scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-08 03:08:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 115

fix(streaming_handler.py): fix streaming chunk calculation

Browse source
This commit is contained in:
Krrish Dholakia 2025-08-16 14:25:29 -07:00
parent 45ebbb9566
commit bd6f2edbf3
1 changed files with 6 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
litellm/litellm_core_utils/streaming_handler.py
View file

@ -1731,6 +1731,11 @@ class CustomStreamWrapper:
# Create a new object without the removed attribute
processed_chunk = self.model_response_creator(chunk=obj_dict)
print_verbose(f"final returned processed chunk: {processed_chunk}")
# add usage as hidden param
if self.sent_last_chunk is True and self.stream_options is None:
usage = calculate_total_usage(chunks=self.chunks)
processed_chunk._hidden_params["usage"] = usage
return processed_chunk
raise StopAsyncIteration
else: # temporary patch for non-aiohttp async calls
@ -1774,6 +1779,7 @@ class CustomStreamWrapper:
messages=self.messages,
logging_obj=self.logging_obj,
)
response = self.model_response_creator()
if complete_streaming_response is not None:
setattr(