This repository was archived by the owner on Aug 24, 2026. It is now read-only.
fix: record first failed-group errors in grouped provider metadata - #25
Merged
Merged
Conversation
A grouped run that loses groups currently records only their ids — mem0-local lost 24/25 LongMemEval groups and 30/30 ConvoMem groups in matrix v1 with zero diagnostic signal, and the failure does not reproduce in isolation. Capture the first three error messages per provider into provider-status metadata so multi-hour runs are diagnosable from artifacts. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Signed-off-by: Drew Cain <groksrc@gmail.com>
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
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Grouped runs record failed group ids but swallow the exceptions — mem0-local lost 24/25 LongMemEval groups and 30/30 ConvoMem groups in matrix v1 with zero diagnostic signal (and the failure doesn't reproduce in isolation). This captures the first three error messages per provider into provider-status metadata, making multi-hour runs diagnosable from their artifacts.
1 new test; suite green, lint clean.
🤖 Generated with Claude Code