Andrey Mishchenko 355c40ad7e Support end_turn in response.completed (#19610) ...

Some providers of Responses API forward a model-defined `end_turn`
boolean indicating explicitly the model's indication of whether it would
like to end the turn or to be inferenced again. In this PR, we update
the sampling loop to use this field correctly if it's set. If the field
is not set by the provider, we fall back to the existing sampling logic.

2026-04-25 21:57:42 -07:00

..

clients.rs

feat: add AWS SigV4 auth for OpenAI-compatible model providers (#17820)

2026-04-22 01:11:17 +00:00

models_integration.rs

Add max context window model metadata (#18382)

2026-04-17 21:48:14 -07:00

realtime_websocket_e2e.rs

Update realtime handoff transcript handling (#18597)

2026-04-20 14:04:09 -07:00

sse_end_to_end.rs

Support end_turn in response.completed (#19610)

2026-04-25 21:57:42 -07:00