fix(framework): fail closed on a missing checklist verdict#240
Merged
Conversation
A checklist reply with no parseable { blockers } block was coerced to
empty blockers, which is the pass signal, so an unverifiable reply could
be scored production-grade and stop the loop. Surface a concrete blocker
instead so the loop re-prompts (and stops with it at maxPasses).
Closes #239
suleimansh
added
bug
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 checklist reply that never ends with the required
{ blockers }verdict was coerced to empty blockers, which is the pass signal, so an unverifiable reply could be scored production-grade and stop the loop. (ai-autopilot's ownisPassing()already says a missing verdict is not passing; the framework layer defeated it.)Now a missing verdict surfaces a concrete blocker, so the loop re-prompts and, at maxPasses, stops with it rather than declaring the app done. Flipped the one test that asserted the old behavior.
Closes #239