scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-10 22:41:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 83
litellm/tests/test_litellm/completion_extras
History
Exact
mateo-berri 64cbe6d0aa fix(bridge): carry provider metadata on streamed chats and keep served ids in spend logs 
The terminal chunk of a bridged streaming chat now carries the same provider
fields the non-streaming response does (service_tier, content_filters), so
streaming clients see them on the final chunk

The passthrough drops Responses API bookkeeping (background, top_logprobs,
store, ...) by subtracting the OpenAI SDK's Response schema from the fields it
copies instead of a hand-kept denylist

Spend log rows for /v1/messages calls served through the Responses adapter keep
the id the client was handed instead of the decoded upstream id
2026-09-05 19:21:40 -07:00
..
litellm_responses_transformation fix(bridge): carry provider metadata on streamed chats and keep served ids in spend logs 2026-09-05 19:21:40 -07:00
__init__.py Litellm oss staging 030626 (#29578) 2026-06-03 11:01:51 -07:00
test_litellm_responses_transformation_transformation.py fix(litellm): support OpenAI chat completions custom tool calls end to end 2026-08-01 11:26:09 -07:00
test_responses_bridge_provider_propagation.py fix: bedrock mantle fixes (#30083) 2026-06-12 07:25:16 -07:00