scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-21 00:21:49 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 73

refactor(streaming): compute the reasoning token cap once

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
kerry 2026-09-16 23:28:28 +00:00
parent 884e96958c
commit aea9678f61
1 changed files with 3 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
litellm/litellm_core_utils/streaming_chunk_builder_utils.py
View file

@ -1095,8 +1095,8 @@ class ChunkProcessor:
returned_usage.completion_tokens_details = completion_tokens_details
if reasoning_tokens is not None:
capped_reasoning_tokens: Final = min(max(0, reasoning_tokens), returned_usage.completion_tokens)
if returned_usage.completion_tokens_details is None:
capped_reasoning_tokens: Final = min(max(0, reasoning_tokens), returned_usage.completion_tokens)
returned_usage.completion_tokens_details = CompletionTokensDetailsWrapper(
reasoning_tokens=capped_reasoning_tokens,
text_tokens=returned_usage.completion_tokens - capped_reasoning_tokens,
@ -1105,13 +1105,10 @@ class ChunkProcessor:
returned_usage.completion_tokens_details is not None
and returned_usage.completion_tokens_details.reasoning_tokens is None
):
existing_capped_reasoning_tokens: Final = min(
max(0, reasoning_tokens), returned_usage.completion_tokens
)
returned_usage.completion_tokens_details.reasoning_tokens = existing_capped_reasoning_tokens
returned_usage.completion_tokens_details.reasoning_tokens = capped_reasoning_tokens
if returned_usage.completion_tokens_details.text_tokens is None:
returned_usage.completion_tokens_details.text_tokens = (
returned_usage.completion_tokens - existing_capped_reasoning_tokens
returned_usage.completion_tokens - capped_reasoning_tokens
)
if prompt_tokens_details is not None:
returned_usage.prompt_tokens_details = prompt_tokens_details