phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Litellm dev 04 22 2025 p1 (#10206)

Browse source 
* fix(openai.py): initial commit adding generic event type for openai responses api streaming

Ensures handling for undocumented event types - e.g. "response.reasoning_summary_part.added"

* fix(transformation.py): handle unknown openai response type

* fix(datadog_llm_observability.py): handle dict[str, any] -> dict[str, str] conversion

Fixes https://github.com/BerriAI/litellm/issues/9494

* test: add more unit testing

* test: add unit test

* fix(common_utils.py): fix message with content list

* test: update testing
This commit is contained in:
Krish Dholakia 2025-04-22 23:58:43 -07:00 • committed by GitHub
parent f670ebeb2f
commit 217681eb5e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 165 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

4
litellm/responses/streaming_iterator.py
View file

@ -44,12 +44,12 @@ class BaseResponsesAPIStreamingIterator:
self.responses_api_provider_config = responses_api_provider_config
self.completed_response: Optional[ResponsesAPIStreamingResponse] = None
self.start_time = datetime.now()
# set request kwargs
self.litellm_metadata = litellm_metadata
self.custom_llm_provider = custom_llm_provider
def _process_chunk(self, chunk):
def _process_chunk(self, chunk) -> Optional[ResponsesAPIStreamingResponse]:
"""Process a single chunk of data from the stream"""
if not chunk:
return None