; shift 2 ;;
-    --install-dir) install_dir="${2:?}"; shift 2 ;;
-    --public-url) public_url="${2:?}"; shift 2 ;;
-    --host) host_address="${2:?}"; shift 2 ;;
-    --web-port) web_port="${2:?}"; shift 2 ;;
-    -h|--help) usage; exit 0 ;;
-    *) echo "Unknown argument: $1" >&2; usage >&2; exit 1 ;;
-  esac
+  case "$1" in --version) version="${2:?Missing release tag}"; shift 2;; *) shift;; esac
 done
-
-if [[ "$(uname -s)" != Linux || "$(uname -m)" != x86_64 ]]; then
-  echo "Core installs on Linux amd64." >&2
-  exit 1
-fi
-fail() { printf '%s\n' "$*" >&2; exit 1; }
-for tool in docker curl sha256sum flock readlink od sed awk grep; do
-  command -v "$tool" >/dev/null || fail "Required command missing: $tool. Install it and rerun this command. Docker needs Compose 2.26 or newer."
-done
-compose_version="$(docker compose version --short 2>/dev/null | sed 's/^v//' || true)"
-major="${compose_version%%.*}"
-minor="${compose_version#*.}"
-minor="${minor%%.*}"
-if [[ ! "$major" =~ ^[0-9]+$ || ! "$minor" =~ ^[0-9]+$ ]] || (( major < 2 || (major == 2 && minor < 26) )); then
-  fail "Docker Compose 2.26 or newer is required (found ${compose_version:-none})."
-fi
-docker info >/dev/null 2>&1 || fail "Cannot reach Docker. Start Docker and check this account's access, then rerun."
-[[ "$install_dir" == /* && "$install_dir" != / ]] || fail "--install-dir must be an absolute directory other than /."
-# These values are written as literal dotenv strings, never shell commands.
-for value in "$install_dir" "$public_url" "$host_address" "$version"; do
-  [[ "$value" != *$'\n'* && "$value" != *$'\r'* && "$value" != *"'"* && "$value" != *\\* ]] || fail "Installation options cannot contain newlines, quotes or backslashes."
-done
-[[ "$web_port" =~ ^[0-9]{1,5}$ ]] && (( 10#$web_port >= 1 && 10#$web_port <= 65535 )) || fail "--web-port must be between 1 and 65535."
-[[ ! -L "$install_dir" ]] || fail "Installation directory must not be a symbolic link."
-[[ ! -e "$install_dir" || -d "$install_dir" ]] || fail "Installation path must be a directory."
-case "$(basename "$install_dir")" in .|..) fail "--install-dir must name the installation directory, not . or ...";; esac
+base="https://github.com/${OAC_REPOSITORY:-MiniMax-AI/OpenAgentCore}/releases/latest/download"
+if [[ "$version" != latest ]]; then base="https://github.com/${OAC_REPOSITORY:-MiniMax-AI/OpenAgentCore}/releases/download/$version"; fi
 umask 077
-parent="$(dirname "$install_dir")"
-mkdir -p "$parent"
-parent="$(cd "$parent" && pwd -P)"
-install_dir="$parent/$(basename "$install_dir")"
-lock="$install_dir.install.lock"
-[[ ! -L "$lock" && ( ! -e "$lock" || ( -f "$lock" && -O "$lock" ) ) ]] || fail "Invalid installation lock: $lock"
-exec 9>>"$lock"
-flock -n 9 || fail "Another installation is using this directory. Wait for it to finish and rerun."
-stage="$install_dir.staging"
-[[ ! -L "$stage" && ( ! -e "$stage" || ( -d "$stage" && -O "$stage" ) ) ]] || fail "Invalid installation staging directory: $stage"
-if [[ -d "$stage" && -n "$(ls -A "$stage")" ]]; then
-  [[ -L "$stage/.oac-installer" && "$(readlink "$stage/.oac-installer")" == "$install_dir" ]] || fail "Unrecognized staging directory; preserve it and choose another --install-dir: $stage"
-fi
-rm -rf "$stage"
-mkdir "$stage"
-ln -s "$install_dir" "$stage/.oac-installer"
-log="$stage/install.log"
-: >"$log"
-cleanup() {
-  local status=$?
-  trap - EXIT
-  if [[ "$status" != 0 && "$published" == 1 ]]; then
-    printf '\nInstallation and data retained at %s.\n' "$install_dir" >&2
-    (cd "$install_dir" && docker compose ps --all && docker compose logs --no-color --tail 50) >&2 || true
-    printf 'Fix the reported problem, then rerun install.sh --install-dir %q.\n' "$install_dir" >&2
-  fi
-  [[ -z "$stage" ]] || rm -rf "$stage"
-  rm -f "$log"
-  exit "$status"
-}
-trap cleanup EXIT
-trap 'exit 130' INT
-trap 'exit 143' TERM HUP
-
-# step DESCRIPTION COMMAND... prints the command's output only when it fails.
-step() {
-  printf '%s... ' "$1"
-  shift
-  if "$@" >"$log" 2>&1; then echo done; else echo failed; cat "$log" >&2; return 1; fi
-}
-
-resume=0
-if [[ -e "$install_dir" && -n "$(ls -A "$install_dir")" ]]; then
-  for file in compose.yaml compose-sha256sums.txt .env; do
-    [[ -f "$install_dir/$file" && ! -L "$install_dir/$file" ]] || fail "Directory is not a complete Core installation: $install_dir. Preserve it and choose another directory."
-  done
-  resume=1
-  published=1
-fi
-
-port_busy() {
-  local port="$1"
-  if command -v ss >/dev/null; then
-    if ss -ltn | awk '{print $4}' | grep -Eq "(^|:|\\])${port}$"; then
-      return 0
-    fi
-    return 1
-  fi
-  (echo >/dev/tcp/127.0.0.1/"$port") >/dev/null 2>&1
-}
-if [[ "$resume" == 0 ]] && port_busy "$web_port"; then fail "Port $web_port is already in use. Choose another with --web-port."; fi
-asset_base="https://github.com/${repository}/releases/latest/download"
-if [[ "$version" != latest ]]; then
-  asset_base="https://github.com/${repository}/releases/download/${version}"
-fi
-
-# The source address of this host's default route, when it is a private one.
-private_address() {
-  command -v ip >/dev/null || return 0
-  ip -4 route get 1.1.1.1 2>/dev/null | sed -n 's/.* src \([0-9.]*\).*/\1/p' |
-    grep -E '^(10\.|192\.168\.|172\.(1[6-9]|2[0-9]|3[01])\.)' || true
-}
-local_only=0
-if [[ -z "$public_url" && "$host_address" == 0.0.0.0 ]]; then
-  address="$(private_address)"
-  if [[ -n "$address" ]]; then public_url="http://$address:$web_port"; fi
-fi
-if [[ -z "$public_url" ]]; then public_url="http://localhost:$web_port"; local_only=1; fi
-
-if [[ "$resume" == 0 ]]; then
-  # Prepare configuration privately until downloads and image pulls succeed.
-  # Before publication only this invocation's private staging directory is removed.
-  download() {
-    curl --fail --silent --show-error --location --proto '=https' --proto-redir '=https' \
-      --connect-timeout 15 --max-time 120 --retry 2 --retry-connrefused --retry-delay 1 \
-      --max-filesize 1048576 "$asset_base/$1" --output "$stage/$1"
-  }
-  step "Downloading release checksums" download compose-sha256sums.txt
-  step "Downloading Compose configuration" download compose.yaml
-  {
-    echo "COMPOSE_PROJECT_NAME=oac-$(od -An -N5 -tx1 /dev/urandom | tr -d ' \n')"
-    printf "OAC_INSTALL_DIR='%s'\nOAC_HOST='%s'\nOAC_WEB_PORT='%s'\nOAC_PUBLIC_URL='%s'\n" "$install_dir" "$host_address" "$web_port" "$public_url"
-  } >"$stage/.env"
-fi
-
-if [[ "$resume" == 0 ]]; then cd "$stage"; else cd "$install_dir"; fi
-[[ ! -L .oac.lock && ( ! -e .oac.lock || ( -f .oac.lock && -O .oac.lock ) ) ]] || fail "Invalid installation lock: $install_dir/.oac.lock"
-exec 8>>.oac.lock
-flock -n 8 || fail "Another oac command is using this installation. Wait for it to finish and rerun."
-[[ ! -L install.log && ( ! -e install.log || ( -f install.log && -O install.log ) ) ]] || fail "Invalid installation log: $install_dir/install.log"
-log="$PWD/install.log"
-: >"$log"
-step "Verifying saved configuration" sha256sum --check --quiet compose-sha256sums.txt
-step "Checking Compose configuration" docker compose config --quiet
-if [[ "$resume" == 1 ]]; then
-  printf 'Using saved settings from .env; installation flags only apply to new directories. Existing data is preserved.\n'
-fi
-public_url="$(docker compose config --environment | sed -n 's/^OAC_PUBLIC_URL=//p')"
-local_only=0
-[[ "$public_url" != http://localhost:* && "$public_url" != http://127.0.0.1:* ]] || local_only=1
-pull_images() {
-  local images image
-  images="$(docker compose config --images)" || return
-  while IFS= read -r image; do
-    [[ -n "$image" ]] || continue
-    if [[ "$resume" == 0 ]] || ! docker image inspect "$image" >/dev/null 2>&1; then
-      docker pull --platform linux/amd64 "$image" || return
-    fi
-  done <<<"$images"
-}
-step "Checking and downloading images" pull_images
-if [[ "$resume" == 0 ]]; then
-  # An existing empty directory may be replaced, never a directory with user data.
-  if [[ -e "$install_dir" ]]; then rmdir "$install_dir"; fi
-  mv "$stage" "$install_dir"
-  stage=""
-  cd "$install_dir"
-  log="$install_dir/install.log"
-  published=1
-fi
-rm -f .oac-installer
-copy_cli() (
-  [[ ! -L ./oac.download ]] || fail "Temporary oac command must not be a symbolic link."
-  trap 'rm -f ./oac.download' EXIT
-  docker compose create --pull never --no-recreate core &&
-    docker compose cp core:/usr/local/bin/oac ./oac.download &&
-    mv ./oac.download ./oac
-)
-if [[ ! -x ./oac ]]; then step "Installing the oac command" copy_cli; fi
-step "Starting services" docker compose up -d --wait --wait-timeout 180 --pull never --no-recreate
-if ! key="$(./oac core-key --show)"; then
-  fail "Services started, but the Core key could not be read. Inspect Web's logs and retry; data is preserved."
-fi
-
-sudo=""
-if [[ "$EUID" == 0 && -n "${SUDO_USER:-}" ]]; then sudo="sudo "; fi
-cat <<EOF
-
-OpenAgentCore is running.
-
-  Console   $public_url
-  Core key  $key
-
-Sign in to the console with the Core key, the administrator credential.
-${sudo}$install_dir/oac core-key --show prints it again.
-EOF
-if [[ "$local_only" == 1 ]]; then
-  cat <<EOF
-Only this host can open the console. To serve other machines, set
-OAC_PUBLIC_URL in $install_dir/.env, then run ${sudo}$install_dir/oac apply.
-EOF
-fi
-cat <<EOF
-
-Next, on System, set a default model and choose a sandbox backend, then add a
-node on Nodes.
-EOF
+temporary="$(mktemp -d)"
+trap 'rm -rf "$temporary"' EXIT
+asset="oac-$os-$arch"
+for name in "$asset" "$asset.sha256"; do
+  curl --fail --silent --show-error --location --proto '=https' --proto-redir '=https' \
+    --connect-timeout 15 --max-time 180 --retry 2 "$base/$name" --output "$temporary/$name"
+done
+cd "$temporary"
+if command -v sha256sum >/dev/null; then actual="$(sha256sum "$asset")"; else actual="$(shasum -a 256 "$asset")"; fi
+[[ "$actual" == "$(cat "$asset.sha256")" ]] || { echo 'Installer checksum mismatch.' >&2; exit 1; }
+chmod 700 "$asset"
+"./$asset" install "${args[@]}"
diff --git a/deploy/test_install.ps1 b/deploy/test_install.ps1
new file mode 100644
index 000000000..bed472823
--- /dev/null
+++ b/deploy/test_install.ps1
@@ -0,0 +1,34 @@
+# Exercise the actual launcher with a native oac binary and local release assets.
+param([Parameter(Mandatory=$true)][string]$Binary)
+$ErrorActionPreference = 'Stop'
+$testAssets = @{ Binary = $Binary; Corrupt = $false }
+function Invoke-WebRequest {
+    param([switch]$UseBasicParsing, [string]$Uri, [string]$OutFile)
+    if ($Uri.EndsWith('.sha256')) {
+        $digest = (Get-FileHash -Algorithm SHA256 $testAssets.Binary).Hash.ToLowerInvariant()
+        if ($testAssets.Corrupt) { $digest = '0' * 64 }
+        [IO.File]::WriteAllText($OutFile, "$digest  oac-windows-amd64.exe`n")
+    } else {
+        Copy-Item $testAssets.Binary $OutFile
+    }
+}
+& "$PSScriptRoot/install.ps1" --help
+
+$testAssets.Corrupt = $true
+$caught = $false
+try { & "$PSScriptRoot/install.ps1" --help }
+catch {
+    if ($_.Exception.Message -notlike '*checksum mismatch*') { throw }
+    $caught = $true
+}
+if (-not $caught) { throw 'A corrupt binary was executed.' }
+
+$testAssets.Corrupt = $false
+$caught = $false
+try { & "$PSScriptRoot/install.ps1" --unknown-option }
+catch {
+    if ($_.Exception.Message -notlike '*Installation failed*') { throw }
+    $caught = $true
+}
+if (-not $caught) { throw 'A failed native command was reported as successful.' }
+exit 0
diff --git a/deploy/test_install.py b/deploy/test_install.py
index f4bb80cdd..5b3a3ec05 100644
--- a/deploy/test_install.py
+++ b/deploy/test_install.py
@@ -1,294 +1,55 @@
-"""install.sh writes .env and starts Compose without host Python."""
+"""The POSIX launcher selects and verifies a binary; lifecycle tests live in oac."""
+import hashlib
 import os
-import fcntl
-import sys
 from pathlib import Path
-import stat
 import subprocess
 import tempfile
-import textwrap
 import unittest
 
-
-ROOT = Path(__file__).resolve().parents[1]
-INSTALL = ROOT / "deploy/install.sh"
-
-
-class InstallScriptTests(unittest.TestCase):
-    def install(self, root, *args, compose_up=0, docker_info=0, key_status=0, download_status=0, kill_download=False, kill_start=False, pull_status=0, kill_pull=False, file_limit=False, missing_image="", route="1.1.1.1 via 10.0.0.1 dev eth0 src 10.0.0.5 uid 0"):
-        bin_dir = root / "bin"
-        bin_dir.mkdir(exist_ok=True)
-        log = root / "docker.log"
-        self.write_executable(bin_dir / "docker", textwrap.dedent(f"""\
-            #!/bin/sh
-            [ {1 if file_limit else 0} -eq 1 ] || printf '%s\\n' "$*" >> {log}
-            if [ "$1" = info ]; then exit {docker_info}; fi
-            if [ "$1" = pull ]; then {'kill -KILL "$PPID"' if kill_pull else ':'}; exit {pull_status}; fi
-            if [ "$1" = image ] && [ "$2" = inspect ] && [ "$3" = "{missing_image}" ]; then exit 1; fi
-            if [ "$1" = compose ] && [ "$2" = config ] && [ "$3" = --images ]; then printf 'fixture-core:latest\\nfixture-web:latest\\n'; fi
-            if [ "$1" = compose ] && [ "$2" = logs ]; then echo service-diagnostic >&2; fi
-            if [ "$1" = compose ] && [ "$2" = config ] && [ "$3" = --environment ]; then sed "s/'//g" .env; fi
-            if [ "$1" = compose ] && [ "$2" = version ]; then printf 'v2.29.1\\n'; exit 0; fi
-            if [ "$1" = compose ] && [ "$2" = cp ]; then printf '#!/bin/sh\\necho oac_core_fixture\\nexit {key_status}\\n' > ./oac.download; chmod +x ./oac.download; exit 0; fi
-            if [ "$1" = compose ] && [ "$2" = up ]; then {'kill -KILL "$PPID"' if kill_start else ':'}; exit {compose_up}; fi
-            exit 0
-            """))
-        self.write_executable(bin_dir / "curl", textwrap.dedent(f"""\
-            #!/bin/sh
-            exit_status={download_status}
-            [ "$exit_status" = 0 ] || exit "$exit_status"
-            output=""
-            while [ $# -gt 0 ]; do
-              if [ "$1" = --output ]; then output="$2"; shift 2; continue; fi
-              shift
-            done
-            printf 'fixture\\n' > "$output"
-            {'kill -KILL "$PPID"' if kill_download else ':'}
-            """))
-        self.write_executable(bin_dir / "sha256sum", "#!/bin/sh\nexit 0\n")
-        self.write_executable(bin_dir / "uname", '#!/bin/sh\ncase "$1" in -s) echo Linux;; -m) echo x86_64;; esac\n')
-        self.write_executable(bin_dir / "flock", f'#!{sys.executable}\nimport fcntl, sys\ntry: fcntl.flock(int(sys.argv[-1]), fcntl.LOCK_EX | fcntl.LOCK_NB)\nexcept BlockingIOError: sys.exit(1)\n')
-        self.write_executable(bin_dir / "ss", "#!/bin/sh\nexit 0\n")
-        self.write_executable(bin_dir / "ip", f"#!/bin/sh\nprintf '%s\\n' '{route}'\n")
-        env = dict(os.environ, PATH=str(bin_dir) + os.pathsep + os.environ["PATH"], HOME=str(root))
-        command = ["bash", str(INSTALL), "--install-dir", str(root / "oac"), *args]
-        if file_limit:
-            command = ["bash", "-c", 'ulimit -f 0; exec "$@"', "--", *command]
-        completed = subprocess.run(command,
-                                   env=env, capture_output=True, text=True)
-        return completed, log.read_text() if log.exists() else ""
-
-    def test_a_failed_start_preserves_configuration_and_reports_service_logs(self):
-        with tempfile.TemporaryDirectory() as temporary:
-            root = Path(temporary)
-            completed, recorded = self.install(root, "--host", "127.0.0.1", "--web-port", "59991",
-                                               "--public-url", "https://core.example", compose_up=1)
-            self.assertNotEqual(completed.returncode, 0, completed.stderr)
-            self.assertTrue((root / "oac/.env").exists())
-            self.assertNotIn("compose down", recorded)
-            self.assertIn("service-diagnostic", completed.stderr)
-            self.assertIn("data retained", completed.stderr)
-            self.assertIn("pull --platform linux/amd64 fixture-core:latest", recorded)
-            self.assertIn("compose up -d --wait", recorded)
-            self.assertIn("compose logs", recorded, "a failed start must show the services' logs")
-
-    def test_the_private_address_is_the_default_public_url(self):
-        with tempfile.TemporaryDirectory() as temporary:
-            root = Path(temporary)
-            completed, _ = self.install(root)
-            self.assertEqual(completed.returncode, 0, completed.stderr)
-            self.assertIn("OAC_PUBLIC_URL='http://10.0.0.5:8080'\n", (root / "oac/.env").read_text())
-            self.assertIn("Console   http://10.0.0.5:8080", completed.stdout)
-            self.assertIn("Core key  oac_core_fixture", completed.stdout)
-            self.assertNotIn("Only this host", completed.stdout)
-
-    def test_without_a_private_address_only_this_host_reaches_web(self):
-        for args, route in ((["--web-port", "59992"], "1.1.1.1 dev eth0 src 203.0.113.5 uid 0"),
-                            (["--host", "127.0.0.1", "--web-port", "59992"], "1.1.1.1 dev eth0 src 10.0.0.5 uid 0")):
-            with self.subTest(args=args), tempfile.TemporaryDirectory() as temporary:
-                root = Path(temporary)
-                completed, _ = self.install(root, *args, route=route)
-                self.assertEqual(completed.returncode, 0, completed.stderr)
-                self.assertIn("OAC_PUBLIC_URL='http://localhost:59992'\n", (root / "oac/.env").read_text())
-                self.assertIn("Only this host can open the console", completed.stdout)
-
-    def test_env_holds_only_the_installation_choices(self):
-        with tempfile.TemporaryDirectory() as temporary:
-            root = Path(temporary)
-            completed, _ = self.install(root, "--public-url", "https://core.example")
-            self.assertEqual(completed.returncode, 0, completed.stderr)
-            env = dict((lambda pair: (pair[0], pair[1].strip("'")))(line.split("=", 1)) for line in (root / "oac/.env").read_text().splitlines())
-            self.assertEqual(env["OAC_PUBLIC_URL"], "https://core.example")
-            self.assertEqual(sorted(env), ["COMPOSE_PROJECT_NAME", "OAC_HOST", "OAC_INSTALL_DIR", "OAC_PUBLIC_URL", "OAC_WEB_PORT"])
-
-    def test_key_failure_never_removes_a_started_installation(self):
-        with tempfile.TemporaryDirectory() as temporary:
-            root = Path(temporary)
-            completed, recorded = self.install(root, key_status=1)
-            self.assertNotEqual(completed.returncode, 0)
-            self.assertTrue((root / "oac/.env").exists())
-            self.assertNotIn("compose down", recorded)
-            self.assertIn("Core key could not be read", completed.stderr)
-
-    def test_retry_reuses_saved_settings_and_keeps_data(self):
-        with tempfile.TemporaryDirectory() as temporary:
-            root = Path(temporary)
-            failed, _ = self.install(root, "--public-url", "https://core.example", compose_up=1)
-            self.assertNotEqual(failed.returncode, 0)
-            configuration = (root / "oac/.env").read_bytes()
-            data = root / "oac/data"
-            data.mkdir()
-            (data / "keep").write_text("user data")
-            (root / "docker.log").unlink()
-            completed, recorded = self.install(root, download_status=22)
-            self.assertEqual(completed.returncode, 0, completed.stderr)
-            self.assertEqual((root / "oac/.env").read_bytes(), configuration)
-            self.assertEqual((data / "keep").read_text(), "user data")
-            self.assertIn("Console   https://core.example", completed.stdout)
-            self.assertNotIn("pull --platform", recorded)
-            self.assertNotIn("Only this host", completed.stdout)
-
-    def test_retry_downloads_only_missing_images_and_prevents_implicit_updates(self):
-        with tempfile.TemporaryDirectory() as temporary:
-            root = Path(temporary)
-            failed, _ = self.install(root, compose_up=1)
-            self.assertNotEqual(failed.returncode, 0)
-            (root / "docker.log").unlink()
-            (root / "oac/oac").unlink()
-            completed, recorded = self.install(root, missing_image="fixture-web:latest")
-            self.assertEqual(completed.returncode, 0, completed.stderr)
-            self.assertNotIn("pull --platform linux/amd64 fixture-core:latest", recorded)
-            self.assertIn("pull --platform linux/amd64 fixture-web:latest", recorded)
-            for line in recorded.splitlines():
-                if line.startswith(("compose create", "compose up")):
-                    self.assertIn("--pull never", line)
-                    self.assertIn("--no-recreate", line)
-
-    def test_retry_after_file_size_limit_recovers_staging(self):
-        with tempfile.TemporaryDirectory() as temporary:
-            root = Path(temporary)
-            failed, _ = self.install(root, file_limit=True)
-            self.assertNotEqual(failed.returncode, 0)
-            self.assertIn("Downloading release checksums", failed.stdout)
-            completed, _ = self.install(root)
-            self.assertEqual(completed.returncode, 0, completed.stderr)
-            self.assertFalse((root / "oac.staging").exists())
-
-    def test_failed_initial_pull_never_adopts_old_cached_images_on_retry(self):
-        for kill in (False, True):
-            with self.subTest(kill=kill), tempfile.TemporaryDirectory() as temporary:
-                root = Path(temporary)
-                failed, _ = self.install(root, pull_status=1, kill_pull=kill)
-                self.assertNotEqual(failed.returncode, 0)
-                self.assertFalse((root / "oac").exists())
-                (root / "docker.log").unlink()
-                # Every image inspect succeeds: another installation cached old tags.
-                completed, recorded = self.install(root)
-                self.assertEqual(completed.returncode, 0, completed.stderr)
-                for image in ("fixture-core:latest", "fixture-web:latest"):
-                    self.assertIn("pull --platform linux/amd64 " + image, recorded)
-                self.assertFalse((root / "oac.staging").exists())
-
-    def test_invalid_port_and_unavailable_docker_fail_before_installation(self):
-        for args, status in [(["--web-port", "0"], 0), (["--web-port", "70000"], 0), ([], 1)]:
-            with self.subTest(args=args, status=status), tempfile.TemporaryDirectory() as temporary:
-                root = Path(temporary)
-                completed, recorded = self.install(root, *args, docker_info=status)
-                self.assertNotEqual(completed.returncode, 0)
-                self.assertFalse((root / "oac").exists())
-                self.assertNotIn("pull --platform", recorded)
-
-    def test_failed_download_leaves_no_installation_or_staging(self):
-        with tempfile.TemporaryDirectory() as temporary:
-            root = Path(temporary)
-            completed, recorded = self.install(root, download_status=22)
-            self.assertNotEqual(completed.returncode, 0)
-            self.assertFalse((root / "oac").exists())
-            self.assertFalse((root / "oac.staging").exists())
-            self.assertNotIn("compose down", recorded)
-
-    def test_retry_after_sigkill_cleans_unfinished_download(self):
-        with tempfile.TemporaryDirectory() as temporary:
-            root = Path(temporary)
-            killed, _ = self.install(root, kill_download=True)
-            self.assertEqual(killed.returncode, -9, killed.stderr)
-            self.assertTrue((root / "oac.staging").exists())
-            self.assertFalse((root / "oac").exists())
-            completed, _ = self.install(root)
-            self.assertEqual(completed.returncode, 0, completed.stderr)
-            self.assertFalse((root / "oac.staging").exists())
-            self.assertTrue((root / "oac/oac").exists())
-
-    def test_retry_after_start_sigkill_cleans_published_log(self):
-        with tempfile.TemporaryDirectory() as temporary:
-            root = Path(temporary)
-            killed, _ = self.install(root, kill_start=True)
-            self.assertEqual(killed.returncode, -9, killed.stderr)
-            self.assertTrue((root / "oac/install.log").exists())
-            completed, _ = self.install(root)
-            self.assertEqual(completed.returncode, 0, completed.stderr)
-            self.assertFalse((root / "oac/install.log").exists())
-            self.assertFalse((root / "oac.staging").exists())
-
-    def test_retry_clears_staging_from_an_interrupted_process(self):
-        with tempfile.TemporaryDirectory() as temporary:
-            root = Path(temporary)
-            staging = root / "oac.staging"
-            staging.mkdir()
-            (staging / ".oac-installer").symlink_to((root / "oac").resolve())
-            (staging / "partial").write_text("unfinished download")
-            completed, _ = self.install(root)
-            self.assertEqual(completed.returncode, 0, completed.stderr)
-            self.assertFalse(staging.exists())
-            self.assertFalse((root / "oac/partial").exists())
-
-    def test_unrecognized_staging_directory_is_never_deleted(self):
-        with tempfile.TemporaryDirectory() as temporary:
-            root = Path(temporary)
-            staging = root / "oac.staging"
-            staging.mkdir()
-            (staging / "keep").write_text("user data")
-            completed, recorded = self.install(root)
-            self.assertNotEqual(completed.returncode, 0)
-            self.assertIn("Unrecognized staging", completed.stderr)
-            self.assertEqual((staging / "keep").read_text(), "user data")
-            self.assertNotIn("compose up", recorded)
-
-    def test_existing_unrelated_directory_is_never_deleted(self):
-        with tempfile.TemporaryDirectory() as temporary:
-            root = Path(temporary)
-            (root / "oac").mkdir()
-            (root / "oac/keep").write_text("user data")
-            completed, recorded = self.install(root)
-            self.assertNotEqual(completed.returncode, 0)
-            self.assertEqual((root / "oac/keep").read_text(), "user data")
-            self.assertNotIn("compose down", recorded)
-
-    def test_another_installation_holds_the_lock(self):
-        with tempfile.TemporaryDirectory() as temporary:
-            root = Path(temporary)
-            with (root / "oac.install.lock").open("w") as lock:
-                fcntl.flock(lock, fcntl.LOCK_EX | fcntl.LOCK_NB)
-                completed, recorded = self.install(root)
-            self.assertNotEqual(completed.returncode, 0)
-            self.assertIn("Another installation", completed.stderr)
-            self.assertFalse((root / "oac").exists())
-            self.assertNotIn("pull --platform", recorded)
-
-    def test_retry_does_not_overlap_an_oac_mutation(self):
-        with tempfile.TemporaryDirectory() as temporary:
-            root = Path(temporary)
-            completed, _ = self.install(root)
-            self.assertEqual(completed.returncode, 0, completed.stderr)
-            (root / "docker.log").unlink()
-            with (root / "oac/.oac.lock").open("r+") as lock:
-                fcntl.flock(lock, fcntl.LOCK_EX | fcntl.LOCK_NB)
-                completed, recorded = self.install(root)
-            self.assertNotEqual(completed.returncode, 0)
-            self.assertIn("Another oac command", completed.stderr)
-            self.assertNotIn("compose up", recorded)
-
-    def test_rerun_does_not_silently_replace_settings(self):
-        with tempfile.TemporaryDirectory() as temporary:
-            root = Path(temporary)
-            completed, _ = self.install(root)
-            self.assertEqual(completed.returncode, 0, completed.stderr)
-            before = (root / "oac/.env").read_bytes()
-            completed, _ = self.install(root, "--web-port", "9000")
-            self.assertEqual(completed.returncode, 0, completed.stderr)
-            self.assertIn("Using saved settings", completed.stdout)
-            self.assertIn("only apply to new directories", completed.stdout)
-            self.assertEqual((root / "oac/.env").read_bytes(), before)
-
-    def test_help_does_not_need_docker(self):
-        help_text = subprocess.run(["bash", str(INSTALL), "--help"], capture_output=True, text=True, check=True)
-        self.assertIn("--web-port", help_text.stdout)
-        self.assertNotIn("--external-proxy", help_text.stdout)
-
-    def write_executable(self, path, text):
-        path.write_text(text)
-        path.chmod(path.stat().st_mode | stat.S_IEXEC)
-
-
-if __name__ == "__main__":
+SCRIPT = Path(__file__).with_name('install.sh').resolve()
+
+
+class LauncherTests(unittest.TestCase):
+    def run_launcher(self, system='Darwin', machine='arm64', corrupt=False):
+        with tempfile.TemporaryDirectory() as directory:
+            root = Path(directory)
+            binary = b'#!/bin/sh\nprintf "%s\\n" "$@"\n'
+            digest = hashlib.sha256(binary).hexdigest()
+            scripts = {
+                'uname': '#!/bin/sh\nif [ "$1" = -s ]; then echo ' + system + '; else echo ' + machine + '; fi\n',
+                'curl': '''#!/usr/bin/env python3
+import pathlib,sys
+args=sys.argv
+url=args[-3]; target=pathlib.Path(args[-1])
+asset=url.rsplit('/',1)[1]
+if asset.endswith('.sha256'):
+    target.write_text(DIGEST + '  ' + asset.removesuffix('.sha256') + '\\n')
+else:
+    target.write_bytes(BINARY)
+'''.replace('DIGEST', repr('0' * 64 if corrupt else digest)).replace('BINARY', repr(binary)),
+            }
+            for name, contents in scripts.items():
+                (root / name).write_text(contents); (root / name).chmod(0o700)
+            return subprocess.run(['bash', str(SCRIPT), '--install-dir', '/path with spaces/core', '--version', 'v1.2.3'],
+                                  env={**os.environ, 'PATH': str(root) + os.pathsep + os.environ['PATH']}, capture_output=True, text=True)
+
+    def test_linux_and_mac_share_argument_forwarding(self):
+        for system, machine in [('Linux', 'x86_64'), ('Linux', 'aarch64'), ('Darwin', 'arm64'), ('Darwin', 'x86_64')]:
+            with self.subTest(system=system, machine=machine):
+                result = self.run_launcher(system, machine)
+                self.assertEqual(result.returncode, 0, result.stderr)
+                self.assertEqual(result.stdout.splitlines(), ['install', '--install-dir', '/path with spaces/core', '--version', 'v1.2.3'])
+
+    def test_corrupt_binary_is_never_executed(self):
+        result = self.run_launcher(corrupt=True)
+        self.assertNotEqual(result.returncode, 0)
+        self.assertIn('checksum mismatch', result.stderr)
+        self.assertEqual(result.stdout, '')
+
+    def test_unsupported_host_fails_before_downloading(self):
+        result = self.run_launcher(system='FreeBSD')
+        self.assertNotEqual(result.returncode, 0)
+
+
+if __name__ == '__main__':
     unittest.main()
diff --git a/docs/configuration.md b/docs/configuration.md
index 3f22bda4e..5b0a63367 100644
--- a/docs/configuration.md
+++ b/docs/configuration.md
@@ -9,7 +9,7 @@ Every setting of a Core installation has exactly one home. There are two kinds:
 | [Process settings](#process-settings-configjson) | Public URL, ports, logging, harnesses, execution concurrency, audit retention, OAuth origins, Runtime history export | `.env` in the installation directory (default `~/.oac/core`) | Edit `.env`, then run `oac apply` | `oac apply` recreates the services that read the changed settings |
 | [Runtime settings](#runtime-settings-web) | Sandbox backend and size, nodes, Projects and keys, default models, executor credentials | Core's PostgreSQL database | Web, or the Core API (`/core/v1`) with the Core key | Saved without a Core restart; nodes prepare Runtime changes asynchronously |
 
-Web's **System** page shows the installation's addresses, the default models, the sandbox configuration and, under **Startup settings**, the process settings Core loaded. Secrets live in [`data/secrets/`](#installation-directory), one copy each. No configuration file defines Projects or API keys.
+Web's **System** page shows the installation's addresses, the default models, the sandbox configuration and, under **Startup settings**, the process settings Core loaded. Secrets live in [`secrets/`](#compose-installations), one copy each. No configuration file defines Projects or API keys.
 
 ## Process settings {#process-settings-configjson}
 
@@ -23,9 +23,8 @@ Installer flags in [installation options](./getting-started/install-options.md)
 
 1. It runs `oac-core check-config` with the `.env` you edited and changes nothing if a value is invalid.
 2. It runs `docker compose up -d --wait`. Compose recreates only the services whose configuration changed.
-3. If the check fails, no container is recreated. See [stop and restart](./getting-started/operations.md#stop-and-restart) for what a restart interrupts.
 
-`docker compose ps` shows the services. Domain state is `data/domain/status.json`.
+Use `docker compose ps` to check the services. See [stop and restart](./getting-started/operations.md#stop-and-restart) for what a restart interrupts.
 
 ### Changing the public URL {#changing-the-public-url}
 
@@ -44,7 +43,7 @@ To change it, point the reverse proxy at the new address first, then edit `OAC_P
 | Variable | Default | Meaning |
 | --- | --- | --- |
 | `OAC_PUBLIC_URL` | `http://localhost:8080` | Origin applications, nodes, sandboxes and self-hosted executors use. See [changing the public URL](#changing-the-public-url) |
-| `OAC_HOST` | `127.0.0.1` | Web bind address published by `compose.yaml`. `install.sh` sets `0.0.0.0` |
+| `OAC_HOST` | `127.0.0.1` | Web bind address published by `compose.yaml`. The installer sets `0.0.0.0` |
 | `OAC_WEB_PORT` | `8080` | Host port of Web |
 | `OAC_LOG_LEVEL` | `info` | `debug`, `info`, `warn` or `error` |
 | `OAC_LOG_FORMAT` | `auto` | `auto`, `text` or `json` |
@@ -81,7 +80,7 @@ Core approves a node's capacity when you generate its Add node command: **Sandbo
 
 ### Default models
 
-Set a default in **System** → **Default model configuration**, or use `PUT /core/v1/harnesses/{harness}/model-configuration`. Core encrypts provider keys with `secrets/credential.key` and never returns them. [Model execution](../contracts/agents-api/model-execution.md#deployment-defaults) owns the request fields and replacement rules, and [precedence](../contracts/agents-api/model-execution.md#saved-defaults-and-precedence) says which Sessions use a default.
+Set a default in **System** → **Default model configuration**, or use `PUT /core/v1/harnesses/{harness}/model-configuration`. Core encrypts provider keys with `secrets/core/credential.key` and never returns them. [Model execution](../contracts/agents-api/model-execution.md#deployment-defaults) owns the request fields and replacement rules, and [precedence](../contracts/agents-api/model-execution.md#saved-defaults-and-precedence) says which Sessions use a default.
 
 ## Compose installations
 
@@ -100,7 +99,7 @@ The initialization service generates secrets and the installation ID once, then
 
 Initialization prepares this directory; application services receive their secret directories read-only. `docker compose exec web oac-web core-key` prints the Core key to the operator terminal without writing it to container logs. Database passwords and credential encryption keys are never printed.
 
-`OAC_DATA_DIR` selects the directory and defaults to `./data` beside the Compose file. Preserve it together with that project's definition and public URL. Removing only the secret directories does not reset an installation; initialization refuses to start over an existing database. Core also binds the installation ID to its database. Runtime settings continue to live in [Core's database](#runtime-settings-web).
+The named Docker volume `<project>_data` contains these paths. Docker manages Linux ownership on every host; each service mounts only its required subdirectories. Preserve this volume together with the project definition and public URL. Removing only the secret directories does not reset an installation; initialization refuses to start over an existing database. Core also binds the installation ID to its database. Runtime settings continue to live in [Core's database](#runtime-settings-web).
 
 ## Docker node configuration
 
@@ -136,37 +135,31 @@ Never set `GODEBUG=http2debug` for the agent host. With it, Go's HTTP/2 implemen
 
 ## Installation directory
 
-The installer creates the installation directory, `~/.oac/core` by default, with mode `0700`. Secret files are `0600`.
+The installer creates `~/.oac/core` by default (`$HOME/.oac/core` on Windows). Its files contain process settings and the native operator command; persistent service data lives in the [Compose data volume](#compose-installations).
 
 | Path | Content | Changed by |
 | --- | --- | --- |
-| `.env` | [Process settings](#process-settings-configjson). The file you edit | You, then `oac apply` |
-| `compose.yaml` | The release's service definition. Do not edit them | The release |
-| `oac` | The [management command](./getting-started/operations.md#the-oac-command), copied from the Core image | The installer |
-| `data/secrets/web/core.key` | The [Core key](./getting-started/operations.md#core-key) | `oac rotate-core-key` |
-| `data/secrets/core/credential.key` | Encryption key for what Core stores sealed in the database | Nothing. Keep it with the database |
-| `data/secrets/core/core-key-digests.json` | SHA-256 of the Core key | `oac rotate-core-key` |
-| `data/secrets/database/password` | PostgreSQL password | Nothing. PostgreSQL reads it only when the database is created |
-| `data/database/` | PostgreSQL data | PostgreSQL |
-| `data/node-payload/` | Node files Web serves at `/node-install/` | Initialization |
-| `data/state/` | Private Provider state, including E2B receipts | Core |
-| `.oac.lock` | The installation lock | Mutating `oac` commands |
-
-The Compose project is named `oac-<10 hex digits>`. Its services are `init`, `database`, `core` and `web`. Core applies database migrations when it starts. `web` serves the console and forwards `/v1` and `/api/v1` to Core, and it is the only service with a published port, `OAC_WEB_PORT`. No service receives a Docker socket. Apart from Docker's storage, nothing is written outside the installation directory.
+| `.env` | Process settings and the stable Compose project name | You, then `oac apply` |
+| `compose.yaml`, `compose-sha256sums.txt` | Verified release service definition | The release |
+| `oac` (`oac.exe` on Windows) | Native management command | The installer |
+
+The sibling `<install-dir>.lock` directory remains for synchronization; `<install-dir>.staging` holds unpublished installation files. Neither contains service data. On Unix the installer creates private directories with mode `0700` and configuration files with mode `0600`.
+
+The Compose project is named `oac-<10 hex digits>`. Its services are `init`, `database`, `core` and `web`. Core applies database migrations when it starts. Web serves the console and forwards `/v1` and `/api/v1` to Core; it is the only service with a published port, `OAC_WEB_PORT`. No service receives a Docker socket.
 
 ## Appendix: Core environment without the installer
 
-Core reads only its environment. Compose interpolates `.env` into the service environment. Compose must be 2.26.0 or newer. If you run Core yourself, set these variables; see the [service guide](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/services/core/README.md).
+Core reads its process environment. Compose interpolates `.env` into it and mounts secrets at the container paths below. When running Core directly, set the file variables to absolute paths readable by the Core process; see the [service guide](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/services/core/README.md).
 
 | Variable | Set from |
 | --- | --- |
 | `OAC_PUBLIC_URL` | The public origin. Core derives the daemon WebSocket URL, the self-hosted `remote_url`, the hosted sandbox address and the deployment's read-only `core_url` from it, never from request headers. Without it, Core runs no Runtime gateway and executes no Sessions |
 | `OAC_ADDR` | The image sets `:8091`. Independently started Core defaults to `127.0.0.1:8091` when unset or empty |
 | `OAC_DATABASE_URL` | PostgreSQL without a password |
-| `OAC_DATABASE_PASSWORD_FILE` | `data/secrets/database/password`. The URL must then carry no password |
-| `OAC_CREDENTIAL_KEY_FILE` | `data/secrets/core/credential.key` |
-| `OAC_CORE_KEY_DIGESTS_FILE` | `data/secrets/core/core-key-digests.json`: a JSON array with the SHA-256 of the Core key |
-| `OAC_INSTALLATION_ID_FILE` | `data/secrets/core/installation.id`: the installation ID, a canonical UUID. It enables the sandbox deployment and node routes and requires `OAC_PUBLIC_URL` and `OAC_CORE_KEY_DIGESTS_FILE`. Core refuses an ID other than the one its database recorded |
+| `OAC_DATABASE_PASSWORD_FILE` | `/run/database/password`. The URL must then carry no password |
+| `OAC_CREDENTIAL_KEY_FILE` | `/run/oac/credential.key` |
+| `OAC_CORE_KEY_DIGESTS_FILE` | `/run/oac/core-key-digests.json`: a JSON array with the SHA-256 of the Core key |
+| `OAC_INSTALLATION_ID_FILE` | `/run/oac/installation.id`: the installation ID, a canonical UUID. It enables the sandbox deployment and node routes and requires `OAC_PUBLIC_URL` and `OAC_CORE_KEY_DIGESTS_FILE`. Core refuses an ID other than the one its database recorded |
 | `OAC_EXECUTION_CONCURRENCY`, `OAC_DEFAULT_HARNESS`, `OAC_HARNESSES`, `OAC_WRITE_AUDIT_RETENTION`, `OAC_OAUTH_TRUSTED_ORIGINS` | The matching [process settings](#settings). `oac-core check-config` validates them without starting Core |
 | `OAC_HISTORY_SETTINGS_FILE` | Optional Runtime history file. Sensitive; the installation report says only whether it is set |
 | `OAC_LOG_LEVEL`, `OAC_LOG_FORMAT`, `OAC_LOG_ADD_SOURCE` | Logging; Web reads the same three |
@@ -180,7 +173,7 @@ Invalid explicit OAuth trusted origins stop Core at startup. Entries must be HTT
 
 ## Appendix: Web environment without the installer
 
-Compose sets these for Web. Set them yourself only when you run the console without Compose. Of the installation's secrets, Web receives only `data/secrets/web/core.key`.
+Compose sets these for Web. Set them yourself only when you run the console without Compose. Compose mounts the data volume's `secrets/web/` at `/run/oac` and sets `OAC_WEB_CORE_KEY_FILE=/run/oac/core.key`.
 
 | Variable | Default | Meaning |
 | --- | --- | --- |
diff --git a/docs/development.md b/docs/development.md
index e7f6b5879..71d3c842a 100644
--- a/docs/development.md
+++ b/docs/development.md
@@ -101,7 +101,7 @@ Choose focused checks for the current diff and its directly affected behavior us
 | --- | --- |
 | Core handlers, persistence or clients | `make check-core` |
 | SQL queries | `make sqlc-generate`, inspect generated files, then `make check-sqlc` |
-| Handler annotations or API contract | `make openapi`, inspect all three namespace schemas |
+| Public schema, Core extensions or internal handler annotations | `make openapi`, `make check-openapi`; inspect generated types and all three namespace schemas |
 | Shared Runtime protocol | `make check-runtime-contract` |
 | Provider integration | `make check-sandbox-provider-contract` and the provider's native checks |
 | Claude SDK bridge and artifact | `make check-claude-sdk` |
diff --git a/docs/getting-started/install-options.md b/docs/getting-started/install-options.md
index 41c4e50e7..08cdd34e5 100644
--- a/docs/getting-started/install-options.md
+++ b/docs/getting-started/install-options.md
@@ -2,7 +2,7 @@
 title: "Installation options and advanced deployments"
 ---
 
-The [default installation](./install.md) needs no options. Use this page to run behind an existing reverse proxy or install without internet access.
+The [default installation](./install.md) needs no options. Use this page to set installation options, deploy with Compose or configure a reverse proxy.
 
 Pass options to the downloaded script:
 
@@ -10,11 +10,11 @@ Pass options to the downloaded script:
 ./install.sh --public-url https://core.example
 ```
 
-With the one-line command, append them after `bash -s --`. `--version TAG` selects a published release; otherwise the script selects the latest stable release and verifies each Compose file's SHA-256. A failed step stops installation without a success message.
+On Windows, download `install.ps1` and pass the same flags with `& ./install.ps1 --public-url https://core.example`. With the Unix one-line command, append them after `bash -s --`. `--version TAG` selects a published release; otherwise the script selects the latest stable release and verifies the native command and Compose files against their SHA-256 checksums.
 
 ## Docker Compose and hosting platforms
 
-Use the `compose.yaml` from a release with Docker Compose 2.26 or newer on Linux amd64. The release pins its initialization image and source revision in the [Compose template](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/deploy/compose/compose.yaml). Core and Web use the `latest` images, and PostgreSQL uses `postgres:16-alpine`. It starts PostgreSQL, Core and Web. Web forwards `/v1` and `/api/v1` to Core. Data is bind-mounted from a directory. The one-time initialization service generates random secrets there and prepares the node installer; Core applies database migrations when it starts. [Compose configuration](../configuration.md#compose-installations) owns the settings and the data directory.
+Use the `compose.yaml` from a release on any [supported Core host](./install.md#prerequisites). The release pins its initialization image and source revision in the [Compose template](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/deploy/compose/compose.yaml). Core and Web use the `latest` images, and PostgreSQL uses `postgres:16-alpine`. It starts PostgreSQL, Core and Web. Web forwards `/v1` and `/api/v1` to Core. Data lives in a named Docker volume. The one-time initialization service generates random secrets there and prepares the node installer; Core applies database migrations when it starts. [Compose configuration](../configuration.md#compose-installations) owns the settings and the data directory.
 
 For a local trial, download `compose.yaml` from a release into an empty directory, then run:
 
@@ -23,7 +23,7 @@ docker compose up -d --wait --wait-timeout 900
 docker compose exec web oac-web core-key
 ```
 
-`oac-web core-key` prints the generated Core key to your terminal without writing it to container logs. Open `http://localhost:8080` and use that key to sign in. All installation secrets are generated automatically; keep the same Compose project and its data directory when restarting.
+`oac-web core-key` prints the generated Core key to your terminal without writing it to container logs. Open `http://localhost:8080` and use that key to sign in. All installation secrets are generated automatically; keep the same Compose project and its data volume when restarting.
 
 The initialization image contains only the small node installation metadata alongside the initialization command. First startup verifies and copies that metadata without downloading the control archive or requiring access to GitHub Releases. Later starts verify the saved files. Container images still need to be pulled. An interrupted first initialization can be rerun; an existing database with missing installation secrets is refused.
 
@@ -41,7 +41,7 @@ On either platform, open its server terminal and run `docker compose ls` to find
 
 After signing in, choose the sandbox backend and add nodes using [Nodes](./nodes.md). The Compose stack deploys the control plane; execution machines remain separate.
 
-Stop with `docker compose stop` using the same files and environment. Back up the data directory together while the services are stopped. Follow the [installation version policy](./operations.md#installation-version-policy): a different release needs a new Compose project and a fresh data directory.
+Stop with `docker compose stop` using the same files and environment. Back up the data volume and configuration together while the services are stopped. Follow the [installation version policy](./operations.md#installation-version-policy): a different release needs a new Compose project and a fresh data volume.
 
 ## Process settings
 
@@ -60,7 +60,7 @@ These flags are written to `.env` once. After installation, edit that file and r
 
 | Option | Purpose |
 | --- | --- |
-| `--install-dir DIR` | Absolute installation directory; defaults to `~/.oac/core`. A new installation requires an empty or missing directory, or one holding an [installation that never started](./install.md#install) |
+| `--install-dir DIR` | Absolute installation directory; defaults to `~/.oac/core`. Use an empty or missing directory for a new installation, or an existing installation directory to [retry](./install.md#install) |
 
 Several installations can share a machine when they use distinct installation directories and ports. Use distinct IP addresses or a shared reverse proxy for more. Each installation has its own database, Core key and nodes.
 
@@ -131,4 +131,4 @@ The address changes whenever `cloudflared` restarts; nodes bound to the old addr
 
 ## Offline hosts
 
-This installer does not install from an offline bundle. It downloads Compose files and container images from the release.
+Core installation requires access to GitHub Releases and the container registries to download release files and images.
diff --git a/docs/getting-started/install.md b/docs/getting-started/install.md
index ea8fcced3..e254ba35a 100644
--- a/docs/getting-started/install.md
+++ b/docs/getting-started/install.md
@@ -2,7 +2,7 @@
 title: "Install Core and Web"
 ---
 
-One command installs Core, the Web console and PostgreSQL on a Linux host. Sign in to Web with the Core key, set a default model and issue Project API keys. Applications call Core with those keys. Sessions run in sandboxes on nodes you add, or on E2B.
+One command installs Core, the Web console and PostgreSQL on Linux, macOS or Windows. Sign in to Web with the Core key, set a default model and issue Project API keys. Applications call Core with those keys. Sessions run in sandboxes on nodes you add, or on E2B.
 
 1. [Check the prerequisites](#prerequisites).
 2. [Run the installer](#install).
@@ -16,21 +16,29 @@ This page follows the default path. Every flag, existing reverse proxies and off
 
 ## Prerequisites
 
-- Linux amd64 and curl.
-- Docker Engine with Docker Compose 2.26.0 or newer (`docker compose version`).
+- Linux amd64/arm64 or macOS Intel/Apple Silicon with curl; Windows x64 with PowerShell.
+- Docker Engine 26 or newer and Docker Compose 2.26.0 or newer. On macOS and Windows, install and start Docker Desktop using Linux containers.
 - An account that can run `docker` and write to its home directory. Ordinary users and root both work; the installer never calls sudo.
 - Free port 8080 for Web. See [ports](./install-options.md#ports). Docker must be able to publish it; the installer does not change host policy.
 - For anything off this machine, the origin in `OAC_PUBLIC_URL` must be the address browsers, nodes and executors use. You can sign in on this machine first.
 
-The Core host needs no KVM; nodes that run microsandbox do.
+Sandbox nodes run on Linux amd64. When Core runs on macOS or Windows, connect a Linux node or use E2B.
 
 ## Install
 
+Linux and macOS:
+
 ```sh
 curl -fsSL https://github.com/MiniMax-AI/OpenAgentCore/releases/latest/download/install.sh | bash
 ```
 
-On a host whose default route has a private-network address, the installer sets the public URL to `http://<that address>:8080`, so machines on the same network can open Web and add nodes; otherwise only this machine can. If a reverse proxy already serves this host, pass its HTTPS address:
+Windows PowerShell:
+
+```powershell
+irm https://github.com/MiniMax-AI/OpenAgentCore/releases/latest/download/install.ps1 | iex
+```
+
+When binding to all IPv4 addresses, the installer uses the private address of the default route if available; otherwise the console address is `http://localhost:8080`. To choose another reachable origin, pass `--public-url`; if a reverse proxy already serves this host, use its HTTPS address:
 
 ```sh
 curl -fsSL https://github.com/MiniMax-AI/OpenAgentCore/releases/latest/download/install.sh | bash -s -- --public-url https://core.example
@@ -38,13 +46,13 @@ curl -fsSL https://github.com/MiniMax-AI/OpenAgentCore/releases/latest/download/
 
 The script downloads that release's Compose files, checks their SHA-256, and:
 
-1. checks Linux amd64, Docker Compose 2.26 or newer, and that the ports it will publish are free;
-2. creates the [installation directory](../configuration.md#installation-directory), `~/.oac/core`, writes `.env`, and copies the `oac` command out of the Core image;
+1. checks Docker is running Linux containers, meets the required versions, and can publish the chosen port;
+2. prepares the [installation directory](../configuration.md#installation-directory), `~/.oac/core`, with `.env` and the native `oac` command (`oac.exe` on Windows);
 3. starts the services with Docker Compose. Web serves the console on port 8080 and forwards `/v1`, `/api/v1` and `/docs` to Core. Core and PostgreSQL are not published.
 
-It saves no sandbox backend, adds no node, creates no Project or key and makes no model request. It ends by printing the console address and the Core key.
+The installer prints the console address and Core key. After signing in, configure execution resources and create Projects in Web.
 
-Downloads and configuration checks happen before the installation directory is published. After that, failures preserve the configuration and data and show the service logs. Fix the reported cause and rerun the same command, or specify the installation directory:
+Downloads and configuration checks happen before the installation directory is published. After that, failures preserve the configuration and data and report the failed step; inspect it with `docker compose logs --tail 100` in the installation directory. Fix the reported cause and rerun the same command, or specify the installation directory:
 
 ```bash
 curl -fsSL https://github.com/MiniMax-AI/OpenAgentCore/releases/latest/download/install.sh | bash -s -- --install-dir "$HOME/.oac/core"
@@ -63,6 +71,8 @@ For insufficient space or quota, free space on the filesystem named by the error
    ~/.oac/core/oac core-key --show
    ```
 
+   On Windows, use `& "$HOME/.oac/core/oac.exe" core-key --show`. The same command arguments work on every platform.
+
 ## Configure the public address {#configure-the-domain-and-https}
 
 Applications, nodes and sandboxes reach Core at one address, the public URL. HTTP is enough on the local network. When you expose Core beyond it, put a reverse proxy in front and set the public URL to the HTTPS origin it serves. E2B guests reach Core from the internet, so they need a public URL that is not loopback.
diff --git a/docs/getting-started/operations.md b/docs/getting-started/operations.md
index 9759d4c4d..85efe4be5 100644
--- a/docs/getting-started/operations.md
+++ b/docs/getting-started/operations.md
@@ -6,7 +6,7 @@ The installation operator owns the Core host, its storage and its availability.
 
 ## The oac command
 
-Each installation has its own management command in its directory. It needs neither the bundle nor root:
+Each installation has its own native management command in its directory: `oac` on Unix, `oac.exe` on Windows. It needs Docker access and no root privileges:
 
 ```sh
 docker compose -f ~/.oac/core/compose.yaml ps
@@ -18,11 +18,11 @@ docker compose -f ~/.oac/core/compose.yaml ps
 | `docker compose start` | Starts the services |
 | `docker compose stop` | Stops the services. Data, nodes and sandboxes are kept |
 | `oac apply` | Runs `oac-core check-config`, then `docker compose up -d --wait`. A failed check changes no service |
-| `oac core-key [--show]` | Prints the Core key path, or the key itself with `--show` |
+| `oac core-key [--show]` | Identifies the key location in the data volume, or prints the key with `--show` |
 | `oac rotate-core-key` | Replaces the Core key and restarts Core and Web |
 | `docker compose down` | Removes the containers. Data is kept; to delete it, [uninstall](#uninstall) |
 
-For a second installation, use its directory, such as `~/.oac/second`.
+The examples use the default installation directory. On Windows, invoke the management command with `& "$HOME/.oac/core/oac.exe"` followed by the same arguments. For a custom installation directory, replace the path in each command.
 
 ## Service health
 
@@ -63,13 +63,13 @@ A Web restart, including one caused by `oac apply`, signs everyone out of the co
 
 ## Core key
 
-Each installation has one administrator credential, the Core key. The installer generates a key with the `oac_admin_` prefix followed by 64 random lowercase hexadecimal characters in `data/secrets/web/core.key`. Read it with `oac core-key --show`; the file is owned by the container user. The Core key:
+Each installation has one administrator credential, the Core key. The installer generates a key with the `oac_admin_` prefix followed by 64 random lowercase hexadecimal characters in `secrets/web/core.key`. Read it with `oac core-key --show`; the file is owned by the container user. The Core key:
 
 - signs in to Web. The browser gets an HttpOnly session cookie, never the key;
 - authorizes Core API (`/core/v1`) requests sent as `Authorization: Bearer <Core key>`;
 - never authorizes the Agents API (`/v1`). Applications use Project API keys, which in turn can't call `/core/v1`.
 
-Keep it private. Web reads `data/secrets/web/core.key`. Core reads only its SHA-256 from `data/secrets/core/core-key-digests.json`. A Core key has at least 32 characters and no whitespace. Web limits failed sign-ins.
+Keep it private. Web reads `secrets/web/core.key`. Core reads only its SHA-256 from `secrets/core/core-key-digests.json`. A Core key has at least 32 characters and no whitespace. Web limits failed sign-ins.
 
 ### Script the Core API
 
@@ -103,7 +103,7 @@ The [Core administration API](../../contracts/agents-api/admin-api.md) lists eve
 ~/.oac/core/oac rotate-core-key
 ```
 
-It writes a new key to `data/secrets/web/core.key`, regenerates `data/secrets/core/core-key-digests.json`, and restarts Core and Web. The old key stops working as soon as Core restarts, and every console session ends: sign in again and update your scripts.
+It runs in the initialization container, updates `secrets/web/core.key` and `secrets/core/core-key-digests.json` in the data volume, and restarts Core and Web. The old key stops working as soon as Core restarts, and every console session ends: sign in again and update your scripts.
 
 ## Projects and API keys
 
@@ -123,37 +123,33 @@ Core records which key made each public resource write; the retention of that hi
 
 Back up these together; a restore needs all of them:
 
-- the PostgreSQL volume `<project>_database`. It holds Projects, key digests, nodes, default models, encrypted credentials and all execution history, including large objects. A logical dump:
+- the Docker volume `<project>_data`, including its `database/`, `secrets/` and `state/` directories. It holds Projects, key digests, nodes, default models, encrypted credentials and all execution history, including large objects. A logical dump:
 
   ```sh
   docker compose -f "$HOME/.oac/core/compose.yaml" exec -T database \
     pg_dump -U agents_api agents_api > oac-backup.sql
   ```
 
-- the installation directory, especially `data/`. `data/secrets/core/credential.key` must stay with the database, or stored credentials can't be decrypted.
+- the installation directory containing `.env`, `compose.yaml` and the command. The data volume's `secrets/core/credential.key` must stay with the database, or stored credentials cannot be decrypted.
 - each node's state directory on its host, `/var/lib/oac-node/.oac/nodes/<installation-id>/`, with its provider storage: Docker volumes or microsandbox's store. See [when a node host fails](./nodes.md#when-a-node-host-fails) for restoring them.
 
-Stop with `docker compose stop`, archive the installation directory, then `docker compose start`.
-
-Never prune Docker volumes or delete native harness history to make a retry pass. A deleted Session does not prove that all provider resources were reclaimed.
+Stop with `docker compose stop`, export the complete data volume and archive the installation directory, then `docker compose start`. Docker Desktop supports volume export from its **Volumes** view. A SQL dump alone does not include the encryption key or Provider state.
 
 ## Uninstall
 
 ```sh
 cd ~/.oac/core
-docker compose down --remove-orphans
-docker compose run --rm --no-deps --entrypoint find init /data -mindepth 1 -delete
-docker compose down --rmi all
+docker compose down --volumes --remove-orphans --rmi all
 cd && rm -rf ~/.oac/core
 ```
 
-The containers own `data/`, so the `init` image deletes its contents; then `down --rmi all` removes the images and `rm` removes the installation directory. Run these only when you mean to delete the data.
+`down --volumes` deletes the installation data volume. Remove the installation directory afterward; on Windows use `Remove-Item -Recurse "$HOME/.oac/core"`.
 
 All data goes with it: Projects and API keys, Session history, stored credentials and the Core key. To keep the data, stop the installation with `docker compose stop` instead, or [back it up](#back-up) first.
 
 Uninstall stops no sandbox: node sandboxes keep running on their nodes, and E2B sandboxes keep running, and billing, at E2B. While Core is still up, archive their Sessions or [reset the deployment](./nodes.md#change-the-sandbox-configuration) and let it complete; the command shows how many sandboxes Core has in use.
 
-Nodes on other hosts keep running. To uninstall them the usual way, remove them in Web first, as in [Remove a node](./nodes.md#remove-a-node). After the installation directory is gone, their Core is gone: on each node host, run the node uninstall command with `--force`, using `node-install.pyz` from the release that installed them. The installation ID is `data/secrets/core/installation.id`.
+Nodes on other hosts keep running. To uninstall them the usual way, remove them in Web first, as in [Remove a node](./nodes.md#remove-a-node). After the installation directory is gone, their Core is gone: on each node host, run the node uninstall command with `--force`, using `node-install.pyz` from the release that installed them. The installation ID is `secrets/core/installation.id` in the data volume.
 
 ## Installation version policy
 
@@ -163,7 +159,7 @@ To move to a new release, install it into a new, empty directory, with its own d
 
 An interrupted installation can [resume with its saved configuration](./install.md#install). An unrelated nonempty directory is refused.
 
-The installer and mutating `oac` commands hold `.oac.lock`. The installer also holds a sibling `<install-dir>.install.lock` while preparing the directory. If another command holds either lock, retry after it finishes. Never delete a lock file to get past a busy installation.
+Installation and mutating `oac` commands share the [installation lock](../configuration.md#installation-directory). If another command is running, wait for it to finish before retrying.
 
 ## Troubleshooting
 
diff --git a/docs/maintainers.md b/docs/maintainers.md
index c1f75330e..f59822dea 100644
--- a/docs/maintainers.md
+++ b/docs/maintainers.md
@@ -6,7 +6,10 @@ This guide is for maintainers who build and publish OpenAgentCore. To install Co
 
 ## Build a distribution
 
-A distribution is the matched set of Linux amd64 release assets built from one commit: the control archive (the installer, the `oac` command, and the Core, Web, ingress and PostgreSQL images), the Runtime image and node artifacts as separate files, and the native installers.
+A distribution is a matched set of release assets built from one commit: the control archive (the installer, the `oac` command, and the Core, Web, ingress and PostgreSQL images), the Runtime image and node artifacts as separate files, and the native installers.
+
+Core, Web and ingress images are published as verified Linux amd64/arm64 indexes. The arm64 control archive contains those three images; Node, hosted Runtime and offline payloads use Linux amd64. Release builders use QEMU for ARM image steps, including the E2B helper. Host `oac` binaries are built from the same command for Linux amd64/arm64, macOS amd64/arm64 and Windows amd64; launchers only select, verify and invoke them. Each version index is checked against its platform archives before floating tags move.
+
 
 Build on Linux x86_64 with a glibc compatible with Debian 12, Docker, the Go version in `go.mod`, a C compiler (the microsandbox helper is a CGO build), Node, pnpm, Python 3.9 or newer, curl, tar, pigz and sha256sum. The source must be clean and committed. First prepare the pinned Codex package and MiniMax Code companion, then build:
 
@@ -105,7 +108,7 @@ The script runs the three Runtime image builders into one context, adds the stat
 make build-e2b-provider
 ```
 
-Docker builds the Linux amd64 helper with the pinned CPython and Debian 12 image. The Python dependency closure, including PyInstaller, is hash-locked in `services/core/tools/e2b-provider/requirements.lock`; no E2B account key is needed. Set `E2B_PROVIDER_BUILD_DIR` for another output directory. The build is a pure function of the helper sources, `LICENSE` and the build script, so it is cached under `~/.oac/cache/e2b-provider/` by their hash and rebuilt only when they change. The output is `oac-e2b-provider-linux-amd64.tar.gz` with its `.sha256`; it extracts to `oac-e2b-provider/` with the executable, `_internal/`, `licenses/`, `requirements.lock` and `manifest.json`. The Core image uses that tree; the host needs a compatible glibc and CA certificates, not Python.
+Docker builds the Linux helper for `GOARCH=amd64` (default) or `GOARCH=arm64` with the pinned CPython and Debian 12 image. The Python dependency closure, including PyInstaller, is hash-locked in `services/core/tools/e2b-provider/requirements.lock`; no E2B account key is needed. Set `E2B_PROVIDER_BUILD_DIR` for another output directory. The build is a pure function of the helper sources, `LICENSE` and the build script, so it is cached under `~/.oac/cache/e2b-provider/` by their hash and rebuilt only when they change. The output is `oac-e2b-provider-linux-<architecture>.tar.gz` with its `.sha256`; it extracts to `oac-e2b-provider/` with the executable, `_internal/`, `licenses/`, `requirements.lock` and `manifest.json`. The Core image uses that tree; the host needs a compatible glibc and CA certificates, not Python.
 
 **microsandbox helper.** Linux only, with a C compiler:
 
@@ -120,9 +123,9 @@ The helper is written to `~/.oac/build/microsandbox-provider/oac-microsandbox-pr
 
 ### Standalone Core builds
 
-`make build-core` builds `oac-core`, `oac-core-device`, `oac-core-environment-key` and `oac-node` into `${OAC_DEV_HOME:-$HOME/.oac}/build/oac-core` (`OAC_DEV_CORE_BUILD_DIR` selects another absolute directory). The build copies only the source set listed in `scripts/build-core.sh` (the Core service, its contracts, the shared packages it needs and the root Go module files) into a temporary context and builds with CGO disabled, read-only modules and trimmed paths. It needs no Node, Docker or other application. When Core gains a shared dependency, add that package to the list; never copy the whole repository to make it compile.
+`make build-core` builds `oac-core`, `oac-core-device`, `oac-core-environment-key` `oac-node` and `oac` into `${OAC_DEV_HOME:-$HOME/.oac}/build/oac-core` (`OAC_DEV_CORE_BUILD_DIR` selects another absolute directory). The build copies only the source set listed in `scripts/build-core.sh` (the Core service, its contracts, the shared packages it needs and the root Go module files) into a temporary context and builds with CGO disabled, read-only modules and trimmed paths. It needs no Node, Docker or other application. When Core gains a shared dependency, add that package to the list; never copy the whole repository to make it compile.
 
-`make docker-build-core` builds the image `oac-core:dev` (`OAC_DEV_CORE_IMAGE` selects another name) from those five commands and the E2B helper. The base is the digest-pinned `debian:bookworm-slim` with CA certificates and the glibc runtime the helper needs; the default user is UID/GID 65532 and Core listens on `:8091`. The image is Linux amd64 only and is not pushed to a registry. Changes to the image or its build need `make check-core-container` in addition to the relevant source checks: it runs the official-client suite against the image with a read-only root filesystem and needs Linux Docker, a non-root user, and the [test database and pinned SDK](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/services/core/README.md#official-client-verification) of the service checks (`OAC_TEST_DATABASE_URL` naming an `oac_*_tests` database with the migrations applied, and `OAC_TEST_OFFICIAL_SDK_PYTHON`).
+`make docker-build-core` builds the image `oac-core:dev` (`OAC_DEV_CORE_IMAGE` selects another name) from those five commands and the E2B helper. The base is the digest-pinned `debian:bookworm-slim` with CA certificates and the glibc runtime the helper needs; the default user is UID/GID 65532 and Core listens on `:8091`. This local target builds Linux amd64; the [distribution build](#build-a-distribution) builds both architectures. Changes to the image or its build need `make check-core-container` in addition to the relevant source checks: it runs the official-client suite against the image with a read-only root filesystem and needs Linux Docker, a non-root user, and the [test database and pinned SDK](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/services/core/README.md#official-client-verification) of the service checks (`OAC_TEST_DATABASE_URL` naming an `oac_*_tests` database with the migrations applied, and `OAC_TEST_OFFICIAL_SDK_PYTHON`).
 
 ## Publish a version
 
@@ -141,13 +144,13 @@ Distribution and Runtime archives use `pigz` level 6 with at most four compressi
 
 ### Container registry
 
-Version releases and manual `build-<full SHA>` drafts publish Linux amd64 images as `ghcr.io/minimax-ai/openagentcore/<component>:<version>`, where `<component>` is `core`, `web`, `runtime` or `ingress`. For example, `ghcr.io/minimax-ai/openagentcore/core:v1.2.3`. A draft uses the tag `build-<full SHA>`. PostgreSQL uses its upstream image and is not republished. The registry images are loaded from the release archives without rebuilding. Existing version tags are reused only when their image config digest matches the release; a different image stops publication. A stable release also moves each component's `latest` tag to that image. Prereleases and drafts leave `latest` unchanged. SemVer build metadata uses `_` in place of `+` in container tags; version strings longer than 128 characters cannot be published to GHCR. After the images are verified, the publisher uploads the single `compose.yaml` and its checksum list, rendered for that release. Compose pins the ingress image by its registry digest; initialization rejects an image whose build revision differs from the Compose revision. A draft Release stays unpublished.
+Version releases and manual `build-<full SHA>` drafts publish `ghcr.io/minimax-ai/openagentcore/<component>:<version>`, where `<component>` is `core`, `web`, `runtime` or `ingress`. Core, Web and ingress indexes contain Linux amd64 and arm64 images; Runtime contains Linux amd64. Platform images use `<version>-<architecture>` tags and are loaded from the release archives. Existing version tags must match the release images and platform set. The publisher verifies every version index before updating `latest` for a stable release; prereleases and drafts leave `latest` unchanged. PostgreSQL uses its upstream image. SemVer build metadata uses `_` in place of `+` in container tags; version strings are limited to 128 characters. After verifying the images, the publisher uploads the release's `compose.yaml` and checksum list. Compose pins ingress by its index digest, and initialization checks its build revision against the Compose revision.
 
 The combined build/publication job uses `GITHUB_TOKEN` with `packages: write`. On the first publication, GitHub creates each container package as private: a package administrator must change all four packages to **Public** in their package settings before users can pull anonymously. See [GitHub container visibility](https://docs.github.com/en/packages/working-with-a-github-packages-registry/working-with-the-container-registry). Verify an unauthenticated pull after changing visibility. Repository visibility alone does not make a new container package public.
 
 GHCR and GitHub Releases do not share a transaction. A failed release may leave some matching version tags in GHCR; preserve those images and follow the draft recovery procedure below using the original artifacts. Registry failures other than a missing manifest stop publication. The job summary records digest-pinned references. These images and the rendered Compose files still require the configuration, secrets and routing described in [Configuration](./configuration.md).
 
-`install.sh` downloads the Compose files for the latest stable release, or the release named by `--version`, verifies their SHA-256 and starts that release. The [installation guide](./getting-started/install.md#install) covers its use.
+The [installation guide](./getting-started/install.md#install) covers release selection and the platform launchers.
 
 Go check and build jobs share Go module and compiler-cache directories under `~/.oac/cache/`, keyed by runner OS and architecture, all Go module files, the check/build partition and the commit. Partitioned keys prevent concurrent jobs from saving different compiler subsets under one key. Release builds can seed their cache from backend checks as well as earlier release builds. An older cache only seeds downloads and compilation; every check still runs. Release jobs also cache npm package downloads and the pinned microsandbox archive, whose checksum is verified on every build. Actions cache visibility follows GitHub ref scoping; a tag-specific cache is not shared with other release tags. New keys are saved only after a successful job.
 
@@ -188,7 +191,7 @@ The planner compares the PR event's tested merge commit with its verified first
 
 `.github/actionlint.yaml` selects hygiene and lint. Known workflow changes select their consumers: the CI review and actionlint workflows run hygiene and lint; native workflow changes add native checks; API acceptance workflow changes add API checks with container acceptance enabled; website workflow changes add website checks. The shared Node action selects every job that uses it plus lint. A new or unclassified workflow/action selects the full gate until its consumers are declared in the planner. Planner tests and CI measurement scripts run hygiene; changing the planner itself runs the full gate.
 
-Compose template and Compose test changes select both `distribution` fixtures and the `compose` smoke job; Core, Web, shared Go packages and the image Dockerfiles also select the smoke job. Run `python3 scripts/compose-smoke.py` locally with Docker available to repeat it. The script uses a unique project, an automatically assigned loopback port and artifacts under `~/.oac/tests/`; it removes its containers and volumes on exit. CI also performs cleanup after a failed or interrupted smoke step. Diagnostics show container status without printing HTTP response bodies or sign-in keys. Core, Web and the ingress image are built from the checkout; Web serves a placeholder page instead of the console build. Build-time node metadata comes from the release pinned in `deploy/compose/smoke-pins.json`; the initialization container runs with networking disabled. This checks generic Compose behavior; it does not run a Dokploy/Coolify instance or execute a model.
+Compose template and Compose test changes select both `distribution` fixtures and the `compose` smoke job; Core, Web, shared Go packages and the image Dockerfiles also select the smoke job. Run `python3 scripts/compose-smoke.py` locally with Docker available to repeat it. The script uses a unique project, an automatically assigned loopback port and artifacts under `~/.oac/tests/`; it removes its containers and volumes on exit. CI also performs cleanup after a failed or interrupted smoke step. Diagnostics show container status without printing HTTP response bodies or sign-in keys. Core, Web and the ingress image are built from the checkout; Web serves a placeholder page instead of the console build. Build-time node metadata comes from the release pinned in `deploy/compose/smoke-pins.json`; the initialization container runs with networking disabled. The smoke matrix runs on native Linux amd64 and arm64 runners; the native matrix builds and tests the shared Core installer on Linux, macOS and Windows.
 
 Go module and workspace inputs select backend, API (including the container), native and distribution checks. Each Node module owns its manifest and lockfile. Website dependencies select website checks; Web dependencies select Web and browser checks; example dependencies select example checks; shared TypeScript client dependencies select Web, browser and example checks; Claude adapter dependencies select Harness, native and distribution checks. Shared package-manager configuration selects all Node consumers. The root TypeScript configuration selects Web and example checks; the adapter TypeScript configuration selects Harness and native checks. Each selected set includes hygiene. Mixed changes accumulate their consumers, and every job reads the same plan instead of maintaining its own path list. For example, a notification-only PR skips database, browser and native jobs, while a notification plus Core change adds backend and API checks.
 
@@ -198,7 +201,9 @@ The final `check` runs even when planning or a dependency fails. It requires a s
 
 Use **Actions → core-check → Run workflow** for a manual full check. For a transient failure, use GitHub's **Re-run failed jobs** so successful jobs remain completed. PR updates cancel the superseded run through Actions concurrency. Build and dependency caches speed execution; they do not stand in for successful tests. Native release installers are passed between jobs using Actions artifacts, within the same release workflow.
 
-The `CI review and Feishu notification` workflow runs once after a PR merges into main. It checks out the merged commit, reads that PR's existing checks and logs, and reports their actual status. It does not trigger another test run. Closing an unmerged PR does not invoke the review. The workflow uses `pull_request_target` only for the merged event and never checks out an unmerged PR head with notification credentials.
+The `CI review and Feishu notification` workflow runs after a PR merges into main. A matrix runs **Code review** and **Docs review** in independent LLM contexts with `fail-fast: false`. Both read the merged commit and PR diff. Code review checks implementation, repository rules and existing CI results; it does not start another test run. Docs review checks changed behavior against documentation even when no docs changed. When docs change, it also checks contradictions, duplicated facts, topic ownership under CONTRIBUTING, and English/Chinese agreement. Findings include file and line references, supporting evidence and a minimal correction. Reviews read the repository without editing it.
+
+Each review returns a structured result (`ok`, `issues` or `incomplete`) and Chinese sections, retained as an Actions artifact for seven days. **Combined Feishu notification** waits for both jobs and sends one Card 2.0 message containing both results through the existing `FEISHU_WEBHOOK_URL`; `FEISHU_WEBHOOK_SECRET` optionally signs it. The card uses fixed sections for PR details, behavior changes, code and repository rules, CI results, and documentation review, separated by dividers. Its header shows green for no findings, red for findings, and yellow for an incomplete review without findings. Only this notification job receives the webhook secrets. Failed, missing or invalid reports appear as incomplete, alongside any available result from the other review. The notification job runs even when a review fails. Delivery requires Feishu's `code=0` response; a failed or ambiguous request is not automatically retried, avoiding duplicate messages. Each review has a 25-minute execution timeout. Review and delivery failures do not block merges, and closing an unmerged PR does not trigger this workflow. The workflow checks out only the merged commit with notification credentials.
 
 Browser jobs own separate fixtures and servers; increasing workers against the shared mutable fixture is unsafe. Failed browser jobs retain reports/traces for seven days. Native failure phase summaries are retained for seven days and detailed output stays in the Actions logs; credentials and temporary installation trees are not uploaded. Successful native archives are uploaded only for explicit manual packaging or releases, without recompressing the compressed archive. Release distribution artifacts retain their existing recovery policy; failed publication can reuse the original build as described above.
 
diff --git a/docs/runtime-protocol.md b/docs/runtime-protocol.md
index 2ae65bd40..3ccea3be1 100644
--- a/docs/runtime-protocol.md
+++ b/docs/runtime-protocol.md
@@ -20,7 +20,7 @@ A Runtime connects in this order:
 
 The wire version is [`proto.Version`](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/version.go), independent of the Runtime build version that heartbeats report. Core accepts only an exact match, including the patch component. A mismatch returns HTTP 426 `incompatible_version` before any dispatch; the daemon treats it as permanent and stops reconnecting. Deploy matching peers together.
 
-Each physical connection has fresh routing, admission handles and transfer state. A newer connection for the same device replaces the previous one: Core closes the previous connection and evicts its Run and interaction routes, and the new connection inherits none of them. A valid credential and connection are never authority to choose another Session or Environment binding; [assignments](#session-assignments) fence which Session a frame may act for.
+Each physical connection has fresh routing, admission handles and transfer state. A newer connection for the same device replaces the previous one: Core closes the previous connection and evicts its Run routes, and the new connection inherits none of them. A valid credential and connection are never authority to choose another Session or Environment binding; [assignments](#session-assignments) fence which Session a frame may act for.
 
 ## Capability declarations
 
@@ -51,7 +51,7 @@ A declaration describes what the Runtime can do. Core admits a public feature on
 | `message_images`, `function_result_images` | A message, or a function result, carries an image |
 | `mcp_http_tools`, `mcp_http_required`, `mcp_http_bearer_auth` | The Agent declares HTTP MCP servers; one is `required`; a Vault credential is selected for one |
 
-`permissions` gates permission decisions inside the Runtime. Core has no admission rule for `usage` and `resume`.
+Core has no admission rule for `usage` and `resume`.
 
 The `execution_prepare` configuration carries the Session's model configuration and the opt-ins Core sets for each Run:
 
@@ -83,13 +83,10 @@ Every data frame is one JSON [`Envelope`](https://github.com/MiniMax-AI/OpenAgen
 | Preparation request ID | `Envelope.id` for prepare, start, release and status; distinct from a Run |
 | Admission handle | Runtime-generated reservation, valid only on the connection that accepted it |
 | Run ID | One execution attempt; `Envelope.id` for output, cancellation, active input and functions |
-| Interaction ID | `permission_request.payload.request_id` or `prompt_for_user_choice.payload.ask_id`; these request envelopes still carry the Run ID |
 | Delivery ID / input ID / call ID | Resolve attempt, active-input receipt and native function identity; never interchangeable |
 | Transfer ID / suspension ID | Connection-local transfer correlation / persisted suspension-attempt fencing |
 
-Decision and permission-cancel envelopes use the interaction ID. Cancellation and function-result acknowledgements use the Run ID. Every application decision receipt also matches the delivery ID. A reply without the required correlation cannot establish acceptance.
-
-User-choice decisions carry `question_answers`: an explicit `question_id` and an `answers` array for each provided answer. The IDs must belong to the emitted questions and cannot repeat. Question order and display headers do not identify answers; an omitted question stays unanswered, and an empty array is an explicit non-answer. Cancellation carries `cancelled: true` without answers. Shared validation rejects other shapes before native submission.
+Cancellation and function-result acknowledgements use the Run ID and match the delivery ID. A reply without the required correlation cannot establish acceptance.
 
 ## Message families
 
@@ -101,8 +98,7 @@ The linked source files define the required fields, validators, limits and finit
 | Any frame the Runtime cannot route | `protocol_error` | [Session assignments](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/assignment.go) |
 | `runtime_prepare` | `runtime_prepare_result` | [Initialization and capability transfer](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/runtime_prepare.go) |
 | `execution_prepare`, `execution_start`, `execution_release` | `preparation_status` | [Execution admission](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/preparation.go) |
-| `prompt_cancel` | `delta`, `thinking`, `output_message`, `tool_call`, `usage`, `error`, `done`, `heartbeat` | [Requests](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/outbound.go), [events and capabilities](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/inbound.go) |
-| `permission_decision`, `prompt_for_user_choice_decision` | `permission_request`, `permission_cancel`, `prompt_for_user_choice`, `interaction_decision_ack` | [Requests](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/outbound.go), [interactions](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/inbound.go) |
+| `prompt_cancel` | `delta`, `thinking`, `output_message`, `tool_call`, `usage`, `error`, `done`, `heartbeat`, `interaction_decision_ack` | [Requests](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/outbound.go), [events and capabilities](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/inbound.go) |
 | `prompt_steer` | `prompt_steer_ack` | [Active input receipts](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/steering.go) |
 | `function_result` | `function_call`, `interaction_decision_ack` | [Function calls](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/functions.go) |
 | `workspace_read`, `workspace_write`, `workspace_export` | Matching `*_result` | [Read](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/workspace_read.go), [write](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/workspace_write.go), [export](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/workspace_export.go) |
@@ -116,7 +112,7 @@ Usage frames and the final usage snapshot each carry the cumulative measurement
 
 An assignment binds one Session to the Runtime that runs it. `Envelope.assignment` names it as `session_id`, `assignment_id` and `epoch`, and is the only place a frame carries it. Core advances the epoch whenever it changes the assignment's desired state, so a lower epoch is stale.
 
-Every Session frame carries the assignment: `execution_prepare`, `execution_start` and `execution_release`; `prompt_cancel`, `prompt_steer`, `function_result`, `permission_decision` and `prompt_for_user_choice_decision`; every frame of `runtime_prepare`, `workspace_read`, `workspace_write` and `workspace_export`; and `environment_quiesce` and `environment_resume`. A reply echoes its request's assignment, and a Run's frames carry the assignment that started it; Core rejects a reply or Run frame that names another. Heartbeats carry none.
+Every Session frame carries the assignment: `execution_prepare`, `execution_start` and `execution_release`; `prompt_cancel`, `prompt_steer` and `function_result`; every frame of `runtime_prepare`, `workspace_read`, `workspace_write` and `workspace_export`; and `environment_quiesce` and `environment_resume`. A reply echoes its request's assignment, and a Run's frames carry the assignment that started it; Core rejects a reply or Run frame that names another. Heartbeats carry none.
 
 Before a Session's first operation on a connection, including Environment initialization and file work without a Turn, Core sends `assignment_bind` with the Session's Environment ID and waits for `assignment_status` `bound`. When the Runtime is an agent host and the Environment has a live [Link](./sandbox-link-protocol.md) resource, the bind also carries `resource`, that resource as the [bootstrap input](./sandbox-bootstrap.md#launch-input) names it, and `attach_grant`, the base64 grant with which the agent host opens services on that resource generation under this assignment and epoch. The grant is secret. Core sends neither field to any other Runtime. A bind with only one of them, or with a resource of another Environment, fails with `invalid_request`. A repeated bind of the same assignment with the same Environment, resource and grant is `bound` again; any other bind of it fails with `assignment_conflict`. The Runtime admits a Session frame only under the assignment it bound: an older epoch, or a released one, fails with `assignment_stale`; another assignment, Session or Environment fails with `assignment_conflict`. A started Run's frames, including its cancellation receipt, stay admissible under the assignment that started it until the release. A repeated function result or decision whose receipt the Runtime already recorded is answered only under the assignment that applied it; another fails with `assignment_conflict`.
 
@@ -173,7 +169,7 @@ No generic receipt exists for every envelope. A successful send does not prove t
 
 ## Failures, retries and cleanup
 
-Transport and execution outcomes are separate. Core's only Run subscription entry point is `SubscribeDurable`; inspect `Subscription.Err()` when its event channel closes. Disconnection and subscriber overflow close it with an explicit observation error and fabricate no `error` or `done`. Core keeps the durable truth and reconciles from confirmed facts. The Runtime keeps cleanup ownership until native work, input receipts, interactions and child work have settled.
+Transport and execution outcomes are separate. Core's only Run subscription entry point is `SubscribeDurable`; inspect `Subscription.Err()` when its event channel closes. Disconnection and subscriber overflow close it with an explicit observation error and fabricate no `error` or `done`. Core keeps the durable truth and reconciles from confirmed facts. The Runtime keeps cleanup ownership until native work, input receipts, function results and child work have settled.
 
 The public Turn status is a separate projection. [`execution/delivery.go`](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/services/core/internal/execution/delivery.go) records an unsuccessful orchestration attempt as `failed`, including `delivery_unknown` after an unconfirmed send and `event_stream_incomplete` after a subscription failure; a closed subscription can replace the send reason with `event_stream_incomplete`. Both mean the native effect is unknown: a public `failed` status does not prove that the Harness failed, that no side effect occurred or that cleanup completed. Keep the observation reason and any native evidence distinct.
 
@@ -200,7 +196,7 @@ Core stores accepted values in the Turn outcome as `engine_error_code` and `engi
 
 ## Workspace operations
 
-A workspace read that needs no running Turn uses the read-only preparation profile: `execution_prepare` with `workspace_read_only`, which requires the `workspace_read_preparation` capability. It accepts only the bound Environment and resource identity; execution options, model and MCP credentials, native Session continuation and model or tool input are excluded, and the owner rejects `execution_start`. The Runtime serves it from its bound local workspace without starting a Harness process. The profile publishes `released` only after local close succeeds; a cleanup error keeps ownership and reports `cleanup_unconfirmed`. A successful cleanup retry publishes the confirmed release; a stale status snapshot never publishes success. A release request, HTTP disconnect or remote socket closure alone does not confirm cleanup.
+A workspace read that needs no running Turn uses the read-only preparation profile: `execution_prepare` with `workspace_read_only`, which requires the `workspace_read_preparation` capability. It accepts only the bound Environment and resource identity; execution options, model and MCP credentials, native Session continuation and model or tool input are excluded, and the owner rejects `execution_start`. The Runtime serves it from its bound local workspace without starting a Harness process. The profile publishes `released` after the Runtime drops the preparation's ownership; a stale status snapshot never publishes success. A release request, HTTP disconnect or remote socket closure alone does not confirm the release.
 
 `workspace_read` lists one workspace-relative directory (an empty path selects the root) of an existing preparation handle, or the Run it was transferred to, on the same authenticated device connection, with the exact frozen Environment identity; callers cannot supply sockets, credentials or workspace roots. A result carries at most `max_entries` (1 to 1024) single-component UTF-8 names of at most 255 bytes each, the entry kind, regular-file sizes and explicit truncation, and is returned only after directory access and handle cleanup settle. There is no snapshot, recursion or pagination at this layer.
 
diff --git a/docs/sandbox-link-protocol.md b/docs/sandbox-link-protocol.md
index 874594390..3d3d61c92 100644
--- a/docs/sandbox-link-protocol.md
+++ b/docs/sandbox-link-protocol.md
@@ -41,7 +41,15 @@ An attachment outlives its link. After reconnecting, the Runtime opens a stream
 
 ## Run a relay
 
-`relay.New` takes an `Authority` and returns a `*relay.Relay`, which is an `http.Handler`. The relay endpoint is served behind the installation's HTTPS ingress, which terminates TLS, so the handler accepts the upgrade on the ingress's plain HTTP hop; peers enforce TLS when they dial. Each link carries at most 256 concurrent service streams.
+`relay.New` takes an `Authority` and returns a `*relay.Relay`, which is an `http.Handler`. The relay endpoint is served behind the installation's HTTPS ingress, which terminates TLS, so the handler accepts the upgrade on the ingress's plain HTTP hop; peers enforce TLS when they dial.
+
+Each link carries at most 256 concurrent service streams, and each resource has at most 2 serve Hellos being decided. The relay also holds at most 4096 resources, 16384 attachments and 4096 attach links. A Hello or an Open takes the slots it needs before the Authority is consulted. When one is not free, it is refused with `LimitExceeded` and leaves nothing behind:
+
+- A serve Hello takes one of its resource's Hello slots until it is decided.
+- A resource takes a slot at the serve Hello that first names it and keeps it while the relay holds anything for it: its serve peer, a Hello being decided, an attachment or an unwritten `AttachmentClosed` event. A reconnect of a held resource needs no new resource slot. A resource has at most one serve link, so the resource limit also bounds serve links and, with the Hello slots, the serve Hellos being decided.
+- An Open takes a stream slot of its attach link. An opened stream keeps it until the stream ends; a refused Open gives it back once it is decided, even when the peer reset the stream first.
+- An attachment takes a slot at the Open that creates it and keeps it until it is closed and its `AttachmentClosed` events are written or discarded.
+- An attach link takes a slot at its Hello and keeps it until it ends and every stream and renewal it carried has finished.
 
 The owner of the relay implements `Authority` from its durable records, and the relay consults it for every Hello, Open and renewal. To revoke, withdraw the authority first, then call `RevokeAttachment` or `RevokeResource` so the relay closes what it holds.
 
@@ -194,7 +202,7 @@ AttachmentClosed
 1. The peer dials the relay's URL: `wss://`, or `ws://` only when the host is `localhost` or a loopback address. The URL carries no user, query or fragment, and never a credential. `sandboxlink.CheckRelayURL` applies this rule for both peers and the [bootstrap input](./sandbox-bootstrap.md) and refuses any other URL with `sandboxlink.ErrRelayURL`. Over `wss://`, TLS authenticates the relay.
 2. The peer starts yamux and opens the control stream.
 3. It sends a Hello as the first request of the control stream, with request ID 1: `ServeHello` from the Sandbox I/O service, `AttachHello` from a Runtime. Credentials travel only in the Hello.
-4. The relay authenticates the peer with its Authority and answers `HelloAccepted`, or a failure after which the link ends. A Hello of another version is answered `VersionMismatch` without reading past its version. When a revocation lands while the Authority decides a serve Hello, the relay asks again, so a withdrawn credential never installs a serve peer.
+4. The relay takes the [slot](#run-a-relay) the Hello needs, authenticates the peer with its Authority and answers `HelloAccepted`, or a failure after which the link ends. A Hello of another version is answered `VersionMismatch` without reading past its version. When a revocation lands while the Authority decides a serve Hello, the relay asks again, so a withdrawn credential never installs a serve peer.
 
 Later control requests continue the Hello's request IDs. The relay ends an attach link whose request ID does not increase with `ProtocolViolation`. `Open` and `Bind` are each the only request on their stream and use request ID 1.
 
@@ -206,10 +214,11 @@ The relay and the serve peer bound each handshake step, the WebSocket upgrade, t
 
 The attach peer opens a stream and sends `Open`. The relay then:
 
-1. Calls `Authority.AuthorizeOpen`. The Authority checks the grant, the Runtime, the current assignment and its epoch, the resource generation, the permitted service and access, and that the resource's serve authority is current. It returns the binding identity, the service, the lease, the exports for `ServiceFile` and the egress rules for `ServiceNetwork`. When a revocation lands while the Authority decides, the relay asks again.
-2. Checks, in order: each link's stream limit (`LimitExceeded`); that the newest generation the relay has seen for the resource is not newer than the Open's (`StaleGeneration`); that a serve peer of the Open's generation is connected and offers the service (`ServiceUnavailable`) at the Open's version (`VersionMismatch`); that a nonzero `ExpectedServerInstanceID` equals the serve peer's (`InstanceChanged`); that the lease lies in the future (`LeaseExpired`); and that an attachment the relay already holds under this `AttachmentID` has the identical identity and Runtime (`AttachmentConflict`).
-3. Opens a stream to the serve peer and sends `Bind`. The serve peer answers `Bound`, or a failure: `ServiceUnavailable` for a service it does not serve, `VersionMismatch`, `InstanceChanged` when `ExpectedServerInstanceID` is not its own, `LeaseExpired` for a recently closed attachment, or `ProtocolViolation`. The relay passes a failure on to the attach peer. When the `Bind` began to be sent but no answer arrives, the relay answers `ServiceUnavailable` with `EffectPossible`.
-4. Answers `Opened` and splices the two streams.
+1. Takes a stream [slot](#run-a-relay) of the link, and an attachment slot when it holds no attachment under the Open's `AttachmentID`, or answers `LimitExceeded` when one is not free.
+2. Calls `Authority.AuthorizeOpen`. The Authority checks the grant, the Runtime, the current assignment and its epoch, the resource generation, the permitted service and access, and that the resource's serve authority is current. It returns the binding identity, the service, the lease, the exports for `ServiceFile` and the egress rules for `ServiceNetwork`. When a revocation lands while the Authority decides, the relay asks again.
+3. Checks, in order: the serve link's stream limit (`LimitExceeded`); that the newest generation the relay holds for the resource is not newer than the Open's (`StaleGeneration`); that a serve peer of the Open's generation is connected and offers the service (`ServiceUnavailable`) at the Open's version (`VersionMismatch`); that a nonzero `ExpectedServerInstanceID` equals the serve peer's (`InstanceChanged`); that the lease lies in the future and that an attachment the relay held when the Open arrived has not closed since (`LeaseExpired`); and that an attachment the relay already holds under this `AttachmentID` has the identical identity and Runtime (`AttachmentConflict`).
+4. Opens a stream to the serve peer and sends `Bind`. The serve peer answers `Bound`, or a failure: `ServiceUnavailable` for a service it does not serve, `VersionMismatch`, `InstanceChanged` when `ExpectedServerInstanceID` is not its own, `LeaseExpired` for a recently closed attachment, or `ProtocolViolation`. The relay passes a failure on to the attach peer. When the `Bind` began to be sent but no answer arrives, the relay answers `ServiceUnavailable` with `EffectPossible`.
+5. Answers `Opened` and splices the two streams.
 
 An attachment's binding identity is its `AttachmentID`, `Resource`, `SessionID`, `AssignmentID` and `AssignmentEpoch`. Reopening an attachment, on the same link or a later one, requires the identical identity from the same Runtime and a current authorization.
 
@@ -231,7 +240,7 @@ The relay keeps links, attachments and leases in memory. The Authority stays the
 
 A method returns a `*sandboxlink.Error` for a typed refusal; any other error is answered `ServiceUnavailable`. Credential revision and allowed access come from the Authority, never from what a peer asserts.
 
-A recreated resource has a higher generation. A serve peer of the same or a higher generation replaces the resource's current serve peer, and a higher generation also closes every attachment of an older generation with `CloseStaleGeneration`. A serve peer or an Open of a generation older than the newest the relay has seen is refused with `StaleGeneration`.
+A recreated resource has a higher generation. A serve peer of the same or a higher generation replaces the resource's current serve peer, and a higher generation also closes every attachment of an older generation with `CloseStaleGeneration`. A serve peer or an Open of a generation older than the newest the relay holds for the resource is refused with `StaleGeneration`. The relay keeps a resource's generation only while it [holds the resource](#run-a-relay); after that the Authority alone refuses older generations.
 
 ## Leases, closing and revocation
 
@@ -240,7 +249,7 @@ A recreated resource has a higher generation. A serve peer of the same or a high
 - `CloseAttachment` closes the caller's attachment with `CloseRequested`. Closing an unknown attachment succeeds, and closing another Runtime's returns `PermissionDenied`.
 - `Relay.RevokeAttachment` closes one attachment. `Relay.RevokeResource` closes every attachment of a resource generation and older, writes the serve peer their `AttachmentClosed` events and then disconnects it. Both close with `CloseRevoked`.
 
-Closing an attachment resets all its streams and sends `AttachmentClosed` to its attach peer, except after `CloseRequested`, and to the serve peer. The relay holds each serve peer's unwritten events in a set with no size limit and removes an event only once it is written, so a serve peer that is disconnected, or whose link drops before the event is written, receives it when it reconnects with the same generation. An Open that a close interrupts fails with `AttachmentConflict`, `LeaseExpired`, `PermissionDenied` or `StaleGeneration`, matching the reason, with `EffectPossible` when its `Bind` may have reached the serve peer.
+Closing an attachment resets all its streams and sends `AttachmentClosed` to its attach peer, except after `CloseRequested`, and to the serve peer. The relay holds each peer's unwritten events in a set and removes an event once it is written, so a serve peer that is disconnected, or whose link drops before the event is written, receives it when it reconnects with the same generation. Events no peer can read any more are discarded: an attach peer's when its link ends, and a serve peer's when a newer generation connects or `RevokeResource` revokes its generation. An Open that a close interrupts fails with `AttachmentConflict`, `LeaseExpired`, `PermissionDenied` or `StaleGeneration`, matching the reason, with `EffectPossible` when its `Bind` may have reached the serve peer.
 
 Losing a link resets the streams it carries and keeps its attachments until their leases expire or they are closed.
 
@@ -269,7 +278,7 @@ The relay copies each direction through a 32 KiB buffer and holds at most one 25
 | 8 | `InstanceChanged` | The serve peer's `ServerInstanceID` is not `ExpectedServerInstanceID` |
 | 9 | `LeaseExpired` | The lease has passed, or the relay no longer holds the attachment |
 | 10 | `AttachmentConflict` | The `AttachmentID` is held with another identity or Runtime, or was closed during the Open |
-| 11 | `LimitExceeded` | A link's stream limit or its limit of renewals being decided is reached |
+| 11 | `LimitExceeded` | A Hello or an Open needs a [slot](#run-a-relay) that is not free, a serve link has its limit of streams, or an attach link has its limit of renewals being decided |
 | 12 | `ProtocolViolation` | A message is malformed, not allowed where it arrived, or carries a request ID that does not increase |
 
 `ServiceUnavailable` and `LimitExceeded` are transient: the same request may succeed later, and `Code.Retryable` reports them. Every other code is final: repeating the request with the same credential, attachment and generation fails again.
@@ -278,4 +287,4 @@ An answer that is malformed, or that carries another request ID or operation tha
 
 ## Verification
 
-`go test ./internal/sandboxlink/...` covers the golden frames, decode rejection, and the relay's authorization, generation, lease, revocation, renewal bound and reconnect behavior, including orderly end and abort propagation. `go test -run '^$' -fuzz FuzzDecode ./internal/sandboxlink` fuzzes the decoder.
+`go test ./internal/sandboxlink/...` covers the golden frames, decode rejection, and the relay's authorization, generation, lease, revocation, capacity and renewal bounds, and reconnect behavior, including orderly end and abort propagation. `go test -run '^$' -fuzz FuzzDecode ./internal/sandboxlink` fuzzes the decoder.
diff --git a/docs/zh/configuration.md b/docs/zh/configuration.md
index 67127c620..7d6bfafaf 100644
--- a/docs/zh/configuration.md
+++ b/docs/zh/configuration.md
@@ -1,7 +1,7 @@
 ---
 title: "配置参考"
 source: docs/configuration.md
-source_hash: 0172bc723c66dbfa945c76eae575d8560bbd4b75d1a32cab70d1fb7313079032
+source_hash: 61cb35a25bbe3624a9a7dfea02e845b0c393f1e9609900225bb4e82d1b18f36d
 ---
 
 Core 安装的每项设置都恰好只有一个归属位置。共有两类：
@@ -11,7 +11,7 @@ Core 安装的每项设置都恰好只有一个归属位置。共有两类：
 | [进程设置](#process-settings-configjson) | 公共 URL、端口、日志、Harness、执行并发度、审计保留期、OAuth 来源、Runtime 历史记录导出 | 安装目录中的 `.env`（默认 `~/.oac/core`） | 编辑 `.env`，然后运行 `oac apply` | `oac apply` 会重新创建读取了这些已更改设置的服务 |
 | [运行时设置](#runtime-settings-web) | 沙箱后端和大小、节点、项目和密钥、默认模型、执行器凭据 | Core 的 PostgreSQL 数据库 | 在 Web 中修改，或使用 Core 密钥调用 Core API（`/core/v1`） | 保存时无需重启 Core；节点会异步准备 Runtime 变更 |
 
-Web 的 **System** 页面显示该安装的地址、默认模型和沙箱配置，并在 **Startup settings** 下以只读方式显示 Core 加载的进程设置。机密信息存放在 [`data/secrets/`](#installation-directory) 中，每项仅保存一份。没有任何配置文件定义项目或 API 密钥。
+Web 的 **System** 页面显示该安装的地址、默认模型和沙箱配置，并在 **Startup settings** 下以只读方式显示 Core 加载的进程设置。机密信息存放在 [`secrets/`](#compose-installations) 中，每项仅保存一份。没有任何配置文件定义项目或 API 密钥。
 
 ## 进程设置 {#process-settings-configjson}
 
@@ -25,9 +25,8 @@ Web 的 **System** 页面显示该安装的地址、默认模型和沙箱配置
 
 1. 它用你改过的 `.env` 运行 `oac-core check-config`。值无效时什么都不改。
 2. 它运行 `docker compose up -d --wait`。Compose 只重新创建配置有变化的服务。
-3. 校验失败时，不会重新创建任何容器。重启会中断哪些操作，见[停止和重启](getting-started/operations.md#stop-and-restart)。
 
-`docker compose ps` 展示服务。域名状态在 `data/domain/status.json`。
+用 `docker compose ps` 检查服务。重启会中断哪些操作，见[停止和重启](getting-started/operations.md#stop-and-restart)。
 
 ### 更改公共 URL {#changing-the-public-url}
 
@@ -48,7 +47,7 @@ Web 的 **System** 页面显示该安装的地址、默认模型和沙箱配置
 | Variable | Default | Meaning |
 | --- | --- | --- |
 | `OAC_PUBLIC_URL` | `http://localhost:8080` | 应用、节点、沙箱和自托管执行器使用的源地址。参阅[修改公开 URL](#changing-the-public-url) |
-| `OAC_HOST` | `127.0.0.1` | `compose.yaml` 发布的 Web 绑定地址。`install.sh` 设置为 `0.0.0.0` |
+| `OAC_HOST` | `127.0.0.1` | `compose.yaml` 发布的 Web 绑定地址。安装器设置为 `0.0.0.0` |
 | `OAC_WEB_PORT` | `8080` | Host port of Web |
 | `OAC_LOG_LEVEL` | `info` | `debug`, `info`, `warn` or `error` |
 | `OAC_LOG_FORMAT` | `auto` | `auto`, `text` or `json` |
@@ -85,7 +84,7 @@ Web 的 **System** 页面显示该安装的地址、默认模型和沙箱配置
 
 ### 默认模型 {#default-models}
 
-在 **System** → **Default model configuration** 中设置默认值，或使用 `PUT /core/v1/harnesses/{harness}/model-configuration`。Core 使用 `secrets/credential.key` 加密提供商密钥，并且绝不返回这些密钥。[模型执行](../../contracts/agents-api/zh/model-execution.md#deployment-defaults) 定义了请求字段和替换规则，[优先级](../../contracts/agents-api/zh/model-execution.md#saved-defaults-and-precedence)说明了哪些 Session 使用默认值。
+在 **System** → **Default model configuration** 中设置默认值，或使用 `PUT /core/v1/harnesses/{harness}/model-configuration`。Core 使用 `secrets/core/credential.key` 加密提供商密钥，并且绝不返回这些密钥。[模型执行](../../contracts/agents-api/zh/model-execution.md#deployment-defaults) 定义了请求字段和替换规则，[优先级](../../contracts/agents-api/zh/model-execution.md#saved-defaults-and-precedence)说明了哪些 Session 使用默认值。
 
 ## Compose 安装 {#compose-installations}
 
@@ -104,7 +103,7 @@ Web 的 **System** 页面显示该安装的地址、默认模型和沙箱配置
 
 初始化会准备该目录；应用服务以只读方式接收各自的机密目录。`docker compose exec web oac-web core-key` 把 Core 密钥打印到运维人员终端，不写入容器日志。数据库密码和凭据加密密钥绝不打印。
 
-`OAC_DATA_DIR` 选择该目录，默认是 Compose 文件旁的 `./data`。必须将该项目的定义和公共 URL 与该目录一同保留。仅删除机密目录不会重置安装；如果数据库已经存在，初始化会拒绝重新开始。Core 还会将安装 ID 与其数据库绑定。运行时设置仍存储在 [Core 的数据库](#runtime-settings-web)中。
+上述路径位于 Docker 命名卷 `<project>_data` 中。所有宿主机平台都由 Docker 管理 Linux 文件权限；每个服务只挂载需要的子目录。数据卷必须和项目定义、公共 URL 一同保留。仅删除机密目录不会重置安装；数据库已存在时初始化会拒绝重建。Core 也会校验安装 ID 与数据库的绑定。运行时设置仍保存在 [Core 数据库](#runtime-settings-web)中。
 
 ## Docker 节点配置 {#docker-node-configuration}
 
@@ -140,37 +139,31 @@ agent host 需要一个委派给它的 cgroup v2 目录。它在该目录中为
 
 ## 安装目录 {#installation-directory}
 
-安装程序会创建安装目录，默认路径为 `~/.oac/core`，权限模式为 `0700`。机密文件为 `0600`。
+安装目录默认为 `~/.oac/core`（Windows 为 `$HOME/.oac/core`）。其中保存进程设置和原生管理命令；服务持久数据位于 [Compose 数据卷](#compose-installations)。
 
 | 路径 | 内容 | 修改者 |
 | --- | --- | --- |
-| `.env` | [进程设置](#process-settings-configjson)。由你编辑的文件 | 你，然后运行 `oac apply`；托管域名设置写入 `OAC_PUBLIC_URL` |
-| `compose.yaml` | 发行版的服务定义。不要编辑 | 发行版 |
-| `oac` | [管理命令](getting-started/operations.md#the-oac-command)，从 Core 镜像复制 | 安装程序 |
-| `data/secrets/web/core.key` | [Core 密钥](getting-started/operations.md#core-key) | `oac rotate-core-key` |
-| `data/secrets/core/credential.key` | 加密 Core 在数据库中封存内容的密钥 | 无。必须与数据库一同保留 |
-| `data/secrets/core/core-key-digests.json` | Core 密钥的 SHA-256 | `oac rotate-core-key` |
-| `data/secrets/database/password` | PostgreSQL 密码 | 无。PostgreSQL 仅在创建数据库时读取 |
-| `data/database/` | PostgreSQL 数据 | PostgreSQL |
-| `data/node-payload/` | Web 在 `/node-install/` 提供的节点文件 | 初始化 |
-| `data/state/` | 私有 Provider 状态，包括 E2B 回执 | Core |
-| `.oac.lock` | 安装锁 | 会修改安装状态的 `oac` 命令 |
-
-Compose 项目名为 `oac-<10 hex digits>`。服务包括 `init`、`database`、`core` 和 `web`。Core 启动时执行数据库迁移。`web` 提供控制台并把 `/v1` 和 `/api/v1` 转发到 Core，是唯一发布端口（`OAC_WEB_PORT`）的服务。没有服务持有 Docker 套接字。除 Docker 存储外，不会向安装目录之外写入任何内容。
+| `.env` | 进程设置和固定的 Compose 项目名 | 用户修改后运行 `oac apply` |
+| `compose.yaml`、`compose-sha256sums.txt` | 已校验的发行版服务定义 | 发行流程 |
+| `oac`（Windows 为 `oac.exe`） | 原生管理命令 | 安装程序 |
+
+同级 `<install-dir>.lock` 目录用于同步操作并一直保留；`<install-dir>.staging` 保存尚未就位的安装文件。两者都不保存服务数据。Unix 上安装程序以 `0700` 创建私有目录，以 `0600` 创建配置文件。
+
+Compose 项目名为 `oac-<10 hex digits>`，服务包括 `init`、`database`、`core` 和 `web`。Core 启动时执行数据库迁移。Web 提供控制台并把 `/v1`、`/api/v1` 转发到 Core，是唯一发布端口（`OAC_WEB_PORT`）的服务。没有服务持有 Docker 套接字。
 
 ## 附录：没有安装程序时的 Core 环境 {#appendix-core-environment-without-the-installer}
 
-Core 只读取其环境。Compose 把 `.env` 插值进服务环境。Compose 必须为 2.26.0 或更高版本。如果你自行运行 Core，请设置这些变量；见[服务指南](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/services/core/README.md)。
+Core 读取进程环境。Compose 将 `.env` 插值到环境中，并把机密文件挂载到下表中的容器路径。直接运行 Core 时，将文件变量设为 Core 进程可读取的绝对路径；见[服务指南](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/services/core/README.md)。
 
 | 变量 | 设置来源 |
 | --- | --- |
 | `OAC_PUBLIC_URL` | `public_url`，或 Core 的回环源地址。Core 从中派生守护进程 WebSocket URL、自托管 `remote_url`、托管沙箱地址和部署的只读 `core_url`，绝不从请求标头派生。未设置时，Core 不运行 Runtime 网关，也不执行任何 Session |
 | `OAC_ADDR` | 安装程序在容器中设置为 `:8091`。独立启动的 Core 在未设置或为空时，默认使用 `127.0.0.1:8091` |
 | `OAC_DATABASE_URL` | 该安装不含密码的 PostgreSQL URL，并将 `core.database_pool` 作为 `pool_*` 查询参数附加到其中 |
-| `OAC_DATABASE_PASSWORD_FILE` | `data/secrets/database/password`。此时 URL 不得包含密码 |
-| `OAC_CREDENTIAL_KEY_FILE` | `data/secrets/core/credential.key` |
-| `OAC_CORE_KEY_DIGESTS_FILE` | `data/secrets/core/core-key-digests.json`：一个包含 Core 密钥 SHA-256 的 JSON 数组 |
-| `OAC_INSTALLATION_ID_FILE` | `data/secrets/core/installation.id`：安装 ID，采用规范 UUID 格式。它会启用沙箱部署和节点路由，并要求设置 `OAC_PUBLIC_URL` 和 `OAC_CORE_KEY_DIGESTS_FILE`。如果 ID 与数据库记录的 ID 不一致，Core 会拒绝它，因此必须将两者一同保留 |
+| `OAC_DATABASE_PASSWORD_FILE` | `/run/database/password`。此时 URL 不得包含密码 |
+| `OAC_CREDENTIAL_KEY_FILE` | `/run/oac/credential.key` |
+| `OAC_CORE_KEY_DIGESTS_FILE` | `/run/oac/core-key-digests.json`：一个包含 Core 密钥 SHA-256 的 JSON 数组 |
+| `OAC_INSTALLATION_ID_FILE` | `/run/oac/installation.id`：安装 ID，采用规范 UUID 格式。它会启用沙箱部署和节点路由，并要求设置 `OAC_PUBLIC_URL` 和 `OAC_CORE_KEY_DIGESTS_FILE`。如果 ID 与数据库记录的 ID 不一致，Core 会拒绝它，因此必须将两者一同保留 |
 | `OAC_EXECUTION_CONCURRENCY`、`OAC_DEFAULT_HARNESS`、`OAC_HARNESSES`、`OAC_WRITE_AUDIT_RETENTION`、`OAC_OAUTH_TRUSTED_ORIGINS` | 对应的[进程设置](#settings)。`oac-core check-config` 会在不启动 Core 的情况下校验它们 |
 | `OAC_HISTORY_SETTINGS_FILE` | 可选的 Runtime 历史文件。敏感；安装报告只说明它是否已设置 |
 | `OAC_LOG_LEVEL`、`OAC_LOG_FORMAT`、`OAC_LOG_ADD_SOURCE` | `log.*`；Web 也读取这三个设置 |
@@ -184,7 +177,7 @@ Core 会记录所加载文件的路径，但绝不记录环境变量的值或文
 
 ## 附录：没有安装程序时的 Web 环境 {#appendix-web-environment-without-the-installer}
 
-Compose 为 Web 设置这些变量。仅在不使用 Compose 运行控制台时才自行设置。该安装的机密信息中，Web 只收到 `data/secrets/web/core.key`。
+Compose 为 Web 设置这些变量。仅在不使用 Compose 运行控制台时才自行设置。Compose 把数据卷的 `secrets/web/` 挂载到 `/run/oac`，并设置 `OAC_WEB_CORE_KEY_FILE=/run/oac/core.key`。
 
 | 变量 | 默认值 | 含义 |
 | --- | --- | --- |
diff --git a/docs/zh/development.md b/docs/zh/development.md
index d7f3e4936..2ddd14279 100644
--- a/docs/zh/development.md
+++ b/docs/zh/development.md
@@ -1,7 +1,7 @@
 ---
 title: "开发 OpenAgentCore"
 source: docs/development.md
-source_hash: 0b208c7e4ec19ed8f35d3553c9ff9a0b5579a4f2958b8344d669c562ba8b9fe6
+source_hash: f0e5430d71b2d1f5f34569f9e4d0b623b9983175758bb217fa5f208913118da8
 ---
 
 准备工作副本，构建组件并验证修改。如需使用已安装的实例，从[入门指南](getting-started/index.md)开始。修改代码前阅读[贡献者规则](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/CONTRIBUTING.md)。
@@ -103,7 +103,7 @@ Core 构建产物和输出目录设置见[独立 Core 构建](maintainers.md#sta
 | --- | --- |
 | Core handler、持久化或 client | `make check-core` |
 | SQL 查询 | `make sqlc-generate`，检查生成文件，再运行 `make check-sqlc` |
-| Handler annotation 或 API 契约 | `make openapi`，检查三个命名空间的 schema |
+| 公共 schema、Core 扩展或内部处理函数注解 | `make openapi`、`make check-openapi`；检查生成类型和三个命名空间的 schema |
 | 共享 Runtime 协议 | `make check-runtime-contract` |
 | Provider 集成 | `make check-sandbox-provider-contract` 和 provider 的原生检查 |
 | Claude SDK bridge 与产物 | `make check-claude-sdk` |
diff --git a/docs/zh/getting-started/install-options.md b/docs/zh/getting-started/install-options.md
index b0faa317d..fe55a0610 100644
--- a/docs/zh/getting-started/install-options.md
+++ b/docs/zh/getting-started/install-options.md
@@ -1,10 +1,10 @@
 ---
 title: "安装选项与高级部署"
 source: docs/getting-started/install-options.md
-source_hash: e063d7dcd615ef5d6ba8b43f1cbe5a11c75325925605f376161f50b9383297c0
+source_hash: 2e7717f76a46694af3c1ef33a56b195c0a321f54fd7318b488179b4b4c61f336
 ---
 
-[默认安装](install.md)无需任何选项。使用本页可以在现有反向代理后运行，或者在无法访问互联网时进行安装。
+[默认安装](install.md)无需任何选项。本页介绍安装选项、Compose 部署和反向代理配置。
 
 向下载的脚本传递选项：
 
@@ -12,13 +12,11 @@ source_hash: e063d7dcd615ef5d6ba8b43f1cbe5a11c75325925605f376161f50b9383297c0
 ./install.sh --public-url https://core.example
 ```
 
-使用单行命令时，请将选项追加在 `bash -s --` 之后。发布包下载器还接受 `--version TAG` 来选择已发布的版本；否则会选择最新的稳定版本。它会在解压前验证捆绑包的 SHA-256，并保留已验证的捆绑包以供[修复](operations.md#installation-version-policy)。
-
-安装程序会打印每个阶段，然后打印地址、登录信息和后续步骤的摘要。设置 `NO_COLOR=1` 可禁用彩色输出。任一步骤失败都会停止安装，并且不会显示成功消息。
+Windows 可下载 `install.ps1`，然后使用相同参数，例如 `& ./install.ps1 --public-url https://core.example`。Unix 单行命令的参数追加在 `bash -s --` 后。`--version TAG` 选择已发布的版本；默认选择最新稳定版，并校验原生命令和 Compose 文件的 SHA-256。
 
 ## Docker Compose 与托管平台 {#docker-compose-and-hosting-platforms}
 
-在 Linux amd64 上使用发行版中的 `compose.yaml` 和 Docker Compose 2.26 或更高版本。发行流程会在 [Compose 模板](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/deploy/compose/compose.yaml)中固定初始化镜像及源码版本。Core 和 Web 使用 `latest` 镜像，PostgreSQL 使用 `postgres:16-alpine`。它会启动 PostgreSQL、Core 和 Web。Web 把 `/v1` 和 `/api/v1` 转发到 Core。数据通过目录 bind mount 挂载。一次性初始化服务会在该目录中生成随机机密信息并准备节点安装程序；Core 启动时执行数据库迁移。[Compose 配置](../configuration.md#compose-installations)负责管理各项设置和数据目录。
+在任一[支持的 Core 主机](install.md#prerequisites)上使用发行版中的 `compose.yaml`。发行流程会在 [Compose 模板](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/deploy/compose/compose.yaml)中固定初始化镜像及源码版本。Core 和 Web 使用 `latest` 镜像，PostgreSQL 使用 `postgres:16-alpine`。它会启动 PostgreSQL、Core 和 Web。Web 把 `/v1` 和 `/api/v1` 转发到 Core。数据保存在 Docker 命名卷中。一次性初始化服务会在该目录中生成随机机密信息并准备节点安装程序；Core 启动时执行数据库迁移。[Compose 配置](../configuration.md#compose-installations)负责管理各项设置和数据目录。
 
 进行本地试用时，请将发行版的 `compose.yaml` 下载到一个空目录，然后运行：
 
@@ -27,7 +25,7 @@ docker compose up -d --wait --wait-timeout 900
 docker compose exec web oac-web core-key
 ```
 
-`oac-web core-key` 会将生成的 Core 密钥打印到终端，而不会将其写入容器日志。打开 `http://localhost:8080` 并使用该密钥登录。所有安装机密信息都会自动生成；重启时请保留同一个 Compose 项目及其数据目录。
+`oac-web core-key` 会将生成的 Core 密钥打印到终端，而不会将其写入容器日志。打开 `http://localhost:8080` 并使用该密钥登录。所有安装机密信息都会自动生成；重启时请保留同一个 Compose 项目及其数据卷。
 
 初始化镜像除初始化命令外，仅包含较小的节点安装元数据。首次启动会验证并复制这些元数据，无需下载控制归档或访问 GitHub Releases。后续启动会验证已保存的文件。容器镜像仍需拉取。首次初始化中断后可以重新运行；如果现有数据库缺少安装机密信息，初始化会被拒绝。
 
@@ -45,7 +43,7 @@ docker compose exec web oac-web core-key
 
 登录后，使用 [Nodes](nodes.md)选择沙箱后端并添加节点。Compose 堆栈部署控制平面；执行机器仍需单独部署。
 
-使用相同的文件和环境运行 `docker compose stop` 以停止服务。停止服务后，备份数据目录。请遵循[安装版本策略](operations.md#installation-version-policy)：使用不同发布版本时，需要创建新的 Compose 项目并使用全新的数据目录。
+使用相同的文件和环境运行 `docker compose stop` 以停止服务。停止服务后，备份数据卷。请遵循[安装版本策略](operations.md#installation-version-policy)：使用不同发布版本时，需要创建新的 Compose 项目并使用全新的数据卷。
 
 ## 进程设置 {#process-settings}
 
@@ -64,7 +62,7 @@ docker compose exec web oac-web core-key
 
 | 选项 | 用途 |
 | --- | --- |
-| `--install-dir DIR` | 绝对安装目录；默认为 `~/.oac/core`。新安装要求目录为空或不存在，或者包含一个[从未启动过的安装](install.md#install) |
+| `--install-dir DIR` | 绝对安装目录；默认为 `~/.oac/core`。新安装使用空目录或不存在的目录；[重试](install.md#install)使用已有安装目录 |
 
 只要使用不同的安装目录和端口，多个安装就可以共用一台机器。需要更多安装时，请使用不同的 IP 地址或共享反向代理。每个安装都有自己的数据库、Core 密钥和节点。
 
@@ -137,4 +135,4 @@ http://:8443 {
 
 ## 离线主机 {#offline-hosts}
 
-本安装程序不支持从离线捆绑包安装。它从发布版本下载 Compose 文件和容器镜像。
+Core 安装需要访问 GitHub Releases 和容器注册表，以下载发行文件和镜像。
diff --git a/docs/zh/getting-started/install.md b/docs/zh/getting-started/install.md
index 40e140379..8e755c993 100644
--- a/docs/zh/getting-started/install.md
+++ b/docs/zh/getting-started/install.md
@@ -1,10 +1,10 @@
 ---
 title: "安装 Core 和 Web"
 source: docs/getting-started/install.md
-source_hash: 2389430601d1241a9d6fe376f6d3d1fbbf2900f65c152800e14ebd1959c9dcd7
+source_hash: 282d54e2c234a8e0d1d3161cf9f2bb6f0946fd60c2878d5a1c4eaf67bd6955a0
 ---
 
-一条命令即可在 Linux 主机上安装 Core、Web 控制台和 PostgreSQL。用 Core 密钥登录 Web，设置默认模型并签发 Project API 密钥。应用使用这些密钥调用 Core。Session 在你添加的节点上的沙箱中运行，也可以在 E2B 上运行。
+一条命令即可在 Linux、macOS 或 Windows 上安装 Core、Web 控制台和 PostgreSQL。用 Core 密钥登录 Web，设置默认模型并签发 Project API 密钥。应用使用这些密钥调用 Core。Session 在你添加的节点上的沙箱中运行，也可以在 E2B 上运行。
 
 1. [检查前置条件](#prerequisites)。
 2. [运行安装程序](#install)。
@@ -18,21 +18,29 @@ source_hash: 2389430601d1241a9d6fe376f6d3d1fbbf2900f65c152800e14ebd1959c9dcd7
 
 ## 前置条件 {#prerequisites}
 
-- Linux amd64 和 curl。
-- Docker Engine 和 Docker Compose 2.26.0 或更高版本（`docker compose version`）。
+- Linux amd64/arm64 或 macOS Intel/Apple Silicon，需安装 curl；Windows x64 需 PowerShell。
+- Docker Engine 26 或更高版本，以及 Docker Compose 2.26.0 或更高版本。macOS 和 Windows 使用已启动的 Docker Desktop，并选择 Linux 容器。
 - 能运行 `docker` 并向自己的主目录写入文件的账号。普通用户和 root 均可；安装程序不会调用 sudo。
 - Web 的 8080 端口空闲。参阅[端口](install-options.md#ports)。Docker 必须能发布该端口；安装程序不会修改主机策略。
 - 本机以外的访问要求 `OAC_PUBLIC_URL` 就是浏览器、节点和执行器使用的地址。可以先在本机登录。
 
-Core 主机不需要 KVM；运行 microsandbox 的节点需要。
+沙箱节点运行在 Linux amd64 上。在 macOS 或 Windows 上部署 Core 时，可连接 Linux 节点，或使用 E2B。
 
 ## 安装 {#install}
 
+Linux 和 macOS：
+
 ```sh
 curl -fsSL https://github.com/MiniMax-AI/OpenAgentCore/releases/latest/download/install.sh | bash
 ```
 
-如果主机默认路由的源地址是私有网络地址，安装程序把公开 URL 设为 `http://<that address>:8080`，同一网络的机器即可打开 Web 并添加节点；否则只有本机可以访问。反向代理已经提供这台主机时，传入它的 HTTPS 地址：
+Windows PowerShell：
+
+```powershell
+irm https://github.com/MiniMax-AI/OpenAgentCore/releases/latest/download/install.ps1 | iex
+```
+
+绑定所有 IPv4 地址时，安装器会使用默认路由的私网地址；如果没有可用私网地址，则使用 `http://localhost:8080`。也可以通过 `--public-url` 指定可访问的源地址；如果已有反向代理，就使用它的 HTTPS 地址：
 
 ```sh
 curl -fsSL https://github.com/MiniMax-AI/OpenAgentCore/releases/latest/download/install.sh | bash -s -- --public-url https://core.example
@@ -40,13 +48,13 @@ curl -fsSL https://github.com/MiniMax-AI/OpenAgentCore/releases/latest/download/
 
 脚本下载该发布版的 Compose 文件，校验 SHA-256，然后：
 
-1. 检查 Linux amd64、Docker Compose 2.26 或更高版本，以及将要发布的端口是否空闲；
-2. 创建[安装目录](../configuration.md#installation-directory) `~/.oac/core`，写入 `.env`，并从 Core 镜像复制 `oac` 命令；
+1. 检查 Docker 使用 Linux 容器、符合版本要求，并确认所选端口空闲；
+2. 准备[安装目录](../configuration.md#installation-directory) `~/.oac/core`，写入 `.env` 和原生 `oac` 命令（Windows 为 `oac.exe`）；
 3. 用 Docker Compose 启动服务。Web 在 8080 端口提供控制台，并把 `/v1`、`/api/v1` 和 `/docs` 转发到 Core。Core 和 PostgreSQL 不发布端口。
 
-安装程序不保存沙箱后端，不添加节点，不创建 Project 或密钥，也不发起模型请求。完成后输出控制台地址和 Core 密钥。
+安装器会打印控制台地址和 Core 密钥。登录后，在 Web 中配置执行资源并创建 Project。
 
-安装目录就位前，先完成下载和配置检查。之后的失败会保留配置与数据，并显示服务日志。修复报错后，重新执行同一命令，或指定安装目录即可继续：
+安装目录就位前，先完成下载和配置检查。之后的失败会保留配置与数据，并报告失败步骤；在安装目录运行 `docker compose logs --tail 100` 查看日志。修复报错后，重新执行同一命令，或指定安装目录即可继续：
 
 ```bash
 curl -fsSL https://github.com/MiniMax-AI/OpenAgentCore/releases/latest/download/install.sh | bash -s -- --install-dir "$HOME/.oac/core"
@@ -65,6 +73,8 @@ curl -fsSL https://github.com/MiniMax-AI/OpenAgentCore/releases/latest/download/
    ~/.oac/core/oac core-key --show
    ```
 
+   Windows 使用 `& "$HOME/.oac/core/oac.exe" core-key --show`。各平台的命令参数相同。
+
 ## 配置公开地址 {#configure-the-domain-and-https}
 
 应用、节点和沙箱通过同一个地址访问 Core，即公开 URL。局域网上用 HTTP 即可。对外暴露时，在前面放反向代理，并把公开 URL 设为它提供的 HTTPS 源地址。E2B 客户机从互联网访问 Core，因此需要非回环的公开 URL。
diff --git a/docs/zh/getting-started/operations.md b/docs/zh/getting-started/operations.md
index 2c984de19..d3a895836 100644
--- a/docs/zh/getting-started/operations.md
+++ b/docs/zh/getting-started/operations.md
@@ -1,14 +1,14 @@
 ---
 title: "管理你的安装"
 source: docs/getting-started/operations.md
-source_hash: ca3c732922173605cc3ab78e6afce774cc910af67b9547bd7e3c9dfde7f5ce66
+source_hash: c26691a77709f2657dad76cbb63148c625e11c4f47dd55480143158399420a02
 ---
 
 安装运维人员负责 Core 主机、存储和可用性。节点主机运行各自的服务；参阅[节点](nodes.md)。设置见[配置参考](../configuration.md)。
 
 ## oac 命令 {#the-oac-command}
 
-每个安装目录中都有自己的管理命令，无需发行包或 root：
+每个安装目录都有自己的原生管理命令：Unix 使用 `oac`，Windows 使用 `oac.exe`。命令需要 Docker 访问权限，不需要 root：
 
 ```sh
 docker compose -f ~/.oac/core/compose.yaml ps
@@ -20,11 +20,11 @@ docker compose -f ~/.oac/core/compose.yaml ps
 | `docker compose start` | 启动服务 |
 | `docker compose stop` | 停止服务。保留数据、节点和沙箱 |
 | `oac apply` | 先运行 `oac-core check-config`，再执行 `docker compose up -d --wait`。校验失败时不改动任何服务 |
-| `oac core-key [--show]` | 打印 Core 密钥路径；加上 `--show` 时打印密钥本身 |
+| `oac core-key [--show]` | 指出 Core 密钥在数据卷中的位置；加上 `--show` 时打印密钥本身 |
 | `oac rotate-core-key` | 替换 Core 密钥并重启 Core 和 Web |
 | `docker compose down` | 移除容器。数据保留；要删除数据，请[卸载](#uninstall) |
 
-第二个安装使用自己的目录，例如 `~/.oac/second`。
+示例使用默认安装目录。Windows 上使用 `& "$HOME/.oac/core/oac.exe"` 调用管理命令，后接相同参数。使用自定义安装目录时，替换各命令中的路径。
 
 ## 服务健康状态 {#service-health}
 
@@ -65,13 +65,13 @@ Web 重启（包括 `oac apply` 引起的重启）会让所有控制台用户退
 
 ## Core 密钥 {#core-key}
 
-每个安装有一个管理员凭据，即 Core 密钥。安装程序在 `data/secrets/web/core.key` 生成以 `oac_admin_` 为前缀、后接 64 个随机小写十六进制字符的密钥。用 `oac core-key --show` 读取；该文件属于容器用户。Core 密钥：
+每个安装有一个管理员凭据，即 Core 密钥。安装程序在 `secrets/web/core.key` 生成以 `oac_admin_` 为前缀、后接 64 个随机小写十六进制字符的密钥。用 `oac core-key --show` 读取；该文件属于容器用户。Core 密钥：
 
 - 用于登录 Web。浏览器获得 HttpOnly 会话 cookie，不持有密钥；
 - 通过 `Authorization: Bearer <Core key>` 授权 Core API（`/core/v1`）请求；
 - 不授权 Agents API（`/v1`）。应用使用 Project API 密钥，后者也不能调用 `/core/v1`。
 
-请保密。Web 读取 `data/secrets/web/core.key`。Core 只读取 `data/secrets/core/core-key-digests.json` 中的 SHA-256。Core 密钥至少 32 字符且不含空白。Web 限制失败登录。
+请保密。Web 读取 `secrets/web/core.key`。Core 只读取 `secrets/core/core-key-digests.json` 中的 SHA-256。Core 密钥至少 32 字符且不含空白。Web 限制失败登录。
 
 ### 用脚本调用 Core API {#script-the-core-api}
 
@@ -105,7 +105,7 @@ core() (  # core METHOD PATH [JSON body]
 ~/.oac/core/oac rotate-core-key
 ```
 
-它把新密钥写入 `data/secrets/web/core.key`，重新生成 `data/secrets/core/core-key-digests.json`，并重启 Core 和 Web。Core 重启后旧密钥立即失效，所有控制台会话结束：重新登录并更新脚本。
+它在初始化容器中更新数据卷内的 `secrets/web/core.key` 和 `secrets/core/core-key-digests.json`，然后重启 Core 与 Web。Core 重启后旧密钥立即失效，控制台会话也会结束；请重新登录并更新脚本。
 
 ## Project 和 API 密钥 {#projects-and-api-keys}
 
@@ -125,38 +125,34 @@ Core 记录每次公开资源写入所使用的密钥；历史保留策略为 [`
 
 一起备份这些内容；恢复时全部需要：
 
-- PostgreSQL 卷 `<project>_database`。其中包含 Project、密钥摘要、节点、默认模型、加密凭据和全部执行历史（含大对象）。逻辑备份：
+- Docker 卷 `<project>_data`，包括其中的 `database/`、`secrets/` 和 `state/` 目录。其中包含 Project、密钥摘要、节点、默认模型、加密凭据和全部执行历史（含大对象）。逻辑备份：
 
   ```sh
   docker compose -f "$HOME/.oac/core/compose.yaml" exec -T database \
     pg_dump -U agents_api agents_api > oac-backup.sql
   ```
 
-- 安装目录，尤其是 `data/`。`data/secrets/core/credential.key` 必须与数据库一起保留，否则无法解密存储的凭据。
+- 安装目录中的 `.env`、`compose.yaml` 和管理命令。数据卷内的 `secrets/core/credential.key` 必须与数据库一起保留，否则存储的凭据无法解密。
 
-先 `docker compose stop`，打包安装目录，再 `docker compose start`。
 - 各节点主机上的状态目录 `/var/lib/oac-node/.oac/nodes/<installation-id>/` 及提供商存储：Docker 卷或 microsandbox 存储。恢复方法见[节点主机故障时](nodes.md#when-a-node-host-fails)。
-- 安装所使用的发行包，用于修复同一版本。
 
-不要通过清理 Docker 卷或删除原生 Harness 历史来让重试成功。Session 已删除不证明所有提供商资源已回收。
+运行 `docker compose stop`，导出完整数据卷并归档安装目录，再运行 `docker compose start`。Docker Desktop 的 **Volumes** 页面支持导出数据卷。SQL 转储不包含加密密钥和 Provider 状态。
 
 ## 卸载 {#uninstall}
 
 ```sh
 cd ~/.oac/core
-docker compose down --remove-orphans
-docker compose run --rm --no-deps --entrypoint find init /data -mindepth 1 -delete
-docker compose down --rmi all
+docker compose down --volumes --remove-orphans --rmi all
 cd && rm -rf ~/.oac/core
 ```
 
-`data/` 归容器所有，因此由 `init` 镜像删除其内容；随后 `down --rmi all` 移除镜像，`rm` 删除安装目录。只有确定要删数据时才执行这些命令。
+`down --volumes` 会删除安装数据卷。之后删除安装目录；Windows 使用 `Remove-Item -Recurse "$HOME/.oac/core"`。
 
 全部数据随之删除：Project 和 API 密钥、Session 历史、存储的凭据和 Core 密钥。要保留数据，请用 `docker compose stop` 停止安装，或先[备份](#back-up)。
 
 卸载不停止沙箱：节点沙箱在节点继续运行，E2B 沙箱在 E2B 继续运行并计费。Core 仍运行时，归档它们的 Session，或[重置部署](nodes.md#change-the-sandbox-configuration)并等待完成；命令展示 Core 正在使用的沙箱数量。
 
-其他主机上的节点继续运行。按常规方式卸载时，先在 Web 移除，见[移除节点](nodes.md#remove-a-node)。安装目录删除后，它们的 Core 已不存在：在各节点主机使用当时发布版的 `node-install.pyz`，执行带 `--force` 的节点卸载命令。安装 ID 在 `data/secrets/core/installation.id`。
+其他主机上的节点继续运行。按常规方式卸载时，先在 Web 移除，见[移除节点](nodes.md#remove-a-node)。安装目录删除后，它们的 Core 已不存在：在各节点主机使用当时发布版的 `node-install.pyz`，执行带 `--force` 的节点卸载命令。安装 ID 在数据卷的 `secrets/core/installation.id` 中。
 
 ## 安装版本策略 {#installation-version-policy}
 
@@ -166,7 +162,7 @@ cd && rm -rf ~/.oac/core
 
 中断的安装可以[沿用已保存配置继续](install.md#install)。与本安装无关的非空目录会被拒绝。
 
-安装程序和修改状态的 `oac` 命令持有 `.oac.lock`。安装程序准备目录时还持有同级的 `<install-dir>.install.lock`。其他命令持有锁时，等待其结束后重试。不要删除锁文件来绕过忙碌安装。
+安装程序和修改状态的 `oac` 命令共用[安装锁](../configuration.md#installation-directory)。其他命令正在运行时，等待其结束后重试。
 
 ## 问题排查 {#troubleshooting}
 
diff --git a/docs/zh/maintainers.md b/docs/zh/maintainers.md
index 0327a7a09..164886e4c 100644
--- a/docs/zh/maintainers.md
+++ b/docs/zh/maintainers.md
@@ -1,14 +1,17 @@
 ---
 title: "构建并发布 OpenAgentCore"
 source: docs/maintainers.md
-source_hash: 9c10ea0accfa7e2efe74e40e65e498f108d03fe4b09d7f78ea77ca78655aa2be
+source_hash: 5c3db1ed5d8a29741bb90770dcab336711ef06aa95a7f546c0d6586d51b8d7c4
 ---
 
 本指南面向负责构建和发布 OpenAgentCore 的维护者。要安装 Core 和 Web，请使用 [安装指南](getting-started/install.md)。安装器代码遵循的规则见 [部署](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/deploy/README.md) 和 [节点安装器](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/deploy/node/README.md)；必需检查见 [CONTRIBUTING](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/CONTRIBUTING.md#required-checks)。
 
 ## 构建分发包 {#build-a-distribution}
 
-分发包是从同一个提交构建的一组相互匹配的 Linux amd64 发布资源：控制归档（安装器、`oac` 命令，以及 Core、Web、ingress 和 PostgreSQL 镜像）、作为独立文件的 Runtime 镜像和节点构件，以及原生安装器。
+分发包是从同一个提交构建的一组相互匹配的发布资源：控制归档（安装器、`oac` 命令，以及 Core、Web、ingress 和 PostgreSQL 镜像）、作为独立文件的 Runtime 镜像和节点构件，以及原生安装器。
+
+Core、Web 和 ingress 镜像发布为经过校验的 Linux amd64/arm64 多架构索引。arm64 控制归档包含这三个镜像；Node、托管 Runtime 和离线包使用 Linux amd64。发行构建使用 QEMU 执行 ARM 镜像步骤，包括 E2B helper。宿主机 `oac` 从同一份实现构建为 Linux amd64/arm64、macOS amd64/arm64 和 Windows amd64 二进制；启动脚本只选择、校验并运行它们。所有版本索引校验通过后才更新浮动标签。
+
 
 请在 Linux x86_64 上构建，所需环境包括与 Debian 12 兼容的 glibc、Docker、`go.mod` 中指定的 Go 版本、C 编译器（microsandbox 辅助程序使用 CGO 构建）、Node、pnpm、Python 3.9 或更高版本、curl、tar、pigz 和 sha256sum。源代码必须保持干净并已提交。请先准备固定版本的 Codex 包和 MiniMax Code 配套程序，然后执行构建：
 
@@ -107,7 +110,7 @@ bash scripts/build-agent-host-images.sh
 make build-e2b-provider
 ```
 
-Docker 使用固定版本的 CPython 和 Debian 12 镜像构建 Linux amd64 辅助程序。Python 依赖闭包（including PyInstaller）在 `services/core/tools/e2b-provider/requirements.lock` 中按哈希锁定；不需要 E2B 账户密钥。要使用其他输出目录，请设置 `E2B_PROVIDER_BUILD_DIR`。构建结果完全由辅助程序源代码、`LICENSE` 和构建脚本决定，因此会按它们的哈希缓存在 `~/.oac/cache/e2b-provider/` 下，仅在它们变化时重新构建。输出为 `oac-e2b-provider-linux-amd64.tar.gz` 及其 `.sha256`；解压后会得到 `oac-e2b-provider/`，其中包含可执行文件、`_internal/`、`licenses/`、`requirements.lock` 和 `manifest.json`。Core 镜像使用该目录树；主机需要兼容的 glibc 和 CA 证书，而不需要 Python。
+Docker 使用固定版本的 CPython 和 Debian 12 镜像按 `GOARCH=amd64`（默认）或 `GOARCH=arm64` 构建 Linux 辅助程序。Python 依赖闭包（including PyInstaller）在 `services/core/tools/e2b-provider/requirements.lock` 中按哈希锁定；不需要 E2B 账户密钥。要使用其他输出目录，请设置 `E2B_PROVIDER_BUILD_DIR`。构建结果完全由辅助程序源代码、`LICENSE` 和构建脚本决定，因此会按它们的哈希缓存在 `~/.oac/cache/e2b-provider/` 下，仅在它们变化时重新构建。输出为 `oac-e2b-provider-linux-<architecture>.tar.gz` 及其 `.sha256`；解压后会得到 `oac-e2b-provider/`，其中包含可执行文件、`_internal/`、`licenses/`、`requirements.lock` 和 `manifest.json`。Core 镜像使用该目录树；主机需要兼容的 glibc 和 CA 证书，而不需要 Python。
 
 **microsandbox 辅助程序。** 仅支持 Linux，并且需要 C 编译器：
 
@@ -122,9 +125,9 @@ make check-microsandbox-provider
 
 ### 独立 Core 构建 {#standalone-core-builds}
 
-`make build-core` 会将 `oac-core`、`oac-core-device`、`oac-core-environment-key` 和 `oac-node` 构建到 `${OAC_DEV_HOME:-$HOME/.oac}/build/oac-core`（`OAC_DEV_CORE_BUILD_DIR` 可选择其他绝对目录）。构建过程仅将 `scripts/build-core.sh` 中列出的源文件集（Core 服务、其契约、所需的共享软件包以及根 Go 模块文件）复制到临时上下文，并使用禁用 CGO、只读模块和裁剪路径的方式构建。它不需要 Node、Docker 或其他应用程序。Core 新增共享依赖时，请将该软件包加入列表；绝不能复制整个仓库来使其完成编译。
+`make build-core` 会将 `oac-core`、`oac-core-device`、`oac-core-environment-key`、`oac-node` 和 `oac` 构建到 `${OAC_DEV_HOME:-$HOME/.oac}/build/oac-core`（`OAC_DEV_CORE_BUILD_DIR` 可选择其他绝对目录）。构建过程仅将 `scripts/build-core.sh` 中列出的源文件集（Core 服务、其契约、所需的共享软件包以及根 Go 模块文件）复制到临时上下文，并使用禁用 CGO、只读模块和裁剪路径的方式构建。它不需要 Node、Docker 或其他应用程序。Core 新增共享依赖时，请将该软件包加入列表；绝不能复制整个仓库来使其完成编译。
 
-`make docker-build-core` 会根据这五个命令和 E2B 辅助程序构建 `oac-core:dev` 镜像（`OAC_DEV_CORE_IMAGE` 可选择其他名称）。基础镜像是通过摘要固定的 `debian:bookworm-slim`，包含 CA 证书以及辅助程序所需的 glibc 运行时；默认用户的 UID/GID 为 65532，Core 监听 `:8091`。该镜像仅支持 Linux amd64，并且不会推送到注册表。对镜像或其构建进行更改时，除了相关的源代码检查外，还必须运行 `make check-core-container`：它会在只读根文件系统上针对该镜像运行官方客户端测试套件，并且需要 Linux Docker、非 root 用户，以及服务检查中的[测试数据库和固定版本 SDK](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/services/core/README.md#official-client-verification)（`OAC_TEST_DATABASE_URL` 指向一个已应用迁移的 `oac_*_tests` 数据库，并设置 `OAC_TEST_OFFICIAL_SDK_PYTHON`）。
+`make docker-build-core` 会根据这五个命令和 E2B 辅助程序构建 `oac-core:dev` 镜像（`OAC_DEV_CORE_IMAGE` 可选择其他名称）。基础镜像是通过摘要固定的 `debian:bookworm-slim`，包含 CA 证书以及辅助程序所需的 glibc 运行时；默认用户的 UID/GID 为 65532，Core 监听 `:8091`。此本地构建目标生成 Linux amd64 镜像；[分发构建](#build-a-distribution)生成两种架构的镜像。对镜像或其构建进行更改时，除了相关的源代码检查外，还必须运行 `make check-core-container`：它会在只读根文件系统上针对该镜像运行官方客户端测试套件，并且需要 Linux Docker、非 root 用户，以及服务检查中的[测试数据库和固定版本 SDK](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/services/core/README.md#official-client-verification)（`OAC_TEST_DATABASE_URL` 指向一个已应用迁移的 `oac_*_tests` 数据库，并设置 `OAC_TEST_OFFICIAL_SDK_PYTHON`）。
 
 ## 发布版本 {#publish-a-version}
 
@@ -143,13 +146,13 @@ git push origin v1.2.3
 
 ### 容器注册表 {#container-registry}
 
-版本发布和手动的 `build-<full SHA>` 草稿都会将 Linux amd64 镜像发布为 `ghcr.io/minimax-ai/openagentcore/<component>:<version>`，其中 `<component>` 为 `core`、`web`、`runtime` 或 `ingress`。例如，`ghcr.io/minimax-ai/openagentcore/core:v1.2.3`。草稿使用标签 `build-<full SHA>`。PostgreSQL 使用其上游镜像，不会重新发布。注册表镜像从发布归档中加载，不会重新构建。仅当现有版本标签的镜像配置摘要与本次发布相同时才复用该标签；如果镜像不同，则停止发布。稳定版还会把每个组件的 `latest` 标签移到该镜像。预发布和草稿不会改动 `latest`。SemVer 构建元数据在容器标签中使用 `_` 代替 `+`；长度超过 128 个字符的版本字符串无法发布到 GHCR。镜像验证之后，发布器会上传为该发行版渲染的单个 `compose.yaml` 及其校验和清单。Compose 使用注册表摘要固定 ingress 镜像；如果镜像构建版本与 Compose 版本不同，初始化会拒绝运行。草稿 Release 保持未发布。
+版本发布和手动 `build-<full SHA>` 草稿使用 `ghcr.io/minimax-ai/openagentcore/<component>:<version>`，其中 `<component>` 为 `core`、`web`、`runtime` 或 `ingress`。Core、Web 和 ingress 索引包含 Linux amd64 和 arm64 镜像，Runtime 包含 Linux amd64。各平台镜像使用 `<version>-<architecture>` 标签，从发行归档加载。已有版本标签必须与发行镜像及平台集合一致。发布器校验全部版本索引后，才为稳定版更新 `latest`；预发布版和草稿保持 `latest` 不变。PostgreSQL 使用上游镜像。容器标签中的 SemVer 构建元数据用 `_` 替换 `+`，版本字符串上限为 128 个字符。镜像校验后，发布器上传该版本的 `compose.yaml` 和校验和清单。Compose 用索引摘要固定 ingress，初始化时检查其构建版本与 Compose 版本一致。
 
 合并的构建/发布作业使用具有 `packages: write` 权限的 `GITHUB_TOKEN`。首次发布时，GitHub 会将每个容器软件包创建为私有：软件包管理员必须先在各自的软件包设置中将全部四个软件包改为 **Public**，用户才能匿名拉取。请参阅 [GitHub container visibility](https://docs.github.com/en/packages/working-with-a-github-packages-registry/working-with-the-container-registry)。更改可见性后，请验证未认证拉取。仅更改仓库可见性并不会使新的容器软件包变为公开。
 
 GHCR 和 GitHub Releases 不共享事务。发布失败后，GHCR 中可能仍会保留一些匹配的版本标签；请保留这些镜像，并使用原始构件按照下文的草稿恢复流程操作。除清单缺失以外，注册表故障都会停止发布。作业摘要会记录按摘要固定的引用。这些镜像和渲染后的 Compose 文件仍需要[配置](configuration.md)中描述的配置、机密和路由。
 
-`install.sh` 会下载最新稳定版的 Compose 文件，或 `--version` 指定的发布版，校验 SHA-256 后启动该发布版。用法见[安装指南](getting-started/install.md#install)。
+[安装指南](getting-started/install.md#install)介绍版本选择和各平台的启动命令。
 
 Go 检查和构建作业共享 `~/.oac/cache/` 下的 Go 模块和编译器缓存目录，缓存键由运行器 OS 和架构、全部 Go 模块文件、检查/构建分区以及提交确定。分区键可防止并发作业在同一个键下保存不同的编译器子集。发布构建既可以使用后端检查的缓存，也可以使用更早发布构建的缓存。较旧的缓存只会为下载和编译提供初始内容；每项检查仍会运行。发布作业还会缓存 npm 软件包下载内容和固定版本的 microsandbox 归档，并在每次构建时验证后者的校验和。Actions 缓存可见性遵循 GitHub ref 的作用域；特定标签的缓存不会与其他发布标签共享。只有作业成功后才会保存新键。
 
@@ -190,7 +193,7 @@ gh workflow run core-release --repo MiniMax-AI/OpenAgentCore --ref main \
 
 `.github/actionlint.yaml` 会选择 hygiene 和 lint。已知工作流变更会选择其使用方：CI review 和 actionlint 工作流运行 hygiene 和 lint；原生工作流变更会添加原生检查；API 验收工作流变更会添加启用容器验收的 API 检查；网站工作流变更会添加网站检查。共享 Node 操作会选择使用它的每个作业以及 lint。新工作流或未分类的工作流/操作会选择完整门禁，直至在计划器中声明其使用方。计划器测试和 CI 测量脚本运行 hygiene；更改计划器本身会运行完整门禁。
 
-Compose 模板和 Compose 测试发生变更时，会同时选择 `distribution` 固定数据和 `compose` 冒烟作业；Core、Web、共享 Go 软件包和镜像 Dockerfile 的变更也会选择冒烟作业。安装 Docker 后，可在本地运行 `python3 scripts/compose-smoke.py` 重复该测试。该脚本使用唯一的项目、自动分配的回环端口，并将在 `~/.oac/tests/` 下生成构件；退出时移除其容器和数据卷。CI 还会在冒烟步骤失败或中断后执行清理。诊断信息会显示容器状态，但不会打印 HTTP 响应正文或登录密钥。Core、Web 和 ingress 镜像都从当前检出构建；Web 提供占位页面而不是控制台构建。构建时的节点元数据来自 `deploy/compose/smoke-pins.json` 固定的发布版本；初始化容器禁用网络运行。该测试检查通用 Compose 行为；它不会运行 Dokploy/Coolify 实例，也不会执行模型。
+Compose 模板和 Compose 测试发生变更时，会同时选择 `distribution` 固定数据和 `compose` 冒烟作业；Core、Web、共享 Go 软件包和镜像 Dockerfile 的变更也会选择冒烟作业。安装 Docker 后，可在本地运行 `python3 scripts/compose-smoke.py` 重复该测试。该脚本使用唯一的项目、自动分配的回环端口，并将在 `~/.oac/tests/` 下生成构件；退出时移除其容器和数据卷。CI 还会在冒烟步骤失败或中断后执行清理。诊断信息会显示容器状态，但不会打印 HTTP 响应正文或登录密钥。Core、Web 和 ingress 镜像都从当前检出构建；Web 提供占位页面而不是控制台构建。构建时的节点元数据来自 `deploy/compose/smoke-pins.json` 固定的发布版本；初始化容器禁用网络运行。冒烟矩阵使用 Linux amd64 和 arm64 原生 runner；原生矩阵在 Linux、macOS 和 Windows 上构建并测试共享的 Core 安装器。
 
 Go 模块和工作区输入会选择后端、API（包括容器）、原生和分发检查。每个 Node 模块都拥有自己的清单和锁文件。网站依赖项会选择网站检查；Web 依赖项会选择 Web 和浏览器检查；示例依赖项会选择示例检查；共享 TypeScript 客户端依赖项会选择 Web、浏览器和示例检查；Claude 适配器依赖项会选择 Harness、原生和分发检查。共享包管理器配置会选择所有 Node 使用方。根 TypeScript 配置会选择 Web 和示例检查；适配器 TypeScript 配置会选择 Harness 和原生检查。每个所选集合都包含 hygiene。混合变更会累加其使用方，并且每个作业都读取同一计划，而不是维护各自的路径列表。例如，仅修改通知的 PR 会跳过数据库、浏览器和原生作业，而同时修改通知和 Core 的 PR 会添加后端和 API 检查。
 
@@ -200,7 +203,9 @@ Go 模块和工作区输入会选择后端、API（包括容器）、原生和
 
 要手动执行完整检查，请使用 **Actions → core-check → Run workflow**。遇到暂时性故障时，请使用 GitHub 的 **Re-run failed jobs**，这样已成功的作业可保持完成状态。PR 更新后，Actions 并发机制会取消已被取代的运行。构建和依赖项缓存可加快执行，但不能替代成功的测试。原生发布安装器通过 Actions 构建产物在同一发布工作流的不同作业之间传递。
 
-`CI review and Feishu notification` 工作流仅在 PR 合并到 main 后运行一次。它检出合并后的提交，读取该 PR 已有的检查和日志，并报告实际状态，不会触发另一轮测试。关闭未合并 PR 不触发审查。该工作流只针对合并事件使用 `pull_request_target`，绝不在持有通知凭据时检出未合并 PR 的 head。
+`CI review and Feishu notification` 工作流在 PR 合入 main 后运行。矩阵中的 **Code review** 和 **Docs review** 使用独立的 LLM 上下文，并设置 `fail-fast: false`。两者读取合并后的提交和 PR 差异。代码审查检查实现、仓库规则和已有 CI 结果，不触发新一轮测试。文档审查会核对行为变化与文档是否一致，即使没有修改文档；修改文档时，还会检查矛盾、重复维护的事实、CONTRIBUTING 规定的主题归属及中英文含义。每项问题包含文件和行号、依据及最小修改建议。审查只读取仓库，不修改文件。
+
+每项审查返回结构化结果（`ok`、`issues` 或 `incomplete`）及分项中文结论，作为 Actions 构建产物保留七天。**Combined Feishu notification** 等待两项审查结束，通过已有的 `FEISHU_WEBHOOK_URL` 发送一张包含两份结果的 Card 2.0 卡片；可选的 `FEISHU_WEBHOOK_SECRET` 用于签名。卡片固定分为 PR 信息、行为变化、代码与仓库规则、CI 结果和文档审查，各区之间使用分隔线。未发现问题时标题为绿色，发现问题时为红色，审查未完成且尚未发现问题时为黄色。只有通知 job 能读取 webhook 密钥。审查失败、报告缺失或格式无效时标为未完成，另一项已有的结果照常展示。某项审查失败时，通知 job 仍会运行。只有飞书返回 `code=0` 才确认送达；请求失败或送达状态不明时不自动重试，以免重复发消息。每项审查的执行超时为 25 分钟。审查和发送失败不会阻止合并；关闭未合并的 PR 不触发此流程。持有通知凭据时，工作流只检出合并后的提交。
 
 浏览器作业各自拥有独立的固定数据和服务；对共享可变固定数据增加 worker 数不安全。失败的浏览器作业保留报告与 trace 七天。原生失败阶段摘要保留七天，详细输出留在 Actions 日志中；凭据和临时安装目录不上传。成功的原生归档仅用于显式手动打包或发布时上传，不重新压缩已压缩的归档。发布分发产物保留现有恢复策略；失败发布可以按前述方式复用原构建。
 
diff --git a/docs/zh/runtime-protocol.md b/docs/zh/runtime-protocol.md
index 0eb136233..80cd9a6b1 100644
--- a/docs/zh/runtime-protocol.md
+++ b/docs/zh/runtime-protocol.md
@@ -1,7 +1,7 @@
 ---
 title: "Core–Runtime 协议"
 source: docs/runtime-protocol.md
-source_hash: 3d5083634593391e5a3627961d54e1dceb7c4589f74539b3e01b677a9efbe04d
+source_hash: bda8cb83cb7a350d613c44e9b09e6ab78f604643cb31c4f8bfed9e6bcdd45820
 ---
 
 此协议在 Runtime daemon 获取机器凭据后连接 Core 与 daemon，定义 daemon 连接上消息的含义和顺序。wire 类型、限制和验证器仅在 [`internal/agentdaemon/proto`](https://github.com/MiniMax-AI/OpenAgentCore/tree/main/internal/agentdaemon/proto) 中定义一次；Core 的 [gateway](https://github.com/MiniMax-AI/OpenAgentCore/tree/main/services/core/internal/runtimegateway) 与参考 Runtime 的 [dispatcher](https://github.com/MiniMax-AI/OpenAgentCore/tree/main/apps/daemon/internal/dispatch) 都使用它们，因此无需同步第二套 payload schema。签发凭据和打开连接的 HTTP 路由见[机器连接 API](../../contracts/agents-api/zh/machine-api.md)。
@@ -22,7 +22,7 @@ Runtime 按以下顺序连接：
 
 wire 版本为 [`proto.Version`](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/version.go)，独立于 heartbeat 报告的 Runtime 构建版本。Core 仅接受精确匹配，包括 patch 部分。不匹配时，在任何 dispatch 前返回 HTTP 426 `incompatible_version`；daemon 将其视为永久错误并停止重连。应一起部署版本匹配的两端。
 
-每条物理连接拥有新的路由、admission handle 和传输状态。同一设备的新连接替代旧连接：Core 关闭旧连接并移除其 Run 和 interaction 路由，新连接不继承这些状态。有效凭据和连接不授权选择其他 Session 或 Environment 绑定；[分配](#session-assignments)约束 frame 可代表哪个 Session 行事。
+每条物理连接拥有新的路由、admission handle 和传输状态。同一设备的新连接替代旧连接：Core 关闭旧连接并移除其 Run 路由，新连接不继承这些状态。有效凭据和连接不授权选择其他 Session 或 Environment 绑定；[分配](#session-assignments)约束 frame 可代表哪个 Session 行事。
 
 ## 能力声明 {#capability-declarations}
 
@@ -53,7 +53,7 @@ wire 上每个字段都是 JSON boolean，所有字段都必须出现，包括 `
 | `message_images`, `function_result_images` | 消息或 function result 携带图像 |
 | `mcp_http_tools`, `mcp_http_required`, `mcp_http_bearer_auth` | Agent 声明 HTTP MCP server；其中一个为 `required`；其中一个选用了 Vault 凭据 |
 
-`permissions` 控制 Runtime 内部权限决定。Core 对 `usage` 和 `resume` 没有准入规则。
+Core 对 `usage` 和 `resume` 没有准入规则。
 
 `execution_prepare` 的配置携带 Session 的模型配置和 Core 为各 Run 设置的显式启用项：
 
@@ -85,13 +85,10 @@ wire 上每个字段都是 JSON boolean，所有字段都必须出现，包括 `
 | Preparation request ID | prepare、start、release 和 status 的 `Envelope.id`；与 Run 不同 |
 | Admission handle | Runtime 生成的预约，仅在接受它的连接上有效 |
 | Run ID | 一次执行尝试；输出、取消、活动输入和 function 的 `Envelope.id` |
-| Interaction ID | `permission_request.payload.request_id` 或 `prompt_for_user_choice.payload.ask_id`；这些请求 envelope 仍携带 Run ID |
 | Delivery ID / input ID / call ID | 分别标识 resolve 尝试、活动输入回执与原生 function；不能互换 |
 | Transfer ID / suspension ID | 连接本地传输关联 / 持久化 suspension 尝试的 fencing |
 
-Decision 和 permission-cancel envelope 使用 interaction ID。取消和 function-result 确认使用 Run ID。每个应用 decision 回执还要匹配 delivery ID。缺少必需关联的回复不能证明已接受。
-
-User-choice decision 携带 `question_answers`：每个已提供回答都有明确的 `question_id` 和 `answers` 数组。ID 必须属于已发出的问题且不能重复。问题顺序和显示 header 不标识回答；省略的问题仍未回答，空数组表示明确未作答。取消携带 `cancelled: true`，不包含回答。共享验证在原生提交前拒绝其他形式。
+取消和 function-result 确认使用 Run ID，并匹配 delivery ID。缺少必需关联的回复不能证明已接受。
 
 ## 消息族 {#message-families}
 
@@ -103,8 +100,7 @@ User-choice decision 携带 `question_answers`：每个已提供回答都有明
 | Runtime 无法路由的任意 frame | `protocol_error` | [Session 分配](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/assignment.go) |
 | `runtime_prepare` | `runtime_prepare_result` | [初始化与能力传输](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/runtime_prepare.go) |
 | `execution_prepare`, `execution_start`, `execution_release` | `preparation_status` | [执行准入](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/preparation.go) |
-| `prompt_cancel` | `delta`, `thinking`, `output_message`, `tool_call`, `usage`, `error`, `done`, `heartbeat` | [请求](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/outbound.go)、[事件与能力](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/inbound.go) |
-| `permission_decision`, `prompt_for_user_choice_decision` | `permission_request`, `permission_cancel`, `prompt_for_user_choice`, `interaction_decision_ack` | [请求](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/outbound.go)、[交互](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/inbound.go) |
+| `prompt_cancel` | `delta`, `thinking`, `output_message`, `tool_call`, `usage`, `error`, `done`, `heartbeat`, `interaction_decision_ack` | [请求](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/outbound.go)、[事件与能力](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/inbound.go) |
 | `prompt_steer` | `prompt_steer_ack` | [活动输入回执](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/steering.go) |
 | `function_result` | `function_call`, `interaction_decision_ack` | [Function 调用](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/functions.go) |
 | `workspace_read`, `workspace_write`, `workspace_export` | 对应的 `*_result` | [读取](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/workspace_read.go)、[写入](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/workspace_write.go)、[导出](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/internal/agentdaemon/proto/workspace_export.go) |
@@ -118,7 +114,7 @@ Usage frame 和最终 usage snapshot 都携带当前执行的累计测量，替
 
 分配（assignment）把一个 Session 绑定到运行它的 Runtime。`Envelope.assignment` 以 `session_id`、`assignment_id` 和 `epoch` 命名它，这是 frame 携带分配的唯一位置。Core 每次改变分配的期望状态时推进 epoch，因此较低的 epoch 是陈旧的。
 
-每个 Session frame 都携带分配：`execution_prepare`、`execution_start` 和 `execution_release`；`prompt_cancel`、`prompt_steer`、`function_result`、`permission_decision` 和 `prompt_for_user_choice_decision`；`runtime_prepare`、`workspace_read`、`workspace_write` 和 `workspace_export` 的每个 frame；以及 `environment_quiesce` 和 `environment_resume`。回复回显请求的分配，Run 的 frame 携带启动它的分配；Core 拒绝指明其他分配的回复或 Run frame。heartbeat 不携带分配。
+每个 Session frame 都携带分配：`execution_prepare`、`execution_start` 和 `execution_release`；`prompt_cancel`、`prompt_steer` 和 `function_result`；`runtime_prepare`、`workspace_read`、`workspace_write` 和 `workspace_export` 的每个 frame；以及 `environment_quiesce` 和 `environment_resume`。回复回显请求的分配，Run 的 frame 携带启动它的分配；Core 拒绝指明其他分配的回复或 Run frame。heartbeat 不携带分配。
 
 在一条连接上执行 Session 的第一个操作之前，包括没有 Turn 的 Environment 初始化和文件操作，Core 发送带 Session 的 Environment ID 的 `assignment_bind`，并等待 `assignment_status` `bound`。当 Runtime 是 agent host 且 Environment 有存活的 [Link](./sandbox-link-protocol.md) resource 时，绑定还携带 `resource` 和 `attach_grant`：前者是该 resource，形式与[引导输入](./sandbox-bootstrap.md#launch-input)中的相同；后者是 base64 编码的 grant，agent host 凭它在此分配和 epoch 下打开该 resource generation 上的服务。grant 是机密。Core 不向其他任何 Runtime 发送这两个字段。只带其中一个字段、或带其他 Environment 的 resource 的绑定以 `invalid_request` 失败。以相同的 Environment、resource 和 grant 重复绑定同一分配仍得到 `bound`；该分配的其他绑定以 `assignment_conflict` 失败。Runtime 只在其已绑定的分配下准入 Session frame：较旧的 epoch 或已释放的分配以 `assignment_stale` 失败；其他分配、Session 或 Environment 以 `assignment_conflict` 失败。已启动 Run 的 frame，包括其取消回执，在释放前仍可在启动它的分配下准入。Runtime 已记录回执的重复函数结果或决策只在应用它的分配下得到回答；其他分配以 `assignment_conflict` 失败。
 
@@ -175,7 +171,7 @@ Core 通过 `prompt_steer` 交付活动输入，设置 `durable_receipt: true`
 
 ## 故障、重试与清理 {#failures-retries-and-cleanup}
 
-transport 与 execution 结果分开。Core 唯一 Run 订阅入口是 `SubscribeDurable`；事件 channel 关闭时检查 `Subscription.Err()`。断连与 subscriber overflow 以明确 observation error 关闭订阅，不虚构 `error` 或 `done`。Core 保留持久事实，并依据已确认事实协调。Runtime 保留清理所有权，直到原生工作、输入回执、交互和子任务工作都结算完成。
+transport 与 execution 结果分开。Core 唯一 Run 订阅入口是 `SubscribeDurable`；事件 channel 关闭时检查 `Subscription.Err()`。断连与 subscriber overflow 以明确 observation error 关闭订阅，不虚构 `error` 或 `done`。Core 保留持久事实，并依据已确认事实协调。Runtime 保留清理所有权，直到原生工作、输入回执、function 结果和子任务工作都结算完成。
 
 公开 Turn 状态是独立投影。[`execution/delivery.go`](https://github.com/MiniMax-AI/OpenAgentCore/blob/main/services/core/internal/execution/delivery.go) 将不成功的编排尝试记录为 `failed`，包括未确认发送后的 `delivery_unknown` 和订阅失败后的 `event_stream_incomplete`；关闭的订阅可以用 `event_stream_incomplete` 替换发送原因。两者都表示原生效果未知：公开 `failed` 状态不证明 Harness 失败、没有产生副作用或清理已完成。应区分观测原因与原生证据。
 
@@ -202,7 +198,7 @@ Core 在 Turn outcome 中将接受的值保存为 `engine_error_code` 和 `engin
 
 ## 工作区操作 {#workspace-operations}
 
-无需运行 Turn 的工作区读取使用只读 preparation profile：带 `workspace_read_only` 的 `execution_prepare`，要求 `workspace_read_preparation` 能力。仅接受绑定的 Environment 和 resource 身份；不包含 execution option、model 与 MCP 凭据、原生 Session continuation、model 或 tool 输入，owner 拒绝 `execution_start`。Runtime 从绑定的本地工作区提供读取，不启动 Harness 进程。profile 仅在本地 close 成功后发布 `released`；清理错误保留所有权并报告 `cleanup_unconfirmed`。清理重试成功后发布已确认释放；旧 status snapshot 不发布成功。release 请求、HTTP 断连或远端 socket 关闭本身都不确认清理。
+无需运行 Turn 的工作区读取使用只读 preparation profile：带 `workspace_read_only` 的 `execution_prepare`，要求 `workspace_read_preparation` 能力。仅接受绑定的 Environment 和 resource 身份；不包含 execution option、model 与 MCP 凭据、原生 Session continuation、model 或 tool 输入，owner 拒绝 `execution_start`。Runtime 从绑定的本地工作区提供读取，不启动 Harness 进程。profile 在 Runtime 放弃该 preparation 的所有权后发布 `released`；旧 status snapshot 不发布成功。release 请求、HTTP 断连或远端 socket 关闭本身都不确认释放。
 
 `workspace_read` 在同一已认证设备连接上，针对现有 preparation handle 或它已转移给的 Run，使用精确冻结的 Environment 身份，列出一个 workspace 相对目录（空路径选择根目录）；调用方不能提供 socket、凭据或 workspace root。结果最多携带 `max_entries`（1 到 1024）个单路径组件 UTF-8 名称，每个最多 255 字节，并包含 entry kind、普通文件大小和明确截断信息；仅在目录访问与 handle 清理结算后返回。此层没有快照、递归或分页。
 
diff --git a/docs/zh/sandbox-link-protocol.md b/docs/zh/sandbox-link-protocol.md
index 4056fec05..99ca95126 100644
--- a/docs/zh/sandbox-link-protocol.md
+++ b/docs/zh/sandbox-link-protocol.md
@@ -1,7 +1,7 @@
 ---
 title: "沙箱 Link 协议"
 source: docs/sandbox-link-protocol.md
-source_hash: ea2004916489420736d6bc73b31f1e26b409747406c20bf646729a2fe0478c41
+source_hash: f9c047631990775331946f78c7fad835a0663932ac6a2d4bd7c2514405f00b6f
 ---
 
 Link 协议通过 relay 连接沙箱 I/O 的两端。Sandbox I/O 服务运行在沙箱内并为其提供服务，是 serve peer。agent host 上的 Runtime 在沙箱外运行 Harness，并通过该服务使用沙箱，是 attach peer。每个 peer 各自向 relay 认证自己的 link。relay 授权 attach peer 打开的每个服务 stream，将其绑定到该资源当前的 serve peer，然后在两个 stream 之间复制字节而不读取内容。服务帧从不携带凭据或 grant。
@@ -43,7 +43,15 @@ attachment 的生命周期长于其 link。重连后，Runtime 使用相同的 b
 
 ## 运行 relay {#run-a-relay}
 
-`relay.New` 接收 `Authority`，返回 `*relay.Relay`，它是一个 `http.Handler`。relay endpoint 位于安装实例的 HTTPS ingress 之后，由 ingress 终止 TLS，因此 handler 在 ingress 的明文 HTTP 一跳上接受 upgrade；peer 在拨号时强制 TLS。每条 link 最多承载 256 个并发服务 stream。
+`relay.New` 接收 `Authority`，返回 `*relay.Relay`，它是一个 `http.Handler`。relay endpoint 位于安装实例的 HTTPS ingress 之后，由 ingress 终止 TLS，因此 handler 在 ingress 的明文 HTTP 一跳上接受 upgrade；peer 在拨号时强制 TLS。
+
+每条 link 最多承载 256 个并发服务 stream，每个资源最多有 2 个裁决中的 serve Hello。relay 还最多持有 4096 个资源、16384 个 attachment 和 4096 条 attach link。Hello 或 Open 在咨询 Authority 之前占用它所需的名额。某个名额没有空闲时，它会以 `LimitExceeded` 被拒绝，且不留下任何状态：
+
+- serve Hello 在裁决结束前占用其资源的一个 Hello 名额。
+- 资源在首次指明它的 serve Hello 处占用名额，并在 relay 仍为它持有任何东西时保留该名额：其 serve peer、裁决中的 Hello、attachment 或未写出的 `AttachmentClosed` 事件。已持有资源的重连不需要新的资源名额。一个资源最多有一条 serve link，因此资源上限也限制了 serve link 的数量，并与 Hello 名额一起限制了裁决中的 serve Hello 数量。
+- Open 占用其 attach link 的一个 stream 名额。已打开的 stream 保留该名额直到 stream 结束；被拒绝的 Open 在裁决结束后归还名额，即使 peer 已先重置该 stream。
+- attachment 在创建它的 Open 处占用名额，并保留到它被关闭且其 `AttachmentClosed` 事件已写出或丢弃为止。
+- attach link 在其 Hello 处占用名额，并保留到 link 结束且它承载过的每个 stream 和续期都已结束为止。
 
 relay 的 owner 基于其持久记录实现 `Authority`，relay 对每个 Hello、Open 和续期都咨询它。撤销时，先撤回授权，再调用 `RevokeAttachment` 或 `RevokeResource`，让 relay 关闭其持有的对象。
 
@@ -196,7 +204,7 @@ AttachmentClosed
 1. peer 拨号 relay 的 URL：使用 `wss://`；仅当主机为 `localhost` 或 loopback 地址时可用 `ws://`。URL 不含 user、查询或片段，也绝不含凭据。`sandboxlink.CheckRelayURL` 对两个 peer 和[引导输入](./sandbox-bootstrap.md)应用此规则，并以 `sandboxlink.ErrRelayURL` 拒绝其他 URL。使用 `wss://` 时，由 TLS 认证 relay。
 2. peer 启动 yamux 并打开 control stream。
 3. 它以请求 ID 1 发送 Hello，作为 control stream 的第一个请求：Sandbox I/O 服务发送 `ServeHello`，Runtime 发送 `AttachHello`。凭据只在 Hello 中传输。
-4. relay 通过其 Authority 认证 peer，并回复 `HelloAccepted`，或回复失败，随后结束 link。对其他版本的 Hello，relay 不读取版本之后的内容，直接回复 `VersionMismatch`。如果 Authority 裁决 serve Hello 期间发生撤销，relay 会再次询问，因此已撤回的凭据绝不会建立 serve peer。
+4. relay 占用该 Hello 所需的[名额](#run-a-relay)，通过其 Authority 认证 peer，并回复 `HelloAccepted`，或回复失败，随后结束 link。对其他版本的 Hello，relay 不读取版本之后的内容，直接回复 `VersionMismatch`。如果 Authority 裁决 serve Hello 期间发生撤销，relay 会再次询问，因此已撤回的凭据绝不会建立 serve peer。
 
 后续控制请求延续 Hello 的请求 ID。attach link 的请求 ID 未递增时，relay 以 `ProtocolViolation` 结束该 link。`Open` 和 `Bind` 各自是其 stream 上唯一的请求，使用请求 ID 1。
 
@@ -208,10 +216,11 @@ relay 和 serve peer 以 `sandboxlink.HandshakeTimeout`（10 秒）限制每个
 
 attach peer 打开一个 stream 并发送 `Open`。relay 随后：
 
-1. 调用 `Authority.AuthorizeOpen`。Authority 检查 grant、Runtime、当前 assignment 及其 epoch、资源 generation、允许的服务和访问权限，以及资源的 serve 授权是否当前有效。它返回 binding 身份、服务、lease、`ServiceFile` 的 export 和 `ServiceNetwork` 的 egress 规则。如果 Authority 裁决期间发生撤销，relay 会再次询问。
-2. 依次检查：每条 link 的 stream 上限（`LimitExceeded`）；relay 见过的该资源最新 generation 不比 Open 中的更新（`StaleGeneration`）；Open 所指 generation 的 serve peer 已连接并提供该服务（`ServiceUnavailable`），且支持 Open 的版本（`VersionMismatch`）；非零的 `ExpectedServerInstanceID` 等于该 serve peer 的值（`InstanceChanged`）；lease 尚未到期（`LeaseExpired`）；relay 已以该 `AttachmentID` 持有的 attachment 具有完全相同的身份和 Runtime（`AttachmentConflict`）。
-3. 向 serve peer 打开 stream 并发送 `Bind`。serve peer 回复 `Bound`，或回复失败：对其不提供的服务回复 `ServiceUnavailable`，或回复 `VersionMismatch`，`ExpectedServerInstanceID` 不是自身值时回复 `InstanceChanged`，对最近关闭的 attachment 回复 `LeaseExpired`，或回复 `ProtocolViolation`。relay 将失败转交给 attach peer。`Bind` 已开始发送但未收到回复时，relay 回复带 `EffectPossible` 的 `ServiceUnavailable`。
-4. 回复 `Opened`，并将两个 stream 拼接起来。
+1. 占用该 link 的一个 stream [名额](#run-a-relay)，并在 relay 未以 Open 的 `AttachmentID` 持有 attachment 时占用一个 attachment 名额；某个名额没有空闲时回复 `LimitExceeded`。
+2. 调用 `Authority.AuthorizeOpen`。Authority 检查 grant、Runtime、当前 assignment 及其 epoch、资源 generation、允许的服务和访问权限，以及资源的 serve 授权是否当前有效。它返回 binding 身份、服务、lease、`ServiceFile` 的 export 和 `ServiceNetwork` 的 egress 规则。如果 Authority 裁决期间发生撤销，relay 会再次询问。
+3. 依次检查：serve link 的 stream 上限（`LimitExceeded`）；relay 为该资源持有的最新 generation 不比 Open 中的更新（`StaleGeneration`）；Open 所指 generation 的 serve peer 已连接并提供该服务（`ServiceUnavailable`），且支持 Open 的版本（`VersionMismatch`）；非零的 `ExpectedServerInstanceID` 等于该 serve peer 的值（`InstanceChanged`）；lease 尚未到期，且 Open 到达时 relay 持有的 attachment 此后未被关闭（`LeaseExpired`）；relay 已以该 `AttachmentID` 持有的 attachment 具有完全相同的身份和 Runtime（`AttachmentConflict`）。
+4. 向 serve peer 打开 stream 并发送 `Bind`。serve peer 回复 `Bound`，或回复失败：对其不提供的服务回复 `ServiceUnavailable`，或回复 `VersionMismatch`，`ExpectedServerInstanceID` 不是自身值时回复 `InstanceChanged`，对最近关闭的 attachment 回复 `LeaseExpired`，或回复 `ProtocolViolation`。relay 将失败转交给 attach peer。`Bind` 已开始发送但未收到回复时，relay 回复带 `EffectPossible` 的 `ServiceUnavailable`。
+5. 回复 `Opened`，并将两个 stream 拼接起来。
 
 attachment 的 binding 身份由其 `AttachmentID`、`Resource`、`SessionID`、`AssignmentID` 和 `AssignmentEpoch` 组成。无论在同一 link 还是之后的 link 上重新打开 attachment，都要求同一 Runtime 提供完全相同的身份，并具有当前有效的授权。
 
@@ -233,7 +242,7 @@ relay 在内存中保存 link、attachment 和 lease。Authority 始终是持久
 
 方法以 `*sandboxlink.Error` 表示类型化拒绝；其他任何错误都回复为 `ServiceUnavailable`。凭据 revision 和允许的访问来自 Authority，绝不来自 peer 的声明。
 
-重新创建的资源具有更高的 generation。相同或更高 generation 的 serve peer 替换资源当前的 serve peer；更高 generation 还会以 `CloseStaleGeneration` 关闭旧 generation 的所有 attachment。generation 比 relay 见过的最新 generation 更旧的 serve peer 或 Open 会以 `StaleGeneration` 被拒绝。
+重新创建的资源具有更高的 generation。相同或更高 generation 的 serve peer 替换资源当前的 serve peer；更高 generation 还会以 `CloseStaleGeneration` 关闭旧 generation 的所有 attachment。generation 比 relay 为该资源持有的最新 generation 更旧的 serve peer 或 Open 会以 `StaleGeneration` 被拒绝。relay 仅在[持有该资源](#run-a-relay)期间保留其 generation；此后由 Authority 单独拒绝更旧的 generation。
 
 ## Lease、关闭与撤销 {#leases-closing-and-revocation}
 
@@ -242,7 +251,7 @@ relay 在内存中保存 link、attachment 和 lease。Authority 始终是持久
 - `CloseAttachment` 以 `CloseRequested` 关闭调用方的 attachment。关闭未知 attachment 会成功，关闭其他 Runtime 的 attachment 返回 `PermissionDenied`。
 - `Relay.RevokeAttachment` 关闭一个 attachment。`Relay.RevokeResource` 关闭某个资源 generation 及更旧 generation 的所有 attachment，向 serve peer 写入相应的 `AttachmentClosed` 事件，然后断开它。两者都以 `CloseRevoked` 关闭。
 
-关闭 attachment 会重置其全部 stream，并向 serve peer 发送 `AttachmentClosed`；除 `CloseRequested` 外，也向其 attach peer 发送。relay 将每个 serve peer 未写出的事件保存在没有大小上限的集合中，仅在事件写出后才将其移除，因此已断开的 serve peer，或在事件写出前 link 断开的 serve peer，会在以相同 generation 重连时收到该事件。被关闭打断的 Open 根据原因以 `AttachmentConflict`、`LeaseExpired`、`PermissionDenied` 或 `StaleGeneration` 失败；其 `Bind` 可能已到达 serve peer 时带 `EffectPossible`。
+关闭 attachment 会重置其全部 stream，并向 serve peer 发送 `AttachmentClosed`；除 `CloseRequested` 外，也向其 attach peer 发送。relay 将每个 peer 未写出的事件保存在集合中，在事件写出后将其移除，因此已断开的 serve peer，或在事件写出前 link 断开的 serve peer，会在以相同 generation 重连时收到该事件。不再有 peer 能读取的事件会被丢弃：attach peer 的事件在其 link 结束时丢弃，serve peer 的事件在更新的 generation 连接或 `RevokeResource` 撤销其 generation 时丢弃。被关闭打断的 Open 根据原因以 `AttachmentConflict`、`LeaseExpired`、`PermissionDenied` 或 `StaleGeneration` 失败；其 `Bind` 可能已到达 serve peer 时带 `EffectPossible`。
 
 丢失 link 会重置其承载的 stream，并保留其 attachment，直到 lease 到期或 attachment 被关闭。
 
@@ -271,7 +280,7 @@ relay 通过 32 KiB 缓冲区复制每个方向的数据，每个 stream 最多
 | 8 | `InstanceChanged` | serve peer 的 `ServerInstanceID` 不是 `ExpectedServerInstanceID` |
 | 9 | `LeaseExpired` | lease 已过期，或 relay 不再持有该 attachment |
 | 10 | `AttachmentConflict` | 该 `AttachmentID` 以其他身份或 Runtime 被持有，或在 Open 期间被关闭 |
-| 11 | `LimitExceeded` | 达到 link 的 stream 上限，或达到裁决中续期的数量上限 |
+| 11 | `LimitExceeded` | Hello 或 Open 所需的[名额](#run-a-relay)没有空闲，serve link 已达 stream 上限，或 attach link 已达裁决中续期的数量上限 |
 | 12 | `ProtocolViolation` | 消息格式错误、出现在不允许的位置，或携带未递增的请求 ID |
 
 `ServiceUnavailable` 和 `LimitExceeded` 是临时失败：相同请求稍后可能成功，`Code.Retryable` 将它们报告为可重试。其他 code 都是最终失败：以相同凭据、attachment 和 generation 重复请求会再次失败。
@@ -280,4 +289,4 @@ relay 通过 32 KiB 缓冲区复制每个方向的数据，每个 stream 最多
 
 ## 验证 {#verification}
 
-`go test ./internal/sandboxlink/...` 覆盖 golden 帧、解码拒绝，以及 relay 的授权、generation、lease、撤销、续期上限和重连行为，包括有序结束与中止的传播。`go test -run '^$' -fuzz FuzzDecode ./internal/sandboxlink` 对解码器进行 fuzz 测试。
+`go test ./internal/sandboxlink/...` 覆盖 golden 帧、解码拒绝，以及 relay 的授权、generation、lease、撤销、容量与续期上限以及重连行为，包括有序结束与中止的传播。`go test -run '^$' -fuzz FuzzDecode ./internal/sandboxlink` 对解码器进行 fuzz 测试。
diff --git a/internal/agentdaemon/proto/envelope.go b/internal/agentdaemon/proto/envelope.go
index 25a8591ab..047a569f9 100644
--- a/internal/agentdaemon/proto/envelope.go
+++ b/internal/agentdaemon/proto/envelope.go
@@ -14,8 +14,6 @@
 // Envelope.ID correlation:
 //   - prompt_cancel / prompt_steer / function_result: ID = RunID.
 //   - delta / tool_call / usage / error / done: ID = originating RunID.
-//   - permission_request: ID = RunID; payload.request_id is the interaction ID.
-//   - permission_decision / permission_cancel: ID = interaction ID.
 //   - execution_prepare / execution_start / execution_release and
 //     preparation_status: ID = preparation request ID, never RunID.
 //   - runtime_prepare / runtime_prepare_result: ID = connection-local transfer ID.
@@ -101,8 +99,7 @@ func (e Envelope) Reply(typ string, payload any) (Envelope, error) {
 }
 
 // DecodePayload unpacks Envelope.Payload into out. An empty Payload is
-// a non-error so bodyless types (prompt_cancel, permission_cancel)
-// decode cleanly.
+// a non-error so a bodyless prompt_cancel decodes cleanly.
 func (e Envelope) DecodePayload(out any) error {
 	if len(e.Payload) == 0 {
 		return nil
diff --git a/internal/agentdaemon/proto/inbound.go b/internal/agentdaemon/proto/inbound.go
index 84d369d18..cacf1e9c8 100644
--- a/internal/agentdaemon/proto/inbound.go
+++ b/internal/agentdaemon/proto/inbound.go
@@ -28,26 +28,9 @@ const (
 	// before the call, "after" runs after.
 	TypeToolCall = "tool_call"
 
-	// TypePermissionRequest carries an agent's request for human
-	// approval. Envelope.ID is the RunID; payload.request_id identifies the decision.
-	TypePermissionRequest = "permission_request"
-
-	// TypePermissionCancel signals the agent withdrew an earlier
-	// permission request (e.g. its internal timeout fired). Used by
-	// the gateway to unblock pending SubmitPermission calls.
-	TypePermissionCancel = "permission_cancel"
-
-	// TypePromptForUserChoice asks the human to pick one (or more)
-	// answers from a closed list before the agent can continue. Used
-	// to intercept Claude Code's built-in AskUserQuestion tool so the
-	// daemon doesn't deadlock waiting for a tool_result no one will
-	// send. Envelope.ID is the RunID; payload.ask_id identifies the decision.
-	TypePromptForUserChoice = "prompt_for_user_choice"
-
 	// TypeInteractionDecisionAck confirms that the daemon-side agent
-	// accepted (or definitively rejected) a permission/user-input decision or cancellation.
-	// The server must not mark the durable interaction terminal before this
-	// frame arrives.
+	// accepted (or definitively rejected) a function result or cancellation.
+	// The server must not mark the delivery terminal before this frame arrives.
 	TypeInteractionDecisionAck = "interaction_decision_ack"
 
 	// TypeUsage reports a cumulative usage snapshot for the current execution.
@@ -100,18 +83,6 @@ type ToolCallPayload struct {
 	Result      map[string]any   `json:"result,omitempty"`
 }
 
-// PermissionRequestPayload carries an agent's request for human
-// approval. RequestID is the daemon-minted handle used to route a later
-// decision. It lives in the payload because Envelope.ID is the run ID used
-// by the server gateway to deliver the request to the active run subscriber.
-type PermissionRequestPayload struct {
-	RequestID string         `json:"request_id"`
-	Tool      string         `json:"tool"`
-	Title     string         `json:"title"`
-	Detail    string         `json:"detail,omitempty"`
-	Payload   map[string]any `json:"payload,omitempty"`
-}
-
 // InteractionDecisionAckPayload is the daemon's application-level receipt
 // for a server decision. DeliveryID correlates one resolve attempt without
 // relying on the request id, which may outlive a reconnect or timeout race.
@@ -124,44 +95,6 @@ type InteractionDecisionAckPayload struct {
 	Outcome *DonePayload `json:"outcome,omitempty"`
 }
 
-// PromptForUserChoiceOption is one button / checkbox the user can
-// pick when answering a PromptForUserChoice. Label is the human-
-// readable choice; Description is optional inline help.
-type PromptForUserChoiceOption struct {
-	Label       string `json:"label"`
-	Description string `json:"description,omitempty"`
-}
-
-// PromptForUserChoiceQuestion is one question in a (possibly multi-
-// question) AskUserQuestion call. Mirrors the Claude Code built-in
-// schema verbatim so the daemon doesn't translate the shape twice.
-type PromptForUserChoiceQuestion struct {
-	ID          string                      `json:"id"`
-	Header      string                      `json:"header,omitempty"`
-	Question    string                      `json:"question"`
-	MultiSelect bool                        `json:"multi_select,omitempty"`
-	IsOther     bool                        `json:"is_other,omitempty"`
-	IsSecret    bool                        `json:"is_secret,omitempty"`
-	Options     []PromptForUserChoiceOption `json:"options"`
-}
-
-// PromptForUserChoicePayload carries the AskUserQuestion interception.
-//
-// AskID is the daemon-minted "ask_<8hex>" handle the server uses to
-// route SubmitPromptForUserChoice back to the right session. It rides
-// on the payload (not Envelope.ID) because Envelope.ID is reserved for
-// the run id — that's the field server-side session.dispatch fans on
-// to deliver the frame to the run's subscriber channel. ToolUseID is
-// the originating Claude Code tool_use id; empty when the call came
-// through the control_request channel (CCRequestID then identifies the
-// daemon-side waiter instead but it doesn't ride on the wire).
-type PromptForUserChoicePayload struct {
-	AskID            string                        `json:"ask_id"`
-	Questions        []PromptForUserChoiceQuestion `json:"questions"`
-	ToolUseID        string                        `json:"tool_use_id,omitempty"`
-	AutoResolutionMs *uint64                       `json:"auto_resolution_ms,omitempty"`
-}
-
 // TokenUsage is a complete cumulative measurement for the current execution.
 // Adapters publish observed snapshots promptly; historical resume totals belong
 // to the adapter baseline, not this execution. Unknown fields must not become zero.
@@ -222,7 +155,6 @@ const (
 type AgentKindCapabilities struct {
 	SubagentObservations  CapabilitySupport `json:"subagent_observations"`
 	Streaming             CapabilitySupport `json:"streaming"`
-	Permissions           CapabilitySupport `json:"permissions"`
 	Usage                 CapabilitySupport `json:"usage"`
 	Resume                CapabilitySupport `json:"resume"`
 	NativeSessionRecovery CapabilitySupport `json:"native_session_recovery"`
diff --git a/internal/agentdaemon/proto/outbound.go b/internal/agentdaemon/proto/outbound.go
index 8144051c1..445055302 100644
--- a/internal/agentdaemon/proto/outbound.go
+++ b/internal/agentdaemon/proto/outbound.go
@@ -12,16 +12,6 @@ const (
 	// RunID. Idempotent — cancelling an unknown / already-finished
 	// run is a no-op on the daemon side.
 	TypePromptCancel = "prompt_cancel"
-
-	// TypePermissionDecision delivers a human verdict back to the
-	// daemon. Envelope.ID = the perm_<8hex> id the daemon minted in
-	// the matching permission_request.
-	TypePermissionDecision = "permission_decision"
-
-	// TypePromptForUserChoiceDecision delivers the human's answer back
-	// to the daemon. Envelope.ID = the ask_<8hex> id the daemon minted
-	// in the matching prompt_for_user_choice frame.
-	TypePromptForUserChoiceDecision = "prompt_for_user_choice_decision"
 )
 
 // PromptRequestPayload is the execution configuration that execution_prepare
@@ -82,33 +72,6 @@ type PromptCancelPayload struct {
 	DeliveryID string `json:"delivery_id,omitempty"`
 }
 
-// PermissionDecisionPayload carries the human verdict. UpdatedInput
-// lets the approver edit the tool input before letting the call
-// proceed (Claude Code's allow-with-changes path).
-type PermissionDecisionPayload struct {
-	DeliveryID   string         `json:"delivery_id"`
-	Approved     bool           `json:"approved"`
-	Message      string         `json:"message,omitempty"`
-	UpdatedInput map[string]any `json:"updated_input,omitempty"`
-}
-
-// PromptForUserChoiceQuestionAnswer binds answer values to one emitted question ID.
-// Headers and array positions never identify a question.
-type PromptForUserChoiceQuestionAnswer struct {
-	QuestionID string   `json:"question_id"`
-	Answers    []string `json:"answers"`
-}
-
-// PromptForUserChoiceDecisionPayload carries either explicitly identified answers
-// or cancellation. Omitted questions remain unanswered; adapters never reassign
-// answers by position or display text. Native choice validation stays in the adapter.
-type PromptForUserChoiceDecisionPayload struct {
-	DeliveryID      string                              `json:"delivery_id"`
-	QuestionAnswers []PromptForUserChoiceQuestionAnswer `json:"question_answers,omitempty"`
-	Cancelled       bool                                `json:"cancelled,omitempty"`
-	Reason          string                              `json:"reason,omitempty"`
-}
-
 // ExecutionControls requires both values when supplied; omitting the block keeps native defaults.
 // Send only to a peer advertising execution_controls.
 type ExecutionControls struct {
diff --git a/internal/agentdaemon/proto/prototest/capabilities.go b/internal/agentdaemon/proto/prototest/capabilities.go
index f3337682f..82afd39b5 100644
--- a/internal/agentdaemon/proto/prototest/capabilities.go
+++ b/internal/agentdaemon/proto/prototest/capabilities.go
@@ -14,7 +14,6 @@ func Capabilities(overrides proto.AgentKindCapabilities) proto.AgentKindCapabili
 	c := proto.AgentKindCapabilities{
 		SubagentObservations:           proto.CapabilityUnsupported,
 		Streaming:                      proto.CapabilityUnsupported,
-		Permissions:                    proto.CapabilityUnsupported,
 		Usage:                          proto.CapabilityUnsupported,
 		Resume:                         proto.CapabilityUnsupported,
 		NativeSessionRecovery:          proto.CapabilityUnsupported,
diff --git a/internal/agentdaemon/proto/tool_call_test.go b/internal/agentdaemon/proto/tool_call_test.go
new file mode 100644
index 000000000..d65d9d169
--- /dev/null
+++ b/internal/agentdaemon/proto/tool_call_test.go
@@ -0,0 +1,13 @@
+package proto
+
+import (
+	"encoding/json"
+	"testing"
+)
+
+func TestToolCallRejectsEngineSnapshot(t *testing.T) {
+	var call ToolCallPayload
+	if json.Unmarshal([]byte(`{"id":"tool","stage":"after","native_item":{"type":"commandExecution"}}`), &call) == nil {
+		t.Fatal("accepted engine-specific snapshot in common wire")
+	}
+}
diff --git a/internal/agentdaemon/proto/user_choice.go b/internal/agentdaemon/proto/user_choice.go
deleted file mode 100644
index 3c59f701f..000000000
--- a/internal/agentdaemon/proto/user_choice.go
+++ /dev/null
@@ -1,67 +0,0 @@
-package proto
-
-import (
-	"bytes"
-	"encoding/json"
-	"errors"
-	"strings"
-)
-
-// UnmarshalJSON rejects fields outside the current decision contract, including
-// unrecognized fields nested inside question_answers. Do not silently discard an
-// answer from a peer using a different wire shape.
-func (p *PromptForUserChoiceDecisionPayload) UnmarshalJSON(raw []byte) error {
-	if raw = bytes.TrimSpace(raw); len(raw) == 0 || raw[0] != '{' {
-		return errors.New("user-choice decision must be an object")
-	}
-	type decision PromptForUserChoiceDecisionPayload
-	var value decision
-	decoder := json.NewDecoder(bytes.NewReader(raw))
-	decoder.DisallowUnknownFields()
-	if err := decoder.Decode(&value); err != nil {
-		return errors.New("invalid user-choice decision")
-	}
-	decoded := PromptForUserChoiceDecisionPayload(value)
-	if err := decoded.Validate(); err != nil {
-		return err
-	}
-	*p = decoded
-	return nil
-}
-
-// Validate checks answer identity independently of delivery correlation and
-// native question constraints. An empty answer array is an explicit non-answer.
-func (p PromptForUserChoiceDecisionPayload) Validate() error {
-	if p.Cancelled && len(p.QuestionAnswers) != 0 {
-		return errors.New("cancelled user-choice decision cannot contain answers")
-	}
-	seen := make(map[string]bool, len(p.QuestionAnswers))
-	for _, answer := range p.QuestionAnswers {
-		if strings.TrimSpace(answer.QuestionID) == "" || seen[answer.QuestionID] || answer.Answers == nil {
-			return errors.New("user-choice answers require unique question IDs and answer arrays")
-		}
-		seen[answer.QuestionID] = true
-	}
-	return nil
-}
-
-// AnswersFor binds a decision to the exact emitted question identities. It never
-// derives identity from a header, answer text or array position. Call it before
-// consuming the pending interaction or submitting a native response.
-func (p PromptForUserChoiceDecisionPayload) AnswersFor(questionIDs []string) (map[string][]string, error) {
-	if err := p.Validate(); err != nil {
-		return nil, err
-	}
-	known := make(map[string]bool, len(questionIDs))
-	for _, id := range questionIDs {
-		known[id] = true
-	}
-	answers := make(map[string][]string, len(p.QuestionAnswers))
-	for _, answer := range p.QuestionAnswers {
-		if !known[answer.QuestionID] {
-			return nil, errors.New("user-choice answer refers to an unknown question")
-		}
-		answers[answer.QuestionID] = answer.Answers
-	}
-	return answers, nil
-}
diff --git a/internal/agentdaemon/proto/user_choice_test.go b/internal/agentdaemon/proto/user_choice_test.go
deleted file mode 100644
index 74bfc55cf..000000000
--- a/internal/agentdaemon/proto/user_choice_test.go
+++ /dev/null
@@ -1,46 +0,0 @@
-package proto
-
-import (
-	"encoding/json"
-	"reflect"
-	"testing"
-)
-
-func TestUserChoiceOnlyAcceptsCurrentAnswerShape(t *testing.T) {
-	for _, raw := range []string{
-		`null`,
-		`{"answers":["yes"]}`,
-		`{"question_answers":[{"header":"Question","answer":"yes"}]}`,
-		`{"question_answers":[{"question_id":"q","answers":["yes"],"answer":"no"}]}`,
-		`{"question_answers":[{"answers":["yes"]}]}`,
-		`{"question_answers":[{"question_id":"q","answers":null}]}`,
-		`{"question_answers":[{"question_id":"q","answers":["yes"]},{"question_id":"q","answers":["no"]}]}`,
-		`{"cancelled":true,"question_answers":[{"question_id":"q","answers":["yes"]}]}`,
-	} {
-		var decision PromptForUserChoiceDecisionPayload
-		if json.Unmarshal([]byte(raw), &decision) == nil {
-			t.Fatalf("accepted invalid decision: %s", raw)
-		}
-	}
-	var decision PromptForUserChoiceDecisionPayload
-	if err := json.Unmarshal([]byte(`{"delivery_id":"d","question_answers":[{"question_id":"b","answers":["two,three","four"]},{"question_id":"a","answers":[]}]}`), &decision); err != nil {
-		t.Fatal(err)
-	}
-	answers, err := decision.AnswersFor([]string{"a", "b"})
-	if err != nil || !reflect.DeepEqual(answers["b"], []string{"two,three", "four"}) || answers["a"] == nil {
-		t.Fatalf("answers=%v err=%v", answers, err)
-	}
-	if _, err := decision.AnswersFor([]string{"a"}); err == nil {
-		t.Fatal("accepted a foreign question ID")
-	}
-	if _, err := (PromptForUserChoiceDecisionPayload{Cancelled: true}).AnswersFor([]string{"a"}); err != nil {
-		t.Fatal(err)
-	}
-}
-
-func TestToolCallRejectsEngineSnapshot(t *testing.T) {
-	var call ToolCallPayload
-	if json.Unmarshal([]byte(`{"id":"tool","stage":"after","native_item":{"type":"commandExecution"}}`), &call) == nil {
-		t.Fatal("accepted engine-specific snapshot in common wire")
-	}
-}
diff --git a/internal/agentdaemon/proto/version.go b/internal/agentdaemon/proto/version.go
index 101fd8dd3..524883ee6 100644
--- a/internal/agentdaemon/proto/version.go
+++ b/internal/agentdaemon/proto/version.go
@@ -2,7 +2,7 @@ package proto
 
 // Version identifies the complete Core–Runtime wire contract. Change it when
 // removing or changing a payload or its semantics; deploy both endpoints together.
-const Version = "0.12.0"
+const Version = "0.13.0"
 
 // VersionCompatible accepts only this contract. Patch drift, prerelease suffixes
 // and malformed versions do not select an implicit compatibility path.
diff --git a/internal/obs/log/api.go b/internal/obs/log/api.go
index 0b12a74d3..6c0102cda 100644
--- a/internal/obs/log/api.go
+++ b/internal/obs/log/api.go
@@ -1,6 +1,3 @@
-// Direct slog.{Info,Warn,Error,Debug,Default} use outside this package
-// is blocked by .golangci.yml forbidigo so the ctx-first signatures
-// here are how trace_id auto-injection stays enforceable.
 package log
 
 import (
@@ -8,24 +5,12 @@ import (
 	"log/slog"
 )
 
-// Info logs via slog.Default with ctx attached so ContextHandler can
+// Warn logs via slog.Default with ctx attached so ContextHandler can
 // inject trace_id/span_id from ctx.
-func Info(ctx context.Context, msg string, args ...any) {
-	slog.Default().InfoContext(ctx, msg, args...)
-}
-
 func Warn(ctx context.Context, msg string, args ...any) {
 	slog.Default().WarnContext(ctx, msg, args...)
 }
 
-func Error(ctx context.Context, msg string, args ...any) {
-	slog.Default().ErrorContext(ctx, msg, args...)
-}
-
-func Debug(ctx context.Context, msg string, args ...any) {
-	slog.Default().DebugContext(ctx, msg, args...)
-}
-
 // Bg returns slog.Default for ctx-less startup/init/shutdown sites.
 // Using Bg() in any handler-path code is a bug — it bypasses trace
 // attribution silently.
diff --git a/internal/obs/log/api_test.go b/internal/obs/log/api_test.go
index 3be844741..5c7c91e3d 100644
--- a/internal/obs/log/api_test.go
+++ b/internal/obs/log/api_test.go
@@ -3,32 +3,11 @@ package log
 import (
 	"bytes"
 	"context"
-	"encoding/json"
 	"log/slog"
 	"strings"
 	"testing"
 )
 
-func TestInfoEmitsTraceID(t *testing.T) {
-	carrier, _ := ParseTraceparent("00-0af7651916cd43dd8448eb211c80319c-b7ad6b7169203331-01")
-	var buf bytes.Buffer
-	prev := slog.Default()
-	slog.SetDefault(slog.New(NewContextHandler(slog.NewJSONHandler(&buf, nil))))
-	t.Cleanup(func() { slog.SetDefault(prev) })
-
-	Info(WithTrace(context.Background(), carrier), "hello", "k", "v")
-	var got map[string]any
-	if err := json.Unmarshal(bytes.TrimSpace(buf.Bytes()), &got); err != nil {
-		t.Fatalf("unmarshal: %v\nraw=%s", err, buf.String())
-	}
-	if got[AttrTraceID] != "0af7651916cd43dd8448eb211c80319c" {
-		t.Fatalf("trace_id: %v", got[AttrTraceID])
-	}
-	if got["k"] != "v" {
-		t.Fatalf("user attr lost: %v", got["k"])
-	}
-}
-
 // TestBgOmitsTraceID: Bg().Info must not emit trace_id — that's how
 // "log line came from outside a request" stays distinguishable.
 func TestBgOmitsTraceID(t *testing.T) {
diff --git a/internal/obs/log/background.go b/internal/obs/log/background.go
index f999bb9a3..9e0406a95 100644
--- a/internal/obs/log/background.go
+++ b/internal/obs/log/background.go
@@ -7,31 +7,11 @@ import (
 // StartBackgroundTrace returns a child ctx carrying a fresh Carrier
 // so any log under it picks up a stable trace_id. Use at the top of
 // every non-HTTP logical-request entrypoint (sweeper tick, WS envelope
-// handler, CLI command). For a sub-step that should keep the trace,
-// use ChildSpan instead.
-func StartBackgroundTrace(parent context.Context, op string) (context.Context, Carrier) {
+// handler, CLI command).
+func StartBackgroundTrace(parent context.Context) (context.Context, Carrier) {
 	if parent == nil {
 		parent = context.Background()
 	}
 	c := NewCarrier()
-	ctx := WithTrace(parent, c)
-	if op != "" {
-		_ = op
-	}
-	return ctx, c
-}
-
-// ChildSpan returns a ctx with the parent's trace_id and a fresh span_id.
-// If the parent has no carrier, behaves like StartBackgroundTrace so
-// callers don't have to branch on presence.
-func ChildSpan(parent context.Context) (context.Context, Carrier) {
-	if parent == nil {
-		parent = context.Background()
-	}
-	if existing, ok := TraceFromContext(parent); ok {
-		child := existing.ChildSpan()
-		return WithTrace(parent, child), child
-	}
-	c := NewCarrier()
 	return WithTrace(parent, c), c
 }
diff --git a/internal/obs/log/carrier.go b/internal/obs/log/carrier.go
index dc6702632..1b4185163 100644
--- a/internal/obs/log/carrier.go
+++ b/internal/obs/log/carrier.go
@@ -30,11 +30,6 @@ func NewCarrier() Carrier {
 	}
 }
 
-// ChildSpan returns a Carrier sharing this Trace but with a fresh Span.
-func (c Carrier) ChildSpan() Carrier {
-	return Carrier{Trace: c.Trace, Span: NewSpanID(), Sampled: c.Sampled}
-}
-
 // String formats the Carrier as a W3C traceparent. Returns "" for a
 // zero-trace Carrier so callers can use it as a presence check.
 func (c Carrier) String() string {
diff --git a/internal/obs/log/context.go b/internal/obs/log/context.go
index 9b2c4fcdd..0fbdfd242 100644
--- a/internal/obs/log/context.go
+++ b/internal/obs/log/context.go
@@ -66,10 +66,6 @@ type ctxLogger struct {
 	ctx context.Context
 }
 
-func (l ctxLogger) Debug(msg string, args ...any) {
-	slog.Default().DebugContext(l.ctx, msg, args...)
-}
-
 func (l ctxLogger) Info(msg string, args ...any) {
 	slog.Default().InfoContext(l.ctx, msg, args...)
 }
@@ -81,9 +77,3 @@ func (l ctxLogger) Warn(msg string, args ...any) {
 func (l ctxLogger) Error(msg string, args ...any) {
 	slog.Default().ErrorContext(l.ctx, msg, args...)
 }
-
-// With returns a slog.Logger with the supplied attrs bound. Ctx-derived
-// trace attrs still apply on subsequent InfoContext calls.
-func (l ctxLogger) With(args ...any) *slog.Logger {
-	return slog.Default().With(args...)
-}
diff --git a/internal/obs/log/discard.go b/internal/obs/log/discard.go
deleted file mode 100644
index 97fef6a5b..000000000
--- a/internal/obs/log/discard.go
+++ /dev/null
@@ -1,13 +0,0 @@
-package log
-
-import (
-	"io"
-	"log/slog"
-)
-
-// Discard returns a *slog.Logger that drops every record. Wrapped in
-// ContextHandler so tests behave identically to production.
-func Discard() *slog.Logger {
-	inner := slog.NewTextHandler(io.Discard, &slog.HandlerOptions{Level: slog.LevelError + 1})
-	return slog.New(NewContextHandler(inner))
-}
diff --git a/internal/obs/log/http_test.go b/internal/obs/log/http_test.go
index c8930f03b..ca4c998b1 100644
--- a/internal/obs/log/http_test.go
+++ b/internal/obs/log/http_test.go
@@ -84,7 +84,7 @@ func TestHTTPMiddlewareIgnoresMalformedHeader(t *testing.T) {
 }
 
 func TestStartBackgroundTraceMintsFresh(t *testing.T) {
-	ctx, c := StartBackgroundTrace(context.Background(), "test.op")
+	ctx, c := StartBackgroundTrace(context.Background())
 	if c.Trace.IsZero() {
 		t.Fatalf("StartBackgroundTrace returned zero carrier")
 	}
@@ -94,20 +94,6 @@ func TestStartBackgroundTraceMintsFresh(t *testing.T) {
 	}
 }
 
-// TestChildSpanKeepsTraceRotatesSpan: child shares trace_id, has a
-// different span_id.
-func TestChildSpanKeepsTraceRotatesSpan(t *testing.T) {
-	parentCtx, parent := StartBackgroundTrace(context.Background(), "")
-	_, child := ChildSpan(parentCtx)
-	if child.Trace != parent.Trace {
-		t.Fatalf("child should keep trace; parent=%s child=%s",
-			parent.Trace.String(), child.Trace.String())
-	}
-	if child.Span == parent.Span {
-		t.Fatalf("child should rotate span; both=%s", child.Span.String())
-	}
-}
-
 func TestCtxLoggerEmits(t *testing.T) {
 	carrier, _ := ParseTraceparent("00-0af7651916cd43dd8448eb211c80319c-b7ad6b7169203331-01")
 	var buf bytes.Buffer
diff --git a/internal/sandboxlink/relay/export_test.go b/internal/sandboxlink/relay/export_test.go
new file mode 100644
index 000000000..6b07e83ec
--- /dev/null
+++ b/internal/sandboxlink/relay/export_test.go
@@ -0,0 +1,38 @@
+package relay
+
+import (
+	"time"
+
+	"github.com/MiniMax-AI/OpenAgentCore/internal/sandboxwire"
+)
+
+// The per-link and per-resource bounds the tests fill.
+const (
+	MaxStreams     = maxStreams
+	MaxServeHellos = maxServeHellos
+)
+
+// SetLimits lowers rl's capacity for resources, attachments and attach links.
+func SetLimits(rl *Relay, resources, attachments, attachLinks int) {
+	rl.mu.Lock()
+	defer rl.mu.Unlock()
+	rl.maxResources, rl.maxAttachments, rl.maxAttachLinks = resources, attachments, attachLinks
+}
+
+// Held reports the resources, attachment slots and attach links rl holds.
+func Held(rl *Relay) (resources, attachments, attachLinks int) {
+	rl.mu.Lock()
+	defer rl.mu.Unlock()
+	return len(rl.resources), rl.held, rl.attachLinks
+}
+
+// Lease reports the lease of the attachment rl holds under id, or the zero
+// time when it holds none.
+func Lease(rl *Relay, id sandboxwire.ID) time.Time {
+	rl.mu.Lock()
+	defer rl.mu.Unlock()
+	if a := rl.attachments[id]; a != nil {
+		return a.lease
+	}
+	return time.Time{}
+}
diff --git a/internal/sandboxlink/relay/relay.go b/internal/sandboxlink/relay/relay.go
index 51ce1fb6c..ec671954d 100644
--- a/internal/sandboxlink/relay/relay.go
+++ b/internal/sandboxlink/relay/relay.go
@@ -20,7 +20,8 @@ import (
 )
 
 const (
-	// maxStreams bounds the concurrent service streams of each link.
+	// maxStreams bounds the concurrent service streams of each link. An attach
+	// link's stream counts from its Open, through the Authority's decision.
 	maxStreams = 256
 	// spliceBuffer bounds the bytes a splice holds per direction, on top of
 	// one yamux window per stream.
@@ -32,6 +33,26 @@ const (
 	answerQueue = 64
 )
 
+// The relay's capacity, for one Core serving one deployment, which runs at
+// most 1024 executions at once (the maximum OAC_EXECUTION_CONCURRENCY).
+// Measured idle, the relay spends about 64 KiB on a serve link, 48 KiB on an
+// attach link and 1 KiB on an attachment, so at capacity they hold under
+// 500 MiB.
+const (
+	// maxResources bounds the resources held, and with them serve links,
+	// one per resource. It leaves room for idle sandboxes beside busy ones.
+	maxResources = 4096
+	// maxServeHellos bounds the serve Hellos being decided for one resource,
+	// so a redial or a newer generation's peer can arrive while one is.
+	maxServeHellos = 2
+	// maxAttachments bounds attachments, open or with AttachmentClosed events
+	// to write: four per resource.
+	maxAttachments = 16384
+	// maxAttachLinks bounds attach links. An agent host dials one per
+	// attachment it uses, a few per execution.
+	maxAttachLinks = 4096
+)
+
 // Relay accepts Link peers on ServeHTTP. It keeps the current serve peer of
 // each resource, the attachments it has opened and their leases in memory; the
 // Authority stays the durable judge of every grant.
@@ -42,25 +63,41 @@ type Relay struct {
 
 	mu          sync.Mutex
 	epoch       uint64 // counts revocations, so a racing Open re-authorizes
-	generations map[resourceKey]uint64
-	serves      map[resourceKey]*serveLink
-	// closures holds the AttachmentClosed events not yet written to the serve
-	// peer of each resource's newest generation, connected or not.
-	closures    map[resourceKey]closures
+	resources   map[resourceKey]*resource
 	attachments map[sandboxwire.ID]*attachment
+	// held counts attachment slots: open attachments, and closed ones whose
+	// AttachmentClosed events are not yet written or discarded.
+	held        int
+	attachLinks int
+	// The capacity of each bounded kind. New sets the constants above; tests
+	// lower them.
+	maxResources, maxAttachments, maxAttachLinks int
+}
+
+// resource is what the relay holds for one resource. It takes one of
+// maxResources from the serve Hello that creates it until it holds nothing:
+// no serve peer, Hello being decided, attachment or event.
+type resource struct {
+	generation uint64     // the newest generation seen
+	serve      *serveLink // nil while the serve peer is away
+	// closures holds the AttachmentClosed events not yet written to the serve
+	// peer of generation, connected or not.
+	closures    closures
+	hellos      int // serve Hellos being decided, at most maxServeHellos
+	attachments int // open attachments
 }
 
-// closures is a set of AttachmentClosed events to write, by attachment.
-type closures map[sandboxwire.ID]sandboxlink.CloseReason
+// closures is a set of AttachmentClosed events to write, by attachment ID.
+// Each event keeps its attachment's slot until it is written or discarded.
+type closures map[sandboxwire.ID]*attachment
 
 // New returns a relay that asks auth to authenticate peers and authorize their
 // requests.
 func New(auth sandboxlink.Authority) *Relay {
 	ctx, cancel := context.WithCancel(context.Background())
 	return &Relay{auth: auth, ctx: ctx, cancel: cancel,
-		generations: map[resourceKey]uint64{},
-		serves:      map[resourceKey]*serveLink{},
-		closures:    map[resourceKey]closures{},
+		maxResources: maxResources, maxAttachments: maxAttachments, maxAttachLinks: maxAttachLinks,
+		resources:   map[resourceKey]*resource{},
 		attachments: map[sandboxwire.ID]*attachment{},
 	}
 }
@@ -89,8 +126,8 @@ func (rl *Relay) RevokeAttachment(id sandboxwire.ID) {
 
 // RevokeResource closes every attachment of ref's generation and older and
 // disconnects that serve peer after writing it their AttachmentClosed events.
-// Events it could not write stay for a reconnect of the same generation. The
-// caller withdraws the authority first.
+// The caller withdraws the authority first, so the revoked generation cannot
+// reconnect, and the events it could not read are discarded.
 func (rl *Relay) RevokeResource(ref sandboxlink.ResourceRef) {
 	rl.mu.Lock()
 	defer rl.mu.Unlock()
@@ -101,10 +138,19 @@ func (rl *Relay) RevokeResource(ref sandboxlink.ResourceRef) {
 		}
 	}
 	key := keyOf(ref)
-	if sl := rl.serves[key]; sl != nil && sl.hello.Resource.Generation <= ref.Generation {
-		delete(rl.serves, key)
+	r := rl.resources[key]
+	if r == nil || r.generation > ref.Generation {
+		return
+	}
+	if sl := r.serve; sl != nil {
+		// The link keeps the set to write before it ends.
+		r.serve = nil
 		sl.end()
+	} else {
+		rl.dropLocked(r.closures)
 	}
+	r.closures = closures{}
+	rl.releaseLocked(key, r)
 }
 
 type resourceKey struct {
@@ -117,16 +163,17 @@ func keyOf(r sandboxlink.ResourceRef) resourceKey {
 }
 
 // link is one authenticated connection. Its writer sends answers from a
-// bounded queue and AttachmentClosed events from an unbounded set, so the
-// relay never blocks on a peer while holding its lock and never drops an
-// event: an event leaves the set only once it is written.
+// bounded queue and AttachmentClosed events from a set, so the relay never
+// blocks on a peer while holding its lock: an event leaves the set once it is
+// written, or with the set when no link can write it any more.
 type link struct {
 	sess *yamux.Session
 	ctl  *yamux.Stream
 	out  chan outgoing
 	wake chan struct{} // the set has events to write
-	// Under Relay.mu: the events to write and the open service streams. A
-	// serve link shares its resource's set, which outlives the link.
+	// Under Relay.mu: the events to write, nil once the link no longer
+	// writes them, and the open service streams. A serve link shares its
+	// resource's set, which outlives the link.
 	closures closures
 	streams  uint32
 }
@@ -195,32 +242,66 @@ func (rl *Relay) write(l *link) {
 func (rl *Relay) writeClosures(l *link) error {
 	for {
 		rl.mu.Lock()
-		var c sandboxlink.AttachmentClosed
-		for id, reason := range l.closures {
-			c = sandboxlink.AttachmentClosed{AttachmentID: id, Reason: reason}
+		var a *attachment
+		for _, a = range l.closures {
 			break
 		}
 		rl.mu.Unlock()
-		if c.Reason == 0 {
+		if a == nil {
 			return nil
 		}
-		if err := sandboxlink.WriteMessage(l.ctl, 0, c); err != nil {
+		id := a.identity.AttachmentID
+		if err := sandboxlink.WriteMessage(l.ctl, 0, sandboxlink.AttachmentClosed{AttachmentID: id, Reason: a.reason}); err != nil {
 			return err
 		}
 		rl.mu.Lock()
-		if l.closures[c.AttachmentID] == c.Reason {
-			delete(l.closures, c.AttachmentID)
+		if l.closures[id] == a {
+			delete(l.closures, id)
+			rl.unrefLocked(a)
 		}
 		rl.mu.Unlock()
 	}
 }
 
-// closedLocked adds an AttachmentClosed event to l's set and wakes its writer.
-func (l *link) closedLocked(id sandboxwire.ID, reason sandboxlink.CloseReason) {
-	if l.closures == nil {
-		l.closures = closures{}
+// queueLocked adds a's AttachmentClosed event to set, unless set is nil. An
+// unwritten event of an earlier attachment with the same ID gives way to it.
+func (rl *Relay) queueLocked(set closures, a *attachment) {
+	if set == nil {
+		return
+	}
+	id := a.identity.AttachmentID
+	if old := set[id]; old != nil {
+		rl.unrefLocked(old)
+	}
+	set[id] = a
+	a.refs++
+}
+
+// dropLocked discards the events of a set that no link will write.
+func (rl *Relay) dropLocked(set closures) {
+	for _, a := range set {
+		rl.unrefLocked(a)
+	}
+}
+
+// unrefLocked drops one of a's references, the open attachment or one of its
+// events. The last frees its slot.
+func (rl *Relay) unrefLocked(a *attachment) {
+	a.refs--
+	if a.refs == 0 {
+		rl.held--
 	}
-	l.closures[id] = reason
+}
+
+// releaseLocked forgets r, freeing its slot, once it holds nothing.
+func (rl *Relay) releaseLocked(key resourceKey, r *resource) {
+	if r.serve == nil && r.hellos == 0 && r.attachments == 0 && len(r.closures) == 0 {
+		delete(rl.resources, key)
+	}
+}
+
+// wakeWriter tells l's writer that its set has events.
+func (l *link) wakeWriter() {
 	select {
 	case l.wake <- struct{}{}:
 	default:
@@ -262,7 +343,9 @@ func linger(sess *yamux.Session) {
 }
 
 // attachment is an attachment the relay has opened. It outlives the links
-// that carry its streams until its lease expires or it is closed.
+// that carry its streams until its lease expires or it is closed, and keeps
+// one of maxAttachments until its AttachmentClosed events are written or
+// discarded.
 type attachment struct {
 	identity sandboxlink.Identity
 	runtime  sandboxwire.ID
@@ -271,6 +354,8 @@ type attachment struct {
 	owner    *attachLink // the link that last opened a stream on it
 	bound    bool        // a Bind may have reached the serve peer
 	splices  map[*splice]struct{}
+	reason   sandboxlink.CloseReason // why it closed; zero while open
+	refs     int                     // its slot's holders: the open attachment and its unwritten events
 }
 
 // splice is one service stream from its Open to its end.
@@ -353,17 +438,43 @@ func (rl *Relay) serve(l *link, id uint64, hello sandboxlink.ServeHello) {
 	}()
 	<-l.sess.CloseChan()
 	rl.mu.Lock()
-	if rl.serves[key] == sl {
-		delete(rl.serves, key)
+	defer rl.mu.Unlock()
+	if r := rl.resources[key]; r != nil && r.serve == sl {
+		// The resource keeps the set for a reconnect.
+		r.serve = nil
+		rl.releaseLocked(key, r)
+	} else {
+		// A replaced link has no set; a revoked one takes it along.
+		rl.dropLocked(sl.closures)
 	}
 	sl.closures = nil
-	rl.mu.Unlock()
 }
 
-// admitServe authenticates a serve Hello and installs the link. A revocation
-// that lands while the Authority decides forces a fresh decision, so a
-// withdrawn credential never installs a peer.
+// admitServe authenticates a serve Hello and installs the link. Until it is
+// decided, the Hello takes one of its resource's maxServeHellos, and a
+// resource slot when the relay does not hold the resource. A revocation that
+// lands while the Authority decides forces a fresh decision, so a withdrawn
+// credential never installs a peer.
 func (rl *Relay) admitServe(l *link, id uint64, hello sandboxlink.ServeHello) (*serveLink, error) {
+	key := keyOf(hello.Resource)
+	rl.mu.Lock()
+	r := rl.resources[key]
+	if r == nil && len(rl.resources) >= rl.maxResources || r != nil && r.hellos >= maxServeHellos {
+		rl.mu.Unlock()
+		return nil, sandboxlink.Fail(sandboxlink.LimitExceeded)
+	}
+	if r == nil {
+		r = &resource{closures: closures{}}
+		rl.resources[key] = r
+	}
+	r.hellos++
+	rl.mu.Unlock()
+	defer func() {
+		rl.mu.Lock()
+		r.hellos--
+		rl.releaseLocked(key, r)
+		rl.mu.Unlock()
+	}()
 	for range authorizeAttempts {
 		rl.mu.Lock()
 		epoch := rl.epoch
@@ -382,7 +493,7 @@ func (rl *Relay) admitServe(l *link, id uint64, hello sandboxlink.ServeHello) (*
 			rl.mu.Unlock()
 			continue
 		}
-		sl, old, err := rl.installServeLocked(l, id, hello)
+		sl, old, err := rl.installServeLocked(r, l, id, hello)
 		rl.mu.Unlock()
 		if old != nil {
 			old.sess.Close()
@@ -392,41 +503,62 @@ func (rl *Relay) admitServe(l *link, id uint64, hello sandboxlink.ServeHello) (*
 	return nil, sandboxlink.Fail(sandboxlink.ServiceUnavailable)
 }
 
-// installServeLocked makes l the resource's serve peer and queues its
-// HelloAccepted while the decision is still current; its writer then writes
-// the resource's pending AttachmentClosed events. It returns the replaced
-// link for the caller to close.
-func (rl *Relay) installServeLocked(l *link, id uint64, hello sandboxlink.ServeHello) (sl, old *serveLink, err error) {
-	key, generation := keyOf(hello.Resource), hello.Resource.Generation
-	if rl.generations[key] > generation {
+// installServeLocked makes l r's serve peer and queues its HelloAccepted
+// while the decision is still current; its writer then writes r's pending
+// AttachmentClosed events. It returns the replaced link for the caller to
+// close.
+func (rl *Relay) installServeLocked(r *resource, l *link, id uint64, hello sandboxlink.ServeHello) (sl, old *serveLink, err error) {
+	generation := hello.Resource.Generation
+	if r.generation > generation {
 		return nil, nil, sandboxlink.Fail(sandboxlink.StaleGeneration)
 	}
-	if rl.generations[key] < generation {
-		rl.generations[key] = generation
-		delete(rl.closures, key)
+	if r.generation < generation {
+		r.generation = generation
+		rl.dropLocked(r.closures)
+		r.closures = closures{}
 		for _, a := range rl.attachments {
 			if a.identity.Resource.SameResource(hello.Resource) {
 				rl.closeLocked(a, sandboxlink.CloseStaleGeneration)
 			}
 		}
 	}
-	if rl.closures[key] == nil {
-		rl.closures[key] = closures{}
-	}
 	sl = &serveLink{link: l, hello: hello}
-	sl.closures = rl.closures[key]
-	old = rl.serves[key]
-	if old != nil {
+	sl.closures = r.closures
+	if old = r.serve; old != nil {
 		old.closures = nil
 	}
-	rl.serves[key] = sl
+	r.serve = sl
 	sl.send(id, sandboxlink.HelloAccepted{})
 	return sl, old, nil
 }
 
 // attach serves an attach peer's control requests and service streams until
-// the link ends. Its attachments stay open until their leases expire.
+// the link ends. The link takes an attach link slot first and keeps it until
+// every stream and renewal it carried has finished, so the decisions of a
+// dropped link stay bounded. Its attachments stay open until their leases
+// expire.
 func (rl *Relay) attach(l *link, id uint64, hello sandboxlink.AttachHello) {
+	rl.mu.Lock()
+	full := rl.attachLinks >= rl.maxAttachLinks
+	if !full {
+		rl.attachLinks++
+		l.closures = closures{}
+	}
+	rl.mu.Unlock()
+	if full {
+		l.fail(id, sandboxlink.OpHello, sandboxlink.LimitExceeded)
+		return
+	}
+	var serving sync.WaitGroup
+	defer func() {
+		<-l.sess.CloseChan()
+		serving.Wait()
+		rl.mu.Lock()
+		rl.attachLinks--
+		rl.dropLocked(l.closures)
+		l.closures = nil
+		rl.mu.Unlock()
+	}()
 	ctx, cancel := rl.authorityContext()
 	peer, err := rl.auth.AuthenticateAttach(ctx, hello)
 	cancel()
@@ -441,15 +573,15 @@ func (rl *Relay) attach(l *link, id uint64, hello sandboxlink.AttachHello) {
 	var seq sandboxwire.RequestSequence
 	seq.Admit(id) // the Hello takes the first ID
 	al.send(id, sandboxlink.HelloAccepted{})
-	go func() {
+	serving.Go(func() {
 		for {
 			st, err := l.sess.AcceptStream()
 			if err != nil {
 				return
 			}
-			go rl.open(al, st)
+			serving.Go(func() { rl.open(al, st) })
 		}
-	}()
+	})
 	for {
 		id, m, err := sandboxlink.ReadMessage(l.ctl)
 		if err != nil {
@@ -468,10 +600,10 @@ func (rl *Relay) attach(l *link, id uint64, hello sandboxlink.AttachHello) {
 				al.send(id, sandboxlink.FailureFor(sandboxlink.OpRenewAttachment, sandboxlink.Fail(sandboxlink.LimitExceeded)))
 				continue
 			}
-			go func() {
+			serving.Go(func() {
 				defer al.inflight.Add(-1)
 				rl.renew(al, id, r)
-			}()
+			})
 		case sandboxlink.CloseAttachment:
 			if !admitted {
 				l.fail(id, sandboxlink.OpCloseAttachment, sandboxlink.ProtocolViolation)
@@ -555,27 +687,27 @@ func (rl *Relay) closeRequested(al *attachLink, id uint64, c sandboxlink.CloseAt
 // peer and the serve peer why. A serve peer that is away when its attachment
 // closes hears of it when the same generation reconnects.
 func (rl *Relay) closeLocked(a *attachment, reason sandboxlink.CloseReason) {
-	id := a.identity.AttachmentID
-	delete(rl.attachments, id)
+	delete(rl.attachments, a.identity.AttachmentID)
 	a.timer.Stop()
 	for sp := range a.splices {
 		sp.abortLocked(abortCodes[reason])
 	}
+	a.reason = reason
 	if reason != sandboxlink.CloseRequested {
-		a.owner.closedLocked(id, reason)
-	}
-	key, generation := keyOf(a.identity.Resource), a.identity.Resource.Generation
-	if !a.bound || rl.generations[key] != generation {
-		return
-	}
-	if sl := rl.serves[key]; sl != nil {
-		sl.closedLocked(id, reason)
-		return
-	}
-	if rl.closures[key] == nil {
-		rl.closures[key] = closures{}
+		rl.queueLocked(a.owner.closures, a)
+		a.owner.wakeWriter()
+	}
+	key := keyOf(a.identity.Resource)
+	r := rl.resources[key] // the attachment holds it
+	if a.bound && r.generation == a.identity.Resource.Generation {
+		rl.queueLocked(r.closures, a)
+		if r.serve != nil {
+			r.serve.wakeWriter()
+		}
 	}
-	rl.closures[key][id] = reason
+	r.attachments--
+	rl.releaseLocked(key, r)
+	rl.unrefLocked(a)
 }
 
 // abortCodes answers an Open that an attachment's close interrupts.
@@ -661,15 +793,41 @@ func (rl *Relay) open(al *attachLink, st *yamux.Stream) {
 	rl.splice(sp)
 }
 
-// admit authorizes o and registers its splice. A revocation that lands while
-// the Authority decides forces a fresh decision.
-func (rl *Relay) admit(al *attachLink, st *yamux.Stream, o sandboxlink.Open) (*splice, sandboxlink.Authorization, error) {
+// admit authorizes o and registers its splice. Before the Authority decides,
+// the Open takes a stream slot of its link, which an admitted stream keeps
+// until finish and a refused one gives back once it is decided, whether or
+// not the peer reset it. An Open of an attachment the relay does not hold
+// also takes an attachment slot. A revocation that lands while the Authority
+// decides forces a fresh decision.
+func (rl *Relay) admit(al *attachLink, st *yamux.Stream, o sandboxlink.Open) (sp *splice, auth sandboxlink.Authorization, err error) {
+	rl.mu.Lock()
+	prior := rl.attachments[o.AttachmentID]
+	reserved := prior == nil
+	if al.streams >= maxStreams || reserved && rl.held >= rl.maxAttachments {
+		rl.mu.Unlock()
+		return nil, auth, sandboxlink.Fail(sandboxlink.LimitExceeded)
+	}
+	al.streams++
+	if reserved {
+		rl.held++
+	}
+	rl.mu.Unlock()
+	defer func() {
+		rl.mu.Lock()
+		if sp == nil {
+			al.streams--
+		}
+		if reserved {
+			rl.held--
+		}
+		rl.mu.Unlock()
+	}()
 	for range authorizeAttempts {
 		rl.mu.Lock()
 		epoch := rl.epoch
 		rl.mu.Unlock()
 		ctx, cancel := rl.authorityContext()
-		auth, err := rl.auth.AuthorizeOpen(ctx, al.peer, o)
+		auth, err = rl.auth.AuthorizeOpen(ctx, al.peer, o)
 		cancel()
 		if err != nil {
 			return nil, auth, err
@@ -682,16 +840,25 @@ func (rl *Relay) admit(al *attachLink, st *yamux.Stream, o sandboxlink.Open) (*s
 			rl.mu.Unlock()
 			continue
 		}
-		sp, err := rl.admitLocked(al, st, o, auth)
+		sp, err = rl.admitLocked(al, st, o, auth, prior, &reserved)
 		rl.mu.Unlock()
 		return sp, auth, err
 	}
 	return nil, sandboxlink.Authorization{}, sandboxlink.Fail(sandboxlink.ServiceUnavailable)
 }
 
-func (rl *Relay) admitLocked(al *attachLink, st *yamux.Stream, o sandboxlink.Open, auth sandboxlink.Authorization) (*splice, error) {
+// admitLocked checks o against what the relay holds and registers its
+// splice. A new attachment takes the slot reserved for it. The attachment
+// prior, which the relay held when the Open arrived, must still be the one
+// under its ID: once it closed, the Open fails even if another attachment
+// took the ID since.
+func (rl *Relay) admitLocked(al *attachLink, st *yamux.Stream, o sandboxlink.Open, auth sandboxlink.Authorization, prior *attachment, reserved *bool) (*splice, error) {
 	key, generation := keyOf(o.Resource), o.Resource.Generation
-	sl := rl.serves[key]
+	r := rl.resources[key]
+	var sl *serveLink
+	if r != nil {
+		sl = r.serve
+	}
 	var offered *sandboxlink.ServiceVersion
 	if sl != nil {
 		for i, s := range sl.hello.Services {
@@ -703,9 +870,9 @@ func (rl *Relay) admitLocked(al *attachLink, st *yamux.Stream, o sandboxlink.Ope
 	a := rl.attachments[o.AttachmentID]
 	var code sandboxlink.Code
 	switch {
-	case al.streams >= maxStreams || (sl != nil && sl.streams >= maxStreams):
+	case sl != nil && sl.streams >= maxStreams:
 		code = sandboxlink.LimitExceeded
-	case rl.generations[key] > generation:
+	case r != nil && r.generation > generation:
 		code = sandboxlink.StaleGeneration
 	case sl == nil || sl.hello.Resource.Generation != generation || offered == nil:
 		code = sandboxlink.ServiceUnavailable
@@ -713,7 +880,7 @@ func (rl *Relay) admitLocked(al *attachLink, st *yamux.Stream, o sandboxlink.Ope
 		code = sandboxlink.VersionMismatch
 	case !o.ExpectedServerInstanceID.IsZero() && o.ExpectedServerInstanceID != sl.hello.ServerInstanceID:
 		code = sandboxlink.InstanceChanged
-	case !auth.LeaseExpiresAt.After(time.Now()):
+	case !auth.LeaseExpiresAt.After(time.Now()) || prior != nil && a != prior:
 		code = sandboxlink.LeaseExpired
 	case a != nil && (a.identity != o.Identity() || a.runtime != al.peer.RuntimeID):
 		code = sandboxlink.AttachmentConflict
@@ -722,15 +889,16 @@ func (rl *Relay) admitLocked(al *attachLink, st *yamux.Stream, o sandboxlink.Ope
 		return nil, sandboxlink.Fail(code)
 	}
 	if a == nil {
-		a = &attachment{identity: o.Identity(), runtime: al.peer.RuntimeID, splices: map[*splice]struct{}{}}
+		a = &attachment{identity: o.Identity(), runtime: al.peer.RuntimeID, splices: map[*splice]struct{}{}, refs: 1}
 		rl.attachments[o.AttachmentID] = a
+		r.attachments++
+		*reserved = false
 	}
 	a.owner = al
 	a.bound = true
 	rl.setLeaseLocked(a, auth.LeaseExpiresAt)
 	sp := &splice{att: a, serve: sl, al: al, attach: st}
 	a.splices[sp] = struct{}{}
-	al.streams++
 	sl.streams++
 	return sp, nil
 }
diff --git a/internal/sandboxlink/relay/relay_test.go b/internal/sandboxlink/relay/relay_test.go
index f7bff701b..9db74bad5 100644
--- a/internal/sandboxlink/relay/relay_test.go
+++ b/internal/sandboxlink/relay/relay_test.go
@@ -14,6 +14,7 @@ import (
 	"time"
 
 	"github.com/MiniMax-AI/OpenAgentCore/internal/sandboxlink"
+	"github.com/MiniMax-AI/OpenAgentCore/internal/sandboxlink/relay"
 	"github.com/MiniMax-AI/OpenAgentCore/internal/sandboxlink/sandboxlinktest"
 	"github.com/MiniMax-AI/OpenAgentCore/internal/sandboxwire"
 )
@@ -50,12 +51,12 @@ func put[T any](ch chan T, v T) {
 	}
 }
 
-// hooked runs a test's hook after the Authority decides a serve Hello or a
-// renewal, so a test can hold the decision.
+// hooked runs a test's hook after the Authority decides a serve Hello, an
+// Open or a renewal, so a test can hold the decision.
 type hooked struct {
 	*sandboxlinktest.Authority
-	mu               sync.Mutex
-	onServe, onRenew func()
+	mu                       sync.Mutex
+	onServe, onOpen, onRenew func()
 }
 
 func (h *hooked) hook(f *func()) {
@@ -79,6 +80,12 @@ func (h *hooked) AuthenticateServe(ctx context.Context, hello sandboxlink.ServeH
 	return peer, err
 }
 
+func (h *hooked) AuthorizeOpen(ctx context.Context, peer sandboxlink.AttachPeer, o sandboxlink.Open) (sandboxlink.Authorization, error) {
+	auth, err := h.Authority.AuthorizeOpen(ctx, peer, o)
+	h.hook(&h.onOpen)
+	return auth, err
+}
+
 func (h *hooked) Renew(ctx context.Context, peer sandboxlink.AttachPeer, r sandboxlink.RenewAttachment) (sandboxlink.Authorization, error) {
 	auth, err := h.Authority.Renew(ctx, peer, r)
 	h.hook(&h.onRenew)
@@ -193,6 +200,29 @@ func (f *fixture) startServe(generation uint64) *servePeer {
 	return p
 }
 
+// serveHello sends a serve Hello for ref with an unknown credential over a new
+// link and returns the relay's answer.
+func (f *fixture) serveHello(ref sandboxlink.ResourceRef) error {
+	ctx, cancel := context.WithTimeout(context.Background(), wait)
+	defer cancel()
+	conn, err := sandboxlink.DialWebSocket(ctx, f.srv.URL, f.srv.TLS)
+	if err != nil {
+		return err
+	}
+	sess, _ := sandboxlink.ClientSession(conn)
+	defer sess.Close()
+	ctl, err := sess.OpenStream(ctx)
+	if err == nil {
+		ctl.SetDeadline(time.Now().Add(wait))
+		err = sandboxlink.WriteMessage(ctl, 1, sandboxlink.ServeHello{Version: sandboxlink.Version, Credential: []byte("unknown"), Resource: ref,
+			ServerInstanceID: sandboxwire.NewID(), Services: []sandboxlink.ServiceVersion{{Service: sandboxlink.ServiceFile, Version: 1}}})
+	}
+	if err == nil {
+		_, err = sandboxlink.ReadReply(ctl, sandboxlink.OpHello, 1)
+	}
+	return err
+}
+
 // grant authorizes the fixture's Runtime for the resource's generation.
 func (f *fixture) grant(generation uint64) []byte {
 	grant := []byte(fmt.Sprintf("grant %d", generation))
@@ -438,6 +468,238 @@ func TestClosuresReplayOnReconnect(t *testing.T) {
 	}
 }
 
+// A serve Hello for a resource the relay does not hold takes a slot before the
+// Authority decides: beyond capacity even an unknown credential gets
+// LimitExceeded. A refused Hello leaves no slot taken, and an admitted
+// resource still reconnects at capacity.
+func TestServesAreBounded(t *testing.T) {
+	f := newFixture(t)
+	relay.SetLimits(f.srv.Relay, 1, 16, 16)
+	other := resource(1)
+	other.ID = sandboxwire.NewID()
+	if err := f.serveHello(other); !errors.Is(err, sandboxlink.AuthenticationFailed) {
+		t.Fatalf("serve Hello with an unknown credential: %v, want AuthenticationFailed", err)
+	}
+	p := f.serve(1)
+	if err := f.serveHello(other); !errors.Is(err, sandboxlink.LimitExceeded) {
+		t.Fatalf("serve Hello beyond capacity: %v, want LimitExceeded", err)
+	}
+	if resources, _, _ := relay.Held(f.srv.Relay); resources != 1 {
+		t.Fatalf("relay holds %d resources, want 1", resources)
+	}
+	recv(t, p.conns).Close()
+	recv(t, p.connected)
+}
+
+// Each Hello for a resource takes one of its MaxServeHellos while it is
+// decided: past them, a Hello for a held resource gets LimitExceeded without
+// reaching the Authority.
+func TestServeHellosAreBounded(t *testing.T) {
+	f := newFixture(t)
+	f.serve(1)
+	entered, release := make(chan struct{}, relay.MaxServeHellos+1), make(chan struct{})
+	f.auth.set(&f.auth.onServe, func() {
+		entered <- struct{}{}
+		<-release
+	})
+	errs := make(chan error, relay.MaxServeHellos)
+	for range relay.MaxServeHellos {
+		go func() { errs <- f.serveHello(resource(1)) }()
+		recv(t, entered)
+	}
+	if err := f.serveHello(resource(1)); !errors.Is(err, sandboxlink.LimitExceeded) {
+		t.Fatalf("serve Hello beyond the bound: %v, want LimitExceeded", err)
+	}
+	close(release)
+	for range relay.MaxServeHellos {
+		if err := recv(t, errs); !errors.Is(err, sandboxlink.AuthenticationFailed) {
+			t.Fatalf("serve Hello within the bound: %v, want AuthenticationFailed", err)
+		}
+	}
+	if len(entered) != 0 {
+		t.Fatal("a serve Hello beyond the bound reached the Authority")
+	}
+}
+
+// An Open takes one of its link's MaxStreams before the Authority decides and
+// keeps it until the decision ends, even once the peer has reset the stream.
+func TestOpenDecisionsAreBounded(t *testing.T) {
+	f := newFixture(t)
+	f.serve(1)
+	attachment := sandboxwire.NewID()
+	f.mustOpen(sandboxlink.ServiceFile, attachment, 1) // its stream takes one
+	grant := f.grant(1)
+	pending := relay.MaxStreams - 1
+	entered, release := make(chan struct{}, pending+1), make(chan struct{})
+	f.auth.set(&f.auth.onOpen, func() {
+		entered <- struct{}{}
+		<-release
+	})
+	reset := make(chan error)
+	for range pending {
+		ctx, cancel := context.WithCancel(context.Background())
+		go func() {
+			_, _, err := f.link.OpenService(ctx, sandboxlink.Open{Service: sandboxlink.ServiceFile, Version: 1, Resource: resource(1),
+				AttachmentID: attachment, SessionID: sessionID, AssignmentID: assignmentID, AssignmentEpoch: 1, AttachGrant: grant})
+			reset <- err
+		}()
+		recv(t, entered)
+		cancel() // OpenService resets the stream
+		recv(t, reset)
+	}
+	if _, _, err := f.open(sandboxlink.ServiceFile, attachment, 1, grant); !errors.Is(err, sandboxlink.LimitExceeded) {
+		t.Fatalf("open beyond the stream bound: %v, want LimitExceeded", err)
+	}
+	if len(entered) != 0 {
+		t.Fatal("an Open beyond the bound reached the Authority")
+	}
+	f.auth.set(&f.auth.onOpen, nil)
+	close(release)
+	// The slots return as the decisions end; until then an Open is refused
+	// with LimitExceeded, which is retryable.
+	for {
+		_, _, err := f.open(sandboxlink.ServiceFile, attachment, 1, grant)
+		if err == nil {
+			break
+		}
+		if !errors.Is(err, sandboxlink.LimitExceeded) {
+			t.Fatalf("open after the decisions ended: %v", err)
+		}
+	}
+}
+
+// An Open that finds an attachment fails with LeaseExpired when that
+// attachment closes while the Open is decided, even if another Open has
+// created a new attachment under the same ID since, and leaves the new
+// attachment's lease alone.
+func TestOpenOfAReplacedAttachment(t *testing.T) {
+	f := newFixture(t)
+	p := f.serve(1)
+	calls := make(chan chan struct{})
+	f.auth.set(&f.auth.onOpen, func() {
+		release := make(chan struct{})
+		calls <- release
+		<-release
+	})
+	attachment := sandboxwire.NewID()
+	open := func(grant []byte) <-chan error {
+		errs := make(chan error, 1)
+		go func() {
+			_, _, err := f.open(sandboxlink.ServiceFile, attachment, 1, grant)
+			errs <- err
+		}()
+		return errs
+	}
+	grant := f.grant(1)
+	longer := []byte("longer grant")
+	f.auth.AddGrant(longer, sandboxlinktest.Grant{RuntimeID: f.runtime, Resource: resource(1), SessionID: sessionID,
+		AssignmentID: assignmentID, AssignmentEpoch: 1, Services: []sandboxlink.Service{sandboxlink.ServiceFile}, Lease: 2 * f.lease})
+
+	// Two Opens arrive while the relay holds no attachment; the first creates A.
+	first := open(grant)
+	releaseFirst := recv(t, calls)
+	second := open(grant)
+	releaseSecond := recv(t, calls)
+	close(releaseFirst)
+	if err := recv(t, first); err != nil {
+		t.Fatal(err)
+	}
+	// A third Open finds A, which closes while it is decided.
+	third := open(longer)
+	releaseThird := recv(t, calls)
+	if err := f.link.CloseAttachment(context.Background(), attachment); err != nil {
+		t.Fatal(err)
+	}
+	recv(t, p.closed)
+	// The second Open creates B under the same ID. The serve peer, which saw
+	// A close, refuses to bind it, but the relay holds B.
+	close(releaseSecond)
+	recv(t, second)
+	lease := relay.Lease(f.srv.Relay, attachment)
+	if lease.IsZero() {
+		t.Fatal("the second Open created no attachment")
+	}
+	close(releaseThird)
+	if err := recv(t, third); !errors.Is(err, sandboxlink.LeaseExpired) {
+		t.Fatalf("open of a replaced attachment: %v, want LeaseExpired", err)
+	}
+	if got := relay.Lease(f.srv.Relay, attachment); !got.Equal(lease) {
+		t.Fatalf("the new attachment's lease moved from %s to %s", lease, got)
+	}
+}
+
+// An Open of an attachment the relay does not hold takes a slot before the
+// Authority decides: beyond capacity even a forged grant gets LimitExceeded.
+// A refused Open leaves no slot taken, and an open attachment still opens
+// streams at capacity.
+func TestAttachmentsAreBounded(t *testing.T) {
+	f := newFixture(t)
+	relay.SetLimits(f.srv.Relay, 16, 1, 16)
+	f.serve(1)
+	if _, _, err := f.open(sandboxlink.ServiceFile, sandboxwire.NewID(), 1, []byte("forged grant")); !errors.Is(err, sandboxlink.PermissionDenied) {
+		t.Fatalf("open with a forged grant: %v, want PermissionDenied", err)
+	}
+	attachment := sandboxwire.NewID()
+	f.mustOpen(sandboxlink.ServiceFile, attachment, 1)
+	if _, _, err := f.open(sandboxlink.ServiceFile, sandboxwire.NewID(), 1, []byte("forged grant")); !errors.Is(err, sandboxlink.LimitExceeded) {
+		t.Fatalf("open of a new attachment beyond capacity: %v, want LimitExceeded", err)
+	}
+	f.mustOpen(sandboxlink.ServiceFile, attachment, 1)
+	if _, attachments, _ := relay.Held(f.srv.Relay); attachments != 1 {
+		t.Fatalf("relay holds %d attachment slots, want 1", attachments)
+	}
+}
+
+// A closed attachment keeps its slot until its AttachmentClosed event is
+// written to the serve peer, which is away and then reconnects.
+func TestClosuresKeepTheirSlots(t *testing.T) {
+	f := newFixture(t)
+	relay.SetLimits(f.srv.Relay, 16, 2, 16)
+	p := f.serve(1)
+	ids := []sandboxwire.ID{sandboxwire.NewID(), sandboxwire.NewID()}
+	for _, id := range ids {
+		f.mustOpen(sandboxlink.ServiceFile, id, 1)
+	}
+	held, release := make(chan struct{}), make(chan struct{})
+	var once sync.Once
+	f.auth.set(&f.auth.onServe, func() {
+		once.Do(func() { close(held) })
+		<-release
+	})
+	recv(t, p.conns).Close()
+	recv(t, held)
+	for _, id := range ids {
+		if err := f.link.CloseAttachment(context.Background(), id); err != nil {
+			t.Fatal(err)
+		}
+	}
+	if _, _, err := f.open(sandboxlink.ServiceFile, sandboxwire.NewID(), 1, f.grant(1)); !errors.Is(err, sandboxlink.LimitExceeded) {
+		t.Fatalf("open while both closures are unwritten: %v, want LimitExceeded", err)
+	}
+	close(release)
+	for range ids {
+		if r := recv(t, p.closed); r != sandboxlink.CloseRequested {
+			t.Fatalf("serve peer saw close reason %d, want a requested close", r)
+		}
+	}
+	// The relay frees an event's slot before it writes the next, so one slot
+	// is free once both events have arrived.
+	f.mustOpen(sandboxlink.ServiceFile, sandboxwire.NewID(), 1)
+}
+
+// An attach Hello takes a link slot before the Authority decides: beyond
+// capacity even an unknown credential gets LimitExceeded.
+func TestAttachLinksAreBounded(t *testing.T) {
+	f := newFixture(t)
+	relay.SetLimits(f.srv.Relay, 16, 16, 1)
+	ctx, cancel := context.WithTimeout(context.Background(), wait)
+	defer cancel()
+	_, err := sandboxlink.DialAttach(ctx, sandboxlink.AttachConfig{URL: f.srv.URL, TLS: f.srv.TLS, RuntimeID: sandboxwire.NewID(), Credential: []byte("unknown")})
+	if !errors.Is(err, sandboxlink.LimitExceeded) {
+		t.Fatalf("attach Hello beyond capacity: %v, want LimitExceeded", err)
+	}
+}
+
 // A control call whose context ended before it was sent fails with no effect
 // and leaves the link up.
 func TestCancelledCallKeepsLink(t *testing.T) {
diff --git a/packages/claude-sdk-adapter/README.md b/packages/claude-sdk-adapter/README.md
index 2b374732b..b0a0dd717 100644
--- a/packages/claude-sdk-adapter/README.md
+++ b/packages/claude-sdk-adapter/README.md
@@ -36,7 +36,7 @@ The private bridge accepts `executor_prepare` without model input. It freezes va
 
 Each Turn ends with a result/error and `turn_settled`, independently of process exit. The outer input iterator remains open for later Turns. `turn_cancel` invokes the native interrupt control for that exact Turn. Unconfirmed input, native child work or queue state invalidates the Executor and requires close before replacement. EOF, owner signals and invalid control input close owned resources. Preparation may write native metadata and perform startup traffic; readiness does not prove provider authentication, complete sandbox health or placement authorization.
 
-`claudesdk.NewExecutorFactory` binds this bridge to `agent.Executor`. Direct-call and read-only preparation wrappers delegate to the same implementation. Runtime execution uses the Executor registry for both none and workspace configurations. Its owner context spans all Turns; a Turn's caller cannot replace fixed resources. A failed preparation returns its Executor when cleanup remains unconfirmed. Installed runtime checks are cached by package/file identity, while capability and request validation still run for each Executor configuration.
+`claudesdk.NewExecutorFactory` binds this bridge to `agent.Executor`. Runtime execution uses the Executor registry for both none and workspace configurations. Its owner context spans all Turns; a Turn's caller cannot replace fixed resources. A failed preparation returns its Executor when cleanup remains unconfirmed. Installed runtime checks are cached by package/file identity, while capability and request validation still run for each Executor configuration.
 
 ### Directory listing
 
@@ -62,7 +62,7 @@ Workspace deferred-function discovery uses native ToolSearch alongside the norma
 
 ### Registration and state
 
-For unmanaged bootstrap, daemon `connect` optionally registers this factory as `claude_sdk` when the operator sets `OAC_RUNTIME_CLAUDE_SDK_ENTRYPOINT` to the absolute packaged `dist/main.js`. `OAC_RUNTIME_CLAUDE_SDK_NODE` selects Node (default: `node` on PATH). Discovery resolves Node once and checks that exact configuration before connecting; the SDK's bounded runtime check is independent of CLI version probes. A ready SDK alone is sufficient to start the daemon. No configuration means no SDK probe or descriptor; failed readiness reports an unavailable descriptor with a rejecting factory. Runtime checks establish local readiness, not provider authentication. Installed daemons use `start` and their verified installation manifest for adapter selection and activation; ambient activation variables cannot extend that selection. See [the native installation contract](../../deploy/README.md#native-daemon-installer).
+For unmanaged bootstrap, daemon `connect` optionally registers this adapter as `claude_sdk` when the operator sets `OAC_RUNTIME_CLAUDE_SDK_ENTRYPOINT` to the absolute packaged `dist/main.js`. `OAC_RUNTIME_CLAUDE_SDK_NODE` selects Node (default: `node` on PATH). Discovery resolves Node once and checks that exact configuration before connecting; the SDK's bounded runtime check is independent of CLI version probes. A ready SDK alone is sufficient to start the daemon. No configuration means no SDK probe or descriptor; failed readiness reports an unavailable descriptor without factories. Runtime checks establish local readiness, not provider authentication. Installed daemons use `start` and their verified installation manifest for adapter selection and activation; ambient activation variables cannot extend that selection. See [the native installation contract](../../deploy/README.md#native-daemon-installer).
 
 SDK state lives under `paths.ProfileDir(profile)/runtime/claude-sdk`, independently of the replaceable runtime bundle. Both the entrypoint and managed state root must be absolute. Background re-execution inherits operator configuration; it does not persist provider credentials in credential profiles. It accepts no caller-supplied environment variables or business write authority.
 
diff --git a/scripts/build-core-distribution.sh b/scripts/build-core-distribution.sh
index e6635f418..e2db4d6dd 100755
--- a/scripts/build-core-distribution.sh
+++ b/scripts/build-core-distribution.sh
@@ -44,7 +44,7 @@ case "$build_network" in
   default|host|none) ;;
   *) printf 'CORE_DISTRIBUTION_BUILD_NETWORK must be default, host, or none\n' >&2; exit 1 ;;
 esac
-# Build one Linux amd64 image and write the ID the local image store gives it to
+# Build one selected Linux architecture image and write the ID the local image store gives it to
 # $stage/NAME.id. BuildKit's --iidfile reports the config digest, which is the
 # image ID only in Docker's classic store; the containerd store (Docker 29's
 # default) uses the manifest digest and cannot resolve the config digest. The
@@ -58,14 +58,14 @@ build_image() {
   # declaration persists the operator's network configuration in the images.
   # The metadata file omits build provenance, so it does not record them either.
   BUILDX_METADATA_PROVENANCE=disabled docker build --network "$build_network" \
-    --platform linux/amd64 --provenance=false --metadata-file "$stage/$name.build.json" \
+    --platform "linux/$GOARCH" --provenance=false --metadata-file "$stage/$name.build.json" \
     --label "org.opencontainers.image.revision=$revision" \
     --build-arg HTTP_PROXY --build-arg HTTPS_PROXY --build-arg ALL_PROXY --build-arg NO_PROXY \
     --build-arg "http_proxy=${http_proxy:-${HTTP_PROXY:-}}" \
     --build-arg "https_proxy=${https_proxy:-${HTTPS_PROXY:-}}" \
     --build-arg "all_proxy=${all_proxy:-${ALL_PROXY:-}}" \
     --build-arg "no_proxy=${no_proxy:-${NO_PROXY:-}}" "$@"
-  python3 scripts/core-distribution-manifest.py built-image "$stage/$name.build.json" > "$stage/$name.id"
+  python3 scripts/core-distribution-manifest.py built-image "$stage/$name.build.json" "$GOARCH" > "$stage/$name.id"
 }
 
 require_clean_source() {
@@ -255,3 +255,28 @@ fi
 mv "$stage/artifacts/"* "$output_dir/"
 if [[ -d "$stage/native-artifacts" ]]; then mv "$stage/native-artifacts/"* "$output_dir/"; fi
 mv "$bundle" "$output_dir/"
+
+# Core, Web and initialization also run natively in ARM64 Linux containers.
+# Node and hosted Runtime payloads above remain linux/amd64.
+export GOARCH=arm64
+arm_bundle="$stage/oac-$revision-linux-arm64"
+mkdir -p "$arm_bundle/images"
+OAC_DEV_BUILD_REVISION="$revision" scripts/build-core-image-context.sh "$stage/core"
+OAC_DEV_WEB_BUILD_DIR="$stage/web" scripts/build-web.sh
+cp "$stage/core/bin/oac" "$stage/ingress/oac"
+for name in core web ingress; do
+  build_image "$name" "$stage/$name"
+  docker image save --output "$arm_bundle/images/$name.tar" "$(cat "$stage/$name.id")"
+done
+python3 scripts/core-distribution-manifest.py control-archive "$arm_bundle" "$stage" "$revision" arm64
+mv "$arm_bundle.tar.gz" "$arm_bundle.tar.gz.sha256" "$output_dir/"
+
+# The launchers and operator commands use this same portable implementation.
+for platform in linux-amd64 linux-arm64 darwin-amd64 darwin-arm64 windows-amd64; do
+  extension=""
+  if [[ "$platform" == windows-* ]]; then extension=.exe; fi
+  asset="oac-$platform$extension"
+  GOOS="${platform%-*}" GOARCH="${platform#*-}" CGO_ENABLED=0 go build -mod=readonly -trimpath \
+    -ldflags "-X main.buildRevision=$revision" -o "$output_dir/$asset" ./services/core/cmd/oac
+  (cd "$output_dir" && sha256sum "$asset" > "$asset.sha256")
+done
diff --git a/scripts/build-core-image-context.sh b/scripts/build-core-image-context.sh
index 76d73eb32..fa8d3f0ee 100755
--- a/scripts/build-core-image-context.sh
+++ b/scripts/build-core-image-context.sh
@@ -13,8 +13,8 @@ if [[ "$context" != /* ]]; then
 fi
 
 mkdir -p "$context/bin" "$context/e2b" "$context/native-installers"
-GOOS=linux GOARCH=amd64 OAC_DEV_CORE_BUILD_DIR="$context/bin" "$repo_root/scripts/build-core.sh"
+GOOS=linux GOARCH="${GOARCH:-amd64}" OAC_DEV_CORE_BUILD_DIR="$context/bin" "$repo_root/scripts/build-core.sh"
 E2B_PROVIDER_BUILD_DIR="$context/e2b-build" "$repo_root/scripts/build-e2b-provider.sh"
-tar -xzf "$context/e2b-build/oac-e2b-provider-linux-amd64.tar.gz" --strip-components=1 -C "$context/e2b"
+tar -xzf "$context/e2b-build/oac-e2b-provider-linux-${GOARCH:-amd64}.tar.gz" --strip-components=1 -C "$context/e2b"
 rm -rf "$context/e2b-build"
 cp "$repo_root/deploy/distribution/Dockerfile" "$context/Dockerfile"
diff --git a/scripts/build-e2b-provider.sh b/scripts/build-e2b-provider.sh
index cd91fb5ec..b17f5e071 100755
--- a/scripts/build-e2b-provider.sh
+++ b/scripts/build-e2b-provider.sh
@@ -8,23 +8,25 @@ case "$output_dir" in
   *) printf 'E2B_PROVIDER_BUILD_DIR must be absolute\n' >&2; exit 1 ;;
 esac
 mkdir -p "$output_dir"
-archive=oac-e2b-provider-linux-amd64.tar.gz
+architecture="${GOARCH:-amd64}"
+case "$architecture" in amd64|arm64) ;; *) echo "Unsupported E2B architecture" >&2; exit 1;; esac
+archive="oac-e2b-provider-linux-$architecture.tar.gz"
 # The helper is a pure function of these files, so a build is reused by their hash.
 inputs="$(cd "$repo_root" && {
   find services/core/tools/e2b-provider -type f ! -path '*/__pycache__/*' -print0 | sort -z | xargs -0 sha256sum
   sha256sum LICENSE scripts/build-e2b-provider.sh
 } | sha256sum | cut -c1-64)"
-cache="${OAC_DEV_HOME:-$HOME/.oac}/cache/e2b-provider/$inputs"
+cache="${OAC_DEV_HOME:-$HOME/.oac}/cache/e2b-provider/$architecture-$inputs"
 if [[ ! -f "$cache/$archive.sha256" ]]; then
   mkdir -p "${cache%/*}"
   build="$(mktemp -d "${cache%/*}/.build.XXXXXX")"
-  image="oac-e2b-provider-build:${inputs:0:12}"
+  image="oac-e2b-provider-build:$architecture-${inputs:0:12}"
   # Proxy values are build-only operator settings; no account key is needed.
-  docker build --platform linux/amd64 --build-arg HTTP_PROXY --build-arg HTTPS_PROXY \
+  docker build --platform "linux/$architecture" --build-arg HTTP_PROXY --build-arg HTTPS_PROXY \
     --build-arg ALL_PROXY --build-arg NO_PROXY \
     --file "$repo_root/services/core/tools/e2b-provider/Build.Dockerfile" \
     --tag "$image" "$repo_root/services/core/tools/e2b-provider"
-  docker run --rm --platform linux/amd64 \
+  docker run --rm --platform "linux/$architecture" \
     --env HTTP_PROXY --env HTTPS_PROXY --env ALL_PROXY --env NO_PROXY \
     --mount "type=bind,src=$repo_root,dst=/source,readonly" \
     --mount "type=bind,src=$build,dst=/output" "$image"
diff --git a/scripts/ci_plan.py b/scripts/ci_plan.py
index d51bee462..7d2da4853 100644
--- a/scripts/ci_plan.py
+++ b/scripts/ci_plan.py
@@ -58,6 +58,8 @@
     (("docs/", "contracts/"), ("",), ("website",)),
     (("website/",), (*WEB, ".vue", ".md"), ("website",)),
     (("services/core/",), CORE, ("backend", "api", "compose")),
+    (("services/core/cmd/oac/",), GO, ("native", "distribution")),
+    (("deploy/install.sh", "deploy/install.ps1", "deploy/test_install.ps1"), (".sh", ".ps1"), ("native", "distribution")),
     (("services/core/internal/nativeinstaller/",), GO, ("native", "distribution")),
     (("services/core/deploy/", "services/core/tools/"), CORE, ("distribution",)),
     (("apps/daemon/",), GO, ("backend", "native")),
@@ -83,7 +85,7 @@
     (("scripts/build-codex-runtime.sh",), (".sh",), ("backend", "native", "distribution")),
     (("scripts/build-agent-host-images.sh", "scripts/qualify-agent-host.sh"), (".sh",), ("distribution",)),
     (("scripts/generate-harness-catalog", "scripts/harness-catalog/", "scripts/openapi-split/", "scripts/patch-agents-openapi.py",
-      "scripts/extract-agents-api-upstream.py"), SCRIPTS, JOBS),
+      "scripts/generate-public-api"), SCRIPTS, JOBS),
     (("scripts/check-sqlc.py", "scripts/go-test-shard.py"), (".py",), ("backend",)),
     (("scripts/check-names", "scripts/name-allowlist.json", "scripts/ci_"), (".py", ".json"), ("hygiene",)),
     ((".github/workflows/", ".github/actions/"), (".yml", ".yaml"), JOBS),
diff --git a/scripts/ci_plan_test.py b/scripts/ci_plan_test.py
index 591b8245d..f5a2a6f4a 100644
--- a/scripts/ci_plan_test.py
+++ b/scripts/ci_plan_test.py
@@ -20,7 +20,7 @@ def test_published_documents_also_build_the_website(self):
         self.assertEqual(self.jobs("README.md"), {"hygiene"})
 
     def test_installer_does_not_download_a_browser_or_run_database_tests(self):
-        self.assertEqual(self.jobs("deploy/install.sh", "deploy/node/node_payload.py"), {"hygiene", "distribution"})
+        self.assertEqual(self.jobs("deploy/install.sh", "deploy/node/node_payload.py"), {"hygiene", "distribution", "native"})
 
     def test_compose_inputs_select_live_and_fixture_checks_without_image_builds(self):
         for path in ("deploy/compose/compose.yaml", "deploy/compose/https.yaml", "deploy/compose/dokploy.toml",
@@ -166,13 +166,13 @@ def test_every_job_has_a_plan_condition(self):
 
     def test_mixed_changes_accumulate(self):
         self.assertEqual(self.jobs("docs/maintainers.md", "deploy/install.sh", "apps/web/src/app.tsx"),
-                         {"hygiene", "distribution", "web", "web-acceptance", "website"})
+                         {"hygiene", "distribution", "native", "web", "web-acceptance", "website"})
 
     def test_installer_pr_300_replay(self):
         self.assertEqual(self.jobs(
             "deploy/install.sh", "deploy/README.md", "deploy/node/node_install.py",
             "deploy/node/install_display.py", "deploy/node/node_payload.py",
-            "docs/getting-started/install.md"), {"hygiene", "distribution", "website"})
+            "docs/getting-started/install.md"), {"hygiene", "distribution", "native", "website"})
 
     def test_workflow_graph_cannot_silently_omit_or_add_a_gate_dependency(self):
         workflow = (Path(__file__).resolve().parents[1] / ".github/workflows/check.yml").read_text().split("jobs:\n", 1)[1]
diff --git a/scripts/ci_review.py b/scripts/ci_review.py
new file mode 100644
index 000000000..e7fb16645
--- /dev/null
+++ b/scripts/ci_review.py
@@ -0,0 +1,163 @@
+#!/usr/bin/env python3
+"""Collect independent review reports and deliver one Feishu card."""
+
+import argparse
+import base64
+import hashlib
+import hmac
+import json
+import os
+from pathlib import Path
+import re
+import time
+import urllib.error
+import urllib.request
+
+
+STATUSES = {"ok": "未发现问题", "issues": "发现问题", "incomplete": "未完成"}
+MAX_SECTION = 900
+REPORT_FIELDS = {
+    "code": {"changes": "实际行为变化，1–3 条 Markdown 列表", "review": "代码正确性与仓库规则审查结论", "ci": "已有 CI 结果；失败或未完成时给出具体检查项"},
+    "docs": {"consistency": "文档与代码一致性", "organization": "文档矛盾、重复与归属；未改文档时写本次未修改文档"},
+}
+
+
+def report_schema(kind):
+    properties = {"status": {"type": "string", "enum": list(STATUSES)}}
+    properties.update({name: {"type": "string", "minLength": 1, "maxLength": MAX_SECTION, "description": description}
+                       for name, description in REPORT_FIELDS[kind].items()})
+    return {"type": "object", "properties": properties, "required": list(properties), "additionalProperties": False}
+
+
+def incomplete(reason, kind):
+    fields = dict.fromkeys(REPORT_FIELDS[kind], "未完成。")
+    fields[next(iter(fields))] = reason
+    return {"status": "incomplete", **fields}
+
+
+def parse_report(raw, kind):
+    try:
+        report = json.loads(raw)
+    except (ValueError, TypeError):
+        return incomplete("未收到有效报告，请查看审查日志。", kind)
+    if (not isinstance(report, dict) or set(report) != {"status", *REPORT_FIELDS[kind]}
+            or not isinstance(report["status"], str) or report["status"] not in STATUSES
+            or any(not isinstance(report[name], str) or not report[name].strip()
+                   or len(report[name]) > MAX_SECTION for name in REPORT_FIELDS[kind])):
+        return incomplete("报告格式不完整，请查看审查日志。", kind)
+    return report
+
+
+def collect(outcome, raw, kind):
+    if outcome != "success":
+        return incomplete("审查未成功结束，请查看审查日志。", kind)
+    return parse_report(raw, kind)
+
+
+def read_report(directory, kind):
+    try:
+        return parse_report((directory / f"review-{kind}.json").read_text(), kind)
+    except (OSError, UnicodeError):
+        return incomplete("审查报告缺失，请查看审查日志。", kind)
+
+
+def markdown_text(value):
+    return re.sub(r"([\\`*_{}\[\]()<>!])", r"\\\1", value)
+
+
+def build_card(event, reports, run_url):
+    pr = event["pull_request"]
+    statuses = {report["status"] for report in reports.values()}
+    color = "red" if "issues" in statuses else "yellow" if "incomplete" in statuses else "green"
+    heading = "❌ 审查发现问题" if "issues" in statuses else "⚠️ 审查未完成" if "incomplete" in statuses else "✅ 审查通过"
+    code, docs = reports["code"], reports["docs"]
+
+    def text(value):
+        # Feishu mentions use HTML-like tags; reports are ordinary Markdown.
+        return value.replace("<", "&lt;").replace(">", "&gt;")
+
+    sections = [
+        ("1. 哪个 PR", f"**github id:** {markdown_text(pr['user']['login'])}\n"
+         f"**标题:** {markdown_text(pr['title'][:200])}\n**链接:** [PR #{pr['number']}]({pr['html_url']})"),
+        ("2. 改了什么", text(code["changes"])),
+        ("3. 代码与仓库规则", text(code["review"])),
+        ("4. CI 结果", text(code["ci"])),
+        (f"5. 文档审查 · {STATUSES[docs['status']]}",
+         f"**文档与代码一致性**\n{text(docs['consistency'])}\n\n"
+         f"**文档矛盾、重复与归属**\n{text(docs['organization'])}"),
+    ]
+    elements = []
+    for title, content in sections:
+        if elements:
+            elements.append({"tag": "hr"})
+        elements.append({"tag": "markdown", "content": f"**{title}**\n\n{content}"})
+    elements.append({"tag": "markdown", "content": f"[查看审查日志]({run_url})"})
+    return {
+        "msg_type": "interactive",
+        "card": {
+            "schema": "2.0",
+            "header": {"template": color, "title": {"tag": "plain_text", "content": f"{heading} · PR #{pr['number']}"}},
+            "body": {"elements": elements},
+        },
+    }
+
+
+def card_markdown(card):
+    return "\n\n".join("---" if element["tag"] == "hr" else element["content"]
+                        for element in card["card"]["body"]["elements"]) + "\n"
+
+
+def send_card(webhook, secret, card):
+    if not webhook:
+        raise ValueError("FEISHU_WEBHOOK_URL is not configured")
+    payload = dict(card)
+    if secret:
+        timestamp = str(int(time.time()))
+        key = f"{timestamp}\n{secret}".encode()
+        payload.update(timestamp=timestamp, sign=base64.b64encode(hmac.new(key, b"", hashlib.sha256).digest()).decode())
+    data = json.dumps(payload, ensure_ascii=False).encode()
+    if len(data) > 20000:
+        raise ValueError("Review card exceeds the webhook message size limit")
+    request = urllib.request.Request(webhook, data=data, headers={"Content-Type": "application/json"}, method="POST")
+    # A timeout may follow successful delivery; retrying could send a duplicate.
+    try:
+        with urllib.request.urlopen(request, timeout=30) as response:
+            result = json.load(response)
+    except (OSError, ValueError, urllib.error.URLError):
+        raise ValueError("Feishu delivery failed; delivery status is unknown") from None
+    if not isinstance(result, dict) or type(result.get("code")) is not int or result["code"] != 0:
+        raise ValueError("Feishu did not confirm delivery")
+
+
+def main():
+    parser = argparse.ArgumentParser(description=__doc__)
+    commands = parser.add_subparsers(dest="command", required=True)
+    commands.add_parser("schema").add_argument("kind", choices=REPORT_FIELDS)
+    collector = commands.add_parser("collect")
+    collector.add_argument("kind", choices=REPORT_FIELDS)
+    collector.add_argument("output", type=Path)
+    commands.add_parser("notify").add_argument("directory", type=Path)
+    args = parser.parse_args()
+    if args.command == "schema":
+        print("schema=" + json.dumps(report_schema(args.kind), separators=(",", ":")))
+    elif args.command == "collect":
+        report = collect(os.environ.get("REVIEW_OUTCOME"), os.environ.get("REVIEW_RESULT", ""), args.kind)
+        args.output.write_text(json.dumps(report, ensure_ascii=False))
+    else:
+        event = json.loads(Path(os.environ["GITHUB_EVENT_PATH"]).read_text())
+        reports = {kind: read_report(args.directory, kind) for kind in ("code", "docs")}
+        run_url = f"{os.environ['GITHUB_SERVER_URL']}/{os.environ['GITHUB_REPOSITORY']}/actions/runs/{os.environ['GITHUB_RUN_ID']}"
+        card = build_card(event, reports, run_url)
+        summary = os.environ.get("GITHUB_STEP_SUMMARY")
+        if summary:
+            with open(summary, "a") as output:
+                output.write(card_markdown(card))
+        send_card(os.environ.get("FEISHU_WEBHOOK_URL"), os.environ.get("FEISHU_WEBHOOK_SECRET"), card)
+        print("代码与文档审查结果已合并发送至飞书群。")
+
+
+if __name__ == "__main__":
+    try:
+        main()
+    except ValueError as error:
+        raise SystemExit(str(error)) from None
diff --git a/scripts/ci_review_test.py b/scripts/ci_review_test.py
new file mode 100644
index 000000000..c80fdfd99
--- /dev/null
+++ b/scripts/ci_review_test.py
@@ -0,0 +1,132 @@
+#!/usr/bin/env python3
+"""Exercise combined notification and incomplete-review behavior without sending messages."""
+
+import io
+import json
+from pathlib import Path
+import tempfile
+import unittest
+from unittest.mock import patch
+
+import ci_review as review
+
+
+class ReviewTests(unittest.TestCase):
+    event = {"pull_request": {"number": 485, "title": "Review docs", "html_url": "https://github.com/org/repo/pull/485", "user": {"login": "author"}}}
+    run_url = "https://github.com/org/repo/actions/runs/123"
+
+    def setUp(self):
+        self.ok = {"status": "ok", "changes": "- 更新安装流程", "review": "未发现问题", "ci": "全部通过 ✅"}
+        self.docs = {"status": "ok", "consistency": "与代码一致", "organization": "无矛盾或重复"}
+
+    def card(self, code=None, docs=None):
+        return review.build_card(self.event, {"code": code or self.ok, "docs": docs or self.docs}, self.run_url)
+
+    @patch("ci_review.urllib.request.urlopen")
+    def test_two_reports_make_one_delivery(self, post):
+        post.return_value = io.BytesIO(b'{"code":0}')
+        card = self.card(docs={**self.docs, "status": "issues", "consistency": "docs/install.md:12 与代码不符"})
+        review.send_card("https://example.invalid/webhook", "", card)
+        post.assert_called_once()
+        payload = json.loads(post.call_args.args[0].data)
+        self.assertEqual(payload["card"]["schema"], "2.0")
+        self.assertEqual(payload["card"]["header"]["template"], "red")
+        text = review.card_markdown(payload)
+        self.assertIn("3. 代码与仓库规则", text)
+        self.assertIn("文档审查 · 发现问题", text)
+        self.assertIn("docs/install.md:12", text)
+        self.assertIn(self.run_url, text)
+        self.assertNotIn("sign", payload)
+
+    def test_fixed_sections_preserve_markdown_and_separators(self):
+        card = self.card()
+        elements = card["card"]["body"]["elements"]
+        self.assertEqual(sum(element["tag"] == "hr" for element in elements), 4)
+        text = review.card_markdown(card)
+        for heading in ("1. 哪个 PR", "2. 改了什么", "3. 代码与仓库规则", "4. CI 结果", "5. 文档审查"):
+            self.assertIn(heading, text)
+        self.assertIn("- 更新安装流程", text)
+        self.assertIn("全部通过 ✅", text)
+        self.assertIn("文档与代码一致性", text)
+        self.assertIn("文档矛盾、重复与归属", text)
+        self.assertIn("---", text)
+        self.assertEqual(card["card"]["header"]["template"], "green")
+        self.assertIn("✅ 审查通过", card["card"]["header"]["title"]["content"])
+
+    def test_pending_ci_does_not_label_the_code_review_incomplete(self):
+        card = self.card(code={**self.ok, "status": "incomplete", "ci": "backend 仍在运行"})
+        text = review.card_markdown(card)
+        self.assertIn("**3. 代码与仓库规则**", text)
+        self.assertIn("未发现问题", text)
+        self.assertIn("backend 仍在运行", text)
+        self.assertEqual(card["card"]["header"]["template"], "yellow")
+
+    def test_each_kind_requires_its_own_sections(self):
+        for kind, report in (("code", self.ok), ("docs", self.docs)):
+            self.assertEqual(review.parse_report(json.dumps(report), kind), report)
+            self.assertEqual(set(review.report_schema(kind)["required"]), set(report))
+            for field in review.REPORT_FIELDS[kind]:
+                for value in (None, " ", "x" * (review.MAX_SECTION + 1)):
+                    invalid = {**report, field: value}
+                    self.assertEqual(review.parse_report(json.dumps(invalid), kind)["status"], "incomplete")
+                missing = {key: value for key, value in report.items() if key != field}
+                self.assertEqual(review.parse_report(json.dumps(missing), kind)["status"], "incomplete")
+
+    def test_failed_action_cannot_publish_a_success_report(self):
+        for outcome in ("failure", "cancelled", "skipped", None):
+            with self.subTest(outcome=outcome):
+                result = review.collect(outcome, json.dumps(self.ok), "code")
+                self.assertEqual(result["status"], "incomplete")
+                self.assertEqual(self.card(code=result)["card"]["header"]["template"], "yellow")
+
+    def test_invalid_or_missing_reports_are_incomplete(self):
+        for raw in ("", "not json", "null", "[]", '{"status":"ok"}', '{"status":[],"summary":"x"}', '{"status":"ok","summary":" "}', json.dumps({"status": "ok", "summary": "x" * 2001})):
+            with self.subTest(raw=raw[:50]):
+                self.assertEqual(review.collect("success", raw, "code")["status"], "incomplete")
+        root = Path.home() / ".oac/tests"
+        root.mkdir(parents=True, exist_ok=True)
+        with tempfile.TemporaryDirectory(dir=root) as directory:
+            path = Path(directory)
+            (path / "review-code.json").write_text(json.dumps(self.ok))
+            self.assertEqual(review.read_report(path, "code"), self.ok)
+            self.assertEqual(review.read_report(path, "docs")["status"], "incomplete")
+
+    @patch("ci_review.urllib.request.urlopen")
+    def test_http_success_requires_feishu_confirmation(self, post):
+        for body in (b'{"code":19021}', b'{}', b'{"code":false}', b'not json'):
+            with self.subTest(body=body):
+                post.reset_mock()
+                post.return_value = io.BytesIO(body)
+                with self.assertRaises(ValueError):
+                    review.send_card("https://example.invalid/webhook", "", self.card())
+                post.assert_called_once()
+
+    @patch("ci_review.urllib.request.urlopen", side_effect=TimeoutError("private-webhook"))
+    def test_ambiguous_delivery_is_not_retried_or_logged_with_secrets(self, post):
+        with self.assertRaisesRegex(ValueError, "delivery status is unknown") as error:
+            review.send_card("https://example.invalid/private-webhook", "private-signing-key", self.card())
+        self.assertNotIn("private", str(error.exception))
+        post.assert_called_once()
+
+    @patch("ci_review.time.time", return_value=1700000000)
+    @patch("ci_review.urllib.request.urlopen")
+    def test_optional_signing(self, post, _clock):
+        post.return_value = io.BytesIO(b'{"code":0}')
+        review.send_card("https://example.invalid/webhook", "test-secret", self.card())
+        payload = json.loads(post.call_args.args[0].data)
+        self.assertEqual(payload["timestamp"], "1700000000")
+        self.assertEqual(payload["sign"], "mbm4Y4oluIPQ00qlBIhX8vAZ0EKv3nw0LuTb91jPL84=")
+
+    @patch("ci_review.urllib.request.urlopen")
+    def test_bounded_unicode_reports_and_mentions(self, post):
+        post.return_value = io.BytesIO(b'{"code":0}')
+        reports = {kind: {"status": "issues", **dict.fromkeys(fields, "<at id=all>所有人</at>" + "问" * (review.MAX_SECTION - 20))}
+                   for kind, fields in review.REPORT_FIELDS.items()}
+        review.send_card("https://example.invalid/webhook", "", self.card(reports["code"], reports["docs"]))
+        data = post.call_args.args[0].data
+        self.assertLess(len(data), 20000)
+        self.assertNotIn(b"<at", data)
+
+
+if __name__ == "__main__":
+    unittest.main()
diff --git a/scripts/compose-smoke.py b/scripts/compose-smoke.py
index 2a6b27fa8..f2c4c9946 100644
--- a/scripts/compose-smoke.py
+++ b/scripts/compose-smoke.py
@@ -55,7 +55,7 @@ def prepare_pinned_payload(destination):
 def build_images(directory, tag):
     revision = subprocess.check_output(['git', 'rev-parse', 'HEAD'], cwd=ROOT, text=True).strip()
     protocol = re.search(r'const Version = "([^"]+)"', (ROOT / 'internal/agentdaemon/proto/version.go').read_text()).group(1)
-    go_env = {**os.environ, 'CGO_ENABLED': '0', 'GOOS': 'linux', 'GOARCH': 'amd64'}
+    go_env = {**os.environ, 'CGO_ENABLED': '0', 'GOOS': 'linux', 'GOARCH': os.environ.get('GOARCH', 'amd64')}
 
     def go_build(package, output, build_revision=revision):
         output.parent.mkdir(parents=True, exist_ok=True)
@@ -88,7 +88,7 @@ def go_build(package, output, build_revision=revision):
     images = {}
     for name, context in contexts.items():
         images[name] = f'oac-smoke/{name}:{tag}'
-        subprocess.run(['docker', 'build', '-q', '--platform', 'linux/amd64', '-t', images[name], str(context)],
+        subprocess.run(['docker', 'build', '-q', '--platform', 'linux/' + go_env['GOARCH'], '-t', images[name], str(context)],
                        check=True, stdout=subprocess.DEVNULL)
     return images
 
@@ -113,7 +113,7 @@ def main():
     images = build_images(directory, project.removeprefix('oac-smoke-'))
 
     override.write_text(json.dumps({'services': {'init': {'network_mode': 'none'}}}))
-    env = {**os.environ, 'COMPOSE_PROGRESS': 'plain', 'OAC_DATA_DIR': str(data),
+    env = {**os.environ, 'COMPOSE_PROGRESS': 'plain',
            'OAC_HOST': '127.0.0.1', 'OAC_WEB_PORT': '0',
            **{'OAC_IMAGE_' + name.upper(): image for name, image in images.items()}}
     env.pop('OAC_PUBLIC_URL', None)
@@ -212,7 +212,18 @@ def terminate(_signum, _frame):
         assert any(p['id'] == project_data['id'] for p in get('/core/v1/projects')['data']), 'Project was lost'
         assert get('/v1/files/' + uploaded['id'], headers=api)['bytes'] == len(content), 'Uploaded file metadata was lost'
         assert 'Bundled node installation metadata verified' not in private_logs(key, project_key), 'Completed initialization recopied metadata'
-        print('PASS: startup, origin validation, sign-in, API, upload, node installer and persistent installation', flush=True)
+        compose('run', '--rm', '--no-deps', 'init', '/usr/local/bin/oac', 'rotate-volume-key')
+        compose('restart', 'core', 'web')
+        compose('up', '-d', '--wait', '--wait-timeout', '120', timeout=180)
+        rotated = compose('exec', '-T', 'web', '/usr/local/bin/oac-web', 'core-key').decode().strip()
+        assert rotated != key, 'Core key was not rotated'
+        browser = client()
+        request('/console/auth/login', {'core_key': rotated})
+        compose('down')
+        compose('up', '-d', '--wait', '--wait-timeout', '120', timeout=180)
+        assert compose('exec', '-T', 'web', '/usr/local/bin/oac-web', 'core-key').decode().strip() == rotated, 'Rotated key was not retained'
+        private_logs(key, rotated, project_key)
+        print('PASS: startup, origin validation, sign-in, API, upload, node installer, key rotation and persistent installation', flush=True)
     except BaseException:
         # Service status identifies failed containers without dumping secret-bearing logs.
         status = subprocess.run(command + ['ps', '--all'], env=env, capture_output=True, timeout=30)
@@ -220,9 +231,6 @@ def terminate(_signum, _frame):
         raise
     finally:
         compose('down', '--volumes', '--remove-orphans', timeout=60)
-        # Match the host installer's cleanup without requiring tools in scratch init.
-        compose('run', '--rm', '--no-deps', '--volume', str(data) + ':/data',
-                '--entrypoint', 'find', 'database', '/data', '-mindepth', '1', '-delete')
         subprocess.run(['docker', 'image', 'rm', '-f', *images.values()], capture_output=True, timeout=60)
 
 
diff --git a/scripts/core-distribution-manifest.py b/scripts/core-distribution-manifest.py
index c00f363b1..3529fb8fe 100644
--- a/scripts/core-distribution-manifest.py
+++ b/scripts/core-distribution-manifest.py
@@ -70,26 +70,26 @@ def sha256(path):
     return digest.hexdigest()
 
 
-def verify_image(image):
+def verify_image(image, architecture="amd64"):
     if not DIGEST.fullmatch(image):
         raise ValueError("Distribution image inputs must be immutable sha256 image IDs")
     details = json.loads(subprocess.check_output(["docker", "image", "inspect", image], text=True))[0]
-    if details["Id"] != image or details["Os"] != "linux" or details["Architecture"] != "amd64":
-        raise ValueError("Distribution images must be the selected Linux amd64 image")
+    if details["Id"] != image or details["Os"] != "linux" or details["Architecture"] != architecture:
+        raise ValueError("Distribution images must match the selected Linux architecture")
     return details
 
 
-def built_image(metadata_file):
+def built_image(metadata_file, architecture="amd64"):
     """Print the local store ID of the image one BuildKit build just produced."""
     metadata = json.loads(pathlib.Path(metadata_file).read_text())
     # The classic store names an image by its config digest, the containerd store
     # by its manifest digest; the other value never resolves to itself there.
     config = metadata.get("containerimage.config.digest")
     manifest = metadata.get("containerimage.digest", config)
-    print(resolve_image(config, manifest))
+    print(resolve_image(config, manifest, architecture))
 
 
-def resolve_image(config, manifest):
+def resolve_image(config, manifest, architecture="amd64"):
     """Resolve the archive identities in either supported Docker image store."""
     if not all(isinstance(value, str) and DIGEST.fullmatch(value) for value in (config, manifest)):
         raise ValueError("Build metadata lacks valid image digests")
@@ -101,11 +101,11 @@ def resolve_image(config, manifest):
             resolved.append(candidate)
     if len(resolved) != 1:
         raise ValueError("The local image store does not identify the built image by exactly one of its digests")
-    verify_image(resolved[0])
+    verify_image(resolved[0], architecture)
     return resolved[0]
 
 
-def image_identities(archive, build_id):
+def image_identities(archive, build_id, architecture="amd64"):
     """Bind both Docker store identities to one exported Linux amd64 image."""
     if not DIGEST.fullmatch(build_id):
         raise ValueError("Missing immutable distribution image identity")
@@ -161,7 +161,7 @@ def blob(descriptor, parse=False):
         config_descriptor = image.get("config", {})
         config = blob(config_descriptor, parse=True)
         config_digest = config_descriptor["digest"]
-        if config.get("os") != "linux" or config.get("architecture") != "amd64":
+        if config.get("os") != "linux" or config.get("architecture") != architecture:
             raise ValueError("Image archive contains an unexpected platform")
         for layer in image.get("layers", []):
             blob(layer)
@@ -170,6 +170,21 @@ def blob(descriptor, parse=False):
         return config_digest, manifest_digest
 
 
+def control_archive(bundle, stage, revision, architecture):
+    bundle, stage = pathlib.Path(bundle), pathlib.Path(stage)
+    manifest = {"source_commit": revision, "platform": "linux/" + architecture,
+                "images": {}, "image_manifest_digests": {}}
+    for name in ("core", "web", "ingress"):
+        config, digest = image_identities(bundle / "images" / (name + ".tar"),
+                                         (stage / (name + ".id")).read_text().strip(), architecture)
+        manifest["images"][name], manifest["image_manifest_digests"][name] = config, digest
+    (bundle / "manifest.json").write_text(json.dumps(manifest, indent=2) + "\n")
+    target = bundle.with_name(bundle.name + ".tar.gz")
+    with tarfile.open(target, "w:gz") as output:
+        output.add(bundle, arcname=bundle.name)
+    target.with_name(target.name + ".sha256").write_text(sha256(target) + "  " + target.name + "\n")
+
+
 def verify_runtime(image, daemon, source):
     details = verify_image(image)
     source = pathlib.Path(source)
@@ -583,7 +598,7 @@ def check(image, link):
 
 
 if __name__ == "__main__":
-    commands = {"extract-runtime": extract_runtime, "verify-runtime": verify_runtime, "verify-image": verify_image,
+    commands = {"control-archive": control_archive, "extract-runtime": extract_runtime, "verify-runtime": verify_runtime, "verify-image": verify_image,
                 "built-image": built_image, "node-payload": node_payload, "manifest": manifest, "archive": archive, "bootstraps": bootstraps,
                 "release-base": release_base, "docs": docs, "native-catalog": native_catalog, "native-offline": native_offline}
     try:
diff --git a/scripts/core-distribution-manifest.test.py b/scripts/core-distribution-manifest.test.py
index 4719f05a1..cb4b78ce8 100644
--- a/scripts/core-distribution-manifest.test.py
+++ b/scripts/core-distribution-manifest.test.py
@@ -143,6 +143,13 @@ def test_oci_manifest_identity_is_distinct_from_docker_config_identity(self):
             digest, name = line.split("  ", 1)
             self.assertEqual(digest, distribution.sha256(self.bundle / name))
 
+    def test_arm_archive_uses_explicit_platform_validation(self):
+        path = self.stage / "arm.tar"
+        config, digest = image_archive(path, "core", architecture="arm64")
+        self.assertEqual(distribution.image_identities(path, config, "arm64"), (config, digest))
+        with self.assertRaisesRegex(ValueError, "unexpected platform"):
+            distribution.image_identities(path, config, "amd64")
+
     def test_built_image_records_the_id_each_docker_store_resolves(self):
         config, manifest, other = ("sha256:" + digit * 64 for digit in "123")
         metadata = self.stage / "build.json"
@@ -163,7 +170,7 @@ def test_built_image_records_the_id_each_docker_store_resolves(self):
                         mock.patch("builtins.print") as output:
                     if expected.startswith("sha256:"):
                         distribution.built_image(metadata)
-                        verify.assert_called_once_with(expected)
+                        verify.assert_called_once_with(expected, "amd64")
                         output.assert_called_once_with(expected)
                     else:
                         with self.assertRaisesRegex(ValueError, expected):
diff --git a/scripts/extract-agents-api-upstream.py b/scripts/extract-agents-api-upstream.py
deleted file mode 100644
index b35c3bd34..000000000
--- a/scripts/extract-agents-api-upstream.py
+++ /dev/null
@@ -1,193 +0,0 @@
-#!/usr/bin/env python3
-"""Extract the pinned official Agents API route set and field names.
-
-Run this with a Python environment where the OpenAI Python SDK version pinned in
-contracts/agents-api/upstream.json is installed (``pip install openai==3.13.0``
-from that commit). It reads only the installed SDK source and types:
-
-    python3 scripts/extract-agents-api-upstream.py \
-        contracts/agents-api/upstream.json contracts/agents-api
-
-and writes ``upstream-routes.json`` and ``upstream-fields.json`` to the output
-directory. The public contract covers the Beta Agents resources
-(``openai.resources.beta.agents``), Files (``openai.resources.files``) and
-Skills (``openai.resources.skills``); see docs/api/public-agent-api.md.
-
-Routes come from each synchronous resource method's ``self._get``/``_post``/
-``_delete``/``_get_api_list`` call, with path parameters normalised to ``{}``.
-Field names come from the request params TypedDicts (``body=maybe_transform``),
-the query params TypedDicts (``make_request_options(query=maybe_transform(...))``)
-and the response models (``cast_to`` or ``page``) of the same calls, followed
-through nested models, TypedDicts, lists and unions. JSON names use the SDK's
-wire alias. Page wrappers are the SDK's hand-written classes, not generated
-wire types.
-"""
-
-import ast
-import importlib
-import inspect
-import json
-import pkgutil
-import re
-import sys
-import typing
-from pathlib import Path
-
-import openai
-import pydantic
-import typing_extensions
-from openai._utils import PropertyInfo
-
-RESOURCE_PACKAGES = ("openai.resources.beta.agents", "openai.resources.files", "openai.resources.skills")
-HTTP_CALLS = {"_get": "GET", "_post": "POST", "_delete": "DELETE", "_put": "PUT", "_patch": "PATCH", "_get_api_list": "GET"}
-PARAMETER = re.compile(r"\{[^}]*\}")
-
-
-def modules():
-    for name in RESOURCE_PACKAGES:
-        package = importlib.import_module(name)
-        yield package
-        if hasattr(package, "__path__"):
-            for info in pkgutil.walk_packages(package.__path__, name + "."):
-                yield importlib.import_module(info.name)
-
-
-def literal_path(node):
-    if isinstance(node, ast.Call) and getattr(node.func, "id", None) == "path_template":
-        node = node.args[0]
-    if isinstance(node, ast.Constant) and isinstance(node.value, str):
-        return PARAMETER.sub("{}", node.value)
-    if isinstance(node, ast.JoinedStr):
-        return "".join(part.value if isinstance(part, ast.Constant) else "{}" for part in node.values)
-    raise ValueError(f"unsupported path expression {ast.unparse(node)}")
-
-
-def evaluate(node, namespace):
-    return eval(compile(ast.Expression(node), "<sdk>", "eval"), namespace)  # SDK-owned names only
-
-
-def is_model(value):
-    return inspect.isclass(value) and (issubclass(value, pydantic.BaseModel) or typing_extensions.is_typeddict(value))
-
-
-def type_id(value):
-    generic = getattr(value, "__pydantic_generic_metadata__", None) or {}
-    if generic.get("origin") is not None:
-        items = sorted(type_id(item) for argument in generic["args"] for item in references(argument))
-        return f"{type_id(generic['origin'])}[{' | '.join(items)}]"
-    module = value.__module__.removeprefix("openai.").removeprefix("types.")
-    return f"{module}.{value.__qualname__}"
-
-
-def references(annotation):
-    """Return nested model and TypedDict classes, unwrapping aliases and containers."""
-    if is_model(annotation):
-        return [annotation]
-    origin = typing_extensions.get_origin(annotation)
-    if origin is None or origin in (typing.Literal, typing_extensions.Literal):
-        return []
-    found = []
-    arguments = typing_extensions.get_args(annotation)
-    if origin in (typing.Annotated, typing_extensions.Annotated):
-        arguments = arguments[:1]
-    for argument in arguments:
-        found.extend(value for value in references(argument) if value not in found)
-    return found
-
-
-def alias(annotation, name):
-    if typing_extensions.get_origin(annotation) in (typing.Annotated, typing_extensions.Annotated):
-        for metadata in typing_extensions.get_args(annotation)[1:]:
-            if isinstance(metadata, PropertyInfo) and metadata.alias:
-                return metadata.alias
-    return name
-
-
-def fields(value):
-    if typing_extensions.is_typeddict(value):
-        hints = typing_extensions.get_type_hints(value, include_extras=True)
-        return {alias(annotation, name): annotation for name, annotation in hints.items()}
-    return {field.alias or name: field.annotation for name, field in value.model_fields.items()}
-
-
-def keyword_value(call, name):
-    return next((keyword.value for keyword in call.keywords if keyword.arg == name), None)
-
-
-def request_types(call, namespace, name="body"):
-    """Return the params types transformed into the call's body, or its query."""
-    value = keyword_value(call, "body") if name == "body" else None
-    if name == "query":
-        options = keyword_value(call, "options")
-        if isinstance(options, ast.Call):
-            value = keyword_value(options, "query")
-    found = []
-    for node in ast.walk(value) if value is not None else []:
-        if isinstance(node, ast.Call) and getattr(node.func, "id", "").endswith("maybe_transform") and len(node.args) == 2:
-            for candidate in ast.walk(node.args[1]):
-                if isinstance(candidate, ast.Attribute):
-                    found.extend(value for value in references(evaluate(candidate, namespace)) if value not in found)
-    return found
-
-
-def response_types(call, namespace):
-    for keyword in call.keywords:
-        if keyword.arg == "page":
-            return [evaluate(keyword.value, namespace)]
-        if keyword.arg == "cast_to":
-            node = keyword.value
-            if isinstance(node, ast.Call) and getattr(node.func, "id", None) == "cast":
-                node = node.args[1]
-            return references(evaluate(node, namespace))
-    return []
-
-
-def operations():
-    found = {}
-    for module in modules():
-        tree = ast.parse(inspect.getsource(module))
-        for resource in tree.body:
-            if not isinstance(resource, ast.ClassDef) or not any(getattr(base, "id", None) == "SyncAPIResource" for base in resource.bases):
-                continue
-            for call in ast.walk(resource):
-                if not (isinstance(call, ast.Call) and isinstance(call.func, ast.Attribute) and call.func.attr in HTTP_CALLS
-                        and getattr(call.func.value, "id", None) == "self"):
-                    continue
-                route = f"{HTTP_CALLS[call.func.attr]} {literal_path(call.args[0])}"
-                entry = found.setdefault(route, {"request": [], "query": [], "response": []})
-                namespace = vars(module)
-                for key, values in (("request", request_types(call, namespace)), ("query", request_types(call, namespace, "query")),
-                                    ("response", response_types(call, namespace))):
-                    entry[key].extend(value for value in values if value not in entry[key])
-    return found
-
-
-def main():
-    if len(sys.argv) != 3:
-        sys.exit("usage: extract-agents-api-upstream.py UPSTREAM_JSON OUTPUT_DIRECTORY")
-    pin = json.loads(Path(sys.argv[1]).read_text(encoding="utf-8"))
-    if openai.__version__ != pin["sdk_version"]:
-        sys.exit(f"installed openai {openai.__version__} does not match pinned {pin['sdk_version']}")
-    found = operations()
-    header = {"sdk_version": pin["sdk_version"], "commit": pin["commit"], "generator": "scripts/extract-agents-api-upstream.py"}
-    types, pending = {}, [value for entry in found.values() for key in ("request", "query", "response") for value in entry[key]]
-    while pending:
-        value = pending.pop()
-        if type_id(value) in types:
-            continue
-        nested = {}
-        for name, annotation in fields(value).items():
-            children = references(annotation)
-            nested[name] = sorted(type_id(child) for child in children)
-            pending.extend(children)
-        types[type_id(value)] = dict(sorted(nested.items()))
-    output = Path(sys.argv[2])
-    routes = {**header, "resources": list(RESOURCE_PACKAGES), "routes": sorted(found)}
-    (output / "upstream-routes.json").write_text(json.dumps(routes, indent=2) + "\n", encoding="utf-8")
-    operation_types = {route: {key: sorted(type_id(value) for value in entry[key]) for key in ("request", "query", "response")} for route, entry in sorted(found.items())}
-    document = {**header, "operations": operation_types, "types": dict(sorted(types.items()))}
-    (output / "upstream-fields.json").write_text(json.dumps(document, indent=2) + "\n", encoding="utf-8")
-
-
-if __name__ == "__main__":
-    main()
diff --git a/scripts/generate-harness-catalog.test.py b/scripts/generate-harness-catalog.test.py
index f58e5e079..a0ff636c3 100644
--- a/scripts/generate-harness-catalog.test.py
+++ b/scripts/generate-harness-catalog.test.py
@@ -55,6 +55,10 @@ def test_checked_in_openapi_enums_match_catalog(self):
             text = (catalog.ROOT / "contracts/agents-api" / surface).read_text()
             for definition, member in fields:
                 with self.subTest(surface=surface, definition=definition):
+                    if surface == "openapi.yaml":
+                        actual = json.loads(text)["components"]["schemas"][definition]["properties"][member]["enum"]
+                        self.assertEqual(actual, expected)
+                        continue
                     body = re.search(r"^  " + re.escape(definition) + r":\n(.*?)(?=^  [^ ]|\Z)", text, re.M | re.S)
                     self.assertIsNotNone(body, "missing schema; run make openapi")
                     field = re.search(r"^      " + member + r":\n(.*?)(?=^      [^ ]|^    [^ ]|\Z)", body.group(1), re.M | re.S)
diff --git a/scripts/generate-public-api.py b/scripts/generate-public-api.py
new file mode 100644
index 000000000..69081f3e8
--- /dev/null
+++ b/scripts/generate-public-api.py
@@ -0,0 +1,277 @@
+#!/usr/bin/env python3
+"""Project the pinned OpenAPI into Core's public contract and Go wire types."""
+import argparse
+import copy
+import hashlib
+import json
+from pathlib import Path
+import re
+import subprocess
+
+ROOT = Path(__file__).resolve().parents[1]
+CONTRACT = ROOT / 'contracts/agents-api'
+HTTP_METHODS = {'get', 'post', 'put', 'patch', 'delete', 'head', 'options'}
+
+
+def read_source():
+    pin = json.loads((CONTRACT / 'upstream.json').read_text())
+    raw = (CONTRACT / 'upstream/openapi.json').read_bytes()
+    if hashlib.sha256(raw).hexdigest() != pin['openapi']['sha256']:
+        raise ValueError('Official OpenAPI checksum differs from upstream.json')
+    return json.loads(raw), pin
+
+
+def resolve(document, pointer):
+    value = document
+    for key in pointer.removeprefix('#/').split('/'):
+        value = value[key.replace('~1', '/').replace('~0', '~')]
+    return value
+
+
+def dereference(document, schema):
+    if '$ref' in schema:
+        return {**resolve(document, schema['$ref']), **{k: v for k, v in schema.items() if k != '$ref'}}
+    return schema
+
+
+def variants(document, schema):
+    schema = dereference(document, schema)
+    for keyword in ('oneOf', 'anyOf'):
+        if keyword in schema:
+            return [v for part in schema[keyword] for v in variants(document, part)]
+    return [schema]
+
+
+def object_fields(document, sources):
+    objects = [v for source in sources for v in variants(document, resolve(document, source))]
+    properties = {}
+    required = None
+    for obj in objects:
+        if obj.get('type') == 'null':
+            continue
+        if 'properties' not in obj:
+            raise ValueError(f'Expected object projection: {sources}')
+        required = set(obj.get('required', [])) if required is None else required & set(obj.get('required', []))
+        for name, schema in obj['properties'].items():
+            if name not in properties:
+                properties[name] = []
+            if schema not in properties[name]:
+                properties[name].append(schema)
+    return {k: v[0] if len(v) == 1 else {'anyOf': v} for k, v in properties.items()}, required or set()
+
+
+def nullable(document, schema):
+    return any(v.get('type') == 'null' or isinstance(v.get('type'), list) and 'null' in v['type'] for v in variants(document, schema))
+
+
+def go_name(name):
+    initials = {'id': 'ID', 'ids': 'IDs', 'url': 'URL', 'api': 'API', 'mcp': 'MCP', 'npm': 'NPM', 'ms': 'MS', 'oauth': 'OAuth'}
+    return ''.join(initials.get(part, part.capitalize()) for part in name.split('_'))
+
+
+def go_type(document, schema, aliases):
+    ref = schema.get('$ref')
+    if ref in aliases:
+        return aliases[ref]
+    values = [v for v in variants(document, schema) if v.get('type') != 'null']
+    if len(values) != 1:
+        types = {go_type(document, v, aliases) for v in values}
+        return types.pop() if len(types) == 1 else 'json.RawMessage'
+    value = values[0]
+    kind = value.get('type')
+    if isinstance(kind, list):
+        kinds = set(kind) - {'null'}
+        kind = kinds.pop() if len(kinds) == 1 else None
+    if kind == 'array':
+        return '[]' + go_type(document, value['items'], aliases)
+    if kind == 'object':
+        extra = value.get('additionalProperties')
+        return 'map[string]' + go_type(document, extra, aliases) if isinstance(extra, dict) and not value.get('properties') else 'json.RawMessage'
+    return {'string': 'string', 'integer': 'int64', 'number': 'float64', 'boolean': 'bool'}.get(kind, 'json.RawMessage')
+
+
+def field_type(document, schema, required, aliases):
+    result = go_type(document, schema, aliases)
+    if (not required or nullable(document, schema)) and not result.startswith(('[]', 'map[', '*')) and result != 'json.RawMessage':
+        result = '*' + result
+    return result
+
+
+def enum_values(document, schema):
+    values = []
+    for variant in variants(document, schema):
+        for value in variant.get('enum', []):
+            if value is not None and value not in values:
+                values.append(value)
+    return values
+
+
+def union_marshaler(document, name, binding, field_types):
+    schema = resolve(document, binding['sources'][0])
+    discriminator = schema['discriminator']['propertyName']
+    selector = go_name(discriminator)
+    lines = [f'func (value {name}) MarshalJSON() ([]byte, error) {{', f'switch value.{selector} {{']
+    for variant in variants(document, schema):
+        tag, = variant['properties'][discriminator]['enum']
+        lines += [f'case {json.dumps(tag)}:', 'return json.Marshal(struct {']
+        for field in variant['properties']:
+            go_field, typ = field_types[field]
+            omit = '' if field in variant.get('required', []) else ',omitempty'
+            lines.append(f'{go_field} {typ} `json:"{field}{omit}"`')
+        lines.append('}{')
+        for field in variant['properties']:
+            go_field, _ = field_types[field]
+            lines.append(f'{go_field}: value.{go_field},')
+        lines.append('})')
+    lines += ['default:', f'return nil, fmt.Errorf("invalid {name} {discriminator} %q", value.{selector})', '}', '}']
+    return lines
+
+
+def go_types(document, bindings):
+    aliases = {}
+    for name, binding in sorted(bindings.items()):
+        if len(binding['sources']) == 1:
+            aliases.setdefault(binding['sources'][0], name)
+    lines = ['// Code generated by scripts/generate-public-api.py; DO NOT EDIT.', 'package v1', 'import "encoding/json"', '']
+    if any(binding.get('marshal_union') for binding in bindings.values()):
+        lines.append('import "fmt"')
+    for name, binding in sorted(bindings.items()):
+        properties, required = object_fields(document, binding['sources'])
+        overrides = binding.get('fields', {})
+        unknown = set(overrides) - set(properties) - {'x_agents_core'}
+        if unknown:
+            raise ValueError(f'{name}: bindings for missing official fields {unknown}')
+        lines += [f'// {name} projects ' + ', '.join(s.split('/')[-1] for s in binding['sources']) + '.', f'type {name} struct {{']
+        field_types = {}
+        embedded = set()
+        for embed, fields in binding.get('embed', {}).items():
+            lines.append('\t' + embed)
+            embedded.update(fields)
+        for field in dict.fromkeys(binding.get("order", []) + list(properties)):
+            if field in embedded or field in binding.get('exclude', []):
+                continue
+            if field == "x_agents_core":
+                lines.append('\tXAgentsCore ' + overrides[field]['type'] + ' `json:"x_agents_core,omitempty"`')
+                continue
+            schema = properties[field]
+            override = overrides.get(field, {})
+            typ = override.get('type', field_type(document, schema, field in required, aliases))
+            omit = override.get('omit', field not in required)
+            tags = ['json:"' + field + (',omitempty' if omit else '') + '"']
+            if field in required:
+                tags.append('binding:"required"')
+            if nullable(document, schema):
+                tags.append('extensions:"x-nullable"')
+            enums = enum_values(document, schema)
+            if enums:
+                tags.append('enums:"' + ','.join(str(v).lower() if isinstance(v, bool) else str(v) for v in enums) + '"')
+            # Swag still projects the internal APIs that reference these types.
+            if 'json.RawMessage' in typ:
+                tags.append('swaggertype:"' + ('array,object' if typ.lstrip('*').startswith('[]') else 'object') + '"')
+            field_types[field] = (go_name(field), typ)
+            lines.append('\t' + field_types[field][0] + ' ' + typ + ' `' + ' '.join(tags) + '`')
+        lines.append('}\n')
+        if binding.get('marshal_union'):
+            lines.extend(union_marshaler(document, name, binding, field_types))
+    return subprocess.run(['gofmt'], input='\n'.join(lines).encode(), stdout=subprocess.PIPE, check=True).stdout
+
+
+def prune_components(document):
+    needed = set()
+    def walk(value):
+        if isinstance(value, dict):
+            ref = value.get('$ref')
+            if ref and ref not in needed:
+                if not ref.startswith('#/components/'):
+                    raise ValueError(f'Non-local reference: {ref}')
+                needed.add(ref)
+                walk(resolve(document, ref))
+            # Discriminator mappings are references too.
+            if 'discriminator' in value:
+                for ref in value['discriminator'].get('mapping', {}).values():
+                    walk({'$ref': ref})
+            for child in value.values():
+                walk(child)
+        elif isinstance(value, list):
+            for child in value:
+                walk(child)
+    walk(document['paths'])
+    document['components'] = {section: {k: v for k, v in values.items() if '#/components/' + section + '/' + k in needed} for section, values in document['components'].items()}
+    document['components']['securitySchemes'] = {'ProjectKey': {'type': 'http', 'scheme': 'bearer', 'description': 'OpenAgentCore Project API key.'}}
+
+
+def extension_owners(bindings):
+    owners = {}
+    for binding in bindings.values():
+        extension = binding.get("fields", {}).get("x_agents_core")
+        if extension:
+            for source in binding["sources"]:
+                owners[source.split("/")[-1]] = extension["type"].lstrip("*")
+    return owners
+
+
+def public_document(source, extensions, owners, beta_header):
+    doc = copy.deepcopy(source)
+    doc['info'] = {'title': 'OpenAgentCore public API', 'version': 'v1', 'description': 'The pinned OpenAI Agents, Files and Skills API with x_agents_core extensions. See the coverage ledger for implementation qualification.'}
+    doc['servers'] = [{'url': '/v1'}]
+    doc['security'] = [{'ProjectKey': []}]
+    doc['paths'] = {p: v for p, v in doc['paths'].items() if p.split('/')[1] in ('agents', 'vaults', 'files', 'skills')}
+    for path, item in doc['paths'].items():
+        for method, operation in item.items():
+            if method not in HTTP_METHODS:
+                continue
+            operation.pop('security', None)
+            if path.split('/')[1] in ('agents', 'vaults'):
+                operation['parameters'] = operation.get('parameters', []) + [{'name': 'OpenAI-Beta', 'in': 'header', 'required': True, 'schema': {'type': 'string', 'const': beta_header}}]
+    # Extensions are authored in Core's Go types and projected by swag. Official
+    # properties are never rewritten to accommodate a narrower implementation.
+    def convert(value):
+        if isinstance(value, list):
+            return [convert(v) for v in value]
+        if not isinstance(value, dict):
+            return value
+        result = {k: convert(v) for k, v in value.items() if k != 'x-nullable'}
+        if '$ref' in result:
+            result['$ref'] = result['$ref'].replace('#/definitions/', '#/components/schemas/')
+        if value.get('x-nullable'):
+            return {'anyOf': [result, {'type': 'null'}]}
+        return result
+    doc['components']['schemas'].update({k: convert(v) for k, v in extensions.items()})
+    for name, extension in owners.items():
+        doc['components']['schemas'][name]['properties']['x_agents_core'] = {'anyOf': [{'$ref': '#/components/schemas/v1.' + extension}, {'type': 'null'}]}
+    prune_components(doc)
+    return doc
+
+
+def write(path, data, check):
+    if check:
+        if not path.exists() or path.read_bytes() != data:
+            raise ValueError(f'{path.relative_to(ROOT)} is stale; run make openapi')
+    else:
+        path.write_bytes(data)
+
+
+def main():
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument('--check', action='store_true')
+    stage = parser.add_mutually_exclusive_group(required=True)
+    stage.add_argument('--swag-roots', type=Path, help='Temporary entry points for Go-owned extension types')
+    stage.add_argument('--extensions', type=Path, help='JSON definitions projected from Core extension types')
+    args = parser.parse_args()
+    source, pin = read_source()
+    bindings = json.loads((CONTRACT / 'go-bindings.json').read_text())
+    owners = extension_owners(bindings)
+    if args.swag_roots:
+        write(CONTRACT / 'v1/official.gen.go', go_types(source, bindings), args.check)
+        roots = 'package extensions\n\n' + '\n'.join(f'// @Success 200 {{object}} v1.{name}' for name in sorted(set(owners.values()))) + '\nfunc extensions() {}\n'
+        args.swag_roots.write_text(roots)
+    else:
+        doc = public_document(source, json.loads(args.extensions.read_text()), owners, pin["beta_header"])
+        # JSON is a YAML subset and keeps generation independent of PyYAML.
+        write(CONTRACT / 'openapi.yaml', (json.dumps(doc, indent=2, ensure_ascii=False) + '\n').encode(), args.check)
+        routes = sorted(method.upper() + ' ' + re.sub(r'\{[^}]*\}', '{}', path) for path, item in doc['paths'].items() for method in item if method in HTTP_METHODS)
+        write(CONTRACT / 'upstream-routes.json', (json.dumps({'openapi_commit': pin['openapi']['commit'], 'generator': 'scripts/generate-public-api.py', 'routes': routes}, indent=2) + '\n').encode(), args.check)
+
+
+if __name__ == '__main__':
+    main()
diff --git a/scripts/generate-public-api.test.py b/scripts/generate-public-api.test.py
new file mode 100644
index 000000000..531d205f8
--- /dev/null
+++ b/scripts/generate-public-api.test.py
@@ -0,0 +1,80 @@
+#!/usr/bin/env python3
+"""Regression tests for the official schema projection and extension boundary."""
+import copy
+import importlib.util
+import json
+from pathlib import Path
+import unittest
+
+spec = importlib.util.spec_from_file_location('public_api', Path(__file__).with_name('generate-public-api.py'))
+generator = importlib.util.module_from_spec(spec)
+spec.loader.exec_module(generator)
+
+
+class PublicAPITests(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls):
+        cls.source, cls.pin = generator.read_source()
+        cls.bindings = json.loads((generator.CONTRACT / 'go-bindings.json').read_text())
+        cls.public = json.loads((generator.CONTRACT / 'openapi.yaml').read_text())
+
+    def test_generated_types_are_current(self):
+        self.assertEqual(generator.go_types(self.source, self.bindings), (generator.CONTRACT / 'v1/official.gen.go').read_bytes())
+
+    def test_public_projection_is_current_and_keeps_source_immutable(self):
+        source = copy.deepcopy(self.source)
+        extensions = {k: v for k, v in self.public['components']['schemas'].items() if k.startswith('v1.')}
+        actual = generator.public_document(source, extensions, generator.extension_owners(self.bindings), self.pin["beta_header"])
+        self.assertEqual(actual, self.public)
+        self.assertEqual(source, self.source)
+
+    def test_union_and_nullable_fields_keep_the_official_schema(self):
+        schemas = self.public['components']['schemas']
+        self.assertIn('anyOf', schemas['CreateAgentSessionParams']['properties']['input'])
+        self.assertIn('oneOf', schemas['SessionTurnItemResource'])
+        self.assertIn('discriminator', schemas['SessionEvent'])
+        self.assertEqual(schemas['AgentResource']['required'], self.source['components']['schemas']['AgentResource']['required'])
+
+    def test_extensions_are_optional_and_reachable(self):
+        schemas = self.public['components']['schemas']
+        for owner, extension in generator.extension_owners(self.bindings).items():
+            self.assertNotIn('x_agents_core', schemas[owner].get('required', []))
+            self.assertEqual(schemas[owner]['properties']['x_agents_core'], {'anyOf': [{'$ref': '#/components/schemas/v1.' + extension}, {'type': 'null'}]})
+            self.assertIn('v1.' + extension, schemas)
+        self.assertIn('model_provider', schemas['v1.SessionExecutionInput']['properties'])
+        self.assertNotIn('api.CoreHarness', schemas)
+
+    def test_new_official_fields_reach_go_without_a_second_field_list(self):
+        source = copy.deepcopy(self.source)
+        source['components']['schemas']['VaultResource']['properties']['future_field'] = {'type': ['string', 'null']}
+        generated = generator.go_types(source, self.bindings).decode()
+        self.assertIn('FutureField *string', generated)
+        self.assertIn('json:"future_field,omitempty"', generated)
+
+    def test_stale_binding_cannot_add_a_public_field(self):
+        bindings = copy.deepcopy(self.bindings)
+        bindings['Vault']['fields'] = {'private_data': {'type': 'string'}}
+        with self.assertRaisesRegex(ValueError, 'missing official fields'):
+            generator.go_types(self.source, bindings)
+
+    def test_beta_header_is_only_required_on_beta_resources(self):
+        for path, item in self.public['paths'].items():
+            for method, operation in item.items():
+                if method in generator.HTTP_METHODS:
+                    headers = [p for p in operation.get('parameters', []) if p.get('name') == 'OpenAI-Beta']
+                    self.assertEqual(bool(headers), path.split('/')[1] in ('agents', 'vaults'))
+
+    def test_optional_nullable_and_union_representation(self):
+        self.assertEqual(generator.field_type({}, {'type': ['string', 'null']}, True, {}), '*string')
+        self.assertEqual(generator.field_type({}, {'type': 'boolean'}, False, {}), '*bool')
+        self.assertEqual(generator.field_type({}, {'type': 'array', 'items': {'type': 'string'}}, True, {}), '[]string')
+        self.assertEqual(generator.go_type({}, {'oneOf': [{'type': 'string'}, {'type': 'integer'}]}, {}), 'json.RawMessage')
+
+    def test_every_public_reference_resolves_and_no_other_apis_leak(self):
+        self.assertEqual({p.split('/')[1] for p in self.public['paths']}, {'agents', 'vaults', 'files', 'skills'})
+        generator.prune_components(copy.deepcopy(self.public))
+        self.assertEqual(self.public['security'], [{'ProjectKey': []}])
+
+
+if __name__ == '__main__':
+    unittest.main()
diff --git a/scripts/name-allowlist.json b/scripts/name-allowlist.json
index a2e2a1432..768db4786 100644
--- a/scripts/name-allowlist.json
+++ b/scripts/name-allowlist.json
@@ -44,11 +44,6 @@
     "regex": "parsar-core-runtime@",
     "reason": "The guarded up/down data migration must recognize and restore the historical stored Runtime reference prefix."
   },
-  {
-    "path": "*",
-    "regex": "(?:scripts/)?extract-agents-api-upstream\\.py",
-    "reason": "The upstream contract extraction helper names the pinned OpenAI Agents API protocol, not an installed command."
-  },
   {
     "path": "*",
     "regex": "https://developers\\.openai\\.com/api/docs/guides/agents-api(?:/[A-Za-z0-9_./-]*)?",
diff --git a/scripts/openapi-split/main.go b/scripts/openapi-split/main.go
index 5a3d9236f..66d4f7438 100644
--- a/scripts/openapi-split/main.go
+++ b/scripts/openapi-split/main.go
@@ -1,10 +1,11 @@
-// Command openapi-split separates the generated document by namespace: the
-// application API (/v1), the Core API (/core/v1) and machine connections
-// (/api/v1) each get their own document.
+// Command openapi-split emits internal contracts and exports Go definitions
+// for the public contract extension overlay.
 package main
 
 import (
 	"bytes"
+	"encoding/json"
+	"flag"
 	"fmt"
 	"os"
 	"strings"
@@ -19,83 +20,68 @@ const (
 )
 
 func main() {
-	if len(os.Args) != 5 {
-		fmt.Fprintln(os.Stderr, "usage: openapi-split INPUT PROJECT_OUTPUT CORE_OUTPUT RUNTIME_OUTPUT")
+	check := flag.Bool("check", false, "check generated internal contracts without changing them")
+	flag.Parse()
+	if flag.NArg() != 4 {
+		fmt.Fprintln(os.Stderr, "usage: openapi-split [--check] INPUT EXTENSIONS_OUTPUT CORE_OUTPUT RUNTIME_OUTPUT")
 		os.Exit(1)
 	}
-	if err := run(os.Args[1], os.Args[2], os.Args[3], os.Args[4]); err != nil {
+	if err := run(flag.Arg(0), flag.Arg(1), flag.Arg(2), flag.Arg(3), *check); err != nil {
 		fmt.Fprintln(os.Stderr, err)
 		os.Exit(1)
 	}
 }
-func run(input, projectOutput, coreOutput, runtimeOutput string) error {
+
+// run exports Go-owned definitions for the public extension overlay and emits
+// the two internal contracts. Public operations come only from official OpenAPI.
+func run(input, extensionOutput, coreOutput, runtimeOutput string, check bool) error {
 	raw, err := os.ReadFile(input)
 	if err != nil {
 		return err
 	}
-	var project, core, runtime yaml.Node
-	for _, doc := range []*yaml.Node{&project, &core, &runtime} {
-		if err = yaml.Unmarshal(raw, doc); err != nil {
-			return err
-		}
+	var source yaml.Node
+	if err := yaml.Unmarshal(raw, &source); err != nil {
+		return err
 	}
-	p, m, rt := project.Content[0], core.Content[0], runtime.Content[0]
-	filterPaths(field(p, "paths"), projectSurface)
-	filterPaths(field(m, "paths"), coreSurface)
-	filterPaths(field(rt, "paths"), runtimeSurface)
-	field(m, "basePath").Value = "/"
-	field(field(m, "info"), "title").Value = "OpenAgentCore Core API"
-	field(field(m, "info"), "description").Value = "Deployment and operations routes under /core/v1 for Core Web's server and operator scripts. Every operation requires the Core key; Project API keys and machine credentials are not accepted."
-	field(rt, "basePath").Value = "/"
-	field(field(rt, "info"), "title").Value = "OpenAgentCore Machine Connections"
-	field(field(rt, "info"), "description").Value = "Machine connection routes under /api/v1. Sandbox nodes authenticate with a one-use enrollment token or their node credential; Project API keys and the Core key are not accepted. See each operation's security requirements."
-	// Retain exactly the definitions referenced by each surface, including shared
-	// error DTOs. Follow nested references instead of duplicating the project schema.
-	pruneDefinitions(p)
-	pruneDefinitions(m)
-	pruneDefinitions(rt)
-	// Each document keeps only the security schemes its operations require.
-	pruneSecurityDefinitions(p)
-	pruneSecurityDefinitions(m)
-	pruneSecurityDefinitions(rt)
-	// Keep unrelated existing project definitions and the generator's formatting.
-	// Only definitions exclusive to the Core or machine surfaces are removed.
-	var original yaml.Node
-	if err := yaml.Unmarshal(raw, &original); err != nil {
+	var definitions map[string]any
+	if err := field(source.Content[0], "definitions").Decode(&definitions); err != nil {
 		return err
 	}
-	originalDefinitions := field(original.Content[0], "definitions")
-	projectDefinitions := field(p, "definitions")
-	if originalDefinitions != nil {
-		kept := make([]*yaml.Node, 0, len(originalDefinitions.Content))
-		for i := 0; i < len(originalDefinitions.Content); i += 2 {
-			key := originalDefinitions.Content[i]
-			if field(projectDefinitions, key.Value) != nil || field(field(m, "definitions"), key.Value) == nil && field(field(rt, "definitions"), key.Value) == nil {
-				kept = append(kept, key, originalDefinitions.Content[i+1])
-			}
-		}
-		projectDefinitions.Content = kept
-	}
-	for _, out := range []struct {
-		path string
-		doc  *yaml.Node
-	}{{projectOutput, &project}, {coreOutput, &core}, {runtimeOutput, &runtime}} {
-		if out.path == projectOutput {
-			if err := os.WriteFile(out.path, preserveProjectFormatting(raw, original.Content[0], p), 0644); err != nil {
-				return err
-			}
-			continue
+	extensionJSON, err := json.Marshal(definitions)
+	if err != nil {
+		return err
+	}
+	if err := os.WriteFile(extensionOutput, extensionJSON, 0644); err != nil {
+		return err
+	}
+	for _, output := range []struct {
+		path, title, description string
+		surface                  int
+	}{
+		{coreOutput, "OpenAgentCore Core API", "Deployment and operations routes under /core/v1 for Core Web's server and operator scripts. Every operation requires the Core key; Project API keys and machine credentials are not accepted.", coreSurface},
+		{runtimeOutput, "OpenAgentCore Machine Connections", "Machine connection routes under /api/v1. Sandbox nodes authenticate with a one-use enrollment token or their node credential; Project API keys and the Core key are not accepted. See each operation's security requirements.", runtimeSurface},
+	} {
+		var doc yaml.Node
+		if err := yaml.Unmarshal(raw, &doc); err != nil {
+			return err
 		}
+		root := doc.Content[0]
+		filterPaths(field(root, "paths"), output.surface)
+		field(root, "basePath").Value = "/"
+		field(field(root, "info"), "title").Value = output.title
+		field(field(root, "info"), "description").Value = output.description
+		pruneDefinitions(root)
+		pruneSecurityDefinitions(root)
 		var buf bytes.Buffer
 		encoder := yaml.NewEncoder(&buf)
 		encoder.SetIndent(2)
-		if err := encoder.Encode(out.doc); err != nil {
+		if err := encoder.Encode(&doc); err != nil {
 			return err
 		}
 		if err := encoder.Close(); err != nil {
 			return err
 		}
-		if err := os.WriteFile(out.path, buf.Bytes(), 0644); err != nil {
+		if err := writeGenerated(output.path, buf.Bytes(), check); err != nil {
 			return err
 		}
 	}
@@ -193,42 +179,16 @@ func pruneSecurityDefinitions(root *yaml.Node) {
 	schemes.Content = kept
 }
 
-// Preserve the generated project's lexical form while removing whole mappings.
-// YAML node line locations avoid interpreting indentation or quoted path names.
-func preserveProjectFormatting(raw []byte, original, filtered *yaml.Node) []byte {
-	lines := bytes.SplitAfter(raw, []byte("\n"))
-	removed := make([]bool, len(lines))
-	for _, section := range []string{"paths", "definitions", "securityDefinitions"} {
-		source, target := field(original, section), field(filtered, section)
-		if source == nil {
-			continue
-		}
-		end := len(lines)
-		for i := 0; i+1 < len(original.Content); i += 2 {
-			if original.Content[i].Value == section && i+2 < len(original.Content) {
-				end = original.Content[i+2].Line - 1
-				break
-			}
-		}
-		for i := 0; i+1 < len(source.Content); i += 2 {
-			key := source.Content[i]
-			if field(target, key.Value) != nil {
-				continue
-			}
-			stop := end
-			if i+2 < len(source.Content) {
-				stop = source.Content[i+2].Line - 1
-			}
-			for row := key.Line - 1; row < stop; row++ {
-				removed[row] = true
-			}
+func writeGenerated(path string, data []byte, check bool) error {
+	if check {
+		existing, err := os.ReadFile(path)
+		if err != nil {
+			return err
 		}
-	}
-	var out bytes.Buffer
-	for i, line := range lines {
-		if !removed[i] {
-			out.Write(line)
+		if !bytes.Equal(existing, data) {
+			return fmt.Errorf("%s is stale; run make openapi", path)
 		}
+		return nil
 	}
-	return out.Bytes()
+	return os.WriteFile(path, data, 0644)
 }
diff --git a/scripts/openapi-split/main_test.go b/scripts/openapi-split/main_test.go
index e3f944e52..fa8b65ea7 100644
--- a/scripts/openapi-split/main_test.go
+++ b/scripts/openapi-split/main_test.go
@@ -1,6 +1,7 @@
 package main
 
 import (
+	"encoding/json"
 	"os"
 	"path/filepath"
 	"strings"
@@ -9,10 +10,10 @@ import (
 	"gopkg.in/yaml.v3"
 )
 
-func TestSeparatesTheThreeNamespaces(t *testing.T) {
+func TestInternalContractsAndExtensionDefinitions(t *testing.T) {
 	d := t.TempDir()
 	input := filepath.Join(d, "combined.yaml")
-	project := filepath.Join(d, "project.yaml")
+	project := filepath.Join(d, "extensions.json")
 	core := filepath.Join(d, "core.yaml")
 	machine := filepath.Join(d, "runtime.yaml")
 	raw := `swagger: "2.0"
@@ -71,12 +72,10 @@ securityDefinitions:
 	if err := os.WriteFile(input, []byte(raw), 0600); err != nil {
 		t.Fatal(err)
 	}
-	if err := run(input, project, core, machine); err != nil {
+	if err := run(input, project, core, machine, false); err != nil {
 		t.Fatal(err)
 	}
 	for _, check := range []struct{ path, base, own, other, definition, absent string }{
-		{project, "/v1", "/agents/sessions", "/core/v1/sandbox/nodes", "Session", "Node"},
-		{project, "/v1", "/agents/sessions", "/api/v1/sandbox-node/identity", "Session", "NodeIdentity"},
 		{core, "/", "/core/v1/sandbox/nodes", "/agents/sessions", "Node", "Session"},
 		{core, "/", "/core/v1/sandbox/nodes", "/api/v1/sandbox-node/identity", "Node", "NodeIdentity"},
 		{machine, "/", "/api/v1/sandbox-node/identity", "/core/v1/sandbox/nodes", "NodeIdentity", "Node"},
@@ -99,8 +98,19 @@ securityDefinitions:
 			t.Fatal("reference closure was not preserved")
 		}
 	}
-	// Every document keeps only the schemes its operations use.
-	for path, want := range map[string]string{project: "BearerAuth", core: "DeploymentAdminAuth", machine: "NodeAuth"} {
+	rawDefinitions, err := os.ReadFile(project)
+	if err != nil {
+		t.Fatal(err)
+	}
+	var definitions map[string]any
+	if err := json.Unmarshal(rawDefinitions, &definitions); err != nil {
+		t.Fatal(err)
+	}
+	if len(definitions) != 4 {
+		t.Fatalf("missing extension dependencies: %v", definitions)
+	}
+	// Every internal document keeps only the schemes its operations use.
+	for path, want := range map[string]string{core: "DeploymentAdminAuth", machine: "NodeAuth"} {
 		raw, err := os.ReadFile(path)
 		if err != nil {
 			t.Fatal(err)
diff --git a/scripts/publish-core-release.py b/scripts/publish-core-release.py
index 7f27e0306..8ae61caa6 100644
--- a/scripts/publish-core-release.py
+++ b/scripts/publish-core-release.py
@@ -97,7 +97,7 @@ def registry_image(reference):
     if manifest is not None and "manifests" in manifest:
         descriptors = manifest["manifests"]
         if len(descriptors) != 1:
-            raise ValueError("Expected one Linux amd64 registry image: " + reference)
+            raise ValueError("Expected one platform registry image: " + reference)
         digest = descriptors[0]["digest"]
         if not distribution.DIGEST.fullmatch(digest):
             raise ValueError("Invalid registry image descriptor")
@@ -109,87 +109,112 @@ def registry_image(reference):
 
 
 def publish_images(assets, repository, revision, tag, floating_latest=False):
-    """Load the checked release archives; never rebuild or replace another image."""
+    """Verify both architectures before publishing immutable platform tags and indexes."""
     image_tag = tag.replace("+", "_")
-    if not re.fullmatch(r"[A-Za-z0-9_][A-Za-z0-9_.-]{0,127}", image_tag):
+    if not re.fullmatch(r"[A-Za-z0-9_][A-Za-z0-9_.-]{0,120}", image_tag):
         raise ValueError("Release version exceeds the container tag format")
-    stem = "oac-" + revision + "-linux-amd64"
-    # Extract named regular members only, never archive-controlled paths.
     with tempfile.TemporaryDirectory(prefix="oac-ghcr-") as directory:
         directory = pathlib.Path(directory)
-        with tarfile.open(assets / (stem + ".tar.gz"), "r:gz") as archive:
-            manifest = json.load(archive.extractfile(stem + "/manifest.json"))
-            if manifest["source_commit"] != revision or manifest["platform"] != "linux/amd64":
-                raise ValueError("Registry images do not match the release")
-            for name in IMAGE_NAMES:
-                if name == "runtime":
-                    continue
-                member = archive.getmember(stem + "/images/" + name + ".tar")
-                if not member.isfile():
-                    raise ValueError("Expected a regular image archive")
-                with archive.extractfile(member) as source, (directory / (name + ".tar")).open("wb") as target:
-                    shutil.copyfileobj(source, target)
-        runtime = manifest["artifacts"]["images/runtime.tar.gz"]
-        filename = runtime["filename"]
-        if pathlib.Path(filename).name != filename:
-            raise ValueError("Invalid Runtime asset filename")
-        runtime_path = assets / filename
-        if runtime_path.is_symlink() or distribution.sha256(runtime_path) != runtime["sha256"]:
-            raise ValueError("Runtime image checksum mismatch")
-        with gzip.open(runtime_path, "rb") as source, (directory / "runtime.tar").open("wb") as target:
-            shutil.copyfileobj(source, target)
-        for name in IMAGE_NAMES:
-            expected = (manifest["images"][name], manifest["image_manifest_digests"][name])
-            if distribution.image_identities(directory / (name + ".tar"), expected[0]) != expected:
-                raise ValueError("Release image identity mismatch: " + name)
+        entries = {}
+        for architecture in ("amd64", "arm64"):
+            stem = "oac-" + revision + "-linux-" + architecture
+            with tarfile.open(assets / (stem + ".tar.gz"), "r:gz") as archive:
+                manifest = json.load(archive.extractfile(stem + "/manifest.json"))
+                if manifest["source_commit"] != revision or manifest["platform"] != "linux/" + architecture:
+                    raise ValueError("Registry images do not match the release")
+                names = IMAGE_NAMES if architecture == "amd64" else ("core", "web", "ingress")
+                for name in names:
+                    path = directory / (name + "-" + architecture + ".tar")
+                    if name == "runtime":
+                        artifact = manifest["artifacts"]["images/runtime.tar.gz"]
+                        filename = artifact["filename"]
+                        if pathlib.Path(filename).name != filename:
+                            raise ValueError("Invalid Runtime asset filename")
+                        compressed = assets / filename
+                        if compressed.is_symlink() or distribution.sha256(compressed) != artifact["sha256"]:
+                            raise ValueError("Runtime image checksum mismatch")
+                        with gzip.open(compressed, "rb") as source, path.open("wb") as target:
+                            shutil.copyfileobj(source, target)
+                    else:
+                        member = archive.getmember(stem + "/images/" + name + ".tar")
+                        if not member.isfile():
+                            raise ValueError("Expected a regular image archive")
+                        with archive.extractfile(member) as source, path.open("wb") as target:
+                            shutil.copyfileobj(source, target)
+                    expected = (manifest["images"][name], manifest["image_manifest_digests"][name])
+                    if distribution.image_identities(path, expected[0], architecture) != expected:
+                        raise ValueError("Release image identity mismatch: " + name)
+                    entries[name, architecture] = (path, *expected)
         references = {}
-        # Validate every local image and every existing tag before the first push.
-        for name in IMAGE_NAMES:
-            path = directory / (name + ".tar")
+        for (name, architecture), (path, config, digest) in entries.items():
             subprocess.run(["docker", "load", "--input", str(path)], check=True)
-            config = manifest["images"][name]
-            local = distribution.resolve_image(config, manifest["image_manifest_digests"][name])
-            reference = "ghcr.io/" + repository.lower() + "/" + name + ":" + image_tag
-            remote, selected = registry_image(reference)
+            local = distribution.resolve_image(config, digest, architecture)
+            reference = "ghcr.io/" + repository.lower() + "/" + name + ":" + image_tag + "-" + architecture
+            remote, _ = registry_image(reference)
             if remote is not None and remote.get("config", {}).get("digest") != config:
                 raise ValueError("Registry tag already names a different image: " + reference)
-            references[name] = (reference, config, local, remote)
+            references[name, architecture] = (reference, config, local, remote)
+        # Version indexes are immutable too. Check every existing one before pushing.
+        bases = {name: "ghcr.io/" + repository.lower() + "/" + name + ":" + image_tag for name in IMAGE_NAMES}
+        for name, reference in bases.items():
+            current = registry_manifest(reference)
+            if current is not None:
+                verify_index(reference, current, {arch: entry[1] for (n, arch), entry in entries.items() if n == name})
+
         def push_image(item):
-            name, (reference, config, local, remote) = item
-            print("Publishing registry image " + name, flush=True)
+            key, (reference, config, local, remote) = item
             if remote is None:
                 subprocess.run(["docker", "tag", local, reference], check=True)
                 subprocess.run(["docker", "push", reference], check=True)
             remote, selected = registry_image(reference)
             if remote is None or remote.get("config", {}).get("digest") != config:
                 raise ValueError("Registry image verification failed: " + reference)
-            # Inspect the registry's descriptor, not the local Docker image ID.
             details = json.loads(subprocess.check_output(
                 ["docker", "manifest", "inspect", "--verbose", selected], text=True))
             digest = details["Descriptor"]["digest"]
             if not distribution.DIGEST.fullmatch(digest):
                 raise ValueError("Invalid registry manifest digest")
-            print("Verified registry image " + name, flush=True)
-            return name, {"tag": reference, "digest": reference.rsplit(":", 1)[0] + "@" + digest}
-        result = dict(sorted(parallel_each(push_image, references.items())))
+            return key, reference.rsplit(":", 1)[0] + "@" + digest
+        platforms = dict(parallel_each(push_image, references.items()))
+        result = {}
+        for name, reference in bases.items():
+            sources = [value for (n, _), value in platforms.items() if n == name]
+            expected = {arch: entry[1] for (n, arch), entry in entries.items() if n == name}
+            if registry_manifest(reference) is None:
+                subprocess.run(["docker", "buildx", "imagetools", "create", "--tag", reference, *sources], check=True)
+            verify_index(reference, registry_manifest(reference), expected)
+            digest = subprocess.check_output(["docker", "buildx", "imagetools", "inspect", reference,
+                                               "--format", "{{.Manifest.Digest}}"], text=True).strip()
+            if not distribution.DIGEST.fullmatch(digest):
+                raise ValueError("Invalid registry index digest")
+            pinned = reference.rsplit(":", 1)[0] + "@" + digest
+            result[name] = {"tag": reference, "digest": pinned}
+        # Advance floating tags only after all version indexes are verified.
         if floating_latest:
-            def push_latest(item):
-                name, (reference, config, local, remote) = item
-                latest = reference.rsplit(":", 1)[0] + ":latest"
-                current, _selected = registry_image(latest)
-                if current is not None and current.get("config", {}).get("digest") == config:
-                    return name, latest
-                print("Publishing registry image " + name + ":latest", flush=True)
-                subprocess.run(["docker", "tag", local, latest], check=True)
-                subprocess.run(["docker", "push", latest], check=True)
-                current, selected = registry_image(latest)
-                if current is None or current.get("config", {}).get("digest") != config:
-                    raise ValueError("Registry image verification failed: " + latest)
-                return name, latest
-            parallel_each(push_latest, references.items())
+            for name, entry in result.items():
+                latest = bases[name].rsplit(":", 1)[0] + ":latest"
+                expected = {arch: value[1] for (n, arch), value in entries.items() if n == name}
+                subprocess.run(["docker", "buildx", "imagetools", "create", "--tag", latest, entry["digest"]], check=True)
+                verify_index(latest, registry_manifest(latest), expected)
         return result
 
 
+def verify_index(reference, index, expected):
+    if not index or len(index.get("manifests", [])) != len(expected):
+        raise ValueError("Registry index has unexpected platforms: " + reference)
+    actual = {}
+    for descriptor in index["manifests"]:
+        platform = descriptor.get("platform", {})
+        architecture = platform.get("architecture")
+        digest = descriptor.get("digest", "")
+        if platform.get("os") != "linux" or architecture in actual or not distribution.DIGEST.fullmatch(digest):
+            raise ValueError("Invalid registry platform descriptor")
+        child = registry_manifest(reference.rsplit(":", 1)[0] + "@" + digest)
+        actual[architecture] = (child or {}).get("config", {}).get("digest")
+    if actual != expected:
+        raise ValueError("Registry index names a different image: " + reference)
+
+
 def publish(assets, repository, revision, tag, mode):
     if not REPOSITORY.fullmatch(repository):
         raise ValueError("Expected an owner/repository")
@@ -209,7 +234,8 @@ def publish(assets, repository, revision, tag, mode):
     # The builder validates the manifest and Runtime assets. Verify archives again
     # after the Actions artifact transfer between jobs.
     stem = "oac-" + revision + "-linux-amd64"
-    archives = [assets / (stem + ".tar.gz"), assets / "install.sh"]
+    archives = [assets / (stem + ".tar.gz"), assets / ("oac-" + revision + "-linux-arm64.tar.gz"), assets / "install.sh", assets / "install.ps1"]
+    archives.extend(assets / name for name in ("oac-linux-amd64", "oac-linux-arm64", "oac-darwin-amd64", "oac-darwin-arm64", "oac-windows-amd64.exe"))
     if mode == "publish" or (assets / (stem + "-offline.tar.gz")).exists():
         archives.append(assets / (stem + "-offline.tar.gz"))
     for archive in archives:
@@ -244,7 +270,7 @@ def publish(assets, repository, revision, tag, mode):
     release = api(repository, "releases", "--method", "POST",
                   "-f", "tag_name=" + tag, "-f", "target_commitish=" + revision,
                   "-f", "name=OpenAgentCore " + tag,
-                  "-f", "body=Linux amd64 distribution from commit " + revision + ".",
+                  "-f", "body=Core for Linux, macOS and Windows; Linux amd64 Node distribution from commit " + revision + ".",
                   "-F", "draft=true", "-F", "prerelease=" + str(prerelease).lower())
     verify_draft(release, tag, revision)
     release_id = release["id"]
diff --git a/scripts/publish-core-release.test.py b/scripts/publish-core-release.test.py
index 29ff5258b..175bc9cd6 100644
--- a/scripts/publish-core-release.test.py
+++ b/scripts/publish-core-release.test.py
@@ -29,7 +29,7 @@ def setUp(self):
         self.assets = pathlib.Path(self.temp.name)
         self.revision = "a" * 40
         self.stem = "oac-" + self.revision + "-linux-amd64"
-        for name in (self.stem + ".tar.gz", self.stem + "-offline.tar.gz", "install.sh"):
+        for name in (self.stem + ".tar.gz", self.stem + "-offline.tar.gz", "install.sh", "install.ps1", "oac-" + self.revision + "-linux-arm64.tar.gz", "oac-linux-amd64", "oac-linux-arm64", "oac-darwin-amd64", "oac-darwin-arm64", "oac-windows-amd64.exe"):
             (self.assets / name).write_bytes(b"archive fixture")
             (self.assets / (name + ".sha256")).write_text(
                 hashlib.sha256(b"archive fixture").hexdigest() + "  " + name + "\n")
@@ -68,7 +68,7 @@ def test_draft_publishes_images_and_stays_unpublished(self):
         self.publish(tag="build-" + self.revision, mode="draft")
         self.images.assert_called_once()
         self.assertTrue(self.release["draft"])
-        self.assertEqual(len(self.release["assets"]), 14)
+        self.assertEqual(len(self.release["assets"]), 28)
 
     def test_missing_native_asset_refuses_release_creation(self):
         (self.assets / f"oac-native-{self.revision}-windows-amd64.tar.gz").unlink()
@@ -142,7 +142,7 @@ def response(repo, endpoint, *args):
                 return result
             if endpoint == "releases/7":
                 self.assertEqual(active, 0)
-                self.assertIn(len(self.release["assets"]), (12, 14))
+                self.assertIn(len(self.release["assets"]), (26, 28))
             return self.response(repo, endpoint, *args)
         self.api.side_effect = response
         self.publish()
@@ -153,7 +153,7 @@ def test_version_tag_publishes_complete_fixed_id(self):
         self.publish()
         self.assertFalse(self.release["draft"])
         self.assertFalse(self.release["prerelease"])
-        self.assertEqual(len(self.release["assets"]), 14)
+        self.assertEqual(len(self.release["assets"]), 28)
         self.assertEqual({a["name"] for a in self.release["assets"] if a["name"].endswith(".yaml")}, {"compose.yaml"})
         self.assertEqual(self.api.call_args.args[1:],
                          ("releases/7", "--method", "PATCH", "-F", "draft=false"))
@@ -343,142 +343,112 @@ def setUp(self):
         self.temp = tempfile.TemporaryDirectory()
         self.addCleanup(self.temp.cleanup)
         self.assets = pathlib.Path(self.temp.name)
-        self.revision = "a" * 40
-        self.config = "sha256:" + "b" * 64
-        self.digest = "sha256:" + "c" * 64
-        runtime = self.assets / "runtime.tar.gz"
-        runtime.write_bytes(gzip.compress(b"runtime"))
-        self.manifest = {
-            "source_commit": self.revision, "platform": "linux/amd64",
-            "images": dict.fromkeys(publisher.IMAGE_NAMES, self.config),
-            "image_manifest_digests": dict.fromkeys(publisher.IMAGE_NAMES, self.digest),
-            "artifacts": {"images/runtime.tar.gz": {
-                "filename": runtime.name, "sha256": publisher.distribution.sha256(runtime)}}}
-        with tarfile.open(self.assets / ("oac-" + self.revision + "-linux-amd64.tar.gz"), "w:gz") as archive:
-            for name, data in [("manifest.json", json.dumps(self.manifest).encode())] + [
-                    ("images/" + name + ".tar", b"image") for name in ("core", "web", "ingress")]:
-                member = tarfile.TarInfo("oac-" + self.revision + "-linux-amd64/" + name)
-                member.size = len(data)
-                archive.addfile(member, io.BytesIO(data))
-        stack = contextlib.ExitStack()
-        self.addCleanup(stack.close)
-        self.identities = stack.enter_context(mock.patch.object(publisher.distribution, "image_identities", return_value=(self.config, self.digest)))
-        stack.enter_context(mock.patch.object(publisher.distribution, "resolve_image", return_value=self.digest))
-        self.run = stack.enter_context(mock.patch.object(publisher.subprocess, "run"))
-        stack.enter_context(mock.patch.object(publisher.subprocess, "check_output", return_value=json.dumps({"Descriptor": {"digest": self.digest}})))
-        self.remote = stack.enter_context(mock.patch.object(publisher, "registry_manifest", return_value={"config": {"digest": self.config}}))
-
-    def publish(self, tag="v1.2.3"):
-        return publisher.publish_images(self.assets, "MiniMax-AI/OpenAgentCore", self.revision, tag)
+        self.revision = 'a' * 40
+        self.configs = {'amd64': 'sha256:' + '1' * 64, 'arm64': 'sha256:' + '2' * 64}
+        self.digests = {'amd64': 'sha256:' + '3' * 64, 'arm64': 'sha256:' + '4' * 64}
+        self.index_digest = 'sha256:' + '5' * 64
+        self.remote_images = {}
+        for arch in ('amd64', 'arm64'):
+            names = publisher.IMAGE_NAMES if arch == 'amd64' else ('core', 'web', 'ingress')
+            manifest = {'source_commit': self.revision, 'platform': 'linux/' + arch,
+                        'images': dict.fromkeys(names, self.configs[arch]),
+                        'image_manifest_digests': dict.fromkeys(names, self.digests[arch])}
+            if arch == 'amd64':
+                runtime = self.assets / 'runtime.tar.gz'
+                runtime.write_bytes(gzip.compress(b'runtime'))
+                manifest['artifacts'] = {'images/runtime.tar.gz': {'filename': runtime.name, 'sha256': publisher.distribution.sha256(runtime)}}
+            stem = 'oac-' + self.revision + '-linux-' + arch
+            with tarfile.open(self.assets / (stem + '.tar.gz'), 'w:gz') as archive:
+                for name, raw in [('manifest.json', json.dumps(manifest).encode())] + [('images/' + n + '.tar', b'image') for n in names if n != 'runtime']:
+                    member = tarfile.TarInfo(stem + '/' + name); member.size = len(raw)
+                    archive.addfile(member, io.BytesIO(raw))
+        stack = contextlib.ExitStack(); self.addCleanup(stack.close)
+        self.identities = stack.enter_context(mock.patch.object(publisher.distribution, 'image_identities', side_effect=lambda path, config, arch: (self.configs[arch], self.digests[arch])))
+        stack.enter_context(mock.patch.object(publisher.distribution, 'resolve_image', side_effect=lambda config, digest, arch: digest))
+        self.run = stack.enter_context(mock.patch.object(publisher.subprocess, 'run', side_effect=self.execute))
+        stack.enter_context(mock.patch.object(publisher.subprocess, 'check_output', side_effect=self.output))
+        self.remote = stack.enter_context(mock.patch.object(publisher, 'registry_manifest', side_effect=self.lookup))
+
+    def lookup(self, reference):
+        if '@' in reference:
+            for arch, digest in self.digests.items():
+                if reference.endswith(digest): return {'config': {'digest': self.configs[arch]}}
+        return self.remote_images.get(reference)
+
+    def execute(self, command, **kwargs):
+        if command[1] == 'push':
+            ref = command[-1]; arch = ref.rsplit('-', 1)[1]
+            self.remote_images[ref] = {'config': {'digest': self.configs[arch]}}
+        if command[1:4] == ['buildx', 'imagetools', 'create']:
+            ref = command[5]; name = ref.rsplit('/', 1)[1].split(':')[0]
+            arches = ('amd64',) if name == 'runtime' else ('amd64', 'arm64')
+            self.remote_images[ref] = {'manifests': [{'platform': {'os': 'linux', 'architecture': arch}, 'digest': self.digests[arch]} for arch in arches]}
+
+    def output(self, command, **kwargs):
+        if command[1] == 'buildx': return self.index_digest
+        ref = command[-1]
+        arch = 'arm64' if ref.endswith('arm64') else 'amd64'
+        return json.dumps({'Descriptor': {'digest': self.digests[arch]}})
+
+    def publish(self, **kwargs):
+        return publisher.publish_images(self.assets, 'MiniMax-AI/OpenAgentCore', self.revision, 'v1.2.3', **kwargs)
 
     def pushes(self):
-        return [c.args[0] for c in self.run.call_args_list if c.args[0][1] == "push"]
-
-    def test_matching_tags_are_reused_and_receipts_use_registry_digest(self):
-        result = self.publish()
-        self.assertEqual(self.pushes(), [])
-        self.assertEqual(result["core"]["digest"], "ghcr.io/minimax-ai/openagentcore/core@" + self.digest)
-
-    def test_stable_release_moves_latest_after_the_version_tags(self):
-        seen = {}
-        def remote(reference):
-            seen[reference] = seen.get(reference, 0) + 1
-            if seen[reference] == 1:
-                return None
-            return {"config": {"digest": self.config}}
-        self.remote.side_effect = remote
-        publisher.publish_images(self.assets, "MiniMax-AI/OpenAgentCore", self.revision, "v1.2.3", floating_latest=True)
-        pushed = [command[-1].rsplit("/", 1)[-1] for command in self.pushes()]
-        self.assertEqual(sorted(name for name in pushed if name.endswith(":v1.2.3")),
-                         sorted(name + ":v1.2.3" for name in publisher.IMAGE_NAMES))
-        self.assertEqual(sorted(name for name in pushed if name.endswith(":latest")),
-                         sorted(name + ":latest" for name in publisher.IMAGE_NAMES))
-
-    def test_matching_latest_tag_is_reused(self):
-        publisher.publish_images(self.assets, "MiniMax-AI/OpenAgentCore", self.revision, "v1.2.3", floating_latest=True)
-        self.assertEqual(self.pushes(), [])
+        return [call.args[0] for call in self.run.call_args_list if call.args[0][1] == 'push']
 
-    def test_new_images_use_resolved_store_identity_and_version_only(self):
-        self.remote.side_effect = [None] * 4 + [{"config": {"digest": self.config}}] * 4
-        result = self.publish("v1.2.3-rc.1+build.2")
-        self.assertEqual(len(self.pushes()), 4)
-        self.assertTrue(all(c[-1].endswith(":v1.2.3-rc.1_build.2") for c in self.pushes()))
-        tags = [c.args[0] for c in self.run.call_args_list if c.args[0][1] == "tag"]
-        self.assertTrue(all(c[2] == self.digest for c in tags))
-        self.assertEqual(len(result), 4)
-
-    def test_single_platform_indexes_are_verified_by_child_config(self):
-        index = {"manifests": [{"digest": self.digest}]}
-        image = {"config": {"digest": self.config}}
-        self.remote.side_effect = lambda reference: image if "@" in reference else index
+    def test_publishes_and_reuses_verified_multiarch_indexes(self):
         result = self.publish()
+        self.assertEqual(len(self.pushes()), 7)
+        self.assertEqual(result['ingress']['digest'], 'ghcr.io/minimax-ai/openagentcore/ingress@' + self.index_digest)
+        self.assertEqual(len(self.remote_images['ghcr.io/minimax-ai/openagentcore/core:v1.2.3']['manifests']), 2)
+        self.run.reset_mock(); self.publish(); self.assertEqual(self.pushes(), [])
+
+    def test_latest_updates_after_all_version_indexes(self):
+        self.publish(floating_latest=True)
+        creates = [c.args[0][5] for c in self.run.call_args_list if c.args[0][1:4] == ['buildx', 'imagetools', 'create']]
+        self.assertTrue(all(ref.endswith(':v1.2.3') for ref in creates[:4]))
+        self.assertTrue(all(ref.endswith(':latest') for ref in creates[4:]))
+
+    def test_conflicting_platform_prevents_every_push(self):
+        self.remote_images['ghcr.io/minimax-ai/openagentcore/web:v1.2.3-arm64'] = {'config': {'digest': 'different'}}
+        with self.assertRaisesRegex(ValueError, 'different image'): self.publish()
         self.assertEqual(self.pushes(), [])
-        self.assertEqual(result["core"]["digest"], "ghcr.io/minimax-ai/openagentcore/core@" + self.digest)
-        self.assertTrue(any("@" in call.args[0] for call in self.remote.call_args_list))
 
-    def test_multi_image_index_is_rejected(self):
-        self.remote.return_value = {"manifests": [{"digest": self.digest}] * 2}
-        with self.assertRaisesRegex(ValueError, "Expected one"):
-            self.publish()
+    def test_conflicting_index_prevents_every_push(self):
+        self.remote_images['ghcr.io/minimax-ai/openagentcore/core:v1.2.3'] = {'manifests': []}
+        with self.assertRaisesRegex(ValueError, 'unexpected platforms'): self.publish()
         self.assertEqual(self.pushes(), [])
 
-    def test_conflicting_tag_prevents_all_pushes(self):
-        self.remote.side_effect = [None, {"config": {"digest": "different"}}]
-        with self.assertRaisesRegex(ValueError, "different image"):
-            self.publish()
-        self.assertEqual(self.pushes(), [])
+    def test_missing_arm_archive_prevents_loading(self):
+        (self.assets / ('oac-' + self.revision + '-linux-arm64.tar.gz')).unlink()
+        with self.assertRaises(FileNotFoundError): self.publish()
+        self.run.assert_not_called()
 
     def test_corrupt_runtime_prevents_loading(self):
-        (self.assets / "runtime.tar.gz").write_bytes(b"corrupt")
-        with self.assertRaisesRegex(ValueError, "checksum"):
-            self.publish()
+        (self.assets / 'runtime.tar.gz').write_bytes(b'corrupt')
+        with self.assertRaisesRegex(ValueError, 'checksum'): self.publish()
         self.run.assert_not_called()
 
-    def test_archive_identity_mismatch_prevents_loading(self):
-        self.identities.return_value = (self.config, "different")
-        with self.assertRaisesRegex(ValueError, "identity mismatch"):
-            self.publish()
+    def test_wrong_archive_identity_prevents_loading(self):
+        self.identities.side_effect = None; self.identities.return_value = ('wrong', 'wrong')
+        with self.assertRaisesRegex(ValueError, 'identity mismatch'): self.publish()
         self.run.assert_not_called()
 
-    def test_failed_push_stops_publication(self):
-        self.remote.return_value = None
-        def run(command, **kwargs):
-            if command[1] == "push":
-                raise subprocess.CalledProcessError(1, command)
-        self.run.side_effect = run
-        with self.assertRaises(subprocess.CalledProcessError):
-            self.publish()
-        self.assertGreaterEqual(len(self.pushes()), 1)
-        self.assertEqual(len({command[-1] for command in self.pushes()}), len(self.pushes()))
-
-    def test_registry_pushes_overlap_after_all_preflight_checks(self):
-        barrier = threading.Barrier(4, timeout=5)
-        pushed = set()
-        lock = threading.Lock()
-        def remote(reference):
-            with lock:
-                return {"config": {"digest": self.config}} if reference in pushed else None
-        def run(command, **kwargs):
-            if command[1] == "push":
-                self.assertEqual(sum(c.args[0][1] == "load" for c in self.run.call_args_list), 4)
-                barrier.wait()
-                with lock:
-                    pushed.add(command[-1])
-        self.remote.side_effect = remote
-        self.run.side_effect = run
-        self.assertEqual(len(self.publish()), 4)
-        self.assertEqual(len(pushed), 4)
+    def test_push_failure_stops_index_publication(self):
+        def fail(command, **kwargs):
+            if command[1] == 'push': raise subprocess.CalledProcessError(1, command)
+        self.run.side_effect = fail
+        with self.assertRaises(subprocess.CalledProcessError): self.publish()
+        self.assertFalse(any(c.args[0][1] == 'buildx' for c in self.run.call_args_list))
 
     def test_registry_auth_failure_is_not_missing_image(self):
-        # Test the actual inspection function separately from the publication fixture.
-        with mock.patch.object(publisher.subprocess, "run", return_value=subprocess.CompletedProcess([], 1, "", "unauthorized")):
-            with self.assertRaisesRegex(RuntimeError, "Cannot inspect"):
-                REAL_REGISTRY_MANIFEST("ghcr.io/example/core:v1")
+        with mock.patch.object(publisher.subprocess, 'run', return_value=subprocess.CompletedProcess([], 1, '', 'unauthorized')):
+            with self.assertRaisesRegex(RuntimeError, 'Cannot inspect'): REAL_REGISTRY_MANIFEST('ghcr.io/example/core:v1')
 
     def test_registry_missing_manifest(self):
-        with mock.patch.object(publisher.subprocess, "run", return_value=subprocess.CompletedProcess([], 1, "", "manifest unknown")):
-            self.assertIsNone(REAL_REGISTRY_MANIFEST("ghcr.io/example/core:v1"))
+        with mock.patch.object(publisher.subprocess, 'run', return_value=subprocess.CompletedProcess([], 1, '', 'manifest unknown')):
+            self.assertIsNone(REAL_REGISTRY_MANIFEST('ghcr.io/example/core:v1'))
 
 
-if __name__ == "__main__":
+if __name__ == '__main__':
     unittest.main()
diff --git a/services/core/README.md b/services/core/README.md
index 424600be8..19563a3c2 100644
--- a/services/core/README.md
+++ b/services/core/README.md
@@ -62,4 +62,4 @@ It checks the upstream and generated response schemas, retries, ordering, tenant
 
 ## Generated contracts
 
-Handler annotations generate the OpenAPI documents. Run `make openapi` after changing them: it runs the pinned swaggo generator and splits the result by namespace into [`openapi.yaml`](../../contracts/agents-api/openapi.yaml) (`/v1`), [`core.openapi.yaml`](../../contracts/agents-api/core.openapi.yaml) (`/core/v1`) and [`runtime.openapi.yaml`](../../contracts/agents-api/runtime.openapi.yaml) (`/api/v1`), each with only the security schemes its operations use. Review and commit the three diffs. Contract tests hold `openapi.yaml` to the pinned routes and fields, and hold all three to exactly the routes the server registers.
+Run `make openapi` after changing the pinned public schema, Go bindings, Core extensions or internal handler annotations. The [contract generation guide](../../contracts/agents-api/index.md#pinned-baseline) owns the inputs, generated files and checks. Review and commit the generated diffs. `make check-openapi` verifies freshness; contract tests check all three documents against registered routes.
diff --git a/services/core/cmd/oac/init.go b/services/core/cmd/oac/init.go
index 7c8f6c8b4..9128bc68b 100644
--- a/services/core/cmd/oac/init.go
+++ b/services/core/cmd/oac/init.go
@@ -12,7 +12,6 @@ import (
 	"os"
 	"path/filepath"
 	"strings"
-	"syscall"
 	"time"
 
 	"github.com/MiniMax-AI/OpenAgentCore/internal/obs/log"
@@ -45,7 +44,6 @@ func initCommand() error {
 		log.Bg().Error("Initialization failed", "step", "validate_revision", "revision", revision, "error", err)
 		return err
 	}
-	syscall.Umask(0o077)
 	release := releaseIdentity{revision}
 	return initialize("/data", release, func() (map[string][]byte, error) {
 		return readRelease("/opt/oac/node-payload", release)
@@ -140,7 +138,7 @@ type installReceipt struct {
 }
 
 func initialize(root string, release releaseIdentity, fetch func() (map[string][]byte, error)) (err error) {
-	ctx, _ := log.StartBackgroundTrace(context.Background(), "installation.init")
+	ctx, _ := log.StartBackgroundTrace(context.Background())
 	logger := log.With("component", "oac-init", "revision", release.revision)
 	started := time.Now()
 	step, stepStarted := "prepare_directories", started
@@ -173,131 +171,129 @@ func initialize(root string, release releaseIdentity, fetch func() (map[string][
 		}
 	}
 	nextStep("acquire_lock")
-	lock, err := os.OpenFile(filepath.Join(root, "secrets", ".init.lock"), os.O_CREATE|os.O_WRONLY, 0o600)
-	if err != nil {
-		return err
-	}
-	defer lock.Close()
-	if err := syscall.Flock(int(lock.Fd()), syscall.LOCK_EX); err != nil {
-		return err
-	}
-	nextStep("verify_existing_installation")
-	marker := filepath.Join(root, "installation.json")
-	if raw, err := os.ReadFile(marker); err == nil {
-		var receipt installReceipt
-		if err := json.Unmarshal(raw, &receipt); err != nil {
+	return withLock(filepath.Join(root, "secrets", "init"), func() error {
+
+		nextStep("verify_existing_installation")
+		marker := filepath.Join(root, "installation.json")
+		if raw, err := os.ReadFile(marker); err == nil {
+			var receipt installReceipt
+			if err := json.Unmarshal(raw, &receipt); err != nil {
+				return err
+			}
+			if receipt.SourceCommit != release.revision {
+				return errors.New("this data directory belongs to another release; create a new installation")
+			}
+			for name, checksum := range receipt.Files {
+				actual, err := fileDigest(filepath.Join(root, name))
+				if err != nil {
+					return err
+				}
+				if actual != checksum {
+					return errors.New("installation files changed; restore the matching data directory")
+				}
+			}
+			if err := syncCoreKeyDigest(root); err != nil {
+				return err
+			}
+			logger.InfoContext(ctx, "Existing installation verified", "file_count", len(receipt.Files))
+			return nil
+		} else if !errors.Is(err, fs.ErrNotExist) {
 			return err
 		}
-		if receipt.SourceCommit != release.revision {
-			return errors.New("this data directory belongs to another release; create a new installation")
-		}
-		for name, checksum := range receipt.Files {
-			actual, err := fileDigest(filepath.Join(root, name))
+		nextStep("verify_empty_data")
+		for _, name := range []string{"database", "state"} {
+			entries, err := os.ReadDir(filepath.Join(root, name))
 			if err != nil {
 				return err
 			}
-			if actual != checksum {
-				return errors.New("installation files changed; restore the matching data directory")
+			if len(entries) > 0 {
+				return errors.New("existing data requires its original installation files")
 			}
 		}
-		logger.InfoContext(ctx, "Existing installation verified", "file_count", len(receipt.Files))
-		return nil
-	} else if !errors.Is(err, fs.ErrNotExist) {
-		return err
-	}
-	nextStep("verify_empty_data")
-	for _, name := range []string{"database", "state"} {
-		entries, err := os.ReadDir(filepath.Join(root, name))
+		nextStep("verify_bundled_metadata")
+		files, err := fetch()
 		if err != nil {
 			return err
 		}
-		if len(entries) > 0 {
-			return errors.New("existing data requires its original installation files")
+		logger.InfoContext(ctx, "Bundled node installation metadata verified", "file_count", len(files))
+		nextStep("publish_node_metadata")
+		prefix := "node-payload/releases/" + release.revision + "/"
+		names := []string{}
+		for _, name := range releaseMembers {
+			if err := writeOwned(filepath.Join(root, prefix+name), files[name]); err != nil {
+				return err
+			}
+			logger.InfoContext(ctx, "Node metadata file copied", "file", name)
+			names = append(names, prefix+name)
 		}
-	}
-	nextStep("verify_bundled_metadata")
-	files, err := fetch()
-	if err != nil {
-		return err
-	}
-	logger.InfoContext(ctx, "Bundled node installation metadata verified", "file_count", len(files))
-	nextStep("publish_node_metadata")
-	prefix := "node-payload/releases/" + release.revision + "/"
-	names := []string{}
-	for _, name := range releaseMembers {
-		if err := writeOwned(filepath.Join(root, prefix+name), files[name]); err != nil {
+		active, _ := json.Marshal(map[string]string{"source_commit": release.revision})
+		if err := writeOwned(filepath.Join(root, "node-payload", "active.json"), active); err != nil {
 			return err
 		}
-		logger.InfoContext(ctx, "Node metadata file copied", "file", name)
-		names = append(names, prefix+name)
-	}
-	active, _ := json.Marshal(map[string]string{"source_commit": release.revision})
-	if err := writeOwned(filepath.Join(root, "node-payload", "active.json"), active); err != nil {
-		return err
-	}
-	if err := filepath.WalkDir(filepath.Join(root, "node-payload"), func(path string, entry fs.DirEntry, err error) error {
-		if err != nil || !entry.IsDir() {
+		if err := filepath.WalkDir(filepath.Join(root, "node-payload"), func(path string, entry fs.DirEntry, err error) error {
+			if err != nil || !entry.IsDir() {
+				return err
+			}
+			if err := os.Chmod(path, 0o755); err != nil {
+				return err
+			}
+			return chown(path, 65532, 65532)
+		}); err != nil {
 			return err
 		}
-		if err := os.Chmod(path, 0o755); err != nil {
+		nextStep("prepare_credentials")
+		generators := []struct {
+			name     string
+			generate func() string
+		}{
+			{"secrets/web/core.key", func() string {
+				key, err := generateCoreKey()
+				if err != nil {
+					panic(err)
+				}
+				return key
+			}},
+			{"secrets/database/password", func() string { return randomHex(32) }},
+			{"secrets/core/credential.key", func() string { return base64.StdEncoding.EncodeToString(randomBytes(32)) }},
+			{"secrets/core/installation.id", func() string { return uuid.NewString() }},
+		}
+		for _, secret := range generators {
+			path := filepath.Join(root, secret.name)
+			if _, err := os.Stat(path); errors.Is(err, fs.ErrNotExist) {
+				if err := writeOwned(path, []byte(secret.generate()+"\n")); err != nil {
+					return err
+				}
+				logger.InfoContext(ctx, "Credential file generated", "file", secret.name)
+			} else if err != nil {
+				return err
+			} else {
+				logger.InfoContext(ctx, "Credential file retained", "file", secret.name)
+			}
+			if secret.name != "secrets/web/core.key" {
+				names = append(names, secret.name)
+			}
+		}
+		if err := syncCoreKeyDigest(root); err != nil {
 			return err
 		}
-		return chown(path, 65532, 65532)
-	}); err != nil {
-		return err
-	}
-	nextStep("prepare_credentials")
-	generators := []struct {
-		name     string
-		generate func() string
-	}{
-		{"secrets/web/core.key", func() string {
-			key, err := generateCoreKey()
+
+		names = append(names, "node-payload/active.json")
+		nextStep("write_installation_receipt")
+		receipt := installReceipt{SourceCommit: release.revision, Files: map[string]string{}}
+		for _, name := range names {
+			checksum, err := fileDigest(filepath.Join(root, name))
 			if err != nil {
-				panic(err)
-			}
-			return key
-		}},
-		{"secrets/database/password", func() string { return randomHex(32) }},
-		{"secrets/core/credential.key", func() string { return base64.StdEncoding.EncodeToString(randomBytes(32)) }},
-		{"secrets/core/installation.id", func() string { return uuid.NewString() }},
-	}
-	for _, secret := range generators {
-		path := filepath.Join(root, secret.name)
-		if _, err := os.Stat(path); errors.Is(err, fs.ErrNotExist) {
-			if err := writeOwned(path, []byte(secret.generate()+"\n")); err != nil {
 				return err
 			}
-			logger.InfoContext(ctx, "Credential file generated", "file", secret.name)
-		} else if err != nil {
-			return err
-		} else {
-			logger.InfoContext(ctx, "Credential file retained", "file", secret.name)
+			receipt.Files[name] = checksum
 		}
-		names = append(names, secret.name)
-	}
-	key, err := coreKey(root)
-	if err != nil {
-		return err
-	}
-	digests, _ := json.Marshal([]string{keyDigest(key)})
-	if err := writeOwned(filepath.Join(root, "secrets", "core", "core-key-digests.json"), digests); err != nil {
-		return err
-	}
-	names = append(names, "secrets/core/core-key-digests.json", "node-payload/active.json")
-	nextStep("write_installation_receipt")
-	receipt := installReceipt{SourceCommit: release.revision, Files: map[string]string{}}
-	for _, name := range names {
-		if receipt.Files[name], err = fileDigest(filepath.Join(root, name)); err != nil {
+		raw, _ := json.Marshal(receipt)
+		if err := writeOwned(marker, raw); err != nil {
 			return err
 		}
-	}
-	raw, _ := json.Marshal(receipt)
-	if err := writeOwned(marker, raw); err != nil {
-		return err
-	}
-	logger.InfoContext(ctx, "Installation initialized", "sign_in_key_command", "docker compose exec web oac-web core-key")
-	return nil
+		logger.InfoContext(ctx, "Installation initialized", "sign_in_key_command", "docker compose exec web oac-web core-key")
+		return nil
+	})
 }
 
 func randomBytes(n int) []byte {
diff --git a/services/core/cmd/oac/init_test.go b/services/core/cmd/oac/init_test.go
index b0164d682..c005a2fc3 100644
--- a/services/core/cmd/oac/init_test.go
+++ b/services/core/cmd/oac/init_test.go
@@ -12,6 +12,7 @@ import (
 	"maps"
 	"os"
 	"path/filepath"
+	"runtime"
 	"strings"
 	"testing"
 
@@ -42,7 +43,7 @@ func snapshot(t *testing.T, root string) map[string]string {
 		}
 		data, err := os.ReadFile(path)
 		relative, _ := filepath.Rel(root, path)
-		saved[relative] = string(data)
+		saved[filepath.ToSlash(relative)] = string(data)
 		return err
 	}); err != nil {
 		t.Fatal(err)
@@ -81,7 +82,7 @@ func TestInitializeKeepsIdentityAndKeysAcrossRestarts(t *testing.T) {
 	}
 	for _, name := range []string{"secrets/web/core.key", "secrets/database/password", "secrets/core/credential.key"} {
 		info, err := os.Stat(filepath.Join(root, name))
-		if err != nil || info.Mode().Perm() != 0o600 {
+		if err != nil || (runtime.GOOS != "windows" && info.Mode().Perm() != 0o600) {
 			t.Fatalf("%s: %v %v", name, info.Mode(), err)
 		}
 	}
@@ -301,3 +302,29 @@ func TestInitializationLogsFailureStep(t *testing.T) {
 		t.Fatal("failure logged success or generated credentials")
 	}
 }
+
+func TestInitializationRetainsRotatedKeyAndRepairsItsDerivedDigest(t *testing.T) {
+	root, release, files := initFixture(t)
+	if err := initialize(root, release, fixed(files)); err != nil {
+		t.Fatal(err)
+	}
+	key, err := generateCoreKey()
+	if err != nil {
+		t.Fatal(err)
+	}
+	// Simulate interruption after publishing the new key but before its digest.
+	if err := writeOwned(filepath.Join(root, "secrets", "web", "core.key"), []byte(key+"\n")); err != nil {
+		t.Fatal(err)
+	}
+	if err := initialize(root, release, refuseDownload(t)); err != nil {
+		t.Fatal(err)
+	}
+	after, _ := coreKey(root)
+	if after != key {
+		t.Fatal("rotated key replaced")
+	}
+	digest, _ := os.ReadFile(filepath.Join(root, "secrets", "core", "core-key-digests.json"))
+	if !strings.Contains(string(digest), keyDigest(key)) {
+		t.Fatal("derived digest not repaired")
+	}
+}
diff --git a/services/core/cmd/oac/install.go b/services/core/cmd/oac/install.go
new file mode 100644
index 000000000..efe7d5955
--- /dev/null
+++ b/services/core/cmd/oac/install.go
@@ -0,0 +1,358 @@
+package main
+
+import (
+	"context"
+	"crypto/sha256"
+	"encoding/hex"
+	"errors"
+	"flag"
+	"fmt"
+	"io"
+	"net"
+	"net/http"
+	"net/url"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"runtime"
+	"strconv"
+	"strings"
+	"time"
+)
+
+// Installation is host-independent. Only the launchers select a native binary;
+// Docker owns the Linux filesystem, service identities and persistent data.
+type installOptions struct {
+	dir, version, publicURL, host string
+	port                          int
+}
+type installer struct {
+	docker     func(context.Context, string, ...string) ([]byte, error)
+	download   func(context.Context, string, string) error
+	executable string
+}
+
+func installCommand(ctx context.Context, args []string) error {
+	home, err := os.UserHomeDir()
+	if err != nil {
+		return err
+	}
+	flags := flag.NewFlagSet("oac install", flag.ContinueOnError)
+	var o installOptions
+	flags.StringVar(&o.dir, "install-dir", filepath.Join(home, ".oac", "core"), "absolute installation directory")
+	flags.StringVar(&o.version, "version", "latest", "release tag")
+	flags.StringVar(&o.publicURL, "public-url", "", "URL reachable by browsers and nodes")
+	flags.StringVar(&o.host, "host", "0.0.0.0", "Web bind address")
+	flags.IntVar(&o.port, "web-port", 8080, "Web port")
+	if err := flags.Parse(args); err != nil {
+		return err
+	}
+	if flags.NArg() != 0 {
+		return errors.New("unexpected installation arguments")
+	}
+	exe, err := os.Executable()
+	if err != nil {
+		return err
+	}
+	i := installer{docker: dockerOutput, download: downloadAsset, executable: exe}
+	return i.install(ctx, o)
+}
+
+func dockerOutput(ctx context.Context, dir string, args ...string) ([]byte, error) {
+	cmd := exec.CommandContext(ctx, "docker", args...)
+	cmd.Dir = dir
+	output, err := cmd.CombinedOutput()
+	if err != nil {
+		return nil, fmt.Errorf("docker %s: %w\n%s", args[0], err, output)
+	}
+	return output, nil
+}
+
+func downloadAsset(ctx context.Context, address, path string) error {
+	client := &http.Client{Timeout: 2 * time.Minute, CheckRedirect: func(req *http.Request, via []*http.Request) error {
+		if req.URL.Scheme != "https" || len(via) >= 10 {
+			return errors.New("invalid release redirect")
+		}
+		return nil
+	}}
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, address, nil)
+	if err != nil {
+		return err
+	}
+	res, err := client.Do(req)
+	if err != nil {
+		return err
+	}
+	defer res.Body.Close()
+	if res.StatusCode != http.StatusOK {
+		return fmt.Errorf("download %s: HTTP %d", address, res.StatusCode)
+	}
+	raw, err := io.ReadAll(io.LimitReader(res.Body, (1<<20)+1))
+	if err != nil {
+		return err
+	}
+	if len(raw) > 1<<20 {
+		return errors.New("release configuration exceeds size limit")
+	}
+	return os.WriteFile(path, raw, 0o600)
+}
+
+func (i installer) install(ctx context.Context, o installOptions) error {
+	if !filepath.IsAbs(o.dir) || filepath.Clean(o.dir) == filepath.VolumeName(o.dir)+string(filepath.Separator) {
+		return errors.New("--install-dir must name an absolute directory other than the filesystem root")
+	}
+	if o.port < 1 || o.port > 65535 {
+		return errors.New("--web-port must be between 1 and 65535")
+	}
+	if net.ParseIP(o.host) == nil {
+		return errors.New("--host must be an IP address")
+	}
+	if o.publicURL == "" {
+		o.publicURL = "http://localhost:" + strconv.Itoa(o.port)
+		if o.host == "0.0.0.0" {
+			// UDP connect selects a route without transmitting a packet.
+			if route, err := net.DialTimeout("udp4", "1.1.1.1:53", time.Second); err == nil {
+				address := route.LocalAddr().(*net.UDPAddr).IP
+				route.Close()
+				if address.IsPrivate() {
+					o.publicURL = "http://" + net.JoinHostPort(address.String(), strconv.Itoa(o.port))
+				}
+			}
+		}
+	}
+	u, err := url.Parse(o.publicURL)
+	if err != nil || (u.Scheme != "http" && u.Scheme != "https") || u.Hostname() == "" || u.User != nil || u.RawQuery != "" || u.Fragment != "" || (u.Path != "" && u.Path != "/") {
+		return errors.New("--public-url must be an HTTP(S) origin")
+	}
+	for _, value := range []string{o.publicURL, o.version} {
+		if strings.ContainsAny(value, "\r\n'\\") {
+			return errors.New("installation options contain invalid characters")
+		}
+	}
+	o.dir = filepath.Clean(o.dir)
+	if err := os.MkdirAll(filepath.Dir(o.dir), 0o700); err != nil {
+		return err
+	}
+	parent, err := filepath.EvalSymlinks(filepath.Dir(o.dir))
+	if err != nil {
+		return err
+	}
+	o.dir = filepath.Join(parent, filepath.Base(o.dir))
+	if info, err := os.Lstat(o.dir); err == nil && !info.IsDir() {
+		return errors.New("installation path must be a directory, not a symbolic link or file")
+	} else if err != nil && !errors.Is(err, os.ErrNotExist) {
+		return err
+	}
+	return withLock(o.dir, func() error { return i.installLocked(ctx, o) })
+}
+
+func (i installer) installLocked(ctx context.Context, o installOptions) error {
+	info, err := i.docker(ctx, "", "info", "--format", "{{.OSType}}/{{.Architecture}}")
+	if err != nil {
+		return fmt.Errorf("start Docker and check this account's access: %w", err)
+	}
+	switch strings.TrimSpace(string(info)) {
+	case "linux/x86_64", "linux/amd64", "linux/aarch64", "linux/arm64":
+	default:
+		return errors.New("Docker must run Linux amd64 or arm64 containers; on Windows select Linux containers in Docker Desktop")
+	}
+	version, err := i.docker(ctx, "", "compose", "version", "--short")
+	if err != nil {
+		return err
+	}
+	var major, minor int
+	if _, err := fmt.Sscanf(strings.TrimPrefix(strings.TrimSpace(string(version)), "v"), "%d.%d", &major, &minor); err != nil || major < 2 || (major == 2 && minor < 26) {
+		return errors.New("Docker Compose 2.26 or newer is required")
+	}
+	engine, err := i.docker(ctx, "", "version", "--format", "{{.Server.APIVersion}}")
+	if err != nil {
+		return err
+	}
+	if _, err := fmt.Sscanf(strings.TrimSpace(string(engine)), "%d.%d", &major, &minor); err != nil || major < 1 || (major == 1 && minor < 45) {
+		return errors.New("Docker Engine 26 or newer is required for data volume subdirectories")
+	}
+	stage := o.dir + ".staging"
+	if err := cleanStage(stage, o.dir); err != nil {
+		return err
+	}
+	entries, err := os.ReadDir(o.dir)
+	if err != nil && !errors.Is(err, os.ErrNotExist) {
+		return err
+	}
+	resume := len(entries) > 0
+	working := o.dir
+	if !resume {
+		listener, err := net.Listen("tcp", net.JoinHostPort(o.host, strconv.Itoa(o.port)))
+		if err != nil {
+			return fmt.Errorf("Web port unavailable; choose --web-port: %w", err)
+		}
+		listener.Close()
+		if err := os.Mkdir(stage, 0o700); err != nil {
+			return err
+		}
+		defer os.RemoveAll(stage)
+		// Directory creation publishes ownership atomically, including on Windows.
+		if err := os.Mkdir(filepath.Join(stage, stageMarker(o.dir)), 0o700); err != nil {
+			return err
+		}
+		working = stage
+		repository := os.Getenv("OAC_REPOSITORY")
+		if repository == "" {
+			repository = "MiniMax-AI/OpenAgentCore"
+		}
+		base := "https://github.com/" + repository + "/releases/latest/download/"
+		if o.version != "latest" {
+			base = "https://github.com/" + repository + "/releases/download/" + url.PathEscape(o.version) + "/"
+		}
+		fmt.Println("Downloading release configuration...")
+		for _, name := range []string{"compose-sha256sums.txt", "compose.yaml"} {
+			if err := i.download(ctx, base+name, filepath.Join(stage, name)); err != nil {
+				return err
+			}
+		}
+		contents := fmt.Sprintf("COMPOSE_PROJECT_NAME=oac-%s\nOAC_HOST='%s'\nOAC_WEB_PORT='%d'\nOAC_PUBLIC_URL='%s'\n", randomHex(5), o.host, o.port, o.publicURL)
+		if err := os.WriteFile(filepath.Join(stage, ".env"), []byte(contents), 0o600); err != nil {
+			return err
+		}
+		source, err := os.Open(i.executable)
+		if err != nil {
+			return err
+		}
+		defer source.Close()
+		target, err := os.OpenFile(filepath.Join(stage, cliName()), os.O_CREATE|os.O_EXCL|os.O_WRONLY, 0o700)
+		if err != nil {
+			return err
+		}
+		_, copyErr := io.Copy(target, source)
+		closeErr := target.Close()
+		if copyErr != nil {
+			return copyErr
+		}
+		if closeErr != nil {
+			return closeErr
+		}
+	} else {
+		fmt.Println("Using saved settings and retaining existing data.")
+	}
+	for _, name := range []string{"compose.yaml", "compose-sha256sums.txt", ".env", cliName()} {
+		info, err := os.Lstat(filepath.Join(working, name))
+		if err != nil || !info.Mode().IsRegular() {
+			return fmt.Errorf("incomplete installation: preserve %s and choose another directory", o.dir)
+		}
+	}
+	if err := verifyCompose(working); err != nil {
+		return err
+	}
+	compose := func(args ...string) ([]byte, error) {
+		return i.docker(ctx, working, append([]string{"compose"}, args...)...)
+	}
+	if _, err := compose("config", "--quiet"); err != nil {
+		return err
+	}
+	images, err := compose("config", "--images")
+	if err != nil {
+		return err
+	}
+	fmt.Println("Checking and downloading images...")
+	for _, image := range strings.Fields(string(images)) {
+		if resume {
+			if _, err := i.docker(ctx, working, "image", "inspect", image); err == nil {
+				continue
+			}
+		}
+		if _, err := i.docker(ctx, working, "pull", image); err != nil {
+			return err
+		}
+	}
+	if !resume {
+		if _, err := os.Stat(o.dir); err == nil {
+			if err := os.Remove(o.dir); err != nil {
+				return err
+			}
+		}
+		if err := os.Rename(stage, o.dir); err != nil {
+			return err
+		}
+		working = o.dir
+		_ = os.Remove(filepath.Join(o.dir, stageMarker(o.dir)))
+	}
+	fmt.Println("Starting services...")
+	if _, err := compose("up", "-d", "--wait", "--wait-timeout", "180", "--pull", "never", "--no-recreate"); err != nil {
+		return fmt.Errorf("startup failed; data retained, rerun the installer: %w", err)
+	}
+	key, err := compose("exec", "-T", "web", "/usr/local/bin/oac-web", "core-key")
+	if err != nil {
+		return err
+	}
+	environment, err := compose("config", "--environment")
+	if err != nil {
+		return err
+	}
+	for _, line := range strings.Split(string(environment), "\n") {
+		if strings.HasPrefix(line, "OAC_PUBLIC_URL=") {
+			o.publicURL = strings.TrimPrefix(line, "OAC_PUBLIC_URL=")
+		}
+	}
+	fmt.Printf("\nOpenAgentCore is running.\n\nConsole: %s\nCore key: %s\nCommand: %s\n", o.publicURL, strings.TrimSpace(string(key)), filepath.Join(o.dir, cliName()))
+	if u, _ := url.Parse(o.publicURL); u != nil && (u.Hostname() == "localhost" || u.Hostname() == "127.0.0.1") {
+		fmt.Println("For remote access, set OAC_PUBLIC_URL in .env to a reachable origin and run oac apply.")
+	}
+	return nil
+}
+
+func cliName() string {
+	if runtime.GOOS == "windows" {
+		return "oac.exe"
+	}
+	return "oac"
+}
+
+func cleanStage(stage, owner string) error {
+	info, err := os.Lstat(stage)
+	if errors.Is(err, os.ErrNotExist) {
+		return nil
+	}
+	if err != nil {
+		return err
+	}
+	if !info.IsDir() {
+		return errors.New("staging path must be a directory, not a link or file")
+	}
+	entries, err := os.ReadDir(stage)
+	if err != nil {
+		return err
+	}
+	if len(entries) > 0 {
+		marker := filepath.Join(stage, stageMarker(owner))
+		info, err := os.Lstat(marker)
+		if err != nil || !info.IsDir() {
+			return errors.New("unrecognized staging directory; preserve it and choose another installation directory")
+		}
+		contents, err := os.ReadDir(marker)
+		if err != nil || len(contents) != 0 {
+			return errors.New("invalid staging ownership marker")
+		}
+
+	}
+	return os.RemoveAll(stage)
+}
+
+func verifyCompose(dir string) error {
+	raw, err := os.ReadFile(filepath.Join(dir, "compose.yaml"))
+	if err != nil {
+		return err
+	}
+	sums, err := os.ReadFile(filepath.Join(dir, "compose-sha256sums.txt"))
+	if err != nil {
+		return err
+	}
+	digest := sha256.Sum256(raw)
+	if strings.TrimSpace(string(sums)) != hex.EncodeToString(digest[:])+"  compose.yaml" {
+		return errors.New("Compose checksum mismatch; restore the matching release configuration")
+	}
+	return nil
+}
+
+func stageMarker(owner string) string {
+	return fmt.Sprintf(".oac-installer-%x", sha256.Sum256([]byte(owner)))
+}
diff --git a/services/core/cmd/oac/install_test.go b/services/core/cmd/oac/install_test.go
new file mode 100644
index 000000000..be48b1bfc
--- /dev/null
+++ b/services/core/cmd/oac/install_test.go
@@ -0,0 +1,245 @@
+package main
+
+import (
+	"context"
+	"crypto/sha256"
+	"fmt"
+	"net"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strings"
+	"testing"
+	"time"
+)
+
+type installFixture struct {
+	installer
+	options installOptions
+	calls   []string
+	failure string
+	cached  bool
+}
+
+func newInstallFixture(t *testing.T) *installFixture {
+	t.Helper()
+	root, err := filepath.EvalSymlinks(t.TempDir())
+	if err != nil {
+		t.Fatal(err)
+	}
+	listener, err := net.Listen("tcp", "127.0.0.1:0")
+	if err != nil {
+		t.Fatal(err)
+	}
+	port := listener.Addr().(*net.TCPAddr).Port
+	listener.Close()
+	exe := filepath.Join(root, "source")
+	if err := os.WriteFile(exe, []byte("binary"), 0o700); err != nil {
+		t.Fatal(err)
+	}
+	f := &installFixture{options: installOptions{dir: filepath.Join(root, "installation with spaces"), version: "latest", host: "127.0.0.1", port: port}}
+	f.executable = exe
+	compose := []byte("services: {}\n")
+	f.download = func(_ context.Context, address, path string) error {
+		if f.failure == "download" {
+			return os.ErrPermission
+		}
+		raw := compose
+		if strings.HasSuffix(address, "sums.txt") {
+			raw = []byte(fmt.Sprintf("%x  compose.yaml\n", sha256.Sum256(compose)))
+		}
+		return os.WriteFile(path, raw, 0o600)
+	}
+	f.docker = func(_ context.Context, dir string, args ...string) ([]byte, error) {
+		command := strings.Join(args, " ")
+		f.calls = append(f.calls, command)
+		if f.failure != "" && strings.HasPrefix(command, f.failure) {
+			return nil, os.ErrPermission
+		}
+		switch command {
+		case "info --format {{.OSType}}/{{.Architecture}}":
+			return []byte("linux/aarch64"), nil
+		case "compose version --short":
+			return []byte("v2.26.0"), nil
+		case "version --format {{.Server.APIVersion}}":
+			return []byte("1.45"), nil
+		case "compose config --images":
+			return []byte("example/core:latest\nexample/web:latest"), nil
+		case "compose config --environment":
+			return []byte("OAC_PUBLIC_URL=http://localhost:8080"), nil
+		}
+		if strings.HasPrefix(command, "image inspect") && !f.cached {
+			return nil, os.ErrNotExist
+		}
+		if strings.HasPrefix(command, "compose up") {
+			if _, err := os.Stat(filepath.Join(f.options.dir, ".env")); err != nil {
+				t.Fatal("services started before configuration publication")
+			}
+		}
+		return nil, nil
+	}
+	return f
+}
+func (f *installFixture) run() error { return f.install(context.Background(), f.options) }
+
+func TestInstallFailureBeforePublicationAndRetry(t *testing.T) {
+	for _, failure := range []string{"download", "compose config --quiet", "pull"} {
+		t.Run(failure, func(t *testing.T) {
+			f := newInstallFixture(t)
+			f.failure = failure
+			if err := f.run(); err == nil {
+				t.Fatal("expected failure")
+			}
+			for _, path := range []string{f.options.dir, f.options.dir + ".staging"} {
+				if _, err := os.Stat(path); !os.IsNotExist(err) {
+					t.Fatalf("unpublished state remains: %s", path)
+				}
+			}
+			f.failure = ""
+			if err := f.run(); err != nil {
+				t.Fatal(err)
+			}
+		})
+	}
+}
+func TestInstallResumePreservesConfigAndUsesCachedImages(t *testing.T) {
+	f := newInstallFixture(t)
+	f.failure = "compose up"
+	if err := f.run(); err == nil {
+		t.Fatal("expected startup failure")
+	}
+	saved, err := os.ReadFile(filepath.Join(f.options.dir, ".env"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	f.failure = ""
+	f.cached = true
+	f.calls = nil
+	f.download = func(context.Context, string, string) error {
+		t.Fatal("resume downloaded replacement release")
+		return nil
+	}
+	f.options.publicURL = "https://replacement.invalid"
+	if err := f.run(); err != nil {
+		t.Fatal(err)
+	}
+	after, _ := os.ReadFile(filepath.Join(f.options.dir, ".env"))
+	if string(saved) != string(after) {
+		t.Fatal("saved configuration replaced")
+	}
+	for _, call := range f.calls {
+		if strings.HasPrefix(call, "pull") || strings.Contains(call, "down") {
+			t.Fatal(call)
+		}
+	}
+	if !strings.Contains(strings.Join(f.calls, "\n"), "--pull never --no-recreate") {
+		t.Fatal(f.calls)
+	}
+}
+func TestInstallRecoversRecognizedStageAndPreservesUnknownData(t *testing.T) {
+	for _, owned := range []bool{true, false} {
+		t.Run(fmt.Sprint(owned), func(t *testing.T) {
+			f := newInstallFixture(t)
+			stage := f.options.dir + ".staging"
+			os.Mkdir(stage, 0o700)
+			os.WriteFile(filepath.Join(stage, "partial"), []byte("untouched"), 0o600)
+			if owned {
+				os.Mkdir(filepath.Join(stage, stageMarker(f.options.dir)), 0o700)
+			}
+			err := f.run()
+			if owned && err != nil {
+				t.Fatal(err)
+			}
+			if !owned {
+				if err == nil {
+					t.Fatal("unrecognized staging accepted")
+				}
+				if raw, _ := os.ReadFile(filepath.Join(stage, "partial")); string(raw) != "untouched" {
+					t.Fatal("unknown contents removed")
+				}
+			}
+		})
+	}
+	f := newInstallFixture(t)
+	os.Mkdir(f.options.dir, 0o700)
+	os.WriteFile(filepath.Join(f.options.dir, "user-file"), []byte("keep"), 0o600)
+	if err := f.run(); err == nil {
+		t.Fatal("unrelated directory accepted")
+	}
+	if raw, _ := os.ReadFile(filepath.Join(f.options.dir, "user-file")); string(raw) != "keep" {
+		t.Fatal("user data lost")
+	}
+}
+func TestInstallRejectsBusyPortAndLock(t *testing.T) {
+	f := newInstallFixture(t)
+	listener, err := net.Listen("tcp", net.JoinHostPort(f.options.host, fmt.Sprint(f.options.port)))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if err := f.run(); err == nil {
+		t.Fatal("busy port accepted")
+	}
+	listener.Close()
+	if err := withLock(f.options.dir, func() error {
+		if err := f.run(); err == nil {
+			t.Fatal("concurrent installation accepted")
+		}
+		return nil
+	}); err != nil {
+		t.Fatal(err)
+	}
+}
+func TestInstallRefusesModifiedCompose(t *testing.T) {
+	f := newInstallFixture(t)
+	if err := f.run(); err != nil {
+		t.Fatal(err)
+	}
+	os.WriteFile(filepath.Join(f.options.dir, "compose.yaml"), []byte("changed"), 0o600)
+	f.calls = nil
+	if err := f.run(); err == nil {
+		t.Fatal("changed compose accepted")
+	}
+	for _, call := range f.calls {
+		if strings.HasPrefix(call, "compose up") {
+			t.Fatal("started modified compose")
+		}
+	}
+}
+func TestInstallerInterruptedProcess(t *testing.T) {
+	if root := os.Getenv("OAC_TEST_INSTALL_KILL"); root != "" {
+		err := withLock(root, func() error {
+			stage := root + ".staging"
+			os.Mkdir(stage, 0o700)
+			os.Mkdir(filepath.Join(stage, stageMarker(root)), 0o700)
+			os.WriteFile(filepath.Join(stage, "ready"), nil, 0o600)
+			time.Sleep(time.Minute)
+			return nil
+		})
+		if err != nil {
+			os.Exit(2)
+		}
+		return
+	}
+	f := newInstallFixture(t)
+	cmd := exec.Command(os.Args[0], "-test.run=^TestInstallerInterruptedProcess$")
+	cmd.Env = append(os.Environ(), "OAC_TEST_INSTALL_KILL="+f.options.dir)
+	if err := cmd.Start(); err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(func() { _ = cmd.Process.Kill() })
+	deadline := time.Now().Add(15 * time.Second)
+	for {
+		if _, err := os.Stat(filepath.Join(f.options.dir+".staging", "ready")); err == nil {
+			break
+		}
+		if time.Now().After(deadline) {
+			t.Fatal("child never acquired lock")
+		}
+		time.Sleep(20 * time.Millisecond)
+	}
+	cmd.Process.Kill()
+	cmd.Wait()
+	if err := f.run(); err != nil {
+		t.Fatalf("killed installer left unrecoverable state: %v", err)
+	}
+}
diff --git a/services/core/cmd/oac/install_unix_test.go b/services/core/cmd/oac/install_unix_test.go
new file mode 100644
index 000000000..73e875d08
--- /dev/null
+++ b/services/core/cmd/oac/install_unix_test.go
@@ -0,0 +1,46 @@
+//go:build unix
+
+package main
+
+import (
+	"os"
+	"os/exec"
+	"os/signal"
+	"syscall"
+	"testing"
+)
+
+func TestInstallWriteFailureLeavesRetryableState(t *testing.T) {
+	if os.Getenv("OAC_TEST_FILE_LIMIT") != "1" {
+		cmd := exec.Command(os.Args[0], "-test.run=^TestInstallWriteFailureLeavesRetryableState$")
+		cmd.Env = append(os.Environ(), "OAC_TEST_FILE_LIMIT=1")
+		if output, err := cmd.CombinedOutput(); err != nil {
+			t.Fatalf("write failure probe: %v\n%s", err, output)
+		}
+		return
+	}
+	f := newInstallFixture(t)
+	var original syscall.Rlimit
+	if err := syscall.Getrlimit(syscall.RLIMIT_FSIZE, &original); err != nil {
+		t.Fatal(err)
+	}
+	limited := original
+	limited.Cur = 0
+	signal.Ignore(syscall.SIGXFSZ)
+	if err := syscall.Setrlimit(syscall.RLIMIT_FSIZE, &limited); err != nil {
+		t.Fatal(err)
+	}
+	err := f.run()
+	if restore := syscall.Setrlimit(syscall.RLIMIT_FSIZE, &original); restore != nil {
+		t.Fatal(restore)
+	}
+	if err == nil {
+		t.Fatal("installation succeeded without writable files")
+	}
+	if _, err := os.Stat(f.options.dir + ".staging"); !os.IsNotExist(err) {
+		t.Fatal("failed installation retained staging")
+	}
+	if err := f.run(); err != nil {
+		t.Fatalf("installation did not recover after restoring writes: %v", err)
+	}
+}
diff --git a/services/core/cmd/oac/main.go b/services/core/cmd/oac/main.go
index 0d1318c78..f2b3393d3 100644
--- a/services/core/cmd/oac/main.go
+++ b/services/core/cmd/oac/main.go
@@ -7,6 +7,7 @@ import (
 	"encoding/hex"
 	"encoding/json"
 	"errors"
+	"flag"
 	"fmt"
 	"os"
 	"os/signal"
@@ -15,6 +16,7 @@ import (
 	"syscall"
 
 	"github.com/MiniMax-AI/OpenAgentCore/internal/obs/log"
+	"github.com/MiniMax-AI/OpenAgentCore/internal/runtimefs"
 )
 
 func main() {
@@ -28,6 +30,9 @@ func main() {
 	ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGINT, syscall.SIGTERM)
 	defer stop()
 	if err := run(ctx, os.Args[1], os.Args[2:]); err != nil {
+		if errors.Is(err, flag.ErrHelp) {
+			return
+		}
 		if os.Args[1] != "init" {
 			fmt.Fprintln(os.Stderr, err.Error())
 		}
@@ -39,27 +44,35 @@ func main() {
 var buildRevision = "development"
 
 func usage() {
-	fmt.Fprintf(os.Stderr, "oac (%s)\nUsage: oac apply|core-key|rotate-core-key|init\n", buildRevision)
+	fmt.Fprintf(os.Stderr, "oac (%s)\nUsage: oac install|apply|core-key|rotate-core-key\n", buildRevision)
 }
 
 func run(ctx context.Context, command string, args []string) error {
 	switch command {
+	case "install":
+		return installCommand(ctx, args)
 	case "init":
 		return initCommand()
+	case "rotate-volume-key":
+		return withLock("/data/secrets/init", func() error { return rotateVolumeKey("/data") })
 	}
 	root, err := installDir()
 	if err != nil {
 		return err
 	}
-	in := installation{root: root, data: dataDir(root)}
 	runner := execRunner{dir: root}
 	switch command {
 	case "apply":
 		return withLock(root, func() error { return apply(ctx, runner) })
 	case "core-key":
-		return coreKeyCommand(ctx, in, runner, args)
+		return coreKeyCommand(ctx, runner, args)
 	case "rotate-core-key":
-		return withLock(root, func() error { return rotateCoreKey(ctx, in, runner) })
+		return withLock(root, func() error {
+			if err := runner.Run(ctx, "run", "--rm", "--no-deps", "init", "/usr/local/bin/oac", "rotate-volume-key"); err != nil {
+				return err
+			}
+			return runner.Run(ctx, "restart", "core", "web")
+		})
 	default:
 		usage()
 		return errors.New("unknown command")
@@ -81,25 +94,24 @@ func installDir() (string, error) {
 	return "", errors.New("run oac from an installation directory that contains compose.yaml")
 }
 
-type installation struct{ root, data string }
-
-func dataDir(root string) string {
-	if dir := os.Getenv("OAC_DATA_MOUNT"); dir != "" {
-		return dir
-	}
-	return filepath.Join(root, "data")
-}
-
 func withLock(root string, fn func() error) error {
-	file, err := os.OpenFile(filepath.Join(root, ".oac.lock"), os.O_CREATE|os.O_RDWR, 0o600)
-	if err != nil {
+	dir := root + ".lock"
+	if info, err := os.Lstat(dir); err == nil && !info.IsDir() {
+		return errors.New("invalid installation lock directory")
+	}
+	if err := os.MkdirAll(dir, 0o700); err != nil {
 		return err
 	}
-	defer file.Close()
-	if err := syscall.Flock(int(file.Fd()), syscall.LOCK_EX); err != nil {
+	handle, err := os.OpenRoot(dir)
+	if err != nil {
 		return err
 	}
-	defer syscall.Flock(int(file.Fd()), syscall.LOCK_UN)
+	defer handle.Close()
+	unlock, err := runtimefs.LockDirectory(handle)
+	if err != nil {
+		return fmt.Errorf("another operation is using this installation: %w", err)
+	}
+	defer unlock()
 	return fn()
 }
 
@@ -110,8 +122,8 @@ func apply(ctx context.Context, runner Runner) error {
 	return runner.Run(ctx, "up", "-d", "--wait")
 }
 
-func coreKeyCommand(ctx context.Context, in installation, runner Runner, args []string) error {
-	path := filepath.Join(in.data, "secrets", "web", "core.key")
+func coreKeyCommand(ctx context.Context, runner Runner, args []string) error {
+	path := "Docker volume: secrets/web/core.key (use oac core-key --show)"
 	if len(args) == 0 {
 		fmt.Println(path)
 		return nil
@@ -130,24 +142,33 @@ func generateCoreKey() (string, error) {
 	return "oac_admin_" + hex.EncodeToString(buf), nil
 }
 
-func rotateCoreKey(ctx context.Context, in installation, runner Runner) error {
+func rotateVolumeKey(data string) error {
 	key, err := generateCoreKey()
 	if err != nil {
 		return err
 	}
-	keyPath := filepath.Join(in.data, "secrets", "web", "core.key")
-	digestPath := filepath.Join(in.data, "secrets", "core", "core-key-digests.json")
-	if err := writeSecret(keyPath, key+"\n"); err != nil {
+	keyPath := filepath.Join(data, "secrets", "web", "core.key")
+	if err := writeOwned(keyPath, []byte(key+"\n")); err != nil {
 		return err
 	}
-	raw, err := json.Marshal([]string{keyDigest(key)})
+	return syncCoreKeyDigest(data)
+}
+
+func syncCoreKeyDigest(data string) error {
+	key, err := coreKey(data)
 	if err != nil {
 		return err
 	}
-	if err := writeSecret(digestPath, string(raw)+"\n"); err != nil {
-		return err
+	value, err := hex.DecodeString(strings.TrimPrefix(key, "oac_admin_"))
+	if err != nil || !strings.HasPrefix(key, "oac_admin_") || len(value) != 32 {
+		return errors.New("invalid saved Core key")
 	}
-	return runner.Run(ctx, "restart", "core", "web")
+	raw, _ := json.Marshal([]string{keyDigest(key)})
+	path := filepath.Join(data, "secrets", "core", "core-key-digests.json")
+	if saved, err := os.ReadFile(path); err == nil && strings.TrimSpace(string(saved)) == string(raw) {
+		return nil
+	}
+	return writeOwned(path, raw)
 }
 
 func coreKey(data string) (string, error) {
@@ -162,23 +183,3 @@ func keyDigest(key string) string {
 	sum := sha256.Sum256([]byte(key))
 	return hex.EncodeToString(sum[:])
 }
-
-func writeSecret(path, contents string) error {
-	info, err := os.Stat(path)
-	if err != nil {
-		return err
-	}
-	stat, ok := info.Sys().(*syscall.Stat_t)
-	if !ok {
-		return os.ErrInvalid
-	}
-	temporary := path + ".tmp"
-	if err := os.WriteFile(temporary, []byte(contents), 0o600); err != nil {
-		return err
-	}
-	if err := os.Chown(temporary, int(stat.Uid), int(stat.Gid)); err != nil {
-		_ = os.Remove(temporary)
-		return err
-	}
-	return os.Rename(temporary, path)
-}
diff --git a/services/core/cmd/oac/oac_test.go b/services/core/cmd/oac/oac_test.go
index ee865c213..d3ccd058d 100644
--- a/services/core/cmd/oac/oac_test.go
+++ b/services/core/cmd/oac/oac_test.go
@@ -28,40 +28,36 @@ func TestApplyDoesNotStartWhenTheConfigurationCheckFails(t *testing.T) {
 
 func TestRotateCoreKeyDigestDoesNotEchoTheKey(t *testing.T) {
 	root := t.TempDir()
-	in := installation{root: root, data: filepath.Join(root, "data")}
-	if err := os.MkdirAll(filepath.Join(in.data, "secrets", "web"), 0o755); err != nil {
+	data := filepath.Join(root, "data")
+	if err := os.MkdirAll(filepath.Join(data, "secrets", "web"), 0o755); err != nil {
 		t.Fatal(err)
 	}
-	if err := os.MkdirAll(filepath.Join(in.data, "secrets", "core"), 0o755); err != nil {
+	if err := os.MkdirAll(filepath.Join(data, "secrets", "core"), 0o755); err != nil {
 		t.Fatal(err)
 	}
-	if err := os.WriteFile(filepath.Join(in.data, "secrets", "web", "core.key"), []byte("old\n"), 0o600); err != nil {
+	if err := os.WriteFile(filepath.Join(data, "secrets", "web", "core.key"), []byte("old\n"), 0o600); err != nil {
 		t.Fatal(err)
 	}
-	if err := os.WriteFile(filepath.Join(in.data, "secrets", "core", "core-key-digests.json"), []byte("[]\n"), 0o600); err != nil {
+	if err := os.WriteFile(filepath.Join(data, "secrets", "core", "core-key-digests.json"), []byte("[]\n"), 0o600); err != nil {
 		t.Fatal(err)
 	}
-	var restarted bool
-	runner := scriptedRunner{run: func(args ...string) error {
-		restarted = args[0] == "restart"
-		return nil
-	}}
-	if err := rotateCoreKey(context.Background(), in, runner); err != nil {
+	previous := chown
+	chown = func(string, int, int) error { return nil }
+	t.Cleanup(func() { chown = previous })
+	if err := rotateVolumeKey(data); err != nil {
 		t.Fatal(err)
 	}
-	raw, err := os.ReadFile(filepath.Join(in.data, "secrets", "web", "core.key"))
+
+	raw, err := os.ReadFile(filepath.Join(data, "secrets", "web", "core.key"))
 	if err != nil {
 		t.Fatal(err)
 	}
 	key := strings.TrimSpace(string(raw))
 	assertCoreKeyFormat(t, key)
-	digest, err := os.ReadFile(filepath.Join(in.data, "secrets", "core", "core-key-digests.json"))
+	digest, err := os.ReadFile(filepath.Join(data, "secrets", "core", "core-key-digests.json"))
 	if err != nil || !strings.Contains(string(digest), keyDigest(key)) || strings.Contains(string(digest), key) {
 		t.Fatalf("digest %s key leaked %v", digest, err)
 	}
-	if !restarted {
-		t.Fatal("core was not restarted")
-	}
 }
 
 type scriptedRunner struct {
diff --git a/services/core/deploy/mcode/Dockerfile b/services/core/deploy/mcode/Dockerfile
index df7c80c9a..774c1be79 100644
--- a/services/core/deploy/mcode/Dockerfile
+++ b/services/core/deploy/mcode/Dockerfile
@@ -11,8 +11,6 @@ ENV HOME=/home/runtime OAC_RUNTIME_HOME=/home/runtime/.oac \
     OAC_RUNTIME_MCODE_NODE=/usr/local/bin/node \
     OAC_RUNTIME_MCODE_BIN=/opt/mcode-harness/native/cli.js \
     OAC_RUNTIME_MCODE_WORKSPACE_BRIDGE=/opt/mcode-harness/bridge.mjs \
-    OAC_RUNTIME_MCODE_AGENTS_API=1 \
-    OAC_RUNTIME_MCODE_WORKSPACE=managed \
     OAC_RUNTIME_WORKSPACE=/environment/workspace \
     OAC_RUNTIME_INITIALIZATION_DIRECTORY=/environment/initialization \
     OAC_RUNTIME_PACKAGE_DIRECTORY=/environment/packages
diff --git a/services/core/deploy/mcode/README.md b/services/core/deploy/mcode/README.md
index eed55d773..58cbbcea0 100644
--- a/services/core/deploy/mcode/README.md
+++ b/services/core/deploy/mcode/README.md
@@ -6,7 +6,7 @@ Native tools run with the daemon user's permissions; the outer sandbox provides
 
 ## Native pin and readiness
 
-The adapter accepts only `@minimax-ai/code` `0.4.12` ([`version.go`](../../../../apps/daemon/internal/agent/mcode/version.go)), built from the upstream source revision in [`source.json`](../../../../packages/mcode-harness/source.json) and run with Node.js 22. The daemon advertises MiniMax execution only when `OAC_RUNTIME_MCODE_AGENTS_API=1` and the version matches ([`execution.go`](../../../../apps/daemon/internal/agent/mcode/execution.go)); the native installer and the Runtime image set it. MiniMax Code runs on Linux and macOS.
+The adapter accepts only `@minimax-ai/code` `0.4.12` ([`version.go`](../../../../apps/daemon/internal/agent/mcode/version.go)), built from the upstream source revision in [`source.json`](../../../../packages/mcode-harness/source.json) and run with Node.js 22. MiniMax Code runs on Linux and macOS.
 
 Workspace execution also requires the companion's readiness report: private protocol 2, the pinned native version and the pinned source revision ([`workspace_readiness.go`](../../../../apps/daemon/internal/agent/mcode/workspace_readiness.go)). An older companion is rejected even when the upstream version matches.
 
@@ -47,7 +47,7 @@ In the workspace profile, the frozen installation's Skills are linked into the S
 | Base | Digest-pinned `node:22.23.1-bookworm-slim` with `ca-certificates`, `bash`, `git`, `python3`, `python3-pip` and `ripgrep` |
 | Programs | `/usr/local/bin/oac-daemon` and the companion at `/opt/mcode-harness` (native CLI at `native/cli.js`, bridge at `bridge.mjs`) |
 | User | UID/GID 1000 with `HOME=/home/runtime` |
-| Environment | `OAC_RUNTIME_HOME=/home/runtime/.oac`, `OAC_RUNTIME_MCODE_NODE`, `OAC_RUNTIME_MCODE_BIN`, `OAC_RUNTIME_MCODE_WORKSPACE_BRIDGE`, `OAC_RUNTIME_MCODE_AGENTS_API=1`, `OAC_RUNTIME_WORKSPACE=/environment/workspace`, `OAC_RUNTIME_INITIALIZATION_DIRECTORY=/environment/initialization`, `OAC_RUNTIME_PACKAGE_DIRECTORY=/environment/packages` |
+| Environment | `OAC_RUNTIME_HOME=/home/runtime/.oac`, `OAC_RUNTIME_MCODE_NODE`, `OAC_RUNTIME_MCODE_BIN`, `OAC_RUNTIME_MCODE_WORKSPACE_BRIDGE`, `OAC_RUNTIME_WORKSPACE=/environment/workspace`, `OAC_RUNTIME_INITIALIZATION_DIRECTORY=/environment/initialization`, `OAC_RUNTIME_PACKAGE_DIRECTORY=/environment/packages` |
 | Entry point | `oac-daemon connect --profile default`, working directory `/environment/workspace` |
 
 The build runs the companion's `check.mjs` and the native `--version`. The combined Runtime image uses this image as its base. Sandboxes run it with the [Docker sandbox settings](../../../../docs/sandbox-provider.md#docker-adapter).
diff --git a/services/core/internal/api/agents.go b/services/core/internal/api/agents.go
index f2f1cb4af..0aa2a0607 100644
--- a/services/core/internal/api/agents.go
+++ b/services/core/internal/api/agents.go
@@ -25,17 +25,6 @@ type AgentsReader interface {
 	GetAgentWithModelProvider(ctx context.Context, tenantID, agentID string) (agents.Agent, *v1.ModelProviderInput, error)
 }
 
-// @Summary Create a reusable Agent
-// @Description Persists configuration independently of execution. Names over 128 characters and metadata outside 16 string pairs with 64-character keys and 512-character values return invalid_request_error with the official param; U+0000 in stored strings is rejected as a local storage limit. As on every Agents API JSON route, a non-JSON Content-Type, invalid UTF-8, malformed JSON, a repeated key at any depth or a non-object root returns invalid_request_error with a null param and the official message before other checks; an empty or null body is {}. Missing, unknown, wrongly typed or unsupported enum members of the pinned configuration shapes (tools, text, reasoning, service_tier, multi_agent) return invalid_request_error with the JSON path as param; duplicate function names, repeated web_search or tool_search and non-object schema root types return it with a null param. Supports model/name/instructions/metadata, explicit reasoning and service tiers, multi_agent, text/json_schema, function/tool_search/programmatic_tool_calling/web_search and HTTP MCP with nullable credential_id, service origin (omitted or null on HTTP transport is saved as service) and boolean required defaulting to false. Saving credential_id grants no access: Session admission checks attached Vault ownership and destination. MCP allowed_tools preserves null versus empty; saved HTTP transport includes empty headers. Model-derived reasoning defaults, other MCP variants and public retry conformance remain incomplete. web_search saves every pinned mode: omitted or null mode is saved as live and omitted or null context_size as medium; allowed_domains preserves null versus empty and a present location, including {}, includes all four keys with null for omitted ones, as observed officially (req_db41d2f6261b4abfb69465eafe719ab5, req_165d53b88445490b9146d8272c54134d). Session execution accepts only explicit disabled web_search and disabled programmatic_tool_calling through qualified Runtime controls; saved enabled forms reject at Session admission. Session execution admits only its supported configuration subset.
-// @Tags Agents
-// @Accept json
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param body body v1.CreateAgentRequest true "Reusable Agent configuration"
-// @Success 201 {object} v1.SavedAgent
-// @Failure 400,401,413,500 {object} v1.ErrorResponse
-// @Router /agents [post]
 func (h *Handler) createAgent(w http.ResponseWriter, r *http.Request) {
 	raw, ok := readJSONObject(w, r)
 	if !ok {
@@ -69,16 +58,6 @@ func (h *Handler) createAgent(w http.ResponseWriter, r *http.Request) {
 	h.respondAgentStatus(w, r, agent, http.StatusCreated)
 }
 
-// @Summary Retrieve a reusable Agent
-// @Description Reads the saved resource owned by the authenticated tenant, independently of execution Sessions.
-// @Tags Agents
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param agent_id path string true "Agent ID"
-// @Success 200 {object} v1.SavedAgent
-// @Failure 400,401,404,500 {object} v1.ErrorResponse
-// @Router /agents/{agent_id} [get]
 func (h *Handler) getAgent(w http.ResponseWriter, r *http.Request) {
 	agent, err := h.AgentsReader.GetAgent(r.Context(), tenantID(r), chi.URLParam(r, "agent_id"))
 	if err != nil {
diff --git a/services/core/internal/api/agents_delete.go b/services/core/internal/api/agents_delete.go
index f0fbe30f1..f90467cd8 100644
--- a/services/core/internal/api/agents_delete.go
+++ b/services/core/internal/api/agents_delete.go
@@ -9,16 +9,6 @@ import (
 	"github.com/go-chi/chi/v5"
 )
 
-// @Summary Delete a reusable Agent
-// @Description Deletes only the authenticated tenant's saved configuration. Existing Session snapshots, history and recorded creation retry identities remain independent. Missing and repeated deletion locally return404; exact hosted error and in-flight creation/deletion semantics remain unverified.
-// @Tags Agents
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param agent_id path string true "Agent ID"
-// @Success 200 {object} v1.AgentDeleted
-// @Failure 400,401,404,413,500 {object} v1.ErrorResponse
-// @Router /agents/{agent_id} [delete]
 func (h *Handler) deleteAgent(w http.ResponseWriter, r *http.Request) {
 	body, ok := readJSONBody(w, r)
 	if !ok {
diff --git a/services/core/internal/api/agents_list.go b/services/core/internal/api/agents_list.go
index 3698cb1be..2a29f7b52 100644
--- a/services/core/internal/api/agents_list.go
+++ b/services/core/internal/api/agents_list.go
@@ -7,18 +7,6 @@ import (
 	"github.com/MiniMax-AI/OpenAgentCore/services/core/internal/agents"
 )
 
-// @Summary List reusable Agents
-// @Description Lists only the authenticated tenant's saved Agents, independently of Sessions. Limit 0 is treated as 1 and larger limits as 100, as observed on the hosted service. The local default is 20; exact upstream default/cap and empty cursor fields remain unverified. An unknown, malformed or foreign after cursor returns not found.
-// @Tags Agents
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param after query string false "Last Agent ID from the previous page"
-// @Param limit query int64 false "Page size; 0 is treated as 1 and values above 100 as 100" minimum(0) default(20)
-// @Param order query string false "Creation order; omit for descending, explicit empty values are invalid" Enums(asc,desc) default(desc)
-// @Success 200 {object} v1.SavedAgentList
-// @Failure 400,401,404,500 {object} v1.ErrorResponse
-// @Router /agents [get]
 func (h *Handler) listAgents(w http.ResponseWriter, r *http.Request) {
 	options, ok := readClampedPage(w, r)
 	if !ok {
diff --git a/services/core/internal/api/agents_update.go b/services/core/internal/api/agents_update.go
index 03843821c..ab7f9d268 100644
--- a/services/core/internal/api/agents_update.go
+++ b/services/core/internal/api/agents_update.go
@@ -10,18 +10,6 @@ import (
 	"github.com/go-chi/chi/v5"
 )
 
-// @Summary Update a reusable Agent
-// @Description Preserves omitted fields and replaces supplied fields using shared saved-configuration validation. Null name/instructions clear; null or empty metadata clears all pairs. Name, metadata and configuration validation errors return invalid_request_error with the official param, using the Agent create rules before the Agent lookup. Existing Session snapshots are unchanged. Empty updates advance updated_at without changing saved fields. Nested replacement/null defaults, model-derived reasoning and exact hosted error behavior remain incompletely verified.
-// @Tags Agents
-// @Accept json
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param agent_id path string true "Agent ID"
-// @Param body body v1.UpdateAgentRequest true "Supplied reusable Agent fields"
-// @Success 200 {object} v1.SavedAgent
-// @Failure 400,401,404,413,500 {object} v1.ErrorResponse
-// @Router /agents/{agent_id} [post]
 func (h *Handler) updateAgent(w http.ResponseWriter, r *http.Request) {
 	raw, ok := readJSONObject(w, r)
 	if !ok {
diff --git a/services/core/internal/api/contract_routes_test.go b/services/core/internal/api/contract_routes_test.go
index 8a2133cc4..9d4fadb95 100644
--- a/services/core/internal/api/contract_routes_test.go
+++ b/services/core/internal/api/contract_routes_test.go
@@ -31,12 +31,18 @@ func contractOperations(t *testing.T, file, prefix string) map[string]bool {
 		t.Fatal(err)
 	}
 	var document struct {
+		Servers []struct {
+			URL string `yaml:"url"`
+		} `yaml:"servers"`
 		BasePath string                    `yaml:"basePath"`
 		Paths    map[string]map[string]any `yaml:"paths"`
 	}
 	if err := yaml.Unmarshal(raw, &document); err != nil {
 		t.Fatal(file, err)
 	}
+	if document.BasePath == "" && len(document.Servers) > 0 {
+		document.BasePath = document.Servers[0].URL
+	}
 	operations := map[string]bool{}
 	for path, item := range document.Paths {
 		full := strings.TrimSuffix(document.BasePath, "/") + path
@@ -55,7 +61,7 @@ func contractOperations(t *testing.T, file, prefix string) map[string]bool {
 	return operations
 }
 
-// The contracts are generated from handler annotations, so they must publish
+// The official public contract and generated internal contracts must publish
 // exactly the routes the server registers, with the same path parameter names.
 // The pinned upstream /v1 set is checked by TestEveryRouteAuthenticatesItsCanonicalPath
 // and the contract tests.
diff --git a/services/core/internal/api/credentials.go b/services/core/internal/api/credentials.go
index c90948ab9..62d0cf985 100644
--- a/services/core/internal/api/credentials.go
+++ b/services/core/internal/api/credentials.go
@@ -10,18 +10,6 @@ import (
 	"github.com/google/uuid"
 )
 
-// @Summary Create a Vault Credential
-// @Description Stores static_bearer or mcp_oauth secrets as execution-owned authenticated ciphertext without contacting any endpoint. Static bearer and OAuth access tokens must be nonempty strings; their bytes are preserved. OAuth accepts a required access token, nullable RFC3339 expiry and optional refresh configuration with none, client_secret_basic or client_secret_post authentication. Required name is trimmed to 1–256 UTF-8 bytes. Credential and token endpoints require HTTPS without userinfo or fragments. Responses contain safe metadata only, including explicit nullable OAuth expiry, refresh, resource and scope. Missing encryption configuration returns local 503. External authorization and provider revocation remain caller responsibilities; exact hosted error/default semantics remain unverified.
-// @Tags Credentials
-// @Accept json
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param vault_id path string true "Vault ID"
-// @Param body body v1.CreateCredentialRequest true "Write-only credential authentication union"
-// @Success 201 {object} v1.Credential
-// @Failure 400,401,404,413,500,503 {object} v1.ErrorResponse
-// @Router /vaults/{vault_id}/credentials [post]
 func (h *Handler) createCredential(w http.ResponseWriter, r *http.Request) {
 	vaultID := chi.URLParam(r, "vault_id")
 	raw, ok := readJSONObject(w, r)
@@ -69,17 +57,6 @@ func (h *Handler) createCredential(w http.ResponseWriter, r *http.Request) {
 	writeJSON(w, http.StatusCreated, credentialResponse(credential))
 }
 
-// @Summary Retrieve safe Vault Credential metadata
-// @Description Reads only non-secret metadata scoped to the authenticated project and owning Vault. No token decryption, network request or execution is performed. Unknown, foreign, wrong-Vault and malformed IDs use the same local not-found response; hosted error parity remains unverified.
-// @Tags Credentials
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param vault_id path string true "Vault ID"
-// @Param credential_id path string true "Credential ID"
-// @Success 200 {object} v1.Credential
-// @Failure 400,401,404,500 {object} v1.ErrorResponse
-// @Router /vaults/{vault_id}/credentials/{credential_id} [get]
 func (h *Handler) getCredential(w http.ResponseWriter, r *http.Request) {
 	vaultID, ok := credentialResourceID(w, r, "vault_id")
 	if !ok {
diff --git a/services/core/internal/api/credentials_delete.go b/services/core/internal/api/credentials_delete.go
index 27a44210a..5345fca5a 100644
--- a/services/core/internal/api/credentials_delete.go
+++ b/services/core/internal/api/credentials_delete.go
@@ -8,17 +8,6 @@ import (
 	"github.com/MiniMax-AI/OpenAgentCore/services/core/internal/vaults"
 )
 
-// @Summary Delete a Vault Credential
-// @Description Removes one Credential and its encrypted token within the authenticated project and owning Vault, without an encryption key or secret decryption. Subsequent metadata reads, updates and dispatch lookups cannot use it. Existing Session snapshots and history retain their frozen identities; already-resolved tokens and running Sessions are not revoked or cancelled. This local policy removes the row rather than defining archived lifecycle; missing/repeated deletion returns 404. Exact hosted archive, post-delete visibility and retry/error semantics remain unverified. Provider revocation and physical erasure from native history, WAL or backups are separate concerns.
-// @Tags Credentials
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param vault_id path string true "Vault ID"
-// @Param credential_id path string true "Credential ID"
-// @Success 200 {object} v1.CredentialDeleted
-// @Failure 400,401,404,413,500 {object} v1.ErrorResponse
-// @Router /vaults/{vault_id}/credentials/{credential_id} [delete]
 func (h *Handler) deleteCredential(w http.ResponseWriter, r *http.Request) {
 	body, ok := readJSONBody(w, r)
 	if !ok {
diff --git a/services/core/internal/api/credentials_list.go b/services/core/internal/api/credentials_list.go
index 6f2f335df..7fbd75515 100644
--- a/services/core/internal/api/credentials_list.go
+++ b/services/core/internal/api/credentials_list.go
@@ -7,21 +7,6 @@ import (
 	"github.com/go-chi/chi/v5"
 )
 
-// @Summary List safe Vault Credential metadata
-// @Description Lists only metadata from the authenticated project's requested Vault, without decryption or execution. An unknown, malformed or foreign after cursor, including another Vault's Credential, returns not found. Includes active and archived Credentials by default, independently of Vault status. Status accepts a scalar, the SDK status[] array or both, filtering by their union; a repeated scalar is rejected. Limits default to 20 and clamp to 1–100. Equal creation times use ID ordering. Hosted errors, concurrent-page behavior and archive/delete lifecycle remain unverified or unimplemented.
-// @Tags Credentials
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param vault_id path string true "Vault ID"
-// @Param after query string false "Last Credential ID from the previous page"
-// @Param limit query integer false "Requested page size, clamped to 1–100" default(20)
-// @Param order query string false "Creation order; omit for descending, explicit empty values are invalid" Enums(asc,desc) default(desc)
-// @Param status query string false "Scalar status filter" Enums(active,archived)
-// @Param status[] query []string false "Array status filter; combined with status as a union" collectionFormat(multi) Enums(active,archived)
-// @Success 200 {object} v1.CredentialList
-// @Failure 400,401,404,500 {object} v1.ErrorResponse
-// @Router /vaults/{vault_id}/credentials [get]
 func (h *Handler) listCredentials(w http.ResponseWriter, r *http.Request) {
 	vaultID := chi.URLParam(r, "vault_id")
 	query, ok := readVaultPage(w, r)
diff --git a/services/core/internal/api/credentials_update.go b/services/core/internal/api/credentials_update.go
index 58323a2ab..a47108a35 100644
--- a/services/core/internal/api/credentials_update.go
+++ b/services/core/internal/api/credentials_update.go
@@ -9,19 +9,6 @@ import (
 	"github.com/go-chi/chi/v5"
 )
 
-// @Summary Replace Vault Credential authentication secrets
-// @Description Explicitly empty static bearer or OAuth access tokens and OAuth patches without a mutable field are rejected before storage. Omitted OAuth access tokens preserve the existing grant when expiry or refresh fields change. Updates the existing static_bearer or mcp_oauth authentication method without network requests. OAuth access_token omission/null retains the token; a new token clears omitted expiry, explicit null clears expiry, and other omitted fields remain unchanged. OAuth refresh patches cannot add configuration or change client, endpoint, resource or authentication method; nullable token/client-secret values retain stored secrets while explicit null scope clears scope. Whole-null refresh and token_endpoint_auth retain existing configuration under local policy. Identity, destination, creation time and Session bindings remain unchanged. Responses expose safe metadata only. Already-dispatched work is not revoked; provider revocation, storage-key rotation and exact hosted concurrent-update/error semantics remain separate.
-// @Tags Credentials
-// @Accept json
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param vault_id path string true "Vault ID"
-// @Param credential_id path string true "Credential ID"
-// @Param body body v1.UpdateCredentialRequest true "Write-only credential authentication replacement union"
-// @Success 200 {object} v1.Credential
-// @Failure 400,401,404,413,500,503 {object} v1.ErrorResponse
-// @Router /vaults/{vault_id}/credentials/{credential_id} [post]
 func (h *Handler) updateCredential(w http.ResponseWriter, r *http.Request) {
 	vaultID, id := chi.URLParam(r, "vault_id"), chi.URLParam(r, "credential_id")
 	raw, ok := readJSONObject(w, r)
diff --git a/services/core/internal/api/environment_files.go b/services/core/internal/api/environment_files.go
index afb2b0efd..d829775e0 100644
--- a/services/core/internal/api/environment_files.go
+++ b/services/core/internal/api/environment_files.go
@@ -23,20 +23,6 @@ type EnvironmentWorkspaces interface {
 	WriteEnvironmentFile(context.Context, sessions.Environment, string, []byte) (int64, error)
 }
 
-// @Summary List live Environment files
-// @Description Lists direct regular files in one authorized self_hosted or qualified local workspace directory. Local paths use the public /workspace root and must be in cleaned form. This partial implementation defaults to the workspace root and limit 20; recursive scope and these defaults are not verified upstream semantics. A missing path, a regular file or a symbolic link returns an empty page; links are never followed. Daemons without a local workspace binding use the Claude SDK adapter reader, which keeps 404 for a missing path and 503 for a regular file or symbolic link. Well-formed unknown query keys are ignored; malformed query encoding and a repeated supported key are rejected. Sorts by case-sensitive path components, descending by default. Keep the same path, order and limit when using page. Each page rereads the complete bounded directory; changed file paths/sizes invalidate continuation locally with 400. There is no snapshot guarantee. An openai_hosted Environment that has not connected yet returns 400. Truncated or uncertain native results fail with 503 without returning a partial page. This read never starts a Turn or admits model input. Actual transport disconnect/reconnect events remain observable.
-// @Tags Environments
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param environment_id path string true "Environment ID"
-// @Param path query string false "Absolute directory in cleaned form inside /workspace"
-// @Param limit query int false "Maximum file count; local default 20" minimum(1) maximum(100)
-// @Param order query string false "Case-sensitive path-component order; omit for descending, explicit empty values are invalid" Enums(asc,desc) default(desc)
-// @Param page query string false "Opaque continuation token; keep path, order and limit unchanged"
-// @Success 200 {object} v1.EnvironmentFileList
-// @Failure 400,401,404,500,503 {object} v1.ErrorResponse
-// @Router /agents/environments/{environment_id}/files [get]
 func (h *Handler) listEnvironmentFiles(w http.ResponseWriter, r *http.Request) {
 	environment, err := h.EnvironmentsReader.GetEnvironment(r.Context(), tenantID(r), chi.URLParam(r, "environment_id"))
 	if err != nil {
diff --git a/services/core/internal/api/environment_files_create.go b/services/core/internal/api/environment_files_create.go
index 956af680f..0cec14045 100644
--- a/services/core/internal/api/environment_files_create.go
+++ b/services/core/internal/api/environment_files_create.go
@@ -22,18 +22,6 @@ import (
 	"github.com/go-chi/chi/v5"
 )
 
-// @Summary Create an Environment file from inline bytes or a source file
-// @Description Uploads standard Base64 bytes to a file beneath /workspace in a qualified local Environment and returns 201. Accepts inline bytes or a project-owned source file_id through the same write path. Unknown body fields are rejected with their name as param. Basic public hosted creation requires explicit managed Runtime configuration; an openai_hosted Environment that has not connected yet returns 400. Inline data is limited to 5 MiB decoded and a file_id copy to 50 MiB. Missing parent directories are created with mode 0700 and the file with mode 0600. An existing destination is never replaced; a directory, an existing file or a path through a symlink or non-directory returns 400. Idle writes exclude execution. Missing receipts return unavailable and retain a durable mutation gate without automatic replay. Error/timing parity with upstream remains unverified.
-// @Tags Environments
-// @Accept json
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param environment_id path string true "Environment ID"
-// @Param request body v1.EnvironmentFileCreateRequest true "Inline bytes or source file ID and absolute workspace path"
-// @Success 201 {object} v1.EnvironmentFile
-// @Failure 400,401,404,409,413,500,503 {object} v1.ErrorResponse
-// @Router /agents/environments/{environment_id}/files [post]
 func (h *Handler) createEnvironmentFile(w http.ResponseWriter, r *http.Request) {
 	const maxJSON = int64(((proto.WorkspaceWriteMaxBytes+2)/3)*4 + (16 << 10))
 	raw, ok := readJSONObjectLimit(w, r, maxJSON, "Inline upload exceeds this service's bounded file limit.")
diff --git a/services/core/internal/api/environment_templates.go b/services/core/internal/api/environment_templates.go
index 7c97f5d1c..5104f895f 100644
--- a/services/core/internal/api/environment_templates.go
+++ b/services/core/internal/api/environment_templates.go
@@ -90,17 +90,6 @@ func readTemplateInput(w http.ResponseWriter, r *http.Request) (environmenttempl
 	return in, true
 }
 
-// @Summary Create an Environment Template
-// @Description Saves tenant-owned hosted configuration. Supports nullable name, enabled/disabled or exact-domain restricted network, initial inline/file_id files, confidential env, ordered setup_commands, npm/Python packages inline/referenced Skill ZIPs, Plugin ZIPs and workspace-contained capability directories. Omitted/null network defaults to enabled. Restricted network requires 1–100 exact ASCII hostnames; other host forms and populated unsupported installations are rejected before persistence without echoing input. Network policy rejections return invalid_request_error with a null param. System dependencies must be preinstalled in the sandbox image or template, or on the host machine; packages.system is rejected. No compute is allocated. Exact hosted error/retry semantics remain unverified.
-// @Tags Environment Templates
-// @Accept json
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param body body v1.EnvironmentTemplateRequest true "Reusable configuration"
-// @Success 201 {object} v1.EnvironmentTemplate
-// @Failure 400,401,413,500 {object} v1.ErrorResponse
-// @Router /agents/environments/templates [post]
 func (h *Handler) createEnvironmentTemplate(w http.ResponseWriter, r *http.Request) {
 	in, ok := readTemplateInput(w, r)
 	if !ok {
@@ -114,16 +103,6 @@ func (h *Handler) createEnvironmentTemplate(w http.ResponseWriter, r *http.Reque
 	writeJSON(w, http.StatusCreated, templateResponse(value))
 }
 
-// @Summary Retrieve an Environment Template
-// @Description Returns safe tenant-owned configuration metadata without allocating compute. Missing and foreign resources return the same not-found response.
-// @Tags Environment Templates
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param environment_template_id path string true "Template ID"
-// @Success 200 {object} v1.EnvironmentTemplate
-// @Failure 400,401,404,500 {object} v1.ErrorResponse
-// @Router /agents/environments/templates/{environment_template_id} [get]
 func (h *Handler) getEnvironmentTemplate(w http.ResponseWriter, r *http.Request) {
 	value, err := h.EnvironmentTemplatesReader.Get(r.Context(), tenantID(r), chi.URLParam(r, "environment_template_id"))
 	if err != nil {
@@ -133,18 +112,6 @@ func (h *Handler) getEnvironmentTemplate(w http.ResponseWriter, r *http.Request)
 	writeJSON(w, http.StatusOK, templateResponse(value))
 }
 
-// @Summary Update an Environment Template
-// @Description Supplied fields replace atomically; omitted fields remain unchanged. Null name clears and null network resets to the pinned enabled default. Existing Session snapshots and creation retries remain unchanged. Initial files replace as a list; null/empty clears. File data is encrypted separately and excluded from response metadata. Skills replace as a list; null/empty clears. Skill archives are encrypted separately and omitted from responses. Plugins and capability directories replace as lists; null/empty clears. Plugin archives are encrypted and omitted from responses. Capability directories are snapshotted after setup. Environment MCP execution requires a qualified native transport and runtime network policy. Empty updates advance updated_at without changing saved fields or confidential contents. Network policy rejections return invalid_request_error with a null param.
-// @Tags Environment Templates
-// @Accept json
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param environment_template_id path string true "Template ID"
-// @Param body body v1.EnvironmentTemplateRequest true "Configuration replacements"
-// @Success 200 {object} v1.EnvironmentTemplate
-// @Failure 400,401,404,413,500 {object} v1.ErrorResponse
-// @Router /agents/environments/templates/{environment_template_id} [post]
 func (h *Handler) updateEnvironmentTemplate(w http.ResponseWriter, r *http.Request) {
 	in, ok := readTemplateInput(w, r)
 	if !ok {
@@ -158,16 +125,6 @@ func (h *Handler) updateEnvironmentTemplate(w http.ResponseWriter, r *http.Reque
 	writeJSON(w, http.StatusOK, templateResponse(value))
 }
 
-// @Summary Delete an Environment Template
-// @Description Deletes the tenant-owned reusable configuration without changing or deleting existing Sessions and their frozen configuration.
-// @Tags Environment Templates
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param environment_template_id path string true "Template ID"
-// @Success 200 {object} v1.EnvironmentTemplateDeleted
-// @Failure 400,401,404,500 {object} v1.ErrorResponse
-// @Router /agents/environments/templates/{environment_template_id} [delete]
 func (h *Handler) deleteEnvironmentTemplate(w http.ResponseWriter, r *http.Request) {
 	id, err := h.EnvironmentTemplates.Delete(r.Context(), environmenttemplates.DeleteCommand{TenantID: tenantID(r), TemplateID: chi.URLParam(r, "environment_template_id")})
 	if err != nil {
@@ -177,18 +134,6 @@ func (h *Handler) deleteEnvironmentTemplate(w http.ResponseWriter, r *http.Reque
 	writeJSON(w, http.StatusOK, v1.EnvironmentTemplateDeleted{ID: id, Object: "agent.environment.template.deleted", Deleted: true})
 }
 
-// @Summary List Environment Templates
-// @Description Lists tenant-owned safe template metadata in creation order with ID tie-breaking. Defaults to limit 20 and descending order; limit 0 is treated as 1 and larger limits as 100. Foreign, missing and malformed cursors return the same not found error. Concurrent-page and exact hosted error behavior remain unverified.
-// @Tags Environment Templates
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param after query string false "Previous Template ID"
-// @Param limit query integer false "Page size; 0 is treated as 1 and values above 100 as 100" default(20) minimum(0)
-// @Param order query string false "Creation order; omit for descending, explicit empty values are invalid" Enums(asc,desc) default(desc)
-// @Success 200 {object} v1.EnvironmentTemplateList
-// @Failure 400,401,404,500 {object} v1.ErrorResponse
-// @Router /agents/environments/templates [get]
 func (h *Handler) listEnvironmentTemplates(w http.ResponseWriter, r *http.Request) {
 	options, ok := readClampedPage(w, r)
 	if !ok {
diff --git a/services/core/internal/api/environments.go b/services/core/internal/api/environments.go
index 0224efa06..9c75d471a 100644
--- a/services/core/internal/api/environments.go
+++ b/services/core/internal/api/environments.go
@@ -31,16 +31,6 @@ type Environments interface {
 	RevokeProjectExecutorCredential(context.Context, identity.Principal, string, string) error
 }
 
-// @Summary Retrieve an execution Environment
-// @Description Returns durable connection status and safe installed metadata for supported self_hosted and basic openai_hosted profiles. Initial files expose frozen safe metadata without content; Plugin/Skill entries expose only safe configured installation metadata. Capability-directory discoveries are not added to those arrays. Unsupported installation configurations remain implementation gaps. This read does not prepare execution, start compute or require an enabled execution worker. Session deletion removes the associated Environment from public reads; project-shared read authorization is unchanged. Connection status does not prove native readiness or process quiescence.
-// @Tags Environments
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param environment_id path string true "Environment ID"
-// @Success 200 {object} v1.EnvironmentInfo
-// @Failure 400,401,404,500 {object} v1.ErrorResponse
-// @Router /agents/environments/{environment_id} [get]
 func (h *Handler) getEnvironment(w http.ResponseWriter, r *http.Request) {
 	environment, err := h.EnvironmentsReader.GetEnvironment(r.Context(), tenantID(r), chi.URLParam(r, "environment_id"))
 	if err != nil {
diff --git a/services/core/internal/api/handler.go b/services/core/internal/api/handler.go
index af771c4f1..2e358785e 100644
--- a/services/core/internal/api/handler.go
+++ b/services/core/internal/api/handler.go
@@ -124,18 +124,6 @@ func (h *Handler) routes() *chi.Mux {
 }
 
 // createSession atomically reserves or admits initial text with the Session.
-// @Summary Create an execution Session
-// @Description The optional Core model_provider bundle resolves from the Session override, saved Agent defaults, then the deployment default of the resolved harness, for every environment type. A Session that resolves no bundle returns 400 model_provider_required with param x_agents_core.model_provider before any write. Core encrypts and freezes the resolved bundle; later Agent or deployment default edits and same-key retries cannot change it. Keys are never returned. Supports inline configuration or a tenant-owned saved agent_id with per-Session field replacements. Execution supports model/instructions, text verbosity, non-deferred function tools, adapter-qualified multi_agent with persisted Subagent reads, implicit reasoning, service tier auto and environment type none, subject to the configured engine. Codex additionally supports HTTP MCP with service origin (omitted or null on HTTP transport is saved as service), native allowed_tools and boolean required defaulting to false. Session vault_ids attach only project-owned Vaults; credential_id selects an attached static bearer or OAuth credential for the exact HTTPS URL, while null/omission selects a unique match or remains anonymous. Session reads, lists and event snapshots show that implicitly selected credential ID in a null or omitted credential_id, also after the credential is deleted; anonymous selections stay null and the stored caller intent is unchanged. After the input requirement and before any write, a credential_id without vault_ids, one outside the attached Vaults (one message for missing, foreign and unattached IDs) or one for another server_url returns 400 invalid_request_error, and several implicit matches return 409 conflict_error. Missing decryption configuration fails dispatch without anonymous fallback. Required initialization uses native startup before the first native Turn, including cold resume, and requires a separately advertised capability; exact hosted creation timing and error parity remain unverified. Explicit environment-origin HTTP MCP is supported on managed and self-hosted workspaces through the same Runtime bindings; native OAuth login remains unsupported. The self_hosted profile uses a qualified native harness, a clean absolute workspace_directory and optional absolute local capability_directories prepared by Runtime, with optional non-deferred function tools and HTTP MCP using explicit environment origin, optionally authenticated by the attached Vault rules. Service-origin HTTP remains restricted to service-side environment:none. Remote MCP and remote Bearer authentication each require separately advertised combination support; old peers cannot receive unsupported work. Omitted/null capability_directories use the empty-list default; self_hosted requires configured execution plus executor registry. Claude SDK currently requires medium verbosity and object-root function schemas. It supports anonymous or attached static-bearer service-origin HTTP MCP on none with boolean required and separately advertised MCP/bearer/required runtime support. Required servers must be connected before the first native input is released; pending or failed startup rejects execution. The shared Vault selection and immutable binding rules apply; unsupported native labels/tool names reject before persistence. An attached Vault with no matching credential may remain anonymous; missing keys or failed credential lookup/decryption never fall back to anonymous execution. Omitted stream defaults to false; stream and agent_id cannot be null. Metadata may be null; non-string values and limit violations return invalid_request_error with a metadata or metadata.<key> param. The inline agent uses the Agent create configuration validation with agent.-prefixed params, reported before the input requirement and saved-Agent lookup; saved configurations with conflicting tools or schema roots reject admission with the same errors, and execution limits keep unsupported_or_invalid_configuration. Hosted network policy rejections return invalid_request_error with a null param. Initial input accepts a string or ordered user-message array. Codex and Claude SDK on none and qualified managed or self_hosted workspace profiles also accept inline PNG/JPEG image content; other image combinations and remote URLs are unsupported. None initial input atomically starts a Turn; self_hosted initial input is reserved while returning its Environment connection target, with execution deferred to native readiness and Session failure on initial timeout. Initial input is required for none and for streamed creation outside self_hosted. Omitted/null input remains valid for non-streaming hosted and self_hosted creation. With stream=true, returns live Session events starting with the committed creation snapshot and closes right after the first agent.session.idle recorded when a Turn ends or an input reservation stops being pending, or any agent.session.failed, without sending later events. A creation that admitted nothing closes after the snapshot; a settlement that records no event closes after events up to the cursor read with a settled Session projection. Required actions keep it open; disconnect does not cancel execution. The GET events stream remains live-only. New Sessions retain their authenticated creator; all creation retries require the same typed subject, including across key rotation. Every creation records caller intent before saved Agents, templates, Vault credentials or deployment defaults resolve, so a same-intent retry returns the committed Session independently of later changes to those resources. Provider keys enter retry hashes only as fingerprints keyed by the credential key. Unknown historical creators reject retries. These conflict policies are local and not verified hosted parity. A same-key stream=true retry of an existing creation returns 201 with no events and closes at once; retry with stream=false or use the GET events stream to recover. Claude SDK on none, Core-managed Docker openai_hosted and self_hosted supports qualified object-root json_schema output with medium verbosity, single-Agent execution and ordinary functions. Hosted execution reuses native workspace tools and Files/Artifacts; Skills, Plugins, capability directories, HTTP MCP, Subagent and tool_search combinations remain unqualified, including inherited template contents. Other non-text initial input remains unsupported. The Claude workspace profile supports non-deferred function tools with text or successful inline PNG/JPEG results alongside native workspace tools; explicit environment-origin HTTP MCP uses the common Runtime path. MiniMax accepts public environment-origin HTTP MCP only with null or omitted allowed_tools and required=false; even an empty non-null allowlist rejects. Idle Sessions provision automatically; initial provisioning has no caller connection action. Network defaults to enabled; disabled and restricted policies reject before compute allocation because the current Runtime cannot enforce them. The x_agents_core.environment extension accepts common preparation fields for either hosted or self-hosted placement: environment_template_id, files, env, packages, setup_commands, skills, plugins and capability_directories. Duplicate fields in environment and the extension reject. Confidential env, npm/Python packages and ordered setup commands use the same Environment-owned initialization lifecycle; compute allocation does not own preparation. Unknown side effects are not replayed after disconnect or restart. System dependencies must be preinstalled in the sandbox image or template, or on the host machine; packages.system is rejected. Initial inline and tenant-owned file_id files freeze encrypted bytes before provisioning, then install through the common Core lifecycle before native execution or live Files access. With a template reference, omitted/null files, env, packages and setup_commands inherit. Non-null files and command lists replace; env overlays by key; each package manager inherits on omission/null and otherwise replaces its list. Empty lists clear their selected field. Tenant-owned environment_template_id references inherit omitted/null network and allow only narrowing overrides. Inline hosted network:null retains the enabled default; updating a Template with network:null resets its saved policy to enabled. Core freezes effective configuration; template updates/deletion do not alter Session snapshots or same-intent creation retries. Inline or tenant-owned skill_reference Skills share initialization. Templates preserve default/latest/explicit selectors; Session creation freezes concrete metadata and encrypted content atomically. Skill, Plugin and capability-directory list omission/null inherit; a non-null list replaces, including empty-list clearing. Omitted/null Skill version selectors resolve the default version. Source deletion/default updates cannot change committed Session Skill contents. Deferred function discovery uses type-only tool_search and per-function defer_loading in the qualified single-agent Claude function profile on none or a managed/user-owned workspace, including qualified inline image messages and text results. Explicit web_search mode disabled and programmatic_tool_calling enabled false use frozen common Runtime controls. Enabled forms, including those saved on an Agent, remain unqualified and reject before any write unless the Session replaces tools. Omitted programmatic configuration preserves native behavior, a documented difference from the official default-on behavior. Other combinations remain unqualified; see the operation coverage.
-// @Tags Sessions
-// @Accept json
-// @Produce json,text/event-stream
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param Idempotency-Key header string false "Creation retry key, up to 128 bytes"
-// @Param body body v1.CreateSessionRequest true "Session configuration"
-// @Success 201 {object} v1.Session
-// @Failure 400,401,404,409,413,500,503 {object} v1.ErrorResponse
-// @Router /agents/sessions [post]
 func (h *Handler) createSession(w http.ResponseWriter, r *http.Request) {
 	raw, ok := readJSONObjectLimit(w, r, 16*1024*1024, "Request exceeds 16 MiB.")
 	if !ok {
@@ -292,16 +280,6 @@ func (h *Handler) createSession(w http.ResponseWriter, r *http.Request) {
 	h.respondSessionStatus(w, r, result.Session, http.StatusCreated)
 }
 
-// @Summary Retrieve an execution Session
-// @Description Returns supported none, self_hosted and basic openai_hosted Session environments. Self-hosted pending input can require a caller connection before a Turn exists. Hosted initial provisioning remains idle until a Turn starts; connection observations are not native execution readiness.
-// @Tags Sessions
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param session_id path string true "Session ID"
-// @Success 200 {object} v1.Session
-// @Failure 400,401,404,500,503 {object} v1.ErrorResponse
-// @Router /agents/sessions/{session_id} [get]
 func (h *Handler) getSession(w http.ResponseWriter, r *http.Request) {
 	session, err := h.SessionsReader.GetSession(r.Context(), tenantID(r), chi.URLParam(r, "session_id"))
 	if err != nil {
@@ -328,19 +306,6 @@ func (h *Handler) respondSessionStatus(w http.ResponseWriter, r *http.Request, s
 	writeJSON(w, status, response)
 }
 
-// @Summary List execution Sessions
-// @Description Cursor and results are scoped to the authenticated execution tenant; an unknown, malformed or foreign after cursor returns not found. Optional agent_id matches the immutable root Agent ID, including inline Agents and historical Sessions whose saved source was updated or deleted. Omission lists all Agents. Returns the same Environment and pending-input activity projection as Session retrieval, including self_hosted Sessions.
-// @Tags Sessions
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param agent_id query string false "Root Agent ID whose Sessions to return"
-// @Param after query string false "Last Session ID from the previous page"
-// @Param limit query int false "Page size; 0 is treated as 1 and values above 100 as 100" minimum(0) default(20)
-// @Param order query string false "Creation order; omit for descending, explicit empty values are invalid" Enums(asc,desc) default(desc)
-// @Success 200 {object} v1.SessionList
-// @Failure 400,401,404,500 {object} v1.ErrorResponse
-// @Router /agents/sessions [get]
 func (h *Handler) listSessions(w http.ResponseWriter, r *http.Request) {
 	options, ok := readClampedPage(w, r, "agent_id")
 	if !ok {
diff --git a/services/core/internal/api/inputs.go b/services/core/internal/api/inputs.go
index f63e87dcc..84a7a0adf 100644
--- a/services/core/internal/api/inputs.go
+++ b/services/core/internal/api/inputs.go
@@ -19,18 +19,6 @@ type InputAdmission interface {
 	SubmitInputs(context.Context, string, string, string, []sessions.Input) ([]sessions.InputReceipt, error)
 }
 
-// @Summary Submit Session input events
-// @Description An empty events array is a resource-authorized no-op; it creates no execution retry identity, Turn, Item or input receipt. For environment none, atomically accepts text messages, cancellation and function results. Messages steer active work or start a queued Turn. Qualified Codex and Claude SDK workspace profiles accept text and inline PNG/JPEG messages, independently of managed or self_hosted ownership. Under the Session lock, matching retries retain their original target; new active messages append to the current Turn, while idle messages reserve work and wait up to the original five-minute connection/admission deadline. Return 202 only after durable admission, without claiming native application; active messages create no Turn or reservation. Cancellation-only prepared-environment batches use existing durable cancellation admission and return 202 without waiting for native exit; a new cancellation conflicts while a pre-Turn reservation is pending. Homogeneous tool_result-only prepared-environment batches reuse existing scoped result admission and application receipts without creating a Turn or bypassing a pending reservation. Mixed prepared-environment batches remain unsupported. HTTP expiry/cancellation use local 409 environment_input_expired/environment_input_cancelled errors. New input on a Session whose hosted Environment failed to provision returns the observed 409 conflict_error "the hosted environment failed to provision"; input already waiting when it fails and expired Environments keep the local 409 environment_unavailable. Input the Session cannot accept in its current state, such as a result after cancellation or a batch while earlier input is pending, and a result that differs from the call's saved result return 409 with type and code conflict_error; reusing an Idempotency-Key with a different batch returns the local 409 idempotency_conflict. Inside an owned Session, a result for an unknown call or for a call of another Turn returns 400 invalid_request_error and changes nothing; missing and foreign Sessions return 404. Losing execution ownership returns 503. The response write deadline accommodates the admission window for either prepared Environment, independently of new-hosted-admission and executor URL settings. Disconnecting the waiting HTTP request does not cancel retained work or restart its deadline. Retry keys identify the whole ordered batch. Function output accepts text or ordered text/image parts subject to engine support; Claude SDK accepts text results and, on none and qualified workspace profiles, successful inline PNG/JPEG results, preserving ordered content; error images and remote references reject before admission. Native image resizing may change bytes. Runtime image-result support is checked only for image-bearing delivery. Codex and Claude SDK on none and qualified managed or self_hosted workspace profiles accept ordered inline PNG/JPEG image messages. Other engines remain text-only; remote image URLs are unsupported. Image references are retained unchanged without service-side downloads.
-// @Tags Sessions
-// @Accept json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param Idempotency-Key header string false "Retry key, up to 128 bytes"
-// @Param session_id path string true "Session ID"
-// @Param body body v1.CreateEventsRequest true "Ordered input events"
-// @Success 202
-// @Failure 400,401,404,409,413,500,503 {object} v1.ErrorResponse
-// @Router /agents/sessions/{session_id}/events [post]
 func (h *Handler) createEvents(w http.ResponseWriter, r *http.Request) {
 	raw, ok := readJSONObject(w, r)
 	if !ok {
diff --git a/services/core/internal/api/installation.go b/services/core/internal/api/installation.go
index 081a3d7ee..229da8835 100644
--- a/services/core/internal/api/installation.go
+++ b/services/core/internal/api/installation.go
@@ -1,15 +1,8 @@
 package api
 
 import (
-	"bytes"
 	"context"
-	"encoding/json"
-	"errors"
-	"io"
 	"net/http"
-	"path/filepath"
-	"regexp"
-	"slices"
 	"time"
 
 	"github.com/MiniMax-AI/OpenAgentCore/services/core/internal/deployment"
@@ -62,46 +55,6 @@ type InstallationSetting struct {
 	Restarts []string `json:"restarts"`
 }
 
-var installationSettingKey = regexp.MustCompile(`^[a-z][a-z0-9_]*(\.[a-z][a-z0-9_]*)*$`)
-
-const maxInstallationSettings = 64 << 10
-
-// ParseInstallationConfiguration validates the installer's settings snapshot.
-// A sensitive setting that carries a value is rejected, so the snapshot cannot
-// leak a secret through this read.
-func ParseInstallationConfiguration(raw []byte) (*InstallationConfiguration, error) {
-	invalid := errors.New("installation configuration is invalid")
-	if len(raw) > maxInstallationSettings {
-		return nil, invalid
-	}
-	var value InstallationConfiguration
-	decoder := json.NewDecoder(bytes.NewReader(raw))
-	decoder.DisallowUnknownFields()
-	if decoder.Decode(&value) != nil || decoder.Decode(new(any)) != io.EOF {
-		return nil, invalid
-	}
-	if value.Path != "" && !filepath.IsAbs(value.Path) || len(value.ApplyCommand) > 4096 || value.Settings == nil {
-		return nil, invalid
-	}
-	if value.Path != "" && (value.ApplyCommand == "" || value.AppliedAt == nil || value.AppliedAt.IsZero()) {
-		return nil, invalid
-	}
-	seen := make(map[string]bool, len(value.Settings))
-	for _, setting := range value.Settings {
-		if !installationSettingKey.MatchString(setting.Key) || seen[setting.Key] || setting.Restarts == nil ||
-			setting.Sensitive != (setting.Configured != nil) || (setting.Sensitive && (setting.Value != nil || setting.Default != nil)) {
-			return nil, invalid
-		}
-		for _, service := range setting.Restarts {
-			if !slices.Contains([]string{"core", "web", "database"}, service) {
-				return nil, invalid
-			}
-		}
-		seen[setting.Key] = true
-	}
-	return &value, nil
-}
-
 // InstallationBindings counts what is bound to the current public URL.
 type InstallationBindings interface {
 	AddressBindings(context.Context) (deployment.AddressBindings, error)
diff --git a/services/core/internal/api/installation_test.go b/services/core/internal/api/installation_test.go
index 94cd2bf7c..721703bf8 100644
--- a/services/core/internal/api/installation_test.go
+++ b/services/core/internal/api/installation_test.go
@@ -19,12 +19,7 @@ func TestInstallationReadNeedsOnlyTheCoreKey(t *testing.T) {
 	fakes.projectsReader.resolveAPIKey = projectKeys(t, callerBinding()).ResolveAPIKey
 	deps.CoreKeys = coreKeys(t, "administrator")
 	public, id := "https://core.example", "5b7c0f3e-0000-4000-8000-000000000001"
-	settings, err := ParseInstallationConfiguration([]byte(`{"path":"/home/alice/.oac/core/config.json","apply_command":"/home/alice/.oac/core/oac apply",
-		"applied_at":"2026-09-25T09:30:00Z","settings":[{"key":"ports.core","value":8091,"default":8091,"changeable":true,"sensitive":false,"restarts":["core"]},
-		{"key":"core.runtime_history.headers","value":null,"default":null,"configured":true,"changeable":true,"sensitive":true,"restarts":["core"]}]}`))
-	if err != nil {
-		t.Fatal(err)
-	}
+	settings := &InstallationConfiguration{Path: "/home/alice/.oac/core/config.json", Settings: []InstallationSetting{{Key: "ports.core", Value: 8091, Default: 8091, Changeable: true, Restarts: []string{"core"}}}}
 	fakes.installationBindings.addressBindings = func(context.Context) (deployment.AddressBindings, error) {
 		return deployment.AddressBindings{Nodes: 2, NodesOnOtherAddress: 1}, nil
 	}
@@ -50,19 +45,6 @@ func TestInstallationReadNeedsOnlyTheCoreKey(t *testing.T) {
 	}
 }
 
-func TestInstallationSnapshotCannotCarryASensitiveValue(t *testing.T) {
-	for _, setting := range []string{
-		`{"key":"core.runtime_history.headers","value":{"authorization":"secret"},"default":null,"configured":true,"changeable":true,"sensitive":true,"restarts":["core"]}`,
-		`{"key":"core.runtime_history.headers","value":null,"default":null,"changeable":true,"sensitive":true,"restarts":["core"]}`,
-		`{"key":"ports.core","value":8091,"default":8091,"changeable":true,"sensitive":false,"restarts":["core"],"unknown":true}`,
-	} {
-		raw := `{"path":"/c/config.json","apply_command":"/c/oac apply","applied_at":"2026-09-25T09:30:00Z","settings":[` + setting + `]}`
-		if _, err := ParseInstallationConfiguration([]byte(raw)); err == nil || strings.Contains(err.Error(), "secret") {
-			t.Fatal("accepted", setting, err)
-		}
-	}
-}
-
 func TestDeploymentAddressIsNotInput(t *testing.T) {
 	deps, fakes := sandboxFakes(t)
 	initializations := 0
diff --git a/services/core/internal/api/items.go b/services/core/internal/api/items.go
index cc2ddf834..82dc61e59 100644
--- a/services/core/internal/api/items.go
+++ b/services/core/internal/api/items.go
@@ -14,19 +14,6 @@ type Items interface {
 	ListItems(context.Context, string, string, string, int, bool) (sessions.ItemPage, error)
 }
 
-// @Summary List persisted execution Items
-// @Description Returns supported message and tool Items in first-observation order. Native engine fields are projected explicitly; unfinished Items on terminal Turns are incomplete. Cursors are Items of the same tenant and Session. Any other after value, including a malformed one, returns 400 invalid_request_error with the message "Invalid session item ID in `after`".
-// @Tags Items
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param session_id path string true "Session ID"
-// @Param after query string false "Last Item ID from the previous page"
-// @Param limit query int false "Page size; 0 is treated as 1 and values above 100 as 100" minimum(0) default(20)
-// @Param order query string false "Creation order; omit for descending, explicit empty values are invalid" Enums(asc,desc) default(desc)
-// @Success 200 {object} v1.ItemList
-// @Failure 400,401,404,500 {object} v1.ErrorResponse
-// @Router /agents/sessions/{session_id}/items [get]
 func (h *Handler) listItems(w http.ResponseWriter, r *http.Request) {
 	options, ok := readClampedPage(w, r)
 	if !ok {
diff --git a/services/core/internal/api/saved_configuration.go b/services/core/internal/api/saved_configuration.go
index a73036000..37463d1bc 100644
--- a/services/core/internal/api/saved_configuration.go
+++ b/services/core/internal/api/saved_configuration.go
@@ -63,7 +63,7 @@ func resolveSavedFields(input v1.CreateAgentRequest) (agents.CreateCommand, erro
 	}
 	// Model-derived effort resolution is a recorded gap. Do not manufacture a
 	// default from the operator's execution engine or another model's catalog.
-	cfg.Text, err = resolveSavedText(input.Text)
+	cfg.Text, err = resolveText(input.Text)
 	if err != nil {
 		return agents.CreateCommand{}, err
 	}
@@ -103,21 +103,21 @@ func resolveSavedMultiAgent(raw json.RawMessage) (v1.MultiAgentConfig, error) {
 	return result, nil
 }
 
-func resolveSavedText(input *v1.SavedAgentTextInput) (v1.SavedAgentText, error) {
-	result := v1.SavedAgentText{Format: v1.SavedAgentTextFormat{Type: "text"}, Verbosity: "medium"}
+func resolveText(input *v1.TextConfigInput) (v1.TextConfig, error) {
+	result := v1.TextConfig{Format: v1.TextFormat{Type: "text"}, Verbosity: "medium"}
 	if input == nil {
 		return result, nil
 	}
-	// Reuse the Session verbosity policy without its narrower format admission.
-	text, err := resolveText(&v1.TextConfigInput{Verbosity: input.Verbosity})
-	if err != nil {
-		return result, err
+	if input.Verbosity != nil {
+		if err := validateTextVerbosity(*input.Verbosity); err != nil {
+			return result, err
+		}
+		result.Verbosity = *input.Verbosity
 	}
-	result.Verbosity = text.Verbosity
 	if len(input.Format) == 0 || bytes.Equal(bytes.TrimSpace(input.Format), []byte("null")) {
 		return result, nil
 	}
-	result.Format = v1.SavedAgentTextFormat{}
+	result.Format = v1.TextFormat{}
 	if decodeInputObject(input.Format, &result.Format, "type", "schema") != nil {
 		return result, errors.New("text.format must be a supported format object.")
 	}
@@ -136,3 +136,10 @@ func resolveSavedText(input *v1.SavedAgentTextInput) (v1.SavedAgentText, error)
 	}
 	return result, nil
 }
+
+func validateTextVerbosity(value string) error {
+	if !slices.Contains([]string{"low", "medium", "high"}, value) {
+		return errors.New("text.verbosity must be low, medium or high.")
+	}
+	return nil
+}
diff --git a/services/core/internal/api/session_agent.go b/services/core/internal/api/session_agent.go
index eb7b2ce24..bd95dfa65 100644
--- a/services/core/internal/api/session_agent.go
+++ b/services/core/internal/api/session_agent.go
@@ -84,11 +84,9 @@ func admitSessionAgent(cfg v1.SavedAgentConfiguration) (v1.Agent, error) {
 	if cfg.ServiceTier != "auto" {
 		return v1.Agent{}, errors.New("Execution currently supports service_tier=auto only.")
 	}
-	text, err := resolveText(&v1.TextConfigInput{Verbosity: &cfg.Text.Verbosity})
-	if err != nil {
+	if err := validateTextVerbosity(cfg.Text.Verbosity); err != nil {
 		return v1.Agent{}, err
 	}
-	text.Format = v1.TextFormat{Type: cfg.Text.Format.Type, Schema: cfg.Text.Format.Schema}
 	tools, err := resolveSessionTools(cfg.Tools)
 	if err != nil {
 		return v1.Agent{}, err
@@ -99,5 +97,5 @@ func admitSessionAgent(cfg v1.SavedAgentConfiguration) (v1.Agent, error) {
 	}
 	return v1.Agent{XAgentsCore: extension, Model: cfg.Model, Name: cfg.Name, Instructions: cfg.Instructions,
 		MultiAgent: cfg.MultiAgent, Reasoning: cfg.Reasoning, ServiceTier: cfg.ServiceTier,
-		Text: text, Tools: tools}, nil
+		Text: cfg.Text, Tools: tools}, nil
 }
diff --git a/services/core/internal/api/session_artifacts.go b/services/core/internal/api/session_artifacts.go
index 70ee53e9c..79275ca82 100644
--- a/services/core/internal/api/session_artifacts.go
+++ b/services/core/internal/api/session_artifacts.go
@@ -23,20 +23,6 @@ type ArtifactsReader interface {
 	ReadSessionArtifact(context.Context, string, string, string, func(sessions.Artifact, io.Reader) error) error
 }
 
-// @Summary List immutable Session artifacts
-// @Description Lists published outputs independently of Environment availability. Sorting uses publication time and ID. A later Turn publishes a path again only when it is new, its bytes changed, or no Artifact remains for it. A malformed environment_id matches nothing. An after value that is not an Artifact of this Session, including a malformed one, returns 400 invalid_request_error with the message "after is not a valid artifact ID". The local default page size is 20; exact upstream defaults remain unverified.
-// @Tags Artifacts
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param session_id path string true "Session ID"
-// @Param environment_id query string false "Producing Environment ID; an unknown or malformed ID returns an empty page"
-// @Param after query string false "Last immutable artifact ID"
-// @Param limit query int false "Page size" minimum(1) maximum(100) default(20)
-// @Param order query string false "Publication order; omit for descending, explicit empty values are invalid" Enums(asc,desc) default(desc)
-// @Success 200 {object} v1.SessionArtifactList
-// @Failure 400,401,404,500,503 {object} v1.ErrorResponse
-// @Router /agents/sessions/{session_id}/artifacts [get]
 func (h *Handler) listSessionArtifacts(w http.ResponseWriter, r *http.Request) {
 	options, ok := readPage(w, r, "environment_id")
 	if !ok {
@@ -55,16 +41,6 @@ func (h *Handler) listSessionArtifacts(w http.ResponseWriter, r *http.Request) {
 	writeJSON(w, http.StatusOK, v1.SessionArtifactList{Object: "list", Data: data, HasMore: page.NextCursor != "", FirstID: first, LastID: last})
 }
 
-// @Summary Retrieve immutable artifact metadata
-// @Tags Artifacts
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param session_id path string true "Session ID"
-// @Param artifact_id path string true "Artifact ID"
-// @Success 200 {object} v1.SessionArtifact
-// @Failure 400,401,404,500,503 {object} v1.ErrorResponse
-// @Router /agents/sessions/{session_id}/artifacts/{artifact_id} [get]
 func (h *Handler) getSessionArtifact(w http.ResponseWriter, r *http.Request) {
 	artifact, err := h.ArtifactsReader.GetSessionArtifact(r.Context(), tenantID(r), chi.URLParam(r, "session_id"), chi.URLParam(r, "artifact_id"))
 	if err != nil {
@@ -74,17 +50,6 @@ func (h *Handler) getSessionArtifact(w http.ResponseWriter, r *http.Request) {
 	writeJSON(w, http.StatusOK, artifactResponse(artifact))
 }
 
-// @Summary Delete a published artifact
-// @Description Deletes the published copy without modifying its original workspace file. Already admitted content reads may finish; later reads reject.
-// @Tags Artifacts
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param session_id path string true "Session ID"
-// @Param artifact_id path string true "Artifact ID"
-// @Success 200 {object} v1.SessionArtifactDeleted
-// @Failure 400,401,404,500,503 {object} v1.ErrorResponse
-// @Router /agents/sessions/{session_id}/artifacts/{artifact_id} [delete]
 func (h *Handler) deleteSessionArtifact(w http.ResponseWriter, r *http.Request) {
 	id := chi.URLParam(r, "artifact_id")
 	if err := h.Artifacts.DeleteSessionArtifact(r.Context(), sessions.DeleteSessionArtifactCommand{TenantID: tenantID(r), SessionID: chi.URLParam(r, "session_id"), ArtifactID: id}); err != nil {
@@ -94,17 +59,6 @@ func (h *Handler) deleteSessionArtifact(w http.ResponseWriter, r *http.Request)
 	writeJSON(w, http.StatusOK, v1.SessionArtifactDeleted{ID: id, Object: "agent.session.artifact.deleted", Deleted: true})
 }
 
-// @Summary Download immutable artifact bytes
-// @Description Streams stored bytes after tenant and Session authorization, including after Environment expiration. Exact upstream headers and Range behavior remain unverified.
-// @Tags Artifacts
-// @Produce octet-stream
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param session_id path string true "Session ID"
-// @Param artifact_id path string true "Artifact ID"
-// @Success 200 {file} binary
-// @Failure 400,401,404,500,503 {object} v1.ErrorResponse
-// @Router /agents/sessions/{session_id}/artifacts/{artifact_id}/content [get]
 func (h *Handler) sessionArtifactContent(w http.ResponseWriter, r *http.Request) {
 	err := serveStoredContent(w, r, func(ctx context.Context, consume func(string, int64, io.Reader) error) error {
 		return h.ArtifactsReader.ReadSessionArtifact(ctx, tenantID(r), chi.URLParam(r, "session_id"), chi.URLParam(r, "artifact_id"), func(a sessions.Artifact, body io.Reader) error {
diff --git a/services/core/internal/api/session_deletion.go b/services/core/internal/api/session_deletion.go
index 7a88b3b04..014ca6406 100644
--- a/services/core/internal/api/session_deletion.go
+++ b/services/core/internal/api/session_deletion.go
@@ -10,16 +10,6 @@ import (
 	"github.com/google/uuid"
 )
 
-// @Summary Delete an execution Session
-// @Description Removes a durably idle or failed Session and its history from the public API. A Session whose root Turn is queued, in progress or waiting (including required actions) or whose input reservation is pending returns 409 conflict_error and is left unchanged; cancel it and wait until it is idle before deleting. Subagent child Turns and pending Environment file writes are not checked and do not block deletion. Repeating the deletion of the caller's own deleted Session returns the same confirmation; missing and foreign Sessions return 404. Internal records and native history are retained pending separate physical cleanup; overlapping stream timing remains unverified.
-// @Tags Sessions
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param session_id path string true "Session ID"
-// @Success 200 {object} v1.SessionDeleted
-// @Failure 400,401,404,409,413,500 {object} v1.ErrorResponse
-// @Router /agents/sessions/{session_id} [delete]
 func (h *Handler) deleteSession(w http.ResponseWriter, r *http.Request) {
 	body, ok := readJSONBody(w, r)
 	if !ok {
diff --git a/services/core/internal/api/session_metadata.go b/services/core/internal/api/session_metadata.go
index 5ccea02ec..213fbd667 100644
--- a/services/core/internal/api/session_metadata.go
+++ b/services/core/internal/api/session_metadata.go
@@ -14,18 +14,6 @@ import (
 	"github.com/go-chi/chi/v5"
 )
 
-// @Summary Update execution Session metadata
-// @Description The metadata field is required in an update body. Send null or {} to clear it, or supply an object to replace all pairs. Up to 16 string pairs, with keys at most 64 characters and values at most 512 characters; violations and non-string values return invalid_request_error with a metadata or metadata.<key> param. U+0000 is rejected as a local storage limit. Malformed, missing and foreign Session IDs share the not-found response. Execution configuration and activity are unchanged. Returns the same safe Environment and pending-input activity projection as Session retrieval.
-// @Tags Sessions
-// @Accept json
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param session_id path string true "Session ID"
-// @Param body body v1.UpdateSessionRequest true "Session metadata"
-// @Success 200 {object} v1.Session
-// @Failure 400,401,404,413,500,503 {object} v1.ErrorResponse
-// @Router /agents/sessions/{session_id} [post]
 func (h *Handler) updateSession(w http.ResponseWriter, r *http.Request) {
 	raw, ok := readJSONObject(w, r)
 	if !ok {
diff --git a/services/core/internal/api/skills.go b/services/core/internal/api/skills.go
index 948103faa..392c3c8d4 100644
--- a/services/core/internal/api/skills.go
+++ b/services/core/internal/api/skills.go
@@ -47,14 +47,6 @@ func (h *Handler) registerSkillRoutes(r chi.Router) {
 	r.Head("/v1/skills/{skill_id}/versions/{version}/content", methodNotAllowed)
 }
 
-// @Summary Retrieve Skill metadata
-// @Description Returns tenant-owned metadata without decrypting contents or starting Runtime. No Beta header is required.
-// @Tags Skills
-// @Produce json
-// @Security BearerAuth
-// @Param skill_id path string true "Skill ID"
-// @Success 200 {object} v1.Skill
-// @Router /skills/{skill_id} [get]
 func (h *Handler) getSkill(w http.ResponseWriter, r *http.Request) {
 	value, err := h.SkillsReader.Skill(r.Context(), tenantID(r), skills.PathID(chi.URLParam(r, "skill_id")))
 	if err != nil {
@@ -64,16 +56,6 @@ func (h *Handler) getSkill(w http.ResponseWriter, r *http.Request) {
 	writeJSON(w, http.StatusOK, skillResponseResource(value))
 }
 
-// @Summary Update the default Skill version
-// @Description Changes only the tenant-owned default pointer; immutable versions and existing Session snapshots remain unchanged.
-// @Tags Skills
-// @Accept json
-// @Produce json
-// @Security BearerAuth
-// @Param skill_id path string true "Skill ID"
-// @Param body body v1.SkillUpdateRequest true "Default version"
-// @Success 200 {object} v1.Skill
-// @Router /skills/{skill_id} [post]
 func (h *Handler) updateSkill(w http.ResponseWriter, r *http.Request) {
 	body, ok := readJSONBodyLimit(w, r, 64<<10, "Request exceeds 64 KiB.")
 	if !ok {
@@ -92,14 +74,6 @@ func (h *Handler) updateSkill(w http.ResponseWriter, r *http.Request) {
 	writeJSON(w, http.StatusOK, skillResponseResource(value))
 }
 
-// @Summary Delete a Skill and its versions
-// @Description Deletes tenant-owned source bundles. Existing Session installation snapshots remain independent.
-// @Tags Skills
-// @Produce json
-// @Security BearerAuth
-// @Param skill_id path string true "Skill ID"
-// @Success 200 {object} v1.SkillDeleted
-// @Router /skills/{skill_id} [delete]
 func (h *Handler) deleteSkill(w http.ResponseWriter, r *http.Request) {
 	id := chi.URLParam(r, "skill_id")
 	if err := h.Skills.DeleteSkill(r.Context(), skills.DeleteSkill{TenantID: tenantID(r), SkillID: skills.PathID(id)}); err != nil {
@@ -109,14 +83,6 @@ func (h *Handler) deleteSkill(w http.ResponseWriter, r *http.Request) {
 	writeJSON(w, http.StatusOK, v1.SkillDeleted{ID: id, Object: "skill.deleted", Deleted: true})
 }
 
-// @Summary Retrieve Skill version metadata
-// @Tags Skills
-// @Produce json
-// @Security BearerAuth
-// @Param skill_id path string true "Skill ID"
-// @Param version path string true "Concrete version number"
-// @Success 200 {object} v1.SkillVersion
-// @Router /skills/{skill_id}/versions/{version} [get]
 func (h *Handler) getSkillVersion(w http.ResponseWriter, r *http.Request) {
 	value, err := h.SkillsReader.Version(r.Context(), tenantID(r), skills.PathID(chi.URLParam(r, "skill_id")), skills.PathVersion(chi.URLParam(r, "version")))
 	if err != nil {
@@ -126,15 +92,6 @@ func (h *Handler) getSkillVersion(w http.ResponseWriter, r *http.Request) {
 	writeJSON(w, http.StatusOK, skillVersionResponse(value))
 }
 
-// @Summary Delete a Skill version
-// @Description Deleting the only remaining version also deletes the Skill; existing Session installation snapshots remain independent. The default version cannot be deleted while other versions remain. Version numbers are never reused.
-// @Tags Skills
-// @Produce json
-// @Security BearerAuth
-// @Param skill_id path string true "Skill ID"
-// @Param version path string true "Concrete version number"
-// @Success 200 {object} v1.SkillVersionDeleted
-// @Router /skills/{skill_id}/versions/{version} [delete]
 func (h *Handler) deleteSkillVersion(w http.ResponseWriter, r *http.Request) {
 	value, err := h.Skills.DeleteVersion(r.Context(), skills.DeleteVersion{TenantID: tenantID(r), SkillID: skills.PathID(chi.URLParam(r, "skill_id")), Version: skills.PathVersion(chi.URLParam(r, "version"))})
 	if err != nil {
diff --git a/services/core/internal/api/skills_list.go b/services/core/internal/api/skills_list.go
index bab40c047..6640b63a6 100644
--- a/services/core/internal/api/skills_list.go
+++ b/services/core/internal/api/skills_list.go
@@ -8,16 +8,6 @@ import (
 	"github.com/go-chi/chi/v5"
 )
 
-// @Summary List Skills
-// @Description Lists tenant-owned metadata in timestamp order. Default page size 20, maximum 100. Limit 0 returns an empty page whose has_more reports whether any Skill follows the cursor; exact hosted defaults remain unverified.
-// @Tags Skills
-// @Produce json
-// @Security BearerAuth
-// @Param after query string false "Skill resource cursor"
-// @Param limit query integer false "Page size; 0 returns an empty page" default(20) minimum(0) maximum(100)
-// @Param order query string false "Creation order; omit for descending, explicit empty values are invalid" Enums(asc,desc)
-// @Success 200 {object} v1.SkillList
-// @Router /skills [get]
 func (h *Handler) listSkills(w http.ResponseWriter, r *http.Request) {
 	options, ok := readPage(w, r)
 	if !ok {
@@ -39,17 +29,6 @@ func (h *Handler) listSkills(w http.ResponseWriter, r *http.Request) {
 	writeJSON(w, http.StatusOK, result)
 }
 
-// @Summary List Skill versions
-// @Description Orders by version number; after identifies a version resource, not a version number. An after value that does not begin with skillver, or a version of another Skill, returns 400 invalid_value with param after; a missing version returns not found. No contents are decrypted. Limit 0 returns an empty page whose has_more reports whether any version follows the cursor.
-// @Tags Skills
-// @Produce json
-// @Security BearerAuth
-// @Param skill_id path string true "Skill ID"
-// @Param after query string false "Version resource cursor"
-// @Param limit query integer false "Page size; 0 returns an empty page" default(20) minimum(0) maximum(100)
-// @Param order query string false "Version order; omit for descending, explicit empty values are invalid" Enums(asc,desc)
-// @Success 200 {object} v1.SkillVersionList
-// @Router /skills/{skill_id}/versions [get]
 func (h *Handler) listSkillVersions(w http.ResponseWriter, r *http.Request) {
 	options, ok := readPage(w, r)
 	if !ok {
diff --git a/services/core/internal/api/skills_transfer.go b/services/core/internal/api/skills_transfer.go
index 4696bd6bf..975017902 100644
--- a/services/core/internal/api/skills_transfer.go
+++ b/services/core/internal/api/skills_transfer.go
@@ -13,27 +13,8 @@ import (
 	"github.com/go-chi/chi/v5"
 )
 
-// @Summary Upload a Skill
-// @Description Accepts one ZIP in files or a directory in files[]. Applies the qualified portable Skill bundle profile. No Beta header is required; full hosted upload limits and activation extensions are not qualified.
-// @Tags Skills
-// @Accept multipart/form-data
-// @Produce json
-// @Security BearerAuth
-// @Param files formData file true "Skill ZIP or directory files"
-// @Success 200 {object} v1.Skill
-// @Router /skills [post]
 func (h *Handler) createSkill(w http.ResponseWriter, r *http.Request) { h.uploadSkill(w, r, false) }
 
-// @Summary Upload an immutable Skill version
-// @Tags Skills
-// @Accept multipart/form-data
-// @Produce json
-// @Security BearerAuth
-// @Param skill_id path string true "Skill ID"
-// @Param files formData file true "Skill ZIP or directory files"
-// @Param default formData boolean false "Set as default"
-// @Success 200 {object} v1.SkillVersion
-// @Router /skills/{skill_id}/versions [post]
 func (h *Handler) createSkillVersion(w http.ResponseWriter, r *http.Request) {
 	h.uploadSkill(w, r, true)
 }
@@ -75,14 +56,6 @@ func (h *Handler) uploadSkill(w http.ResponseWriter, r *http.Request, version bo
 	}
 }
 
-// @Summary Download Skill content
-// @Description Downloads an authorized ZIP using the default pointer when no concrete version is supplied. Exact upstream unversioned selection, content headers and range semantics remain unverified.
-// @Tags Skills
-// @Produce octet-stream
-// @Security BearerAuth
-// @Param skill_id path string true "Skill ID"
-// @Success 200 {file} binary
-// @Router /skills/{skill_id}/content [get]
 func (h *Handler) skillContent(w http.ResponseWriter, r *http.Request) {
 	err := serveStoredContent(w, r, func(ctx context.Context, consume func(string, int64, io.Reader) error) error {
 		skill := skills.PathID(chi.URLParam(r, "skill_id"))
@@ -103,14 +76,6 @@ func (h *Handler) skillContent(w http.ResponseWriter, r *http.Request) {
 	}
 }
 
-// @Summary Download immutable Skill version content
-// @Tags Skills
-// @Produce octet-stream
-// @Security BearerAuth
-// @Param skill_id path string true "Skill ID"
-// @Param version path string true "Concrete version number"
-// @Success 200 {file} binary
-// @Router /skills/{skill_id}/versions/{version}/content [get]
 func (h *Handler) skillVersionContent(w http.ResponseWriter, r *http.Request) {
 	h.skillContent(w, r)
 }
diff --git a/services/core/internal/api/source_files.go b/services/core/internal/api/source_files.go
index cd74e7a2d..fbcd18798 100644
--- a/services/core/internal/api/source_files.go
+++ b/services/core/internal/api/source_files.go
@@ -24,15 +24,6 @@ type FilesReader interface {
 	Read(ctx context.Context, tenantID, fileID string, consume func(files.File, io.Reader) error) error
 }
 
-// @Summary Retrieve source file metadata
-// @Description Returns immutable project-owned user_data file metadata. No Beta header is required. Other purposes, expiration and full hosted status/error semantics remain unimplemented or unverified.
-// @Tags Files
-// @Produce json
-// @Security BearerAuth
-// @Param file_id path string true "Source file ID"
-// @Success 200 {object} v1.SourceFile
-// @Failure 400,401,404,500,503 {object} v1.ErrorResponse
-// @Router /files/{file_id} [get]
 func (h *Handler) getSourceFile(w http.ResponseWriter, r *http.Request) {
 	ctx, cancel := context.WithTimeout(r.Context(), 30*time.Second)
 	defer cancel()
@@ -44,15 +35,6 @@ func (h *Handler) getSourceFile(w http.ResponseWriter, r *http.Request) {
 	writeJSON(w, http.StatusOK, sourceFileResponse(file))
 }
 
-// @Summary Delete a source file
-// @Description Atomically deletes project-owned metadata and stored bytes. Already-admitted reads or copies may finish. Workspace copies remain independent. Historical WAL/backups are not erased. No Beta header is required; exact hosted concurrent deletion/error semantics remain unverified.
-// @Tags Files
-// @Produce json
-// @Security BearerAuth
-// @Param file_id path string true "Source file ID"
-// @Success 200 {object} v1.SourceFileDeleted
-// @Failure 400,401,404,500,503 {object} v1.ErrorResponse
-// @Router /files/{file_id} [delete]
 func (h *Handler) deleteSourceFile(w http.ResponseWriter, r *http.Request) {
 	ctx, cancel := context.WithTimeout(r.Context(), 30*time.Second)
 	defer cancel()
diff --git a/services/core/internal/api/source_files_content.go b/services/core/internal/api/source_files_content.go
index e03198ba3..7c2812f0d 100644
--- a/services/core/internal/api/source_files_content.go
+++ b/services/core/internal/api/source_files_content.go
@@ -11,14 +11,6 @@ import (
 	"github.com/go-chi/chi/v5"
 )
 
-// @Summary Download source file bytes
-// @Description Resolves project-owned File metadata before enforcing download policy. Public download of user_data Files returns 400; missing and foreign Files return the same 404. Internal initial-file and workspace copies remain available. No Beta header is required.
-// @Tags Files
-// @Produce json
-// @Security BearerAuth
-// @Param file_id path string true "Source file ID"
-// @Failure 400,401,404,500,503 {object} v1.ErrorResponse
-// @Router /files/{file_id}/content [get]
 func (h *Handler) sourceFileContent(w http.ResponseWriter, r *http.Request) {
 	ctx, cancel := context.WithTimeout(r.Context(), 30*time.Second)
 	defer cancel()
diff --git a/services/core/internal/api/source_files_list.go b/services/core/internal/api/source_files_list.go
index ed266eb2d..75faddd04 100644
--- a/services/core/internal/api/source_files_list.go
+++ b/services/core/internal/api/source_files_list.go
@@ -7,18 +7,6 @@ import (
 	"github.com/MiniMax-AI/OpenAgentCore/services/core/internal/files"
 )
 
-// @Summary List source files
-// @Description Lists project-owned Files without reading their bodies. The limit defaults to 10000 and must be 1–10000. Equal creation times use ID ordering. Purpose validation precedes cursor lookup; current storage contains only user_data. An explicit empty purpose is treated as omitted. Repeated purpose values remain rejected. Hosted positive filtering, default order and concurrent-page behavior remain unverified. No Beta header is required.
-// @Tags Files
-// @Produce json
-// @Security BearerAuth
-// @Param after query string false "Last File ID from the previous page"
-// @Param limit query integer false "Maximum page size, 1–10000" default(10000) minimum(1) maximum(10000)
-// @Param order query string false "Creation order; omit for descending, explicit empty values are invalid" Enums(asc,desc) default(desc)
-// @Param purpose query string false "Only return Files with this purpose"
-// @Success 200 {object} v1.SourceFileList
-// @Failure 400,401,404,500,503 {object} v1.ErrorResponse
-// @Router /files [get]
 func (h *Handler) listSourceFiles(w http.ResponseWriter, r *http.Request) {
 	options, purpose, ok := readSourceFilePage(w, r)
 	if !ok {
diff --git a/services/core/internal/api/source_files_upload.go b/services/core/internal/api/source_files_upload.go
index b4e4c44a3..6aa23d2e5 100644
--- a/services/core/internal/api/source_files_upload.go
+++ b/services/core/internal/api/source_files_upload.go
@@ -13,17 +13,6 @@ import (
 
 const sourceTransferTimeout = 5 * time.Minute
 
-// @Summary Upload a source file
-// @Description Accepts one multipart file and purpose=user_data in either order, with a private 512 MiB content limit and 64 KiB envelope allowance. Commits only after the entire request validates. The source is project-owned, independent of Sessions and workspace copies. No Beta header is required. Other purposes, expires_after, listing, resumable Uploads, quotas/rate-limit and complete hosted error/status parity remain unsupported or unverified.
-// @Tags Files
-// @Accept multipart/form-data
-// @Produce json
-// @Security BearerAuth
-// @Param file formData file true "Source bytes"
-// @Param purpose formData string true "user_data" Enums(user_data)
-// @Success 200 {object} v1.SourceFile
-// @Failure 400,401,413,500,503 {object} v1.ErrorResponse
-// @Router /files [post]
 func (h *Handler) createSourceFile(w http.ResponseWriter, r *http.Request) {
 	deadline := time.Now().Add(sourceTransferTimeout)
 	controller := http.NewResponseController(w)
diff --git a/services/core/internal/api/stream.go b/services/core/internal/api/stream.go
index 9ac502a10..cfda35b6f 100644
--- a/services/core/internal/api/stream.go
+++ b/services/core/internal/api/stream.go
@@ -24,17 +24,6 @@ type SessionEvents interface {
 	SessionStreamSnapshot(context.Context, string, string) (sessions.Session, int64, error)
 }
 
-// @Summary Stream live Session events
-// @Description Live-only events, including command output fragments from capable Codex peers as agent.output.command_execution_output.delta with stable Item/output indexes. Native text conversion and output quotas apply; completion snapshots remain authoritative. Reconnect through Session, Turn and Items reads; missed events are not replayed. A lagging stream closes with an error when its bounded buffer is exceeded. When a hosted Environment fails to provision, the stream sends agent.session.environment.failed, an error event (environment_error/sandbox_error with the safe step and exit-status reason, never command output) and agent.session.failed, then ends. Session activity includes immutable pending-input connection actions before Turn creation; self_hosted environments use the same safe output as Session retrieval.
-// @Description Active streams revalidate the original Project key every second before output; revocation, Project archival or authentication unavailability closes the stream. Authentication checks use a five-second timeout.
-// @Tags Events
-// @Produce text/event-stream
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param session_id path string true "Session ID"
-// @Success 200 {object} v1.SessionEvent
-// @Failure 400,401,404,500,503 {object} v1.ErrorResponse
-// @Router /agents/sessions/{session_id}/events [get]
 func (h *Handler) streamEvents(w http.ResponseWriter, r *http.Request) {
 	id, tenant := chi.URLParam(r, "session_id"), tenantID(r)
 	session, err := h.SessionsReader.GetSession(r.Context(), tenant, id)
diff --git a/services/core/internal/api/subagent_turns.go b/services/core/internal/api/subagent_turns.go
index 6ad9c4d45..f3cb78f54 100644
--- a/services/core/internal/api/subagent_turns.go
+++ b/services/core/internal/api/subagent_turns.go
@@ -6,18 +6,6 @@ import (
 	"github.com/go-chi/chi/v5"
 )
 
-// @Summary Retrieve a Subagent Turn
-// @Description Returns a Turn owned by this Subagent. Its agent_id is the Session's Agent ID and its subagent_id identifies the Subagent. Session Turn routes do not return child Turns. Unknown or inaccessible parent scopes return not found.
-// @Tags Subagents
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param session_id path string true "Session ID"
-// @Param subagent_id path string true "Subagent ID"
-// @Param turn_id path string true "Turn ID"
-// @Success 200 {object} v1.Turn
-// @Failure 400,401,404,500,503 {object} v1.ErrorResponse
-// @Router /agents/sessions/{session_id}/subagents/{subagent_id}/turns/{turn_id} [get]
 func (h *Handler) getSubagentTurn(w http.ResponseWriter, r *http.Request) {
 	value, err := h.Subagents.GetSubagentTurn(r.Context(), tenantID(r), chi.URLParam(r, "session_id"), chi.URLParam(r, "subagent_id"), chi.URLParam(r, "turn_id"))
 	if err != nil {
@@ -27,20 +15,6 @@ func (h *Handler) getSubagentTurn(w http.ResponseWriter, r *http.Request) {
 	writeJSON(w, http.StatusOK, value)
 }
 
-// @Summary List a Subagent's Turns
-// @Description Includes this Subagent's Turns after resume, with the Session's Agent ID as agent_id. Cursors are Turns of the same tenant, Session and Subagent. Any other after value, including a malformed one, returns 400 invalid_request_error with the message "Invalid resource ID in `after`". Missing recorded usage remains null. A limit outside 1–100 is rejected.
-// @Tags Subagents
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param session_id path string true "Session ID"
-// @Param subagent_id path string true "Subagent ID"
-// @Param after query string false "Last Turn ID from the previous page"
-// @Param limit query int false "Page size" minimum(1) maximum(100) default(20)
-// @Param order query string false "Creation order; omit for descending, explicit empty values are invalid" Enums(asc,desc) default(desc)
-// @Success 200 {object} v1.TurnList
-// @Failure 400,401,404,500,503 {object} v1.ErrorResponse
-// @Router /agents/sessions/{session_id}/subagents/{subagent_id}/turns [get]
 func (h *Handler) listSubagentTurns(w http.ResponseWriter, r *http.Request) {
 	options, ok := readPage(w, r)
 	if !ok {
@@ -54,21 +28,6 @@ func (h *Handler) listSubagentTurns(w http.ResponseWriter, r *http.Request) {
 	writeJSON(w, http.StatusOK, turnListResponse(page.Data, page.HasMore))
 }
 
-// @Summary List a Subagent Turn's Items
-// @Description Returns Items owned by this exact Subagent Turn. Cursors are Items of the same tenant, Session, Subagent and Turn. Any other after value, including a malformed one, returns 400 invalid_request_error with the message "Invalid session item ID in `after`".
-// @Tags Subagents
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param session_id path string true "Session ID"
-// @Param subagent_id path string true "Subagent ID"
-// @Param turn_id path string true "Turn ID"
-// @Param after query string false "Last Item ID from the previous page"
-// @Param limit query int false "Page size; 0 is treated as 1 and values above 100 as 100" minimum(0) default(20)
-// @Param order query string false "Resource order; omit for descending, explicit empty values are invalid" Enums(asc,desc) default(desc)
-// @Success 200 {object} v1.ItemList
-// @Failure 400,401,404,500,503 {object} v1.ErrorResponse
-// @Router /agents/sessions/{session_id}/subagents/{subagent_id}/turns/{turn_id}/items [get]
 func (h *Handler) listSubagentTurnItems(w http.ResponseWriter, r *http.Request) {
 	options, ok := readClampedPage(w, r)
 	if !ok {
diff --git a/services/core/internal/api/subagents.go b/services/core/internal/api/subagents.go
index 101f84027..d230e5f84 100644
--- a/services/core/internal/api/subagents.go
+++ b/services/core/internal/api/subagents.go
@@ -29,17 +29,6 @@ func (h *Handler) registerSubagentRoutes(r chi.Router) {
 	r.Get(root+"/{subagent_id}/turns/{turn_id}/items", h.listSubagentTurnItems)
 }
 
-// @Summary Retrieve a Session Subagent
-// @Description Returns this Session's persisted Subagent. Active includes idle between Turns. Resuming preserves opened_at and clears closed_at. Unknown or inaccessible parent scopes return not found.
-// @Tags Subagents
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param session_id path string true "Session ID"
-// @Param subagent_id path string true "Subagent ID"
-// @Success 200 {object} v1.Subagent
-// @Failure 400,401,404,500,503 {object} v1.ErrorResponse
-// @Router /agents/sessions/{session_id}/subagents/{subagent_id} [get]
 func (h *Handler) getSubagent(w http.ResponseWriter, r *http.Request) {
 	value, err := h.Subagents.GetSubagent(r.Context(), tenantID(r), chi.URLParam(r, "session_id"), chi.URLParam(r, "subagent_id"))
 	if err != nil {
@@ -49,19 +38,6 @@ func (h *Handler) getSubagent(w http.ResponseWriter, r *http.Request) {
 	writeJSON(w, http.StatusOK, value)
 }
 
-// @Summary List Session Subagents
-// @Description Includes nested and closed Subagents. Cursors are Subagents of the same tenant and Session. Any other after value, including a malformed one, returns 400 invalid_request_error with the message "Invalid resource ID in `after`". A limit outside 1–100 is rejected.
-// @Tags Subagents
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param session_id path string true "Session ID"
-// @Param after query string false "Last Subagent ID from the previous page"
-// @Param limit query int false "Page size" minimum(1) maximum(100) default(20)
-// @Param order query string false "Resource order; omit for descending, explicit empty values are invalid" Enums(asc,desc) default(desc)
-// @Success 200 {object} v1.SubagentList
-// @Failure 400,401,404,500,503 {object} v1.ErrorResponse
-// @Router /agents/sessions/{session_id}/subagents [get]
 func (h *Handler) listSubagents(w http.ResponseWriter, r *http.Request) {
 	options, ok := readPage(w, r)
 	if !ok {
@@ -75,20 +51,6 @@ func (h *Handler) listSubagents(w http.ResponseWriter, r *http.Request) {
 	writeJSON(w, http.StatusOK, subagentListResponse(page.Data, page.HasMore))
 }
 
-// @Summary List a Subagent's Items
-// @Description Returns only this Subagent's own Items across all its Turns, not its descendants' Items. Cursors are Items of the same tenant, Session and Subagent. Any other after value, including a malformed one, returns 400 invalid_request_error with the message "Invalid session item ID in `after`".
-// @Tags Subagents
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param session_id path string true "Session ID"
-// @Param subagent_id path string true "Subagent ID"
-// @Param after query string false "Last Item ID from the previous page"
-// @Param limit query int false "Page size; 0 is treated as 1 and values above 100 as 100" minimum(0) default(20)
-// @Param order query string false "Resource order; omit for descending, explicit empty values are invalid" Enums(asc,desc) default(desc)
-// @Success 200 {object} v1.ItemList
-// @Failure 400,401,404,500,503 {object} v1.ErrorResponse
-// @Router /agents/sessions/{session_id}/subagents/{subagent_id}/items [get]
 func (h *Handler) listSubagentItems(w http.ResponseWriter, r *http.Request) {
 	options, ok := readClampedPage(w, r)
 	if !ok {
diff --git a/services/core/internal/api/text_configuration.go b/services/core/internal/api/text_configuration.go
deleted file mode 100644
index dca8f5358..000000000
--- a/services/core/internal/api/text_configuration.go
+++ /dev/null
@@ -1,25 +0,0 @@
-package api
-
-import (
-	"errors"
-	v1 "github.com/MiniMax-AI/OpenAgentCore/contracts/agents-api/v1"
-)
-
-func resolveText(input *v1.TextConfigInput) (v1.TextConfig, error) {
-	text := v1.TextConfig{Format: v1.TextFormat{Type: "text"}, Verbosity: "medium"}
-	if input == nil {
-		return text, nil
-	}
-	if input.Format != nil && input.Format.Type != "text" {
-		return text, errors.New("This service currently supports text.format.type=text only.")
-	}
-	if input.Verbosity != nil {
-		switch *input.Verbosity {
-		case "low", "medium", "high":
-			text.Verbosity = *input.Verbosity
-		default:
-			return text, errors.New("text.verbosity must be low, medium or high.")
-		}
-	}
-	return text, nil
-}
diff --git a/services/core/internal/api/turn_diagnostic_failure.go b/services/core/internal/api/turn_diagnostic_failure.go
index 4449831de..1f2081511 100644
--- a/services/core/internal/api/turn_diagnostic_failure.go
+++ b/services/core/internal/api/turn_diagnostic_failure.go
@@ -49,7 +49,7 @@ func turnDiagnosticFailure(turn sessions.Turn) *DiagnosticFailure {
 		code = "delivery_unconfirmed"
 	case "invalid_input", "input_not_applied", "message_input_unsupported", "input_invalid_input", "input_run_inactive", "input_input_conflict", "input_input_limit", "input_unsupported", "input_rejected", "input_not_ready", "input_busy":
 		code = "input_rejected"
-	case "invalid_executor_result", "interaction_not_supported", "execution_state_unavailable", "execution_state_changed", "function_call_invalid", "function_result_invalid":
+	case "invalid_executor_result", "execution_state_unavailable", "execution_state_changed", "function_call_invalid", "function_result_invalid":
 		code = "executor_protocol_error"
 	case "event_persistence_failed", "artifact_capture_failed":
 		code = "core_storage_failed"
diff --git a/services/core/internal/api/turn_diagnostic_failure_test.go b/services/core/internal/api/turn_diagnostic_failure_test.go
index 0cffe47e1..8fe650ca2 100644
--- a/services/core/internal/api/turn_diagnostic_failure_test.go
+++ b/services/core/internal/api/turn_diagnostic_failure_test.go
@@ -14,7 +14,7 @@ func TestDiagnosticFailureWhitelist(t *testing.T) {
 		"harness_error": {"engine_failed"}, "model_provider_required": {"model_provider_required"}, "runtime_unavailable": {"execution_device_unavailable", "execution_unavailable"}, "runtime_disconnected": {"device_disconnected", "event_stream_incomplete"}, "runtime_preparation_failed": {"preparation_start_failed", "preparation_interrupted"}, "execution_interrupted": {"execution_interrupted"},
 		"delivery_unconfirmed":    {"delivery_unknown", "input_outcome_unknown", "cancel_unconfirmed", "cancel_outcome_unavailable", "function_result_unconfirmed"},
 		"input_rejected":          {"invalid_input", "input_not_applied", "message_input_unsupported", "input_invalid_input", "input_run_inactive", "input_input_conflict", "input_input_limit", "input_unsupported", "input_rejected", "input_not_ready", "input_busy"},
-		"executor_protocol_error": {"invalid_executor_result", "interaction_not_supported", "execution_state_unavailable", "execution_state_changed", "function_call_invalid", "function_result_invalid"}, "core_storage_failed": {"event_persistence_failed", "artifact_capture_failed"}, "internal_error": {"secret-canary", "input_secret-canary", "execution_state_secret-canary", ""},
+		"executor_protocol_error": {"invalid_executor_result", "execution_state_unavailable", "execution_state_changed", "function_call_invalid", "function_result_invalid"}, "core_storage_failed": {"event_persistence_failed", "artifact_capture_failed"}, "internal_error": {"secret-canary", "input_secret-canary", "execution_state_secret-canary", ""},
 	}
 	catalog, err := os.ReadFile("../../../../contracts/agents-api/core-errors.md")
 	if err != nil {
diff --git a/services/core/internal/api/turns.go b/services/core/internal/api/turns.go
index d1afadac7..7aa48a01e 100644
--- a/services/core/internal/api/turns.go
+++ b/services/core/internal/api/turns.go
@@ -18,17 +18,6 @@ type Turns interface {
 	ListTurns(context.Context, string, string, string, int, bool) (sessions.TurnPage, error)
 }
 
-// @Summary Retrieve an execution Turn
-// @Description Returns a root Turn of this Session. A Subagent Turn ID returns the same not found error as a missing Turn; read it through the Subagent Turn routes.
-// @Tags Turns
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param session_id path string true "Session ID"
-// @Param turn_id path string true "Turn ID"
-// @Success 200 {object} v1.Turn
-// @Failure 400,401,404,500 {object} v1.ErrorResponse
-// @Router /agents/sessions/{session_id}/turns/{turn_id} [get]
 func (h *Handler) getTurn(w http.ResponseWriter, r *http.Request) {
 	sessionID := chi.URLParam(r, "session_id")
 	turn, err := h.Turns.GetTurn(r.Context(), tenantID(r), sessionID, chi.URLParam(r, "turn_id"))
@@ -49,19 +38,6 @@ func (h *Handler) getTurn(w http.ResponseWriter, r *http.Request) {
 	writeJSON(w, http.StatusOK, response)
 }
 
-// @Summary List execution Turns
-// @Description Returns the Session's root Turns in creation order; Subagent Turns are listed through the Subagent Turn routes. The cursor belongs to the same Session and tenant; any other after value, including a malformed one or a Subagent Turn ID, returns not found. Usage contains the latest recorded complete token breakdown; missing measurements remain null.
-// @Tags Turns
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param session_id path string true "Session ID"
-// @Param after query string false "Last Turn ID from the previous page"
-// @Param limit query int false "Page size" minimum(1) maximum(100) default(20)
-// @Param order query string false "Creation order; omit for descending, explicit empty values are invalid" Enums(asc,desc) default(desc)
-// @Success 200 {object} v1.TurnList
-// @Failure 400,401,404,500 {object} v1.ErrorResponse
-// @Router /agents/sessions/{session_id}/turns [get]
 func (h *Handler) listTurns(w http.ResponseWriter, r *http.Request) {
 	options, ok := readPage(w, r)
 	if !ok {
diff --git a/services/core/internal/api/vaults.go b/services/core/internal/api/vaults.go
index bd2eeb14a..699ae5ebd 100644
--- a/services/core/internal/api/vaults.go
+++ b/services/core/internal/api/vaults.go
@@ -33,17 +33,6 @@ type VaultsReader interface {
 	ListCredentials(ctx context.Context, tenantID, vaultID string, query vaults.PageQuery) (vaults.CredentialPage, error)
 }
 
-// @Summary Create a Vault
-// @Description Creates a project-owned Vault independently of execution. Omitted name stays null; a supplied string is trimmed and must contain 1–256 UTF-8 bytes. Explicit null name is invalid. Omitted/null metadata becomes an empty object; non-string values return invalid_request_error with a metadata.<key> param. Metadata has a local 64 KiB encoded storage bound. U+0000 in stored strings is rejected as a local storage limit. Credentials, Session binding and hosted error/retry parity remain incomplete.
-// @Tags Vaults
-// @Accept json
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param body body v1.CreateVaultRequest true "Vault name and metadata"
-// @Success 201 {object} v1.Vault
-// @Failure 400,401,413,500 {object} v1.ErrorResponse
-// @Router /vaults [post]
 func (h *Handler) createVault(w http.ResponseWriter, r *http.Request) {
 	raw, ok := readJSONObject(w, r)
 	if !ok {
@@ -94,16 +83,6 @@ func (h *Handler) createVault(w http.ResponseWriter, r *http.Request) {
 	writeJSON(w, http.StatusCreated, vaultResponse(vault))
 }
 
-// @Summary Retrieve a Vault
-// @Description Reads a Vault owned by the authenticated project without resolving credentials, Sessions or execution devices. Missing and foreign IDs share the same not-found response; exact hosted error semantics remain unverified.
-// @Tags Vaults
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param vault_id path string true "Vault ID"
-// @Success 200 {object} v1.Vault
-// @Failure 400,401,404,500 {object} v1.ErrorResponse
-// @Router /vaults/{vault_id} [get]
 func (h *Handler) getVault(w http.ResponseWriter, r *http.Request) {
 	id, ok := credentialResourceID(w, r, "vault_id")
 	if !ok {
diff --git a/services/core/internal/api/vaults_delete.go b/services/core/internal/api/vaults_delete.go
index 3e666bf80..aa03251da 100644
--- a/services/core/internal/api/vaults_delete.go
+++ b/services/core/internal/api/vaults_delete.go
@@ -8,16 +8,6 @@ import (
 	"github.com/MiniMax-AI/OpenAgentCore/services/core/internal/vaults"
 )
 
-// @Summary Delete a Vault and all its Credentials
-// @Description Atomically removes the authenticated project's Vault and all its stored Credentials without an encryption key, decryption or external requests. Existing Session snapshots, history and recorded retries retain their frozen identities; subsequent credential lookups fail without reselection or anonymous fallback. Already-resolved tokens and running Sessions are not revoked or cancelled. Missing/repeated deletion locally returns 404. Exact hosted archive, post-delete visibility and concurrent/error semantics remain unverified; physical erasure from native history, WAL or backups is not established.
-// @Tags Vaults
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param vault_id path string true "Vault ID"
-// @Success 200 {object} v1.VaultDeleted
-// @Failure 400,401,404,413,500 {object} v1.ErrorResponse
-// @Router /vaults/{vault_id} [delete]
 func (h *Handler) deleteVault(w http.ResponseWriter, r *http.Request) {
 	body, ok := readJSONBody(w, r)
 	if !ok {
diff --git a/services/core/internal/api/vaults_list.go b/services/core/internal/api/vaults_list.go
index 72ebed7da..305f87ecd 100644
--- a/services/core/internal/api/vaults_list.go
+++ b/services/core/internal/api/vaults_list.go
@@ -6,20 +6,6 @@ import (
 	v1 "github.com/MiniMax-AI/OpenAgentCore/contracts/agents-api/v1"
 )
 
-// @Summary List Vaults
-// @Description Lists project-owned Vaults independently of execution. An unknown, malformed or foreign after cursor returns not found. Includes active and archived records by default. Status accepts a scalar, the SDK's status[] array or both, filtering by their union; a repeated scalar is rejected. Limits default to 20 and clamp to 1–100. Equal creation times use ID ordering; exact hosted errors and concurrent-page behavior remain unverified. Archive/delete lifecycle is not implemented.
-// @Tags Vaults
-// @Produce json
-// @Security BearerAuth
-// @Param OpenAI-Beta header string true "agents=v1"
-// @Param after query string false "Last Vault ID from the previous page"
-// @Param limit query integer false "Requested page size, clamped to 1–100" default(20)
-// @Param order query string false "Creation order; omit for descending, explicit empty values are invalid" Enums(asc,desc) default(desc)
-// @Param status query string false "Scalar status filter" Enums(active,archived)
-// @Param status[] query []string false "Array status filter; combined with status as a union" collectionFormat(multi) Enums(active,archived)
-// @Success 200 {object} v1.VaultList
-// @Failure 400,401,404,500 {object} v1.ErrorResponse
-// @Router /vaults [get]
 func (h *Handler) listVaults(w http.ResponseWriter, r *http.Request) {
 	query, ok := readVaultPage(w, r)
 	if !ok {
diff --git a/services/core/internal/engine/configuration_test.go b/services/core/internal/engine/configuration_test.go
index 61df5799d..74de79937 100644
--- a/services/core/internal/engine/configuration_test.go
+++ b/services/core/internal/engine/configuration_test.go
@@ -17,7 +17,7 @@ func TestProviderDeclarationsAgreeWithAdmission(t *testing.T) {
 			for _, protocol := range []string{"responses", "anthropic", "unknown"} {
 				provider, supported := declared.Provider(protocol)
 				input := v1.ModelProviderInput{Protocol: protocol, BaseURL: "https://example.test", APIKey: "private-fixture", ContextWindow: 100, MaxOutputTokens: 20}
-				if (input.ValidateHarness(kind) == nil) != supported || (v1.ValidateModelProtocol(protocol, kind) == nil) != supported {
+				if (input.ValidateHarness(kind) == nil) != supported {
 					t.Fatalf("protocol %q disagrees with validation", protocol)
 				}
 				if !supported {
diff --git a/services/core/internal/execution/delivery.go b/services/core/internal/execution/delivery.go
index 15bb619de..adc8daa5e 100644
--- a/services/core/internal/execution/delivery.go
+++ b/services/core/internal/execution/delivery.go
@@ -253,9 +253,6 @@ func (d *Dispatcher) deliver(ctx context.Context, tenantID, sessionID string, pe
 						return
 					}
 				}
-			case proto.TypePermissionRequest, proto.TypePromptForUserChoice:
-				result.ErrorCode = "interaction_not_supported"
-				return
 			}
 		case <-ticker.C:
 			select {
diff --git a/services/core/internal/runtimedevice/state.go b/services/core/internal/runtimedevice/state.go
index 1e7771018..5d322c826 100644
--- a/services/core/internal/runtimedevice/state.go
+++ b/services/core/internal/runtimedevice/state.go
@@ -17,7 +17,6 @@ type HeartbeatStatus struct {
 type KindCapabilities struct {
 	SubagentObservations  bool `json:"subagent_observations,omitempty"`
 	Streaming             bool `json:"streaming,omitempty"`
-	Permissions           bool `json:"permissions,omitempty"`
 	Usage                 bool `json:"usage,omitempty"`
 	Resume                bool `json:"resume,omitempty"`
 	NativeSessionRecovery bool `json:"native_session_recovery,omitempty"`
diff --git a/services/core/internal/runtimegateway/mcp_bearer_live_linux_test.go b/services/core/internal/runtimegateway/mcp_bearer_live_linux_test.go
index f89de9525..cff41637b 100644
--- a/services/core/internal/runtimegateway/mcp_bearer_live_linux_test.go
+++ b/services/core/internal/runtimegateway/mcp_bearer_live_linux_test.go
@@ -14,6 +14,7 @@ import (
 	"time"
 
 	"github.com/MiniMax-AI/OpenAgentCore/internal/agentdaemon/proto"
+	"github.com/MiniMax-AI/OpenAgentCore/internal/modelprovider"
 	"github.com/MiniMax-AI/OpenAgentCore/services/core/internal/runtimedevice"
 	"github.com/go-chi/chi/v5"
 	"github.com/google/uuid"
@@ -57,7 +58,7 @@ func TestLiveMCPBearerGatewayColdContinuation(t *testing.T) {
 	t.Cleanup(server.Close)
 	handler := NewHandler(HandlerConfig{Authenticator: auth, Registry: registry, PublicWSURL: "ws" + strings.TrimPrefix(server.URL, "http") + "/agent-daemon/ws", Log: func(format string, args ...any) { _, _ = fmt.Fprintf(capture, format+"\n", args...) }})
 	RegisterRoutes(router, handler)
-	mcpBearerStartDaemon(t, root, daemon, native, provider, fixture.caFile, server.URL, id, runner, capture)
+	mcpBearerStartDaemon(t, root, daemon, native, fixture.caFile, server.URL, id, runner, capture)
 	ctx, cancel := context.WithTimeout(t.Context(), 6*time.Minute)
 	defer cancel()
 	peer, err := registry.WaitForDevice(ctx, id, 30*time.Second)
@@ -91,7 +92,7 @@ func TestLiveMCPBearerGatewayColdContinuation(t *testing.T) {
 		turn := &mcpBearerTurn{}
 		turns = append(turns, turn)
 		runID := uuid.NewString()
-		request := proto.PromptRequestPayload{AgentKind: "codex", AgentStateKey: "agents-api-" + assignment.SessionID, AgentSessionID: resume, ObserveMessages: true, DisableExecutionEnvironment: true, DisableSubagents: true, MCPHTTPServers: &servers, Model: "MiniMax-M3", ExecutionControls: &proto.ExecutionControls{WebSearch: "disabled", TextVerbosity: "medium"}}
+		request := proto.PromptRequestPayload{AgentKind: "codex", AgentStateKey: "agents-api-" + assignment.SessionID, AgentSessionID: resume, ObserveMessages: true, DisableExecutionEnvironment: true, DisableSubagents: true, MCPHTTPServers: &servers, Model: "MiniMax-M3", ModelProvider: &modelprovider.Provider{Protocol: modelprovider.Responses, BaseURL: "https://api.minimax.cn/v1", APIKey: provider}, ExecutionControls: &proto.ExecutionControls{WebSearch: "disabled", TextVerbosity: "medium"}}
 		sub, err := peer.SubscribeDurable(runID, assignment)
 		if err != nil {
 			t.Fatal("cannot subscribe before real daemon dispatch")
@@ -212,8 +213,8 @@ func mcpBearerCollectTurn(t *testing.T, ctx context.Context, sub *Subscription,
 		}
 		turn.Events = append(turn.Events, event)
 		switch event.Type {
-		case proto.TypeError, proto.TypePermissionRequest, proto.TypePromptForUserChoice:
-			t.Fatal("unexpected execution failure or interaction during private MCP acceptance")
+		case proto.TypeError:
+			t.Fatal("unexpected execution failure during private MCP acceptance")
 		case proto.TypeToolCall:
 			var call proto.ToolCallPayload
 			if event.DecodePayload(&call) != nil || call.Observation == nil {
diff --git a/services/core/internal/runtimegateway/mcp_bearer_process_linux_test.go b/services/core/internal/runtimegateway/mcp_bearer_process_linux_test.go
index e2d70ae89..a61bca86c 100644
--- a/services/core/internal/runtimegateway/mcp_bearer_process_linux_test.go
+++ b/services/core/internal/runtimegateway/mcp_bearer_process_linux_test.go
@@ -86,7 +86,7 @@ func (w *mcpBearerLog) snapshot() []byte {
 	return bytes.Clone(w.data.Bytes())
 }
 
-func mcpBearerStartDaemon(t *testing.T, root, daemon, native, provider, caFile, base, id, runner string, log *mcpBearerLog) {
+func mcpBearerStartDaemon(t *testing.T, root, daemon, native, caFile, base, id, runner string, log *mcpBearerLog) {
 	t.Helper()
 	for _, dir := range []string{"home", "tmp", "runtime/daemon/execution"} {
 		if err := os.MkdirAll(filepath.Join(root, dir), 0700); err != nil {
@@ -107,12 +107,12 @@ for argument in "$@"; do
     break
   fi
 done
-exec "$OAC_TEST_MCP_BEARER_NATIVE" -c 'model_provider="minimax_validation"' -c 'model_providers.minimax_validation.name="MiniMax validation"' -c 'model_providers.minimax_validation.base_url="https://api.minimax.cn/v1"' -c 'model_providers.minimax_validation.env_key="MINIMAX_VALIDATION_KEY"' -c 'model_providers.minimax_validation.wire_api="responses"' "$@"
+exec "$OAC_TEST_MCP_BEARER_NATIVE" "$@"
 `
 	if err := os.WriteFile(wrapper, []byte(script), 0700); err != nil {
 		t.Fatal("cannot create owned native wrapper")
 	}
-	env := []string{"HOME=" + filepath.Join(root, "home"), "TMPDIR=" + filepath.Join(root, "tmp"), "OAC_RUNTIME_HOME=" + filepath.Join(root, "runtime"), "OAC_RUNTIME_CODEX_BIN=" + wrapper, "MINIMAX_VALIDATION_KEY=" + provider, "SSL_CERT_FILE=" + caFile, "OAC_TEST_MCP_BEARER_NATIVE=" + native, "OAC_TEST_MCP_BEARER_STARTS=" + filepath.Join(root, "native-starts"), "OAC_TEST_MCP_BEARER_ARGV=" + filepath.Join(root, "native-argv")}
+	env := []string{"HOME=" + filepath.Join(root, "home"), "TMPDIR=" + filepath.Join(root, "tmp"), "OAC_RUNTIME_HOME=" + filepath.Join(root, "runtime"), "OAC_RUNTIME_CODEX_BIN=" + wrapper, "SSL_CERT_FILE=" + caFile, "OAC_TEST_MCP_BEARER_NATIVE=" + native, "OAC_TEST_MCP_BEARER_STARTS=" + filepath.Join(root, "native-starts"), "OAC_TEST_MCP_BEARER_ARGV=" + filepath.Join(root, "native-argv")}
 	for _, name := range []string{"PATH", "LANG", "LC_ALL", "HTTP_PROXY", "HTTPS_PROXY", "ALL_PROXY", "NO_PROXY", "http_proxy", "https_proxy", "all_proxy", "no_proxy"} {
 		if value, ok := os.LookupEnv(name); ok {
 			env = append(env, name+"="+value)
diff --git a/services/core/internal/runtimegateway/registry.go b/services/core/internal/runtimegateway/registry.go
index 74de0139d..b5984821e 100644
--- a/services/core/internal/runtimegateway/registry.go
+++ b/services/core/internal/runtimegateway/registry.go
@@ -1,7 +1,7 @@
 // Package gateway is the server-side hub of the agent_daemon connector.
 // It owns the HTTP / WebSocket entry points the daemon dials in to,
 // per-device long-lived WebSocket sessions, and a process-local
-// registry of deviceID/runID/permID → Session for routing.
+// registry of deviceID/runID → Session for routing.
 //
 // The package deliberately does NOT depend on the connector
 // implementation — the connector imports it, not the other way around.
@@ -18,31 +18,18 @@ import (
 // asks for a device the gateway has no live session for.
 var ErrDeviceNotRegistered = errors.New("agentdaemon gateway: device not registered (offline / never connected)")
 
-// ErrPermissionNotRegistered is returned when SubmitPermission arrives
-// for a perm id we don't have a pending mapping for.
-var ErrPermissionNotRegistered = errors.New("agentdaemon gateway: permission id not registered (expired / unknown)")
-
-// ErrPromptForUserChoiceNotRegistered is returned when
-// SubmitPromptForUserChoice arrives for an ask id we don't have a
-// pending mapping for. Same race semantics as the permission variant
-// (cancelled / expired / never seen).
-var ErrPromptForUserChoiceNotRegistered = errors.New("agentdaemon gateway: prompt_for_user_choice id not registered (expired / unknown)")
-
 // ErrWaitForDeviceTimeout is returned by WaitForDevice when the
 // deadline expires before a daemon dials in.
 var ErrWaitForDeviceTimeout = errors.New("agentdaemon gateway: timed out waiting for device to register")
 
 // Registry is the process-wide map of live daemon sessions. It is
 // concurrency-safe; readers and writers live in different goroutines.
-// Four O(1) indexes are maintained: byDevice (primary), byRun (per
-// Subscribe), byPerm (per permission_request), byAsk (per
-// prompt_for_user_choice).
+// Two O(1) indexes are maintained: byDevice (primary) and byRun (per
+// Subscribe).
 type Registry struct {
 	mu       sync.RWMutex
 	byDevice map[string]*Session
 	byRun    map[string]*Session
-	byPerm   map[string]*Session
-	byAsk    map[string]*Session
 
 	// waiters holds buffered(1) channels that WaitForDevice callers
 	// are blocked on. Register drains the slice the moment a session
@@ -58,15 +45,13 @@ func NewRegistry() *Registry {
 	return &Registry{
 		byDevice: map[string]*Session{},
 		byRun:    map[string]*Session{},
-		byPerm:   map[string]*Session{},
-		byAsk:    map[string]*Session{},
 		waiters:  map[string][]chan *Session{},
 	}
 }
 
 // Register adds a freshly-upgraded session under its deviceID. The
 // latest dial-in wins: if a session was already registered for that
-// device, the old one's run/perm indexes are evicted (the caller
+// device, the old one's run index entries are evicted (the caller
 // closes the displaced *Session).
 func (r *Registry) Register(sess *Session) (previous *Session) {
 	r.mu.Lock()
@@ -80,16 +65,6 @@ func (r *Registry) Register(sess *Session) (previous *Session) {
 				delete(r.byRun, runID)
 			}
 		}
-		for permID, s := range r.byPerm {
-			if s == previous {
-				delete(r.byPerm, permID)
-			}
-		}
-		for askID, s := range r.byAsk {
-			if s == previous {
-				delete(r.byAsk, askID)
-			}
-		}
 	}
 	r.byDevice[sess.DeviceID] = sess
 
@@ -123,16 +98,6 @@ func (r *Registry) Deregister(sess *Session) {
 			delete(r.byRun, runID)
 		}
 	}
-	for permID, s := range r.byPerm {
-		if s == sess {
-			delete(r.byPerm, permID)
-		}
-	}
-	for askID, s := range r.byAsk {
-		if s == sess {
-			delete(r.byAsk, askID)
-		}
-	}
 }
 
 // LookupDevice returns the registered session for a device, or
@@ -175,74 +140,6 @@ func (r *Registry) DetachRun(runID string) {
 	delete(r.byRun, runID)
 }
 
-// AttachPermission records a permID -> session mapping so a later
-// SubmitPermission can route the decision frame to the right device.
-func (r *Registry) AttachPermission(permID string, sess *Session) {
-	if permID == "" || sess == nil {
-		return
-	}
-	r.mu.Lock()
-	defer r.mu.Unlock()
-	r.byPerm[permID] = sess
-}
-
-// DetachPermission clears the permID -> session mapping. Idempotent.
-func (r *Registry) DetachPermission(permID string) {
-	if permID == "" {
-		return
-	}
-	r.mu.Lock()
-	defer r.mu.Unlock()
-	delete(r.byPerm, permID)
-}
-
-// LookupPermission returns the session that owns a pending permID,
-// or ErrPermissionNotRegistered when the permission has expired /
-// been cancelled.
-func (r *Registry) LookupPermission(permID string) (*Session, error) {
-	r.mu.RLock()
-	defer r.mu.RUnlock()
-	if sess, ok := r.byPerm[permID]; ok {
-		return sess, nil
-	}
-	return nil, ErrPermissionNotRegistered
-}
-
-// AttachPromptForUserChoice records askID → session so a later
-// SubmitPromptForUserChoice can route the decision back to the right
-// daemon. Mirrors AttachPermission.
-func (r *Registry) AttachPromptForUserChoice(askID string, sess *Session) {
-	if askID == "" || sess == nil {
-		return
-	}
-	r.mu.Lock()
-	defer r.mu.Unlock()
-	r.byAsk[askID] = sess
-}
-
-// DetachPromptForUserChoice clears the askID → session mapping.
-// Idempotent.
-func (r *Registry) DetachPromptForUserChoice(askID string) {
-	if askID == "" {
-		return
-	}
-	r.mu.Lock()
-	defer r.mu.Unlock()
-	delete(r.byAsk, askID)
-}
-
-// LookupPromptForUserChoice returns the session that owns a pending
-// askID, or ErrPromptForUserChoiceNotRegistered when the ask has
-// expired or been cancelled.
-func (r *Registry) LookupPromptForUserChoice(askID string) (*Session, error) {
-	r.mu.RLock()
-	defer r.mu.RUnlock()
-	if sess, ok := r.byAsk[askID]; ok {
-		return sess, nil
-	}
-	return nil, ErrPromptForUserChoiceNotRegistered
-}
-
 // Devices returns a snapshot of registered device ids in arbitrary order.
 func (r *Registry) Devices() []string {
 	r.mu.RLock()
diff --git a/services/core/internal/runtimegateway/session.go b/services/core/internal/runtimegateway/session.go
index d13143632..36a923397 100644
--- a/services/core/internal/runtimegateway/session.go
+++ b/services/core/internal/runtimegateway/session.go
@@ -34,7 +34,7 @@ var (
 	WriteTimeout = 10 * time.Second
 
 	// InteractionAckTimeout bounds the application-level round trip for a
-	// permission or user-input decision after it is written to the daemon.
+	// function result or cancellation after it is written to the daemon.
 	InteractionAckTimeout = 15 * time.Second
 
 	// ReadLimit caps a single inbound frame at 4 MiB. tool_call
@@ -300,8 +300,8 @@ func (s *Session) Send(ctx context.Context, env proto.Envelope) error {
 
 // SendAndWaitInteractionAck sends a decision and waits until the daemon
 // confirms that its agent session applied it. Queueing or writing the
-// WebSocket frame alone is not success: without this receipt the canonical
-// database interaction must remain retryable.
+// WebSocket frame alone is not success: without this receipt the durable
+// delivery must remain retryable.
 func (s *Session) SendAndWaitInteractionAck(ctx context.Context, env proto.Envelope, deliveryID string) (proto.InteractionDecisionAckPayload, error) {
 	deliveryID = strings.TrimSpace(deliveryID)
 	if deliveryID == "" {
@@ -323,7 +323,7 @@ func (s *Session) SendAndWaitInteractionAck(ctx context.Context, env proto.Envel
 
 	// The exchange prefers an ack that raced the deadline; treating an
 	// already-applied decision as retryable can trigger a contradictory second
-	// human response.
+	// response.
 	waitCtx, cancel := context.WithTimeout(ctx, InteractionAckTimeout)
 	defer cancel()
 	reply, err := s.exchangeFrame(waitCtx, env, waiter)
@@ -450,7 +450,6 @@ func deviceKindsFromHeartbeat(p proto.HeartbeatPayload) []runtimedevice.Supporte
 			Version:   info.Version,
 			Capabilities: runtimedevice.KindCapabilities{
 				Streaming:             info.Capabilities.Streaming.IsSupported(),
-				Permissions:           info.Capabilities.Permissions.IsSupported(),
 				Usage:                 info.Capabilities.Usage.IsSupported(),
 				Resume:                info.Capabilities.Resume.IsSupported(),
 				Steering:              info.Capabilities.Steering.IsSupported(),
@@ -517,29 +516,6 @@ func (s *Session) dispatch(env proto.Envelope) {
 		_ = env.DecodePayload(&p)
 		s.log("agentdaemon gateway: Runtime rejected %s request=%s device=%s: %s", p.Type, env.ID, s.DeviceID, p.ErrorCode)
 		return
-	case proto.TypePermissionRequest:
-		var p proto.PermissionRequestPayload
-		requestID := ""
-		if err := env.DecodePayload(&p); err == nil {
-			requestID = strings.TrimSpace(p.RequestID)
-		}
-		if requestID == "" {
-			return
-		}
-		s.reg.AttachPermission(requestID, s)
-	case proto.TypePermissionCancel:
-		if env.ID != "" {
-			s.reg.DetachPermission(env.ID)
-		}
-	case proto.TypePromptForUserChoice:
-		// env.ID is the run id (so the fan path below delivers this
-		// frame to the run's subscriber). The ask id rides on the
-		// payload — pull it out so SubmitPromptForUserChoice can find
-		// the session by ask id via the byAsk index.
-		var p proto.PromptForUserChoicePayload
-		if err := env.DecodePayload(&p); err == nil && p.AskID != "" {
-			s.reg.AttachPromptForUserChoice(p.AskID, s)
-		}
 	case proto.TypeInteractionDecisionAck:
 		var ack proto.InteractionDecisionAckPayload
 		if err := env.DecodePayload(&ack); err != nil {
@@ -560,9 +536,7 @@ func (s *Session) dispatch(env proto.Envelope) {
 		return
 	}
 
-	// All run-correlated frames fan to the matching subscriber. Current
-	// permission and prompt-for-user-choice frames keep their interaction ID
-	// in the payload so Envelope.ID remains the run ID.
+	// All run-correlated frames fan to the matching subscriber.
 	if env.ID == "" {
 		return
 	}
diff --git a/services/core/internal/runtimegateway/session_test.go b/services/core/internal/runtimegateway/session_test.go
index 2b68bf637..e746dbd2f 100644
--- a/services/core/internal/runtimegateway/session_test.go
+++ b/services/core/internal/runtimegateway/session_test.go
@@ -165,21 +165,17 @@ func TestRegistry_RegisterReplacesAndEvictsRuns(t *testing.T) {
 	old := NewSession(newFakeConn(), "dev-1", "wks-1", "0.1.0", reg, nil)
 	reg.Register(old)
 	reg.AttachRun("run-1", old)
-	reg.AttachPermission("perm-1", old)
 
 	new := NewSession(newFakeConn(), "dev-1", "wks-1", "0.1.0", reg, nil)
 	prev := reg.Register(new)
 	if prev != old {
 		t.Fatalf("expected old session as displaced previous, got %p", prev)
 	}
-	// Old session's run/perm indexes must be cleared so a stale
+	// Old session's run index must be cleared so a stale
 	// Cancel can't be routed to the wrong session.
 	if got := reg.LookupRun("run-1"); got != nil {
 		t.Fatalf("expected run-1 mapping cleared, got %p", got)
 	}
-	if _, err := reg.LookupPermission("perm-1"); !errors.Is(err, ErrPermissionNotRegistered) {
-		t.Fatalf("expected perm-1 cleared, got %v", err)
-	}
 }
 
 func TestRegistry_DeregisterPreservesNewer(t *testing.T) {
@@ -260,48 +256,6 @@ func TestSession_DoneFrameAutoUnsubscribes(t *testing.T) {
 	}
 }
 
-func TestSession_PermissionRequestIndexedInRegistry(t *testing.T) {
-	reg := NewRegistry()
-	conn := newFakeConn()
-	sess := NewSession(conn, "dev-1", "wks-1", "0.1.0", reg, nil)
-	sess.Start()
-	defer sess.Close("test done")
-
-	sub, err := sess.SubscribeDurable("run-1", proto.AssignmentRef{})
-	ch := sub.Events
-	if err != nil {
-		t.Fatalf("subscribe: %v", err)
-	}
-	env, _ := proto.NewEnvelope(proto.TypePermissionRequest, "run-1", proto.PermissionRequestPayload{
-		RequestID: "perm-abc",
-		Tool:      "Bash",
-		Title:     "rm -rf /tmp/scratch",
-	})
-	raw, _ := jsonMarshal(env)
-	conn.Feed(raw)
-
-	// Poll because the read loop is async.
-	deadline := time.Now().Add(2 * time.Second)
-	for {
-		if got, err := reg.LookupPermission("perm-abc"); err == nil && got == sess {
-			break
-		}
-		if time.Now().After(deadline) {
-			t.Fatal("perm-abc never indexed in registry")
-		}
-		time.Sleep(10 * time.Millisecond)
-	}
-
-	select {
-	case got := <-ch:
-		if got.ID != "run-1" || got.Type != proto.TypePermissionRequest {
-			t.Fatalf("subscriber received %+v", got)
-		}
-	case <-time.After(2 * time.Second):
-		t.Fatal("run subscriber never received permission request")
-	}
-}
-
 func TestSession_CloseReportsUnknownWithoutExecutionEvents(t *testing.T) {
 	sess := NewSession(newFakeConn(), "device", "tenant", proto.Version, NewRegistry(), nil)
 	sub, err := sess.SubscribeDurable("run", proto.AssignmentRef{})
@@ -388,10 +342,9 @@ func TestSession_HeartbeatPersistsSupportedAgentKinds(t *testing.T) {
 				Available: true,
 				Version:   "1.2.3",
 				Capabilities: prototest.Capabilities(proto.AgentKindCapabilities{
-					Streaming:   proto.CapabilitySupported,
-					Permissions: proto.CapabilitySupported,
-					Usage:       proto.CapabilitySupported,
-					Resume:      proto.CapabilitySupported,
+					Streaming: proto.CapabilitySupported,
+					Usage:     proto.CapabilitySupported,
+					Resume:    proto.CapabilitySupported,
 				}),
 			},
 			{
@@ -416,7 +369,7 @@ func TestSession_HeartbeatPersistsSupportedAgentKinds(t *testing.T) {
 		byKind[info.Kind] = info
 	}
 	claude := byKind["fake_alpha"]
-	if !claude.Available || claude.Version != "1.2.3" || !claude.Capabilities.Permissions || !claude.Capabilities.Usage || !claude.Capabilities.Resume {
+	if !claude.Available || claude.Version != "1.2.3" || !claude.Capabilities.Streaming || !claude.Capabilities.Usage || !claude.Capabilities.Resume {
 		t.Fatalf("fake_alpha descriptor not converted: %#v", claude)
 	}
 	fake_beta := byKind["fake_beta"]
@@ -451,32 +404,6 @@ func TestSession_HeartbeatDoesNotInferCapabilities(t *testing.T) {
 	}
 }
 
-func TestSession_PermissionRequiresPayloadIdentity(t *testing.T) {
-	reg := NewRegistry()
-	sess := NewSession(newFakeConn(), "device", "tenant", proto.Version, reg, nil)
-	defer sess.Close("test done")
-	sub, err := sess.SubscribeDurable("run", proto.AssignmentRef{})
-	if err != nil {
-		t.Fatal(err)
-	}
-	env, _ := proto.NewEnvelope(proto.TypePermissionRequest, "run", proto.PermissionRequestPayload{Tool: "test"})
-	sess.dispatch(env)
-	if _, err := reg.LookupPermission("run"); !errors.Is(err, ErrPermissionNotRegistered) {
-		t.Fatal("run ID was treated as an interaction ID")
-	}
-	if len(sub.Events) != 0 {
-		t.Fatal("invalid permission request was forwarded")
-	}
-	env, _ = proto.NewEnvelope(proto.TypePermissionRequest, "run", proto.PermissionRequestPayload{RequestID: "permission", Tool: "test"})
-	sess.dispatch(env)
-	if got, err := reg.LookupPermission("permission"); err != nil || got != sess {
-		t.Fatalf("declared interaction identity was not registered: %v", err)
-	}
-	if got := <-sub.Events; got.ID != "run" {
-		t.Fatal("run correlation lost")
-	}
-}
-
 // jsonMarshal aliases encoding/json.Marshal so call sites read cleanly.
 func jsonMarshal(v any) ([]byte, error) {
 	return json.Marshal(v)
diff --git a/services/core/internal/sandbox/deployment.go b/services/core/internal/sandbox/deployment.go
index 95b146cc0..712d9e27b 100644
--- a/services/core/internal/sandbox/deployment.go
+++ b/services/core/internal/sandbox/deployment.go
@@ -67,11 +67,6 @@ type RuntimeRelease struct {
 	FirmwareSHA256      string `json:"firmware_sha256"`
 }
 
-func lowerHex(v string, bytes int) bool {
-	x, err := hex.DecodeString(v)
-	return err == nil && len(x) == bytes && hex.EncodeToString(x) == v
-}
-
 func (r RuntimeRelease) Validate() error {
 	values := reflect.ValueOf(r)
 	for i, rule := range runtimeContract {
diff --git a/services/core/internal/sandbox/e2b/provider.go b/services/core/internal/sandbox/e2b/provider.go
index c368d8866..3328eb0db 100644
--- a/services/core/internal/sandbox/e2b/provider.go
+++ b/services/core/internal/sandbox/e2b/provider.go
@@ -141,7 +141,6 @@ func (c Config) Validate() error {
 	}
 	return nil
 }
-func New(c Config) (*Provider, error) { return NewWithCaller(c, &ProcessCaller{}) }
 func NewWithCaller(c Config, caller Caller) (*Provider, error) {
 	if c.Validate() != nil || caller == nil {
 		return nil, sandbox.ErrInvalid
diff --git a/services/core/internal/sandbox/microsandbox/provider.go b/services/core/internal/sandbox/microsandbox/provider.go
index d6df19ec7..6ba4eeafc 100644
--- a/services/core/internal/sandbox/microsandbox/provider.go
+++ b/services/core/internal/sandbox/microsandbox/provider.go
@@ -18,7 +18,6 @@ type Provider struct {
 var _ sandbox.SandboxProvider = (*Provider)(nil)
 var _ sandbox.CheckpointProvider = (*Provider)(nil)
 
-func New(c Config) (*Provider, error) { return NewWithCaller(c, &ProcessCaller{}) }
 func NewWithCaller(c Config, caller Caller) (*Provider, error) {
 	if c.Validate() != nil || caller == nil {
 		return nil, sandbox.ErrInvalid
diff --git a/services/core/internal/sandbox/node/capacity_test.go b/services/core/internal/sandbox/node/capacity_test.go
index 1de42f08a..c408cb82a 100644
--- a/services/core/internal/sandbox/node/capacity_test.go
+++ b/services/core/internal/sandbox/node/capacity_test.go
@@ -34,7 +34,7 @@ func TestCapacityRefreshUsesAuthenticatedCoreIdentity(t *testing.T) {
 	if err != nil || refreshed.Identity.MaxActive != 2 || refreshed.Identity.MaxRetained != 8 || refreshed.Credential != stored.Credential {
 		t.Fatal("approved capacity not refreshed", err)
 	}
-	persisted, err := LoadIdentity(dir)
+	persisted, err := readIdentity(dir)
 	if err != nil || persisted != refreshed {
 		t.Fatal("approved capacity not persisted", err)
 	}
@@ -42,7 +42,7 @@ func TestCapacityRefreshUsesAuthenticatedCoreIdentity(t *testing.T) {
 	if _, err = RefreshIdentity(t.Context(), dir); err == nil {
 		t.Fatal("foreign identity accepted")
 	}
-	after, _ := LoadIdentity(dir)
+	after, _ := readIdentity(dir)
 	if after != persisted {
 		t.Fatal("rejected response changed retained identity")
 	}
diff --git a/services/core/internal/sandbox/node/docker_live_test.go b/services/core/internal/sandbox/node/docker_live_test.go
index 5862b308c..13ab16b51 100644
--- a/services/core/internal/sandbox/node/docker_live_test.go
+++ b/services/core/internal/sandbox/node/docker_live_test.go
@@ -140,7 +140,7 @@ func TestDockerNodeTransportLifecycle(t *testing.T) {
 	}
 	running = false
 	wait(t, func() bool { return !hub.Online(id.NodeID) })
-	persisted, err := LoadIdentity(dir)
+	persisted, err := readIdentity(dir)
 	if err != nil || persisted.Credential != credential || persisted.Identity.NodeID != id.NodeID {
 		t.Fatal("node restart changed identity", err)
 	}
diff --git a/services/core/internal/sandbox/node/identity.go b/services/core/internal/sandbox/node/identity.go
index ec24276a7..3b556033e 100644
--- a/services/core/internal/sandbox/node/identity.go
+++ b/services/core/internal/sandbox/node/identity.go
@@ -140,14 +140,6 @@ func initIdentity(dir, coreURL string, identity Identity) (StoredIdentity, error
 	}
 	return stored, nil
 }
-func LoadIdentity(dir string) (StoredIdentity, error) {
-	release, err := lockDirectory(dir)
-	if err != nil {
-		return StoredIdentity{}, err
-	}
-	defer release()
-	return readIdentity(dir)
-}
 
 func endpoint(raw, path string) (string, error) {
 	u, err := url.Parse(raw)
diff --git a/services/core/internal/sandbox/node/node_test.go b/services/core/internal/sandbox/node/node_test.go
index 977d00c89..aab23036f 100644
--- a/services/core/internal/sandbox/node/node_test.go
+++ b/services/core/internal/sandbox/node/node_test.go
@@ -120,7 +120,8 @@ func TestLostCreateResponseDoesNotReplayAndReconnectSerializesCleanup(t *testing
 		}
 	}()
 	wait(t, func() bool { return hub.Online(id.NodeID) })
-	if _, err := LoadIdentity(dir); err == nil {
+	if release, err := lockDirectory(dir); err == nil {
+		release()
 		t.Fatal("running node did not retain lifetime identity lock")
 	}
 	r := reference()
@@ -218,7 +219,7 @@ func TestAgentRejectsDuplicateSequenceAndRetainsEpoch(t *testing.T) {
 	if reads != 1 {
 		t.Fatalf("replayed operation %d", reads)
 	}
-	persisted, e := LoadIdentity(dir)
+	persisted, e := readIdentity(dir)
 	if e != nil || persisted.OwnerEpoch != 9 {
 		t.Fatalf("epoch not retained: %+v %v", persisted.Identity, e)
 	}
diff --git a/services/core/internal/sandbox/node/recovery_test.go b/services/core/internal/sandbox/node/recovery_test.go
index 23ba863e3..d150b6422 100644
--- a/services/core/internal/sandbox/node/recovery_test.go
+++ b/services/core/internal/sandbox/node/recovery_test.go
@@ -68,7 +68,7 @@ func TestCoreRestartFencesOldConnectionAndNodeRestartKeepsIdentity(t *testing.T)
 		t.Fatal(err)
 	}
 	wait(t, func() bool { return !second.Online(id.NodeID) })
-	persisted, err := LoadIdentity(dir)
+	persisted, err := readIdentity(dir)
 	if err != nil || persisted.OwnerEpoch != 5 || persisted.Credential != credential {
 		t.Fatal("restart identity changed")
 	}
@@ -264,7 +264,7 @@ func TestCorruptOrMismatchedIdentityNeverRotates(t *testing.T) {
 	if _, err = InitIdentity(dir, stored.CoreURL, mismatch); err == nil {
 		t.Fatal("adopted wrong backend")
 	}
-	original, err := LoadIdentity(dir)
+	original, err := readIdentity(dir)
 	if err != nil || original.Credential != stored.Credential {
 		t.Fatal("credential rotated")
 	}
@@ -274,10 +274,4 @@ func TestCorruptOrMismatchedIdentityNeverRotates(t *testing.T) {
 	if _, err = InitIdentity(dir, stored.CoreURL, id); err == nil {
 		t.Fatal("corrupt identity replaced")
 	}
-	if err = os.Remove(filepath.Join(dir, "identity.json")); err != nil {
-		t.Fatal(err)
-	}
-	if _, err = LoadIdentity(dir); err == nil {
-		t.Fatal("missing identity recreated by load")
-	}
 }
diff --git a/services/core/tests/integration/mcode_public_native_test.go b/services/core/tests/integration/mcode_public_native_test.go
index 85ed9fca6..f592fc60e 100644
--- a/services/core/tests/integration/mcode_public_native_test.go
+++ b/services/core/tests/integration/mcode_public_native_test.go
@@ -132,7 +132,7 @@ func startNativeEngineDaemon(t *testing.T, h *dispatchHarness, home, binary, eng
 	}
 	old, _ := h.registry.LookupDevice(h.device.ID)
 	cmd := exec.Command(binary, "connect", "--profile", "execution")
-	cmd.Env = append(os.Environ(), "OAC_RUNTIME_HOME="+home, "OAC_RUNTIME_MCODE_AGENTS_API=1")
+	cmd.Env = append(os.Environ(), "OAC_RUNTIME_HOME="+home)
 	cmd.Stdout, cmd.Stderr = log, log
 	if err = cmd.Start(); err != nil {
 		log.Close()
diff --git a/services/core/tests/official_client.py b/services/core/tests/official_client.py
index 4a277a98d..196fc9a0f 100644
--- a/services/core/tests/official_client.py
+++ b/services/core/tests/official_client.py
@@ -18,7 +18,7 @@
 sys.dont_write_bytecode = True
 
 import httpx2
-from jsonschema import Draft4Validator
+from official_schema import ResponseValidator
 from official_items import verify_items
 from official_agents import verify_agents
 from official_vaults import verify_vaults, verify_vault_recovery
@@ -38,47 +38,12 @@
 from official_source_file_list import verify_source_file_list, verify_source_file_list_recovery
 from official_diagnostics import finish_server
 from openai import AuthenticationError, BadRequestError, ConflictError, InternalServerError, NotFoundError, OpenAI
-import yaml
 
 
-def nullable_schema(value):
-    """Translate Swagger 2's nullable extension for JSON Schema validation."""
-    if isinstance(value, list):
-        return [nullable_schema(item) for item in value]
-    if not isinstance(value, dict):
-        return value
-    converted = {key: nullable_schema(item) for key, item in value.items() if key != "x-nullable"}
-    return {"anyOf": [{"type": "null"}, converted]} if value.get("x-nullable") else converted
-
 
 def main():
     root = Path(__file__).resolve().parents[3]
-    contract = nullable_schema(yaml.safe_load((root / "contracts/agents-api/openapi.yaml").read_text()))
-
-    def validate_response(response):
-        response.read()
-        path = response.request.url.path.removeprefix("/v1")
-        if path.startswith("/agents/sessions/"):
-            suffix = path.split("/")[4:]
-            path = "/agents/sessions/{session_id}"
-            if suffix and suffix[0] == "turns":
-                path += "/turns" + ("/{turn_id}" if len(suffix) > 1 else "")
-            elif suffix and suffix[0] in ("items", "events"):
-                path += "/" + suffix[0]
-        elif path.startswith("/vaults/"):
-            suffix = path.split("/")[3:]
-            path = "/vaults/{vault_id}"
-            if suffix and suffix[0] == "credentials":
-                path += "/credentials" + ("/{credential_id}" if len(suffix) > 1 else "")
-        elif path.startswith("/agents/") and path != "/agents/sessions":
-            path = "/agents/{agent_id}"
-        elif path.startswith("/files/"):
-            path = "/files/{file_id}/content" if path.endswith("/content") else "/files/{file_id}"
-        if path.endswith("/events") and response.status_code == 202:
-            assert response.content == b""
-            return
-        schema = contract["paths"][path][response.request.method.lower()]["responses"][str(response.status_code)]["schema"]
-        Draft4Validator({"definitions": contract["definitions"], **schema}).validate(response.json())
+    validate_response = ResponseValidator(root / "contracts/agents-api/openapi.yaml")
     pin = json.loads((root / "contracts/agents-api/upstream.json").read_text())
     distribution = importlib.metadata.distribution("openai")
     source = json.loads(distribution.read_text("direct_url.json") or "{}")
diff --git a/services/core/tests/official_schema.py b/services/core/tests/official_schema.py
new file mode 100644
index 000000000..6bc6b64c8
--- /dev/null
+++ b/services/core/tests/official_schema.py
@@ -0,0 +1,41 @@
+"""Validate HTTP responses against the pinned OpenAPI 3.1 contract."""
+
+import json
+import re
+
+from jsonschema import Draft202012Validator
+
+
+class ResponseValidator:
+    def __init__(self, path):
+        self.contract = json.loads(path.read_text())
+        self.routes = [(re.compile("^" + re.sub(r"\{[^}]+\}", "[^/]+", route) + "$"), methods)
+                       for route, methods in self.contract["paths"].items()]
+        # Existing service differences are recorded in the contract coverage ledger.
+        # Keep these test-only adjustments local; the published schema stays official.
+        schemas = self.contract["components"]["schemas"]
+        for name, fields in {"ErrorBodyResource": ("code",), "ListFilesResponse": ("first_id", "last_id"),
+                             "OpenAIFile": ("expires_at", "status_details")}.items():
+            for field in fields:
+                schema = schemas[name]["properties"][field]
+                schema["type"] = [schema["type"], "null"]
+
+    def __call__(self, response):
+        response.read()
+        path = response.request.url.path.removeprefix("/v1")
+        methods = self.contract["paths"].get(path)
+        if methods is None:
+            methods = next(methods for pattern, methods in self.routes if pattern.fullmatch(path))
+        responses = methods[response.request.method.lower()]["responses"]
+        status = str(response.status_code)
+        if status not in responses and path.startswith(("/files", "/skills")) and response.status_code >= 400:
+            # These upstream operations omit error responses; validate their shared error body.
+            schema = {"$ref": "#/components/schemas/ErrorResponse"}
+        else:
+            content = responses[status].get("content")
+            if not content:
+                assert response.content == b""
+                return
+            media = response.headers["content-type"].split(";", 1)[0]
+            schema = content[media]["schema"]
+        Draft202012Validator({"components": self.contract["components"], **schema}).validate(response.json())
diff --git a/services/core/tests/official_schema_test.py b/services/core/tests/official_schema_test.py
new file mode 100644
index 000000000..0187d8a25
--- /dev/null
+++ b/services/core/tests/official_schema_test.py
@@ -0,0 +1,80 @@
+"""Keep response validation strict when consuming the official OpenAPI format."""
+
+import json
+import subprocess
+import tempfile
+from pathlib import Path
+import unittest
+
+import httpx2
+from jsonschema import Draft202012Validator, ValidationError
+from official_schema import ResponseValidator
+
+
+class ResponseSchemaTests(unittest.TestCase):
+    def setUp(self):
+        self.validator = ResponseValidator(Path(__file__).resolve().parents[3] / "contracts/agents-api/openapi.yaml")
+
+    def response(self, path, body, status=200, method="GET"):
+        response = httpx2.Response(status, json=body, request=httpx2.Request(method, "http://localhost/v1" + path))
+        self.validator(response)
+
+    def test_static_session_route_and_nullable_empty_page(self):
+        body = {"object": "list", "data": [], "first_id": None, "last_id": None, "has_more": False}
+        self.response("/agents/sessions", body)
+        self.response("/files", body)
+        with self.assertRaises(ValidationError):
+            self.response("/files", {**body, "has_more": "false"})
+        with self.assertRaises(ValidationError):
+            self.response("/agents/sessions", {key: value for key, value in body.items() if key != "data"})
+
+    def test_declared_and_shared_error_responses(self):
+        body = {"error": {"message": "Invalid key", "type": "invalid_request_error", "code": None, "param": None}}
+        self.response("/agents/agent_1", body, 401)
+        self.response("/files/file_1", body, 404)
+        with self.assertRaises(ValidationError):
+            self.response("/files/file_1", {"error": "missing"}, 404)
+        with self.assertRaises(KeyError):
+            self.response("/agents/agent_1", body, 418)
+
+    def test_file_nulls_do_not_relax_other_fields(self):
+        body = {"id": "file_1", "object": "file", "bytes": 0, "created_at": 1, "filename": "test.txt",
+                "purpose": "user_data", "status": "processed", "expires_at": None, "status_details": None}
+        self.response("/files/file_1", body)
+        with self.assertRaises(ValidationError):
+            self.response("/files/file_1", {**body, "bytes": None})
+        with self.assertRaises(ValidationError):
+            self.response("/files/file_1", {**body, "purpose": "unknown"})
+
+    def test_generated_union_serialization_matches_official_variants(self):
+        root = Path(__file__).resolve().parents[3]
+        artifacts = Path.home() / ".oac/tests"
+        artifacts.mkdir(parents=True, exist_ok=True)
+        with tempfile.TemporaryDirectory(dir=artifacts) as directory:
+            program = Path(directory) / "main.go"
+            program.write_text('''package main
+import ("encoding/json"; "os"; v1 "github.com/MiniMax-AI/OpenAgentCore/contracts/agents-api/v1")
+func main() {
+    query := "reference"
+    values := []v1.WebSearchAction{
+        {Type: "search", Query: &query}, {Type: "open_page", Query: &query},
+        {Type: "find_in_page"}, {Type: "other", Query: &query},
+    }
+    if err := json.NewEncoder(os.Stdout).Encode(values); err != nil { panic(err) }
+}
+''')
+            payload = subprocess.check_output(["go", "run", str(program)], cwd=root, timeout=120)
+        official = json.loads((root / "contracts/agents-api/upstream/openapi.json").read_text())
+        validator = Draft202012Validator({"components": official["components"], "$ref": "#/components/schemas/WebSearchActionResource"})
+        for action in json.loads(payload):
+            validator.validate(action)
+
+    def test_declared_bodyless_response(self):
+        response = httpx2.Response(202, request=httpx2.Request("POST", "http://localhost/v1/agents/sessions/session_1/events"))
+        self.validator(response)
+        with self.assertRaises(AssertionError):
+            self.response("/agents/sessions/session_1/events", {}, 202, "POST")
+
+
+if __name__ == "__main__":
+    unittest.main()
diff --git a/services/core/tests/requirements.txt b/services/core/tests/requirements.txt
index d37efa74c..12aab9370 100644
--- a/services/core/tests/requirements.txt
+++ b/services/core/tests/requirements.txt
@@ -1,2 +1 @@
 jsonschema==4.25.1
-PyYAML==6.0.2
diff --git a/services/core/tools/e2b-provider/Build.Dockerfile b/services/core/tools/e2b-provider/Build.Dockerfile
index 446fa4cd2..84083cefd 100644
--- a/services/core/tools/e2b-provider/Build.Dockerfile
+++ b/services/core/tools/e2b-provider/Build.Dockerfile
@@ -1,5 +1,5 @@
 # Fixed CPython and glibc baseline shared by native Core and the Debian Core image.
-FROM python:3.12.12-slim-bookworm@sha256:2986c55feb36e6cae00fa1fefb454283e4b33f35e75ff8bdd123b134130be301
+FROM python:3.12.12-slim-bookworm@sha256:593bd06efe90efa80dc4eee3948be7c0fde4134606dd40d8dd8dbcade98e669c
 RUN apt-get update && apt-get install -y --no-install-recommends binutils \
     && rm -rf /var/lib/apt/lists/*
 ENTRYPOINT ["python3", "/source/services/core/tools/e2b-provider/build.py"]
diff --git a/services/core/tools/e2b-provider/build.py b/services/core/tools/e2b-provider/build.py
index 8d6f9badf..8b69302d5 100644
--- a/services/core/tools/e2b-provider/build.py
+++ b/services/core/tools/e2b-provider/build.py
@@ -16,7 +16,7 @@
 SOURCE = Path('/source/services/core/tools/e2b-provider')
 OUTPUT = Path('/output')
 NAME = 'oac-e2b-provider'
-BASE = 'python:3.12.12-slim-bookworm@sha256:2986c55feb36e6cae00fa1fefb454283e4b33f35e75ff8bdd123b134130be301'
+BASE = next(line.split()[1] for line in (SOURCE / 'Build.Dockerfile').read_text().splitlines() if line.startswith('FROM '))
 
 
 def checked(args, **options):
@@ -24,8 +24,9 @@ def checked(args, **options):
 
 
 def main():
-    if sys.version_info[:3] != (3, 12, 12) or platform.system() != 'Linux' or platform.machine() != 'x86_64':
-        raise RuntimeError('Use the pinned Linux amd64 build image')
+    if sys.version_info[:3] != (3, 12, 12) or platform.system() != 'Linux' or platform.machine() not in ('x86_64', 'aarch64'):
+        raise RuntimeError('Use the pinned Linux amd64 or arm64 build image')
+    architecture = {'x86_64': 'amd64', 'aarch64': 'arm64'}[platform.machine()]
     os.umask(0o022)
     with tempfile.TemporaryDirectory(prefix='e2b-build-') as temporary:
         root = Path(temporary)
@@ -56,7 +57,7 @@ def main():
         if report != {'Version': PROTOCOL_VERSION, 'SDKVersion': SDK_VERSION}:
             raise RuntimeError('Unexpected helper readiness report')
         manifest = {'format_version': 1, 'sdk_version': report['SDKVersion'], 'python_version': platform.python_version(),
-                    'platform': 'linux-amd64', 'libc': platform.libc_ver(), 'build_image': BASE,
+                    'platform': 'linux-' + architecture, 'libc': platform.libc_ver(), 'build_image': BASE,
                     'entrypoint': NAME,
                     'source_sha256': {file.name: hashlib.sha256(file.read_bytes()).hexdigest()
                                       for file in sorted(source.glob('*.py'))},
@@ -66,7 +67,7 @@ def main():
             if entry.is_symlink() or not (entry.is_file() or entry.is_dir()):
                 raise RuntimeError('Unsupported artifact entry')
             entry.chmod(0o755 if entry.is_dir() or entry.stat().st_mode & 0o111 else 0o644)
-        destination = OUTPUT / (NAME + '-linux-amd64.tar.gz')
+        destination = OUTPUT / (NAME + '-linux-' + architecture + '.tar.gz')
         with tarfile.open(destination, 'w:gz', dereference=True) as archive:
             archive.add(exported, arcname=NAME)
         checksum = hashlib.sha256(destination.read_bytes()).hexdigest()
diff --git a/services/web/Dockerfile b/services/web/Dockerfile
index 642383d04..cea7c0df0 100644
--- a/services/web/Dockerfile
+++ b/services/web/Dockerfile
@@ -1,5 +1,5 @@
 # The build context contains only oac-web and the existing Web dist.
-FROM gcr.io/distroless/static-debian13:nonroot@sha256:e754765ad9e167b0677b41c617fd44afb7b9818a477f48f17bda08e12cfb98cb
+FROM gcr.io/distroless/static-debian13:nonroot@sha256:e2e927ec666bae08560abb3c55d0659eceabb657f56b6782ab500a9fc7f555e3
 
 COPY --chmod=0555 oac-web /usr/local/bin/oac-web
 COPY dist /www