fast-agent 0.10.40: GPT-6.1 Sol (responses, codexresponses, copilot), openai 3.21.0

docs/docs/_generated/current_models_codexresponses.md

@@ -1,7 +1,8 @@
 | Model string or alias | Resolves to / equivalent | Notes |
 | --- | --- | --- |
 | `astra` | `codexresponses.gpt-6-astra?reasoning=medium` | — |
-| `sol` | `codexresponses.gpt-6-sol?reasoning=medium` | — |
+| `sol` | `codexresponses.gpt-6.1-sol?reasoning=medium` | — |
+| `sol6` | `codexresponses.gpt-6-sol?reasoning=medium` | — |
 | `luna` | `codexresponses.gpt-6-luna?reasoning=medium` | Fast |
 | `sol56` | `codexresponses.gpt-5.6-sol?reasoning=high` | — |
 | `terra` | `codexresponses.gpt-5.6-terra?reasoning=high` | — |

docs/docs/_generated/current_models_responses.md

@@ -1,6 +1,7 @@
 | Model string or alias | Resolves to / equivalent | Notes |
 | --- | --- | --- |
 | `gpt-6-astra` | `responses.gpt-6-astra?reasoning=medium` | — |
+| `gpt-6.1-sol` | `responses.gpt-6.1-sol?reasoning=medium` | — |
 | `gpt-6-sol` | `responses.gpt-6-sol?reasoning=medium` | — |
 | `gpt-6-luna` | `responses.gpt-6-luna?reasoning=medium` | Fast |
 | `gpt-5.6-sol` | `responses.gpt-5.6-sol?reasoning=medium` | — |

docs/docs/_generated/model_aliases_anthropic.md

@@ -1,6 +1,6 @@
 | Model Alias | Maps to | Model Alias | Maps to |
 | --- | --- | --- | --- |
-| `claude` | `claude-sonnet-5` | `claude-sonnet-5` | `claude-sonnet-5` |
+| `claude` | `claude-sonnet-5-5` | `claude-sonnet-5-5` | `claude-sonnet-5-5` |
 | `claude-3-5-haiku` | `claude-3-5-haiku` | `fable` | `claude-fable-5` |
 | `claude-3-5-haiku-latest` | `claude-3-5-haiku-latest` | `fable5` | `claude-fable-5` |
 | `claude-fable-5` | `claude-fable-5` | `haiku` | `claude-haiku-4-5` |
@@ -12,8 +12,9 @@
 | `claude-opus-4-6` | `claude-opus-4-6` | `opus48` | `claude-opus-4-8` |
 | `claude-opus-4-7` | `claude-opus-4-7` | `opus5` | `claude-opus-5` |
 | `claude-opus-4-8` | `claude-opus-4-8` | `opus55` | `claude-opus-5-5` |
-| `claude-opus-5` | `claude-opus-5` | `sonnet` | `claude-sonnet-5` |
+| `claude-opus-5` | `claude-opus-5` | `sonnet` | `claude-sonnet-5-5` |
 | `claude-opus-5-5` | `claude-opus-5-5` | `sonnet4` | `claude-sonnet-4-6` |
 | `claude-sonnet-4-0` | `claude-sonnet-4-0` | `sonnet46` | `claude-sonnet-4-6` |
 | `claude-sonnet-4-5` | `claude-sonnet-4-5` | `sonnet5` | `claude-sonnet-5` |
-| `claude-sonnet-4-6` | `claude-sonnet-4-6` |  |  |
+| `claude-sonnet-4-6` | `claude-sonnet-4-6` | `sonnet55` | `claude-sonnet-5-5` |
+| `claude-sonnet-5` | `claude-sonnet-5` |  |  |

docs/docs/_generated/model_aliases_codexresponses.md

@@ -9,6 +9,7 @@
 | `gpt-5.3-codex-spark` | `gpt-5.3-codex-spark` |
 | `luna` | `codexresponses.gpt-6-luna?reasoning=medium` |
 | `luna56` | `codexresponses.gpt-5.6-luna?reasoning=medium` |
-| `sol` | `codexresponses.gpt-6-sol?reasoning=medium` |
+| `sol` | `codexresponses.gpt-6.1-sol?reasoning=medium` |
 | `sol56` | `codexresponses.gpt-5.6-sol?reasoning=high` |
+| `sol6` | `codexresponses.gpt-6-sol?reasoning=medium` |
 | `terra` | `codexresponses.gpt-5.6-terra?reasoning=high` |

docs/docs/_generated/model_aliases_hf.md

@@ -1,6 +1,6 @@
 | Model Alias | Maps to |
 | --- | --- |
-| `DeepSeek V4 Flash 0731 (baseten)` | `hf.deepseek-ai/DeepSeek-V4-Flash-0731:baseten?max_tokens=384000` |
+| `DeepSeek V4 Flash 0731 (baseten)` | `hf.deepseek-ai/DeepSeek-V4-Flash-0731:baseten` |
 | `DeepSeek V4 Flash 0731 (deepinfra)` | `hf.deepseek-ai/DeepSeek-V4-Flash-0731:deepinfra` |
 | `DeepSeek V4.1 Flash (novita)` | `hf.deepseek-ai/DeepSeek-V4.1-Flash:novita` |
 | `deepseek-ai/deepseek-v3.1` | `deepseek-ai/deepseek-v3.1` |
@@ -62,3 +62,5 @@
 | `qwen36` | `hf.Qwen/Qwen3.6-35B-A3B:deepinfra?temperature=0.6&top_p=0.95&top_k=20&min_p=0.0&presence_penalty=0.0&repetition_penalty=1.0&reasoning=on` |
 | `qwen36instruct` | `hf.Qwen/Qwen3.6-35B-A3B:deepinfra?temperature=0.7&top_p=0.8&top_k=20&min_p=0.0&presence_penalty=1.5&repetition_penalty=1.0&reasoning=off` |
 | `zai-org/glm-5.2` | `zai-org/glm-5.2` |
+| `zai-org/glm-5.3` | `zai-org/glm-5.3` |
+| `zai-org/glm-5.3-flash` | `zai-org/glm-5.3-flash` |

docs/docs/_generated/model_aliases_responses.md

@@ -21,6 +21,7 @@
 | `gpt-6-astra` | `responses.gpt-6-astra?reasoning=medium` |
 | `gpt-6-luna` | `responses.gpt-6-luna?reasoning=medium` |
 | `gpt-6-sol` | `responses.gpt-6-sol?reasoning=medium` |
+| `gpt-6.1-sol` | `responses.gpt-6.1-sol?reasoning=medium` |
 | `gpt51` | `responses.gpt-5.1` |
 | `gpt52` | `responses.gpt-5.2` |
 | `gpt54` | `responses.gpt-5.4` |
@@ -31,6 +32,7 @@
 | `gpt56-luna` | `responses.gpt-5.6-luna` |
 | `gpt56-sol` | `responses.gpt-5.6-sol` |
 | `gpt56-terra` | `responses.gpt-5.6-terra` |
+| `gpt61sol` | `responses.gpt-6.1-sol?reasoning=medium` |
 | `gpt6astra` | `responses.gpt-6-astra?reasoning=medium` |
 | `gpt6luna` | `responses.gpt-6-luna?reasoning=medium` |
 | `gpt6sol` | `responses.gpt-6-sol?reasoning=medium` |

docs/docs/_generated/model_aliases_xai.md

@@ -1,24 +1,13 @@
-| Model Alias | Maps to |
-| --- | --- |
-| `grok` | `xai.grok-4.7` |
-| `Grok 4.3` | `xai.grok-4.3` |
-| `Grok 4.5` | `xai.grok-4.5` |
-| `Grok 4.5 (X Search)` | `xai.grok-4.5?x_search=true` |
-| `Grok 4.6` | `xai.grok-4.6` |
-| `Grok 4.6 (X Search)` | `xai.grok-4.6?x_search=true` |
-| `Grok 4.7` | `xai.grok-4.7` |
-| `Grok 4.7 (X Search)` | `xai.grok-4.7?x_search=true` |
-| `Grok 4.7 Fast (OAuth)` | `xai.grok-4.7-build-fast` |
-| `Grok 4.7 Fast (X Search, OAuth)` | `xai.grok-4.7-build-fast?x_search=true` |
-| `grok-4.3` | `grok-4.3` |
-| `grok-4.5` | `grok-4.5` |
-| `grok-4.6` | `grok-4.6` |
-| `grok-4.7` | `grok-4.7` |
-| `grok-4.7-build-fast` | `grok-4.7-build-fast` |
-| `grok4` | `xai.grok-4.7` |
-| `grok43` | `xai.grok-4.3` |
-| `grok45` | `xai.grok-4.5` |
-| `grok46` | `xai.grok-4.6` |
-| `grok47` | `xai.grok-4.7` |
-| `grok47fast` | `xai.grok-4.7-build-fast` |
-| `grokfast` | `xai.grok-4.7-build-fast` |
+| Model Alias | Maps to | Model Alias | Maps to |
+| --- | --- | --- | --- |
+| `grok` | `xai.grok-4.7` | `grok-4.5` | `grok-4.5` |
+| `Grok 4.3` | `xai.grok-4.3` | `grok-4.6` | `grok-4.6` |
+| `Grok 4.5` | `xai.grok-4.5` | `grok-4.7` | `grok-4.7` |
+| `Grok 4.5 (X Search)` | `xai.grok-4.5?x_search=true` | `grok-4.7-build-fast` | `grok-4.7-build-fast` |
+| `Grok 4.6` | `xai.grok-4.6` | `grok4` | `xai.grok-4.7` |
+| `Grok 4.6 (X Search)` | `xai.grok-4.6?x_search=true` | `grok43` | `xai.grok-4.3` |
+| `Grok 4.7` | `xai.grok-4.7` | `grok45` | `xai.grok-4.5` |
+| `Grok 4.7 (X Search)` | `xai.grok-4.7?x_search=true` | `grok46` | `xai.grok-4.6` |
+| `Grok 4.7 Fast (OAuth)` | `xai.grok-4.7-build-fast` | `grok47` | `xai.grok-4.7` |
+| `Grok 4.7 Fast (X Search, OAuth)` | `xai.grok-4.7-build-fast?x_search=true` | `grok47fast` | `xai.grok-4.7-build-fast` |
+| `grok-4.3` | `grok-4.3` | `grokfast` | `xai.grok-4.7-build-fast` |

docs/docs/_generated/models_reference.md

@@ -23,7 +23,7 @@
 | `claude-sonnet-4-20250514` | `anthropic` | Text, Vision, Document | `tool_use` | budget: `low`, `medium`, `high`, `max`, `0`, `1024`, `16000`, `32000`, `off`<br>Example: `claude-sonnet-4-20250514?reasoning=1024` | — | `web_search` (web_search_20250305)<br>`web_fetch` (web_fetch_20250910) |
 | `claude-sonnet-4-5-20250929` | `anthropic` | Text, Vision, Document | `json` (schema) | budget: `low`, `medium`, `high`, `max`, `0`, `1024`, `16000`, `32000`, `off`<br>Example: `claude-sonnet-4-5-20250929?reasoning=1024` | — | `web_search` (web_search_20250305)<br>`web_fetch` (web_fetch_20250910) |
 | `claude-sonnet-4-5` | `anthropic` | Text, Vision, Document | `json` (schema) | budget: `low`, `medium`, `high`, `max`, `0`, `1024`, `16000`, `32000`, `off`<br>Example: `claude-sonnet-4-5?reasoning=1024` | — | `web_search` (web_search_20250305)<br>`web_fetch` (web_fetch_20250910) |
-| `claude` | `anthropic` | Text, Vision, Document | `json` (schema) | effort: `auto`, `low`, `medium`, `high`, `xhigh`, `max`, `off`<br>Example: `claude?reasoning=auto` | — | `web_search` (web_search_20260209)<br>`web_fetch` (web_fetch_20260209)<br>beta: `code-execution-web-tools-2026-02-09` |
+| `claude` | `anthropic` | Text, Vision, Document | `json` (schema) | effort: `auto`, `low`, `medium`, `high`, `xhigh`, `max`, `off`<br>Example: `claude?reasoning=high` | — | `web_search` (web_search_20260209)<br>`web_fetch` (web_fetch_20260209)<br>beta: `code-execution-web-tools-2026-02-09` |
 | `fable` | `anthropic` | Text, Vision, Document | `json` (schema) | effort: `auto`, `low`, `medium`, `high`, `xhigh`<br>Example: `fable?reasoning=auto` | — | `web_search` (web_search_20260209)<br>`web_fetch` (web_fetch_20260209)<br>beta: `code-execution-web-tools-2026-02-09` |
 | `haiku` | `anthropic` | Text, Vision, Document | `json` (schema) | budget: `low`, `medium`, `high`, `max`, `0`, `1024`, `16000`, `32000`, `off`<br>Example: `haiku?reasoning=1024` | — | `web_search` (web_search_20250305)<br>`web_fetch` (web_fetch_20250910) |
 | `opus46` | `anthropic` | Text, Vision, Document | `json` (schema) | effort: `auto`, `low`, `medium`, `high`, `max`, `off`<br>Example: `opus46?reasoning=auto` | — | `web_search` (web_search_20260209)<br>`web_fetch` (web_fetch_20260209)<br>beta: `code-execution-web-tools-2026-02-09` |
@@ -32,12 +32,14 @@
 | `opus5` | `anthropic` | Text, Vision, Document | `json` (schema) | effort: `auto`, `low`, `medium`, `high`, `xhigh`, `max`, `off`<br>Example: `opus5?reasoning=auto` | — | `web_search` (web_search_20260209)<br>beta: `code-execution-web-tools-2026-02-09` |
 | `opus` | `anthropic` | Text, Vision, Document | `json` (schema) | effort: `auto`, `low`, `medium`, `high`, `xhigh`, `max`<br>Example: `opus?reasoning=medium` | — | `web_search` (web_search_20260209)<br>beta: `code-execution-web-tools-2026-02-09` |
 | `sonnet4` | `anthropic` | Text, Vision, Document | `json` (schema) | effort: `auto`, `low`, `medium`, `high`, `max`, `off`<br>Example: `sonnet4?reasoning=auto` | — | `web_search` (web_search_20260209)<br>`web_fetch` (web_fetch_20260209)<br>beta: `code-execution-web-tools-2026-02-09` |
+| `sonnet5` | `anthropic` | Text, Vision, Document | `json` (schema) | effort: `auto`, `low`, `medium`, `high`, `xhigh`, `max`, `off`<br>Example: `sonnet5?reasoning=auto` | — | `web_search` (web_search_20260209)<br>`web_fetch` (web_fetch_20260209)<br>beta: `code-execution-web-tools-2026-02-09` |
 | `astra` | `codexresponses` | Text, Vision, Document | `json` (schema) | effort: `low`, `medium`, `high`, `xhigh`, `max`<br>Example: `astra?reasoning=medium` | `low`, `medium`, `high`<br>Example: `astra?verbosity=low` | — |
 | `codexspark` | `codexresponses` | Text | `json` (schema) | — | — | — |
 | `luna56` | `codexresponses` | Text, Vision, Document | `json` (schema) | effort: `none`, `low`, `medium`, `high`, `xhigh`, `max`, `off`<br>Example: `luna56?reasoning=high` | `low`, `medium`, `high`<br>Example: `luna56?verbosity=low` | — |
 | `luna` | `codexresponses` | Text, Vision, Document | `json` (schema) | effort: `none`, `low`, `medium`, `high`, `xhigh`, `max`, `off`<br>Example: `luna?reasoning=medium` | `low`, `medium`, `high`<br>Example: `luna?verbosity=low` | — |
 | `sol56` | `codexresponses` | Text, Vision, Document | `json` (schema) | effort: `none`, `low`, `medium`, `high`, `xhigh`, `max`, `off`<br>Example: `sol56?reasoning=high` | `low`, `medium`, `high`<br>Example: `sol56?verbosity=low` | — |
-| `sol` | `codexresponses` | Text, Vision, Document | `json` (schema) | effort: `none`, `low`, `medium`, `high`, `xhigh`, `max`, `off`<br>Example: `sol?reasoning=medium` | `low`, `medium`, `high`<br>Example: `sol?verbosity=low` | — |
+| `sol6` | `codexresponses` | Text, Vision, Document | `json` (schema) | effort: `none`, `low`, `medium`, `high`, `xhigh`, `max`, `off`<br>Example: `sol6?reasoning=medium` | `low`, `medium`, `high`<br>Example: `sol6?verbosity=low` | — |
+| `sol` | `codexresponses` | Text, Vision, Document | `json` (schema) | effort: `low`, `medium`, `high`, `xhigh`, `max`<br>Example: `sol?reasoning=medium` | `low`, `medium`, `high`<br>Example: `sol?verbosity=low` | — |
 | `terra` | `codexresponses` | Text, Vision, Document | `json` (schema) | effort: `none`, `low`, `medium`, `high`, `xhigh`, `max`, `off`<br>Example: `terra?reasoning=high` | `low`, `medium`, `high`<br>Example: `terra?verbosity=low` | — |
 | `deepseek-v4-flash-vision-exp` | `deepseek` | Text, Vision | `json` (schema) | effort: `none`, `low`, `high`, `max`, `off`<br>Example: `deepseek-v4-flash-vision-exp?reasoning=max` | — | — |
 | `deepseek-v4-flash` | `deepseek` | Text, Vision | `json` (schema) | effort: `none`, `low`, `high`, `max`, `off`<br>Example: `deepseek-v4-flash?reasoning=max` | — | — |
@@ -67,6 +69,7 @@
 | `deepseek-ai/deepseek-v3.1` | `hf` | Text | `json` (schema) | — | — | — |
 | `deepseek-hf` | `hf` | Text | `json` (schema) | — | — | — |
 | `deepseek32` | `hf` | Text | `json` (schema) | — | — | — |
+| `deepseek41-hf` | `hf` | Text, Vision | `json` (schema) | effort: `none`, `low`, `high`, `max`, `off`<br>Example: `deepseek41-hf?reasoning=max` | — | — |
 | `gemma4` | `hf` | Text, Vision | `json` (schema) | effort: `none`, `low`, `medium`, `high`, `off`<br>Example: `gemma4?reasoning=none` | — | — |
 | `glimmer` | `hf` | Text, Vision | — | effort: `low`, `medium`, `high`, `xhigh`<br>Example: `glimmer?reasoning=high` | — | — |
 | `glm47` | `hf` | Text | `json` (schema) | toggle: `on`, `off`<br>Example: `glm47?reasoning=off` | — | — |
@@ -88,6 +91,8 @@
 | `qwen/qwen3.8-27b` | `hf` | Text, Vision, Video | `json` (object) | effort: `low`, `medium`, `xhigh`, `off`<br>Example: `qwen/qwen3.8-27b?reasoning=medium` | — | — |
 | `qwen35` | `hf` | Text, Vision | `json` (object) | toggle: `on`, `off`<br>Example: `qwen35?reasoning=off` | — | — |
 | `qwen36` | `hf` | Text | — | toggle: `on`, `off`<br>Example: `qwen36?reasoning=off` | — | — |
+| `zai-org/glm-5.3-flash` | `hf` | Text, Vision, Document, Video | `json` (object) | effort: `low`, `high`, `max`<br>Example: `zai-org/glm-5.3-flash?reasoning=max` | — | — |
+| `zai-org/glm-5.3` | `hf` | Text | `json` (object) | effort: `low`, `high`, `max`<br>Example: `zai-org/glm-5.3?reasoning=max` | — | — |
 | `Muse Spark 1.1` | `metaai` | Text, Vision, Document, Video | `json` (schema) | effort: `minimal`, `low`, `medium`, `high`, `xhigh`<br>Example: `Muse Spark 1.1?reasoning=medium` | — | — |
 | `Muse Spark 1.2 (Contributor)` | `metaai` | Text, Vision, Document, Video | `json` (schema) | effort: `minimal`, `low`, `medium`, `high`, `xhigh`<br>Example: `Muse Spark 1.2 (Contributor)?reasoning=medium` | — | — |
 | `Muse Spark 1.2` | `metaai` | Text, Vision, Document, Video | `json` (schema) | effort: `minimal`, `low`, `medium`, `high`, `xhigh`<br>Example: `Muse Spark 1.2?reasoning=medium` | — | — |

docs/docs/models/providers/copilot.md

@@ -107,6 +107,7 @@ not canonical and has no alias; use `copilot.claude-opus-5`.
 | `copilot.gpt-5.6-terra` | Responses |
 | `copilot.gpt-5.6-sol` | Responses |
 | `copilot.gpt-6-astra` | Responses |
+| `copilot.gpt-6.1-sol` | Responses |
 | `copilot.gpt-6-sol` | Responses |
 | `copilot.gpt-6-luna` | Responses |
 
@@ -116,7 +117,7 @@ with `(cp)`; this does not change the model name used in configuration.
 
 ## Structured output
 
-GPT-6 Astra/Sol/Luna use Responses JSON schema (`text.format`).
+GPT-6 Astra/Sol/Luna and GPT-6.1 Sol use Responses JSON schema (`text.format`).
 Opus 5.5 and Sonnet 5.5 select Messages JSON schema (`output_config.format`)
 automatically, without direct Anthropic beta headers. Regular tools can coexist
 with the schema; explicit `structured_tool_policy` overrides remain supported.
@@ -128,6 +129,10 @@ its `reasoning=off` setting. These results confirm access for the tested account
 availability can still vary by account. Use `structured_schema()` for the tool
 loop. See the [credentialed smoke tests](anthropic.md#structured-output-current-models).
 
+GPT-6.1 Sol (`copilot.gpt-6.1-sol`) passed the same schema-only and
+tool-call-to-schema smoke tests on September 29, 2026 (also verified on the Codex
+OAuth route via `sol`).
+
 ## Claude 5.5 progress visibility
 
 Live-tested on September 28, 2026 through the normal fast-agent tool loop.

docs/docs/models/providers/openai.md

@@ -78,6 +78,7 @@ Examples:
 - `responses.gpt-5.5?web_search=on`
 - `responses.gpt-5.4?service_tier=flex`
 - `responses.gpt-6-luna?service_tier=flex`
+- `responses.gpt-6.1-sol?reasoning=high`
 
 ### Codex Responses models
 
@@ -101,6 +102,7 @@ Examples:
 - `astra`
 - `codexresponses.gpt-6-astra?reasoning=max`
 - `sol`
+- `sol6?reasoning=none`
 - `luna?reasoning=none`
 - `codexplan`
 - `codexresponses.gpt-5.5?reasoning=high`
@@ -219,8 +221,8 @@ for card-scoped runtime targets.
 ## Codex (OAuth Responses)
 
 **`fast-agent`** supports using your OpenAI Codex subscription. Run `fast-agent auth provider login codex`
-once, then use a Codex OAuth model alias such as `astra` (GPT-6-Astra), `sol` (GPT-6-Sol),
-`luna` (GPT-6-Luna), `codexplan` (GPT-6-Astra, medium reasoning),
+once, then use a Codex OAuth model alias such as `astra` (GPT-6-Astra), `sol` (GPT-6.1-Sol),
+`sol6` (GPT-6-Sol), `luna` (GPT-6-Luna), `codexplan` (GPT-6-Astra, medium reasoning),
 `codexplan54` (GPT-5.4 planning), `codexplan53` (GPT-5.3 Codex planning), or
 `codexspark` (GPT-5.3 Codex Spark).
 
@@ -262,10 +264,15 @@ codexresponses:
 - Tokens are stored in your OS keyring, with a secure file fallback, via `fast-agent auth provider login codex`.
 - `astra` maps to `codexresponses.gpt-6-astra?reasoning=medium`.
 - `gpt-6-astra` maps to the API-key-backed `responses.gpt-6-astra?reasoning=medium` route; availability still depends on the OpenAI API account's model access.
-- `sol` maps to `codexresponses.gpt-6-sol?reasoning=medium`, and `luna` maps to
+- `sol` maps to `codexresponses.gpt-6.1-sol?reasoning=medium`; `gpt-6.1-sol` (alias
+  `gpt61sol`) uses the API-key-backed `responses` route. GPT-6.1-Sol uses the same shell
+  tool layout, transports and context windows as GPT-6-Sol, but like Astra it accepts
+  only `low`, `medium` (default), `high`, `xhigh` and `max` reasoning; `none` is rejected.
+- `sol6` maps to `codexresponses.gpt-6-sol?reasoning=medium`, and `luna` maps to
   `codexresponses.gpt-6-luna?reasoning=medium`. `gpt-6-sol` and `gpt-6-luna` use the
-  API-key-backed `responses` route. Unlike Astra, Sol and Luna also accept `reasoning=none`.
-- The previous `sol` and `luna` targets remain available as `sol56`
+  API-key-backed `responses` route. Unlike Astra and GPT-6.1-Sol, GPT-6-Sol and Luna also
+  accept `reasoning=none`.
+- The GPT-5.6 `sol` and `luna` targets remain available as `sol56`
   (`codexresponses.gpt-5.6-sol?reasoning=high`) and `luna56`
   (`codexresponses.gpt-5.6-luna?reasoning=medium`).
 - `codexplan` maps to `codexresponses.gpt-6-astra?reasoning=medium`.
@@ -308,7 +315,7 @@ fast-agent go --model 'astra?lite=on&web_search=false'
 ```
 
 No shell access or MCP server is required. This standalone route applies only to
-Lite requests (`lite=on`) for models such as Astra, GPT-6-Sol and GPT-6-Luna. Without
+Lite requests (`lite=on`) for models such as Astra, GPT-6.1-Sol, GPT-6-Sol and GPT-6-Luna. Without
 `lite=on`, `web_search=true` uses hosted Responses web search, as it does for
 public OpenAI Responses. The existing `codexresponses.web_search.enabled`
 setting provides the configuration default; the model flag overrides it. Existing
@@ -371,9 +378,9 @@ limit. `response_length` requests detail, not a client-side hard cap.
 
 fast-agent keeps the default context window at **272,000 tokens** for both
 `astra` (Codex OAuth) and `gpt-6-astra` (Responses API). Larger context is opt-in,
-not an automatic increase: retaining more input can increase cost. GPT-6-Sol
-(`sol`/`gpt-6-sol`) and GPT-6-Luna (`luna`/`gpt-6-luna`) use the same route-specific
-defaults and opt-in windows as Astra.
+not an automatic increase: retaining more input can increase cost. GPT-6.1-Sol
+(`sol`/`gpt-6.1-sol`), GPT-6-Sol (`sol6`/`gpt-6-sol`) and GPT-6-Luna (`luna`/`gpt-6-luna`)
+use the same route-specific defaults and opt-in windows as Astra.
 
 The local Codex source snapshot (`~/reference/codex/codex-rs/`) lists
 `gpt-6-astra` as the first entry in `models-manager/models.json`, with

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "fast-agent-mcp"
-version = "0.10.39"
+version = "0.10.40"
 description = "Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support"
 readme = "README.md"
 license = { file = "LICENSE" }
@@ -24,7 +24,7 @@ dependencies = [
     "rich==15.0.0",
     "typer==0.27.2",
     "anthropic[vertex]==1.9.0",
-    "openai[aiohttp,realtime]==3.19.2",
+    "openai[aiohttp,realtime]==3.21.0",
     "prompt-toolkit==3.0.53",
     "aiohttp==3.14.3",
     "opentelemetry-exporter-otlp-proto-http==1.44.0",