mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-28 06:23:07 +00:00
The chat stream that wraps the native Responses stream now logs the request, so the spend row carries the chat completion the client received instead of the Responses object. The Responses iterator hands its completed response to the bridge instead of dispatching success logging itself. |
||
|---|---|---|
| .. | ||
| litellm_responses_transformation | ||
| __init__.py | ||
| test_litellm_responses_transformation_transformation.py | ||
| test_responses_bridge_provider_propagation.py | ||