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): prevent user metadata flag from bypassing model allowlist

Browse source 
The skip_batch_input_file_rate_limiting flag in litellm_metadata is
user-controllable for batch requests (request-body metadata lands in
litellm_metadata via LITELLM_METADATA_ROUTES). Honoring it
unconditionally also skipped _enforce_batch_file_model_access, letting
a restricted key submit a JSONL referencing models outside its
allowlist. Only honor the metadata-based skip when the key has no
model allowlist to enforce.

Co-authored-by: Yassin Kortam <yassin@berri.ai>
This commit is contained in:
Cursor Agent 2026-05-28 06:23:21 +00:00
parent 7afd657c46
commit b391f772ad
No known key found for this signature in database
1 changed files with 10 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
litellm/proxy/hooks/batch_rate_limiter.py
View file

@ -151,8 +151,17 @@ class _PROXY_BatchRateLimiter(CustomLogger):
if general_settings.get("disable_batch_input_file_rate_limiting") is True:
return True
# Only honor the metadata-based skip when the key has no model
# allowlist to enforce. Otherwise a caller could set this flag in
# the request body (it lands in ``litellm_metadata`` for batch
# routes) and skip ``_enforce_batch_file_model_access``, smuggling
# restricted models into the JSONL.
litellm_metadata = data.get("litellm_metadata") or {}
if litellm_metadata.get("skip_batch_input_file_rate_limiting") is True:
if litellm_metadata.get(
"skip_batch_input_file_rate_limiting"
) is True and not self._key_requires_batch_model_access_check(
user_api_key_dict
):
return True
batch_model = self._get_batch_routing_model(data)