Provider-specific types: `OpenAiChatReasoningEffort` for Chat `reasoning_effort`, and `OpenAiResponsesReasoningEffort` for Responses `reasoning.effort`. They are intentionally separate even when their current value sets overlap; a value accepted by one field is not treated as valid for the other unless that field's own enum accepts it.
| `max` | `max` for GPT-5.6 | `max` for GPT-5.6 | `max` | `high` | OpenAI emission is capability-gated by the resolved model. |
GPT-5.6 (`gpt-5.6`, `gpt-5.6-sol`, `gpt-5.6-terra`, and `gpt-5.6-luna`) publishes `none`, `low`, `medium`, `high`, `xhigh`, and `max`, and does not support `minimal`. Additional non-empty effort values advertised by a model are preserved verbatim across OpenAI Chat and Responses conversion. `ultra` is a Codex client preset that resolves to `max` before transmission and is not an OpenAI wire effort. Known effort capabilities are validated against the resolved provider model, so aliases mapped to GPT-5.6 receive the GPT-5.6 contract while concrete model families keep their published constraints.
| named function | `{"type":"function","function":{"name":...}}` | `{"type":"function","name":...}` | `{"type":"tool","name":...}` | allowed function name |
Implemented guardrails:
- Claude `output_config.effort=max` maps to OpenAI `xhigh`; unknown Claude effort enums are blocked cross-format.
- Claude `tool_choice.disable_parallel_tool_use` maps inversely to OpenAI `parallel_tool_calls`.
- Gemini `allowedFunctionNames` maps to canonical named tool choice and emits back to `allowedFunctionNames`.
- Gemini `thinkingLevel` maps `low|medium|high` to OpenAI reasoning effort `low|medium|high`; unknown values are blocked cross-format.
- Responses `custom`, `web_search*`, and other built-in tools are blocked when converting to Chat unless a target raw passthrough is explicitly added.
- Cross-format sync response conversion validates source finish/status enums before emitting the target response.
- Same-format canonical response roundtrip preserves raw OpenAI Chat `finish_reason`, OpenAI Responses `status`, Claude `stop_reason`, and Gemini `finishReason` values through provider extension metadata.
- OpenAI Chat unknown `choices[].finish_reason` fails with `InvalidEnumValue`.
- OpenAI Responses non-terminal `status` values (`queued`, `in_progress`, `cancelled`) are valid provider states but are blocked for sync response conversion because target sync formats cannot represent them losslessly.
- Runtime sync finalize does not fall back to legacy conversion when registry response conversion reports strict errors such as invalid enums, unsupported fields, lossy blocks, or invalid target fields.
- Stream terminal reasons now follow the same strict policy: unknown OpenAI / Claude raw finish reasons and Gemini known-but-unmappable values such as `OTHER` surface as `unsupported_finish_reason`, while OpenAI Responses `length` and `content_filter` stream finals emit `response.incomplete`.
- Gemini known but unmappable finish reasons such as `OTHER`, `MALFORMED_FUNCTION_CALL`, `UNEXPECTED_TOOL_CALL`, `MISSING_THOUGHT_SIGNATURE`, and `MALFORMED_RESPONSE` are blocked with `LossyConversionBlocked`; unknown future Gemini values fail with `InvalidEnumValue`.
- Stream finish reason guardrails are covered with provider-specific fixtures for usage, tool calls, reasoning signatures, media, and unknown payloads. Unknown provider stream events are not mapped as finish reasons; cross-format runtime conversion emits a target-format `unsupported_stream_event` error and terminates.
