[Feat] Performance - Don't create 1 task for every hanging request alert #11385
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
There was a problem hiding this comment.
Pull Request Overview
This PR adds a unified mechanism to batch and check for hanging LLM requests instead of spawning an alert task per request.
- Removed the old per-request hanging alert test
- Introduced
AlertingHangingRequestCheckwith in-memory caching and periodic checks - Refactored
response_taking_too_longto enqueue requests rather than sleep per call
Reviewed Changes
Copilot reviewed 6 out of 6 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| tests/logging_callback_tests/test_alerting.py | Removed the legacy hanging request test |
| litellm/types/integrations/slack_alerting.py | Added constants and HangingRequestData model |
| litellm/proxy/utils.py | Scheduled single background task for hanging-request checks |
| litellm/integrations/SlackAlerting/slack_alerting.py | Refactored response_taking_too_long to use the new checker |
| litellm/integrations/SlackAlerting/hanging_request_check.py | New class handling batching, TTL, and alert dispatch |
| litellm/caching/in_memory_cache.py | Added async_get_oldest_n_keys helper |
Comments suppressed due to low confidence (3)
tests/logging_callback_tests/test_alerting.py:146
- There is no test covering the new
AlertingHangingRequestCheckworkflow; consider adding tests that enqueue requests and simulate time passage to verify alerts are sent correctly.
@pytest.mark.asyncio
litellm/integrations/SlackAlerting/slack_alerting.py:458
- The signature of
response_taking_too_longno longer accepts atypeparameter, but existing tests or call sites may still pass it. Update or overload this method to prevent breaking consumers.
async def response_taking_too_long(
litellm/caching/in_memory_cache.py:238
- The
Listtype is used but not imported; addfrom typing import Listto avoid aNameError.
async def async_get_oldest_n_keys(self, n: int) -> List[str]:
ishaan-jaff
added a commit
that referenced
this pull request
Jun 4, 2025
…ert (#11385) * feat: add async_get_oldest_n_keys in memory cache * fix: add add_request_to_hanging_request_check * test: alerting * feat: v2 hanging request check * fix: HangingRequestData * fix: AlertingHangingRequestCheck * fix: check_for_hanging_requests * fix: use correct metadata location for hanging requests * fix: formatting alert * test hanging request check * fix: add guard flags for background tasks alerting
stefan--
pushed a commit
to stefan--/litellm
that referenced
this pull request
Jun 12, 2025
…ert (BerriAI#11385) * feat: add async_get_oldest_n_keys in memory cache * fix: add add_request_to_hanging_request_check * test: alerting * feat: v2 hanging request check * fix: HangingRequestData * fix: AlertingHangingRequestCheck * fix: check_for_hanging_requests * fix: use correct metadata location for hanging requests * fix: formatting alert * test hanging request check * fix: add guard flags for background tasks alerting
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
[Feat] Performance - Don't create 1 task for every hanging request alert
This PR adds a unified mechanism to batch and check for hanging LLM requests instead of spawning an alert task per request.
Relevant issues
Pre-Submission checklist
Please complete all items before asking a LiteLLM maintainer to review your PR
tests/litellm/directory, Adding at least 1 test is a hard requirement - see detailsmake test-unitType
🧹 Refactoring
✅ Test
Changes