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(batches): overwrite fallback flag in place

Browse source 
Avoid a fresh mutable kwargs mapping while still replacing any request-enriched value before router dispatch.
This commit is contained in:
Rithvik Mysore Suresh 2026-07-31 10:39:05 -04:00
parent 55726fc09e
commit efb5f74173
1 changed files with 2 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
litellm/proxy/batches_endpoints/endpoints.py
View file

@ -262,9 +262,8 @@ async def create_batch(
detail={"error": "LLM Router not initialized. Ensure models added to proxy."},
)
response = await llm_router.acreate_batch(
**{**_create_batch_data, "disable_fallbacks": True},
)
_create_batch_data.update(disable_fallbacks=True) # pyright: ignore[reportCallIssue] # router flag
response = await llm_router.acreate_batch(**_create_batch_data)
response.input_file_id = input_file_id
response._hidden_params["unified_file_id"] = unified_file_id
else: