Sign in
latestOpenAPI 3.1.02026-08-19270462702.4 KB

b92f75fd3b61

openai-compat

Responses

OpenAI-compatible Responses API endpoint.

Thin shell over :func:services.inference.adapters.openai_responses.run_responses. The adapter handles input-item to chat-message translation, LLM-passthrough vs Pioneer-task dispatch, SSE rendering, tool-call serialisation, persistence, and error mapping. The router keeps only HTTP-shaped concerns: route declaration, auth, rate limiting.

Args: body: Validated :class:ResponsesRequest. request: FastAPI request (forwarded so the adapter can read API-key billing context out of request.state for streaming responses). response: Response whose headers carry the deprecation and router-tip signals. auth: Authenticated request context.

Returns: JSON response payload or :class:StreamingResponse SSE stream in Responses API format.

post/responses

Request body

modelstring required
instructionsstring
toolsobject[]
parallel_tool_callsboolean
storeboolean

Whether to store response state for turn-to-turn continuation. When true, Pioneer preserves the response for previous_response_id replay, including available tool-call and reasoning context.

streamboolean
previous_response_idstring nullable

Pioneer inference ID or stored Responses wire ID to continue from. When present, Pioneer reconstructs the prior turn from inference history and prepends it to the new input.

includestring[]
service_tierstring nullable
prompt_cache_keystring nullable
max_output_tokensinteger nullable
temperaturenumber nullable
top_pnumber nullable
metadataobject nullable
extra_headersobject nullable
extra_bodyobject nullable
task_typestring nullable

Deprecated. Legacy task hint (extract_entities / classify_text / extract_json / ner / schema). The unified schema on text.format.schema disambiguates the task automatically. Submitting this field emits Deprecation: true and Sunset: <RFC 7231 date> headers on the response.

include_confidenceboolean nullable
include_spansboolean nullable
effort'low' | 'medium' | 'high' | 'xhigh' | 'max'

Per-request routing-effort tier, ascending in cost and quality.

Sent by the caller as the effort param or as a model suffix. The per-router policy each tier used to map to is gone with the routers; the tier itself remains a request-level knob.

modelsstring[] nullable

Per-request candidate-model subset the router may select between. Overrides the router's stored candidate set for this request only; ignored for non-router models.

Response

Successful Response

{"stackTrail":"paths:/responses:post:responses:200:content:application/json:schema","oasType":"schema","type":"unknown"}