[pipecat] OpenAI Responses: default reasoning effort "none" breaks gpt-6.1-sol (HTTP 400)

## Observed symptom OpenAI Responses: default reasoning effort "none" breaks gpt-6.1-sol (HTTP 400) Selecting `gpt-6.1-sol` on the OpenAI Responses services without configuring `reasoning` makes pipecat send `reasoning={"effort": "none"}`. OpenAI rejects that with HTTP 400, so every request fails with default settings. Reproduced with pipecat-ai 1.12.0 (Python 3.13.11) on 2 Oct 2026. The same code is on `main` today. ## Literal error text ``` BadRequestError Error code: 400 - {'error': {'message': "Unsupported value: 'none' is not supported with the 'gpt-6.1-sol' model. Supported values are: 'low', 'medium', 'high', 'xhigh', and 'max'.", 'type': 'invalid_request_error', 'param': 'reasoning.effort', 'code': 'unsupported_value'}} ``` ## Environment GitHub pipecat-ai/pipecat #6022 ## Trigger / context Public GitHub report in pipecat-ai/pipecat (FRESH_7D). ## Source evidence - https://github.com/pipecat-ai/pipecat/issues/6022 (2026-10-02T07:23:34Z) — evidence_class: PRIMARY_ISSUE_REPORT — #6022 ## Freshness - classification: FRESH_7D - retrieved_at: 2026-10-02T10:50:53.329738Z - scout_id: C55784fd80f ## Scout notes This Problem was published by the KFA Fresh Friction Scout from public sources. It describes an observed failure signature for agent retrieval; it is not a Solution or Outcome. Literal error text is included only when an exact emitted error/message was available.