feat(delegate): drive the public @uipath/delegate-stdio host [PILOT-7854]

.env.example

@@ -89,36 +89,33 @@ LOG_TO_FILE=false  # Set to true to enable file logging
 # CODER_EVAL_REMEDIATE_HOME_PLUGINS=0
 
 # Delegate agent settings (UiPath Autopilot's Delegate agent, requires Node.js
-# on PATH plus `npm install @uipath/delegate-sdk` — a genuinely public package,
-# no token needed). See docs/agents/DELEGATE.md.
+# on PATH plus `npm install -g @uipath/delegate-stdio`, a release that accepts the
+# `auth` init option). coder_eval finds the install itself. See docs/agents/DELEGATE.md.
 #
-# DELEGATE_SDK_NODE_MODULES / DELEGATE_SDK_PATH — override the auto-located
-# install (ancestor-walk from cwd, plus home); set at most one.
-# DELEGATE_SDK_NODE_MODULES="/path/to/install/root"
-# DELEGATE_SDK_PATH="/path/to/node_modules/@uipath/delegate-sdk/dist/index.mjs"
-#
-# DELEGATE_ENV — cloud environment slug (alpha/staging/production/localhost),
-# used to derive the backend URL from the auth record's org/tenant slugs.
+# DELEGATE_ENV — cloud environment slug (alpha/staging/production),
+# used to derive the backend URL from the org/tenant slugs.
 # DELEGATE_ENV="alpha"
 #
 # DELEGATE_BACKEND_URL — pin the full agent-service URL directly instead
 # (wins over DELEGATE_ENV when both are set).
 # DELEGATE_BACKEND_URL="https://cloud.uipath.com/<org>/<tenant>/delegate_"
 #
-# Auth: either the token set below, or a prior `delegate-sdk`/`delegate-cli`
-# login that wrote ~/.aria/sdk-auth.json (read by the Node host itself, not
-# by coder_eval). Each var also accepts a DELEGATE_-namespaced spelling
-# (DELEGATE_AUTH_TOKEN, DELEGATE_TENANT_ID, ...), checked first -- prefer that
-# spelling in a shared environment, since the bare names collide with what
-# other tooling (npm, Vault, Terraform) commonly exports.
-# AUTH_TOKEN="..."
-# TENANT_ID="..."
-# ORG_ID="..."
+# Auth: either the token set below, or a prior `delegate-cli login`
+# that wrote ~/.aria/sdk-auth.json (read by the Node host itself, not
+# by coder_eval). coder_eval sends these values to the host as its `auth`
+# init option, so the token stays out of the environment that the agent's
+# shell tools inherit. Each var also accepts the bare spelling (AUTH_TOKEN,
+# TENANT_ID, ORG_ID, ORG_SLUG, TENANT_SLUG) as a fallback -- prefer the
+# DELEGATE_ spelling in a shared environment, since the bare names collide
+# with what other tooling (npm, Vault, Terraform) commonly exports.
+# DELEGATE_AUTH_TOKEN="..."
+# DELEGATE_TENANT_ID="..."
+# DELEGATE_ORG_ID="..."
 # With DELEGATE_ENV (not DELEGATE_BACKEND_URL) also set these two -- the
 # human-readable org/tenant names, not the GUIDs above -- or init fails with
-# "--env alpha needs org/tenant slugs". See docs/agents/DELEGATE.md.
-# ORG_SLUG="..."
-# TENANT_SLUG="..."
+# 'env="alpha" requires org/tenant slugs'. See docs/agents/DELEGATE.md.
+# DELEGATE_ORG_SLUG="..."
+# DELEGATE_TENANT_SLUG="..."
 
 # Usage Telemetry (anonymous; on by default).
 # Disable entirely:

.github/workflows/pr-checks.yml

@@ -1175,8 +1175,8 @@ jobs:
           retention-days: 7
 
   delegate-live-tests:
-    # Live Delegate e2e: spawns the real Node host (agents/delegate/delegate_host.mjs)
-    # wrapping the public @uipath/delegate-sdk against a real UiPath backend. Runs on
+    # Live Delegate e2e: spawns the real Node host from the public
+    # @uipath/delegate-stdio package against a real UiPath backend. Runs on
     # every PR/push like the other live-test jobs (codex-live-tests, byoa-live-tests)
     # now that the DELEGATE_ROPC_* secrets are provisioned; the presence-check gate
     # below skips cleanly ONLY on a fork PR (no secrets available there) and fails
@@ -1187,10 +1187,10 @@ jobs:
     # and implemented in coder_eval_uipath/eval_runner/scripts/ci/refresh-auth.sh —
     # rather than a long-lived AUTH_TOKEN secret, since a minted token's ~1h TTL
     # would make a static secret stale between runs. A dedicated bot user's
-    # username/password is the durable credential; the Delegate SDK reads the
-    # minted token straight from AUTH_TOKEN/TENANT_ID/ORG_ID (see
-    # docs/agents/DELEGATE.md), so no sdk-auth.json or client-secret refresh chain
-    # is needed here.
+    # username/password is the durable credential; the agent sends the minted
+    # token (DELEGATE_AUTH_TOKEN, with DELEGATE_TENANT_ID / DELEGATE_ORG_ID) to the
+    # host as its `auth` init option (see docs/agents/DELEGATE.md), so no
+    # sdk-auth.json or client-secret refresh chain is needed here.
     name: Delegate Live E2E (ROPC)
     runs-on: uipath-ubuntu-24.04
     timeout-minutes: 15
@@ -1260,7 +1260,7 @@ jobs:
         if: steps.gate.outputs.present == 'true'
         run: uv sync --frozen --extra dev
 
-      - name: Install @uipath/delegate-sdk (public npm, no token needed)
+      - name: Install @uipath/delegate-stdio (public npm, no token needed)
         if: steps.gate.outputs.present == 'true'
         working-directory: src/coder_eval/agents/delegate
         # --safe-chain-skip-minimum-package-age (not a growing exclusion-list entry
@@ -1372,17 +1372,15 @@ jobs:
       - name: Run fizzbuzz delegate task (assert PASS)
         if: steps.gate.outputs.present == 'true'
         env:
-          DELEGATE_SDK_NODE_MODULES: ${{ github.workspace }}/src/coder_eval/agents/delegate
           DELEGATE_ENV: ${{ github.event.inputs.delegate_uipath_env || 'alpha' }}
-          AUTH_TOKEN: ${{ steps.ropc.outputs.access_token }}
-          TENANT_ID: ${{ secrets.DELEGATE_TENANT_ID }}
-          ORG_ID: ${{ secrets.DELEGATE_ORG_ID }}
-          # Forwarded into `auth.organizationName` / `auth.tenantName` by
-          # DelegateAgent._build_init_options (see .claude/notes/agents.md §
-          # Delegate agent) — needed alongside the GUIDs above whenever
-          # `environment` (rather than `backendUrl`) resolves the backend.
-          ORG_SLUG: ${{ secrets.DELEGATE_ORG_SLUG }}
-          TENANT_SLUG: ${{ secrets.DELEGATE_TENANT_SLUG }}
+          DELEGATE_AUTH_TOKEN: ${{ steps.ropc.outputs.access_token }}
+          DELEGATE_TENANT_ID: ${{ secrets.DELEGATE_TENANT_ID }}
+          DELEGATE_ORG_ID: ${{ secrets.DELEGATE_ORG_ID }}
+          # Needed alongside the GUIDs above whenever DELEGATE_ENV (rather than
+          # DELEGATE_BACKEND_URL) resolves the backend; the agent sends all five to
+          # the host as its `auth` init option (see .claude/notes/agents.md § Delegate agent).
+          DELEGATE_ORG_SLUG: ${{ secrets.DELEGATE_ORG_SLUG }}
+          DELEGATE_TENANT_SLUG: ${{ secrets.DELEGATE_TENANT_SLUG }}
         run: .venv/bin/coder-eval run tasks/delegate/fizzbuzz_delegate.yaml --run-dir runs/delegate-live
 
       - name: Verify Delegate live run PASSED
@@ -1405,13 +1403,12 @@ jobs:
       - name: Run Delegate live unit tests (assert PASS)
         if: steps.gate.outputs.present == 'true'
         env:
-          DELEGATE_SDK_NODE_MODULES: ${{ github.workspace }}/src/coder_eval/agents/delegate
           DELEGATE_ENV: ${{ github.event.inputs.delegate_uipath_env || 'alpha' }}
-          AUTH_TOKEN: ${{ steps.ropc.outputs.access_token }}
-          TENANT_ID: ${{ secrets.DELEGATE_TENANT_ID }}
-          ORG_ID: ${{ secrets.DELEGATE_ORG_ID }}
-          ORG_SLUG: ${{ secrets.DELEGATE_ORG_SLUG }}
-          TENANT_SLUG: ${{ secrets.DELEGATE_TENANT_SLUG }}
+          DELEGATE_AUTH_TOKEN: ${{ steps.ropc.outputs.access_token }}
+          DELEGATE_TENANT_ID: ${{ secrets.DELEGATE_TENANT_ID }}
+          DELEGATE_ORG_ID: ${{ secrets.DELEGATE_ORG_ID }}
+          DELEGATE_ORG_SLUG: ${{ secrets.DELEGATE_ORG_SLUG }}
+          DELEGATE_TENANT_SLUG: ${{ secrets.DELEGATE_TENANT_SLUG }}
         run: |
           mkdir -p tmp
           .venv/bin/pytest tests/test_delegate_agent_live.py \

docs/REPORT_SCHEMA.md

@@ -139,8 +139,10 @@ The authoritative per-replicate record.
 **Errors** (populated on failure): `error_message`, `error_details`,
 `error_log_tail` (carries the Docker build-log tail for `BUILD_FAILED`).
 
-**Config/environment:** `environment_info`, `agent_config`, `sdk_options` (raw
-`ClaudeAgentOptions` dump), `sandbox_path`, `task_config`
+**Config/environment:** `environment_info`, `agent_config`, `sdk_options` (the
+options the agent sent to its SDK; the shape depends on the agent: a raw
+`ClaudeAgentOptions` dump on Claude Code, the host's `init` options with
+credentials redacted on Delegate, `null` on the other agents), `sandbox_path`, `task_config`
 (`{resolved, source_yaml, source_file, lineage}` — `lineage` maps each field to
 `{value, source, source_detail}` so you can trace which config layer set it).
 `environment_info.system_prompt_semantics` (`"append"` / `"replace"` /

docs/TASK_DEFINITION_GUIDE.md

@@ -170,18 +170,23 @@ agent:
     - "Write"
     - "Bash"
   model: "claude-sonnet-5"            # Optional: specific model
-  sdk_options:                        # Optional: Claude Code SDK pass-through
-    effort: high                      # any non-framework-managed ClaudeAgentOptions field
+  sdk_options:                        # Optional: agent SDK pass-through (keys depend on `type`)
+    effort: high                      # claude-code: any non-framework-managed ClaudeAgentOptions field
 ```
 
-**`sdk_options`** is a typed pass-through dict for Claude Code SDK
-`ClaudeAgentOptions` fields that Coder Eval doesn't own directly. Keys are
-validated against the SDK's dataclass at YAML load; framework-managed keys
-(`model`, `allowed_tools`, `permission_mode`, `hooks`, `mcp_servers`, …)
-are rejected. Deep-merged across the 5-layer config chain. Override via
-CLI with the repeatable `-D agent.sdk_options.KEY=VALUE`.
-**Requires `type: "claude-code"`** to function; on other agent types it raises
-an error.
+**`sdk_options`** is a pass-through dict for the agent SDK options that Coder
+Eval doesn't own directly. Only an agent type whose config declares the field
+accepts it; on another agent type it raises an error. Each agent type
+validates its own keys at YAML load:
+
+- `claude-code` — `ClaudeAgentOptions` fields, validated against the SDK's
+  dataclass; framework-managed keys (`model`, `allowed_tools`,
+  `permission_mode`, `hooks`, `mcp_servers`, …) are rejected. See the
+  [Claude Code guide](agents/CLAUDE_CODE.md).
+- `delegate` — only `effort`. See the [Delegate guide](agents/DELEGATE.md).
+
+Deep-merged across the 5-layer config chain. Override via CLI with the
+repeatable `-D agent.sdk_options.KEY=VALUE`.
 
 **Permission Modes:**
 - `default` — Default permission handling

docs/USER_GUIDE.md

@@ -429,7 +429,7 @@ Set these in `.env` (copy from `.env.example`).
 | `BEDROCK_SMALL_MODEL` | No | Cross-region Bedrock small/fast model ID |
 | `CODEX_API_KEY` / `CODEX_BASE_URL` / `CODEX_MODEL` / `CODEX_API_VERSION` | For Codex | Codex agent auth & endpoint routing — see [Codex Agent Guide](agents/CODEX.md#endpoint-routing). |
 | `GEMINI_API_KEY` / `ANTIGRAVITY_MODEL` | For Antigravity | Antigravity (Gemini) agent auth & model — see [Antigravity Agent Guide](agents/ANTIGRAVITY.md#setup). |
-| `DELEGATE_ENV` / `DELEGATE_BACKEND_URL` / `AUTH_TOKEN` / `TENANT_ID` / `ORG_ID` / `ORG_SLUG` / `TENANT_SLUG` / `DELEGATE_SDK_NODE_MODULES` / `DELEGATE_SDK_PATH` | For Delegate | Delegate agent backend routing, auth & SDK install location — see [Delegate Agent Guide](agents/DELEGATE.md#setup). |
+| `DELEGATE_ENV` / `DELEGATE_BACKEND_URL` / `DELEGATE_AUTH_TOKEN` / `DELEGATE_TENANT_ID` / `DELEGATE_ORG_ID` / `DELEGATE_ORG_SLUG` / `DELEGATE_TENANT_SLUG` | For Delegate | Delegate agent backend routing & auth — see [Delegate Agent Guide](agents/DELEGATE.md#setup). |
 | `UIPATH_PLUGIN_MARKETPLACE_DIR` | No | Conventional base directory for local plugins. Not special-cased by the framework: **any** `$VAR` / `${VAR}` referenced in a plugin `path` is expanded from the environment, so a plugin path like `$UIPATH_PLUGIN_MARKETPLACE_DIR/my-plugin` resolves against this variable. (An undefined variable in a plugin path logs a warning.) |
 | `PLUGIN_TOOLS_DIR` | No | A *separate* mechanism from the above: the canonical `node_modules/@uipath` directory used to pin UiPath CLI plugin discovery (not path substitution). When unset, the sandbox auto-derives it from the resolved `uip` binary. |
 | `CODER_EVAL_REMEDIATE_HOME_PLUGINS` | No | **DESTRUCTIVE.** Truthy deletes `$HOME/node_modules/@uipath` at sandbox setup to clear sibling-task pollution on dedicated eval hosts. Off by default; do **not** enable on developer workstations. |