Repository navigation
fix(cli): verify the final permitted agent repair - #31
Merged
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
This branch was successfully deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
A developer allowing one coding-agent repair could get
needs-repaireven after the project was fixed: the loop checked only before repairs and never verified the last allowed one. The supervisor now checks after each successfully completed repair, including the final one, without launching beyond the repair budget. No-op claims and partial repairs remain failed after fresh checks.attemptsnow counts launched repair processes; initially green, dry-run and missing-command outcomes report zero. Invalid supplied budgets are rejected before checks or artifacts. Gate snapshot numbering remains compatible and can reach budget + 1. The tracked compiled runtime, walkthrough and tour anchors match the source.Validation: all 364 tests across 35 files pass; the new scenarios use finite local processes for final/early success, false claims, partial repairs, process failure, missing command/gate, malformed API/CLI budgets, three concurrent isolated CLI jobs and twelve successive jobs. The regression scenarios fail against the previous implementation at stale-failure and incorrect-count assertions. TypeScript compilation and production dependency audit pass. No paid model/provider calls.
Existing launcher timeout and overwritten adapter-log limitations are documented and unchanged. This proves supervisor closure, not model-quality improvement or indefinite unattended safety. No dependency, gate configuration, provider, visual or CI change.