openai.ResponsesClient$stream

Signature

The OpenAI Responses API client (POST {base_url}/responses).

Options come in three groups:

• credentials/endpoint — api_key/base_url (or the *_env names read at request time);
• first-class typed request parameters — temperature, top_p, max_output_tokens, reasoning_effort, reasoning_summary, verbosity, parallel_tool_calls, store. Each one is lowered into the typed request class only when it is non-null;
• passthrough — request_body (deep-merged over the serialized typed request as the LAST step, null deletes a key), headers and query_params.

Structured output stays SAP-based: the schema rides in the prompt text and text.format is deliberately never set. A caller who wants native JSON-schema output sets it through request_body.

Deliberately not provided: the engine's finish_reason_allow_list and finish_reason_deny_list. There is no config surface for them here and none is planned — the typed ai.content.StopReason plus the runner's Refused / MaxTokens enforcement covers what the lists were used for, and a caller who wants a stricter policy writes it over the returned turn (or wraps the client) rather than configuring a string list of provider finish reasons.

Source:<builtin>/openai/responses.bamlbytes 0–0