fix(router): add minimum request threshold for error rate cooldown #17464
+61
−0
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
Fixes BerriAI#17418 - Add DEFAULT_FAILURE_THRESHOLD_MINIMUM_REQUESTS constant (default: 5) - Require minimum requests before applying error rate cooldown - Prevents cooldown from triggering on first failure
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
@DevajMody thanks a lot |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Fixes #17418
Pre-Submission checklist
Type
🐛 Bug Fix
✅ Test
Changes
Problem: With
DEFAULT_FAILURE_THRESHOLD_PERCENT=0.5(50%), a deployment gets cooled down after just 1 failed request because 1/1 = 100% > 50%.Fix: Added
DEFAULT_FAILURE_THRESHOLD_MINIMUM_REQUESTSconstant (default: 5) to require a minimum number of requests before applying error rate-based cooldown. This prevents cooldown from triggering on the first failure.Files changed:
litellm/constants.py- Added new configurable constantlitellm/router_utils/cooldown_handlers.py- Added threshold check to cooldown conditiontests/router_unit_tests/test_router_cooldown_utils.py- Added test for new behaviorTest screenshot:
