scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-07 08:26:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 36

fix(prometheus): use return_exceptions=True for budget metric lookups

Browse source 
Make asyncio.gather resilient to partial failures. If key, team, or
user lookup raises, log at debug level and allow the others to
complete. Prevents one failing lookup from blocking the rest.
This commit is contained in:
Alexsander Hamir 2026-02-05 15:43:13 -08:00
parent 05fbb78a38
commit 7355df7ea5
1 changed files with 7 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
litellm/integrations/prometheus.py
View file

@ -1189,7 +1189,7 @@ class PrometheusLogger(CustomLogger):
_user_spend = _metadata.get("user_api_key_user_spend", None)
_user_max_budget = _metadata.get("user_api_key_user_max_budget", None)
await asyncio.gather(
results = await asyncio.gather(
self._set_api_key_budget_metrics_after_api_request(
user_api_key=user_api_key,
user_api_key_alias=user_api_key_alias,
@ -1210,7 +1210,13 @@ class PrometheusLogger(CustomLogger):
user_max_budget=_user_max_budget,
response_cost=response_cost,
),
return_exceptions=True,
)
for i, r in enumerate(results):
if isinstance(r, Exception):
verbose_logger.debug(
f"[Non-Blocking] Prometheus: Budget metric lookup {['key', 'team', 'user'][i]} failed: {r}"
)
def _increment_top_level_request_and_spend_metrics(
self,