Cesar Garcia fd9ff90307 fix(responses): prevent streaming tool_calls from being dropped when text + tool_calls (#17652) ...

When OpenAI Responses API returns both text AND tool_calls, the bridge
transformation was emitting is_finished=True after the text message completed,
causing subsequent tool_call chunks to be dropped.

The fix:
- response.output_item.done for messages no longer emits is_finished=True
- Added handler for response.completed to properly signal stream end

2025-12-08 18:51:59 -08:00

..

litellm_responses_transformation

fix(responses): prevent streaming tool_calls from being dropped when text + tool_calls (#17652)

2025-12-08 18:51:59 -08:00

test_litellm_responses_transformation_transformation.py

fix: Support response_format parameter in completion -> responses bridge

2025-11-19 17:07:46 -03:00