scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-04 02:31:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 71

refactor(proxy/hooks): raise ProxyRateLimitError from budget + iteration limiters

Browse source 
Replaces three bare HTTPException(status_code=429, ...) call sites with
ProxyRateLimitError, which is both a RateLimitError (catchable by category)
and an HTTPException (preserves existing FastAPI serialization). Drops the
now-unused HTTPException import in the iteration / per-session limiters.

LIT-2968

Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
This commit is contained in:
Cursor Agent 2026-05-11 22:43:21 +00:00
parent 8360519f2b
commit 39a9968103
No known key found for this signature in database
3 changed files with 6 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
litellm/proxy/hooks/max_budget_limiter.py
View file

@ -5,6 +5,7 @@ from litellm._logging import verbose_proxy_logger
from litellm.caching.caching import DualCache
from litellm.integrations.custom_logger import CustomLogger
from litellm.proxy._types import UserAPIKeyAuth
from litellm.proxy.common_utils.proxy_rate_limit_error import ProxyRateLimitError
class _PROXY_MaxBudgetLimiter(CustomLogger):
@ -63,7 +64,7 @@ class _PROXY_MaxBudgetLimiter(CustomLogger):
# CHECK IF REQUEST ALLOWED
if curr_spend >= max_budget:
raise HTTPException(status_code=429, detail="Max budget limit reached.")
raise ProxyRateLimitError(detail="Max budget limit reached.")
except HTTPException as e:
raise e
except Exception as e:

6
litellm/proxy/hooks/max_budget_per_session_limiter.py
View file

@ -17,12 +17,11 @@ Follows the same pattern as max_iterations_limiter.py.
import os
from typing import TYPE_CHECKING, Any, Optional, Union
from fastapi import HTTPException
from litellm import DualCache
from litellm._logging import verbose_proxy_logger
from litellm.integrations.custom_logger import CustomLogger
from litellm.proxy._types import UserAPIKeyAuth
from litellm.proxy.common_utils.proxy_rate_limit_error import ProxyRateLimitError
if TYPE_CHECKING:
from litellm.proxy.utils import InternalUsageCache as _InternalUsageCache
@ -112,8 +111,7 @@ class _PROXY_MaxBudgetPerSessionHandler(CustomLogger):
)
if current_spend >= max_budget:
raise HTTPException(
status_code=429,
raise ProxyRateLimitError(
detail=(
f"Session budget exceeded for session {session_id}. "
f"Current spend: ${current_spend:.4f}, "

6
litellm/proxy/hooks/max_iterations_limiter.py
View file

@ -13,12 +13,11 @@ Follows the same pattern as parallel_request_limiter_v3.py.
import os
from typing import TYPE_CHECKING, Any, Optional, Union
from fastapi import HTTPException
from litellm import DualCache
from litellm._logging import verbose_proxy_logger
from litellm.integrations.custom_logger import CustomLogger
from litellm.proxy._types import UserAPIKeyAuth
from litellm.proxy.common_utils.proxy_rate_limit_error import ProxyRateLimitError
if TYPE_CHECKING:
from litellm.proxy.utils import InternalUsageCache as _InternalUsageCache
@ -116,8 +115,7 @@ class _PROXY_MaxIterationsHandler(CustomLogger):
current_count = await self._increment_and_get(cache_key)
if current_count > max_iterations:
raise HTTPException(
status_code=429,
raise ProxyRateLimitError(
detail=(
f"Max iterations exceeded for session {session_id}. "
f"Current count: {current_count}, max_iterations: {max_iterations}."