Move AI eval from per-PR to daily cron schedule#194
Merged
janhesters merged 3 commits intomainfrom Apr 15, 2026
Merged
Conversation
AI evals were running per-PR and hitting Claude rate limits, blocking merges. Move to a dedicated daily workflow (midnight UTC) with manual dispatch, and reduce --runs from 4 to 1 to stay within rate limits.
Posts a message with a link to the failed run when the daily AI eval fails. Requires SLACK_BOT_TOKEN secret with chat:write scope.
Add job-level guard so workflow_dispatch on non-main branches is a no-op. Use github.ref_name in Slack message instead of hardcoded main.
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 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
ai-evaljob fromtest.ymlinto its ownai-eval.ymlworkflow0 0 * * *UTC) +workflow_dispatchinstead of per-PR--runsfrom 4 to 1 to stay within Claude rate limitsWhy
AI evals were running on every PR and hitting Claude rate limits mid-run, blocking merges (#191, #189). A daily schedule avoids rate limit pressure while still catching regressions.
Test plan
Testsworkflow still runs on push/PR without theai-evaljobAI Evalworkflow manually viaworkflow_dispatchto confirm it works