scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-03 02:22:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 80

fix(batch_rate_limiter): wildcard model bypass + fail-open embedded model creds

Browse source 
- _key_requires_batch_model_access_check: check '*' / all-proxy-models
  before access_group_ids so wildcard keys skip the JSONL download.
- _resolve_batch_input_file_fetch_params: wrap embedded-model
  get_credentials_for_model in try/except HTTPException, mirroring the
  request-model fallback path, and always decode the file id.

Co-authored-by: Yassin Kortam <yassin@berri.ai>
This commit is contained in:
Cursor Agent 2026-05-28 06:44:13 +00:00
parent 4f9ceddd52
commit f41ec3e2ab
No known key found for this signature in database
1 changed files with 17 additions and 14 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

31
litellm/proxy/hooks/batch_rate_limiter.py
View file

@ -212,14 +212,14 @@ class _PROXY_BatchRateLimiter(CustomLogger):
) -> bool:
"""True when the key may only call a subset of models (JSONL must be checked)."""
models = user_api_key_dict.models or []
if user_api_key_dict.access_group_ids:
return True
if not models:
return False
if "*" in models:
return False
if SpecialModelNames.all_proxy_models.value in models:
return False
if user_api_key_dict.access_group_ids:
return True
if not models:
return False
return True
@staticmethod
@ -262,16 +262,19 @@ class _PROXY_BatchRateLimiter(CustomLogger):
model_from_file_id = decode_model_from_file_id(file_id)
if model_from_file_id:
credentials = get_credentials_for_model(
llm_router=llm_router,
model_id=model_from_file_id,
operation_context="batch input file read (rate limiting)",
)
fetch_kwargs.update(_extract_file_access_credentials(credentials))
fetch_kwargs["model"] = model_from_file_id
provider = credentials.get("custom_llm_provider")
if provider:
fetch_kwargs["custom_llm_provider"] = provider
try:
credentials = get_credentials_for_model(
llm_router=llm_router,
model_id=model_from_file_id,
operation_context="batch input file read (rate limiting)",
)
fetch_kwargs.update(_extract_file_access_credentials(credentials))
fetch_kwargs["model"] = model_from_file_id
provider = credentials.get("custom_llm_provider")
if provider:
fetch_kwargs["custom_llm_provider"] = provider
except HTTPException:
pass
return get_original_file_id(file_id), fetch_kwargs
request_model = data.get("model")