scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

fix(proxy): clamp parallel slot TTL override to a positive value

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
milan 2026-08-20 01:05:36 +00:00
parent 66dbf2101c
commit 4e608c5426
2 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
litellm/proxy/hooks/parallel_request_limiter_v3.py
View file

@ -369,7 +369,7 @@ PROJECT_OTPM_DESCRIPTOR_KEY: Final = "model_per_project_otpm"
# considered leaked (worker crashed without any release callback firing) and
# pruned. Also the longest request duration the gauge can track: a request
# running longer than this stops occupying its slot.
PARALLEL_REQUEST_SLOT_TTL_SECONDS: Final = int(os.getenv("LITELLM_PARALLEL_REQUEST_SLOT_TTL_SECONDS", "3600"))
PARALLEL_REQUEST_SLOT_TTL_SECONDS: Final = max(1, int(os.getenv("LITELLM_PARALLEL_REQUEST_SLOT_TTL_SECONDS", "3600")))
CacheCounterValue: TypeAlias = int | float | str | bytes

2
tests/test_litellm/litellm_core_utils/test_litellm_logging.py
View file

@ -4960,7 +4960,7 @@ def test_pre_call_redacts_and_masks_raw_request(logging_obj):
assert "key=*****" in raw_api_base
def _streaming_logging_obj_with_callbacks(callbacks):
def _streaming_logging_obj_with_callbacks(callbacks: list[CustomLogger]):
from datetime import datetime
obj = LitellmLogging(