scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-09 03:18:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 109

refactor(responses): freeze split-chunk copy payloads

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Devin AI 2026-08-09 02:11:54 +00:00
parent b9bf5d82db
commit abba4600b0
1 changed files with 17 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
litellm/responses/litellm_completion_transformation/streaming_iterator.py
View file

@ -1,5 +1,6 @@
import time
import uuid
from types import MappingProxyType
from typing import Any, Final, cast
import litellm
@ -152,14 +153,25 @@ class LiteLLMCompletionStreamingIterator(ResponsesAPIStreamingIterator):
choice: Final = chunk.choices[0]
reasoning_choice: Final = choice.model_copy(
update={"delta": delta.model_copy(update={"content": None}), "finish_reason": None}
update=MappingProxyType(
{
"delta": delta.model_copy(update=MappingProxyType({"content": None})),
"finish_reason": None,
}
)
)
content_choice: Final = choice.model_copy(
update={"delta": delta.model_copy(update={"reasoning_content": None, "thinking_blocks": None})}
update=MappingProxyType(
{
"delta": delta.model_copy(
update=MappingProxyType({"reasoning_content": None, "thinking_blocks": None})
)
}
)
)
return (
chunk.model_copy(update={"choices": [reasoning_choice]}),
chunk.model_copy(update={"choices": [content_choice]}),
chunk.model_copy(update=MappingProxyType({"choices": (reasoning_choice,)})),
chunk.model_copy(update=MappingProxyType({"choices": (content_choice,)})),
)
def _queue_reasoning_lifecycle_events(self, chunk: ModelResponseStream) -> None:
@ -192,7 +204,7 @@ class LiteLLMCompletionStreamingIterator(ResponsesAPIStreamingIterator):
reasoning_content=reasoning_content,
sequence_number=self._sequence_number,
)
self._pending_response_events.extend([text_done_event, part_done_event, output_item_done_event])
self._pending_response_events.extend((text_done_event, part_done_event, output_item_done_event))
self._reasoning_done_emitted = True
self._reasoning_active = False