feat(ai-autopilot): production-grade checklist prompt + { blockers } verdict convention (#121)#126
Merged
Merged
Conversation
…verdict convention (#121)
suleimansh
force-pushed
the
feat/production-grade-checklist
branch
from
f47a533 to
62faf16
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Child of #116 (bootstrap). Extends the prompts library (#111) and the loop (#113).
Two pieces:
production-gradechecklist prompt (prompts/production-grade.md) — judges an app as it stands against a production-grade checklist (auth, data layer, error handling, instrumentation, emailing, validation, tests, build/config) and ends with a machine-readable verdict:{ "blockers": ["short, actionable description of each remaining gap"] }An empty list means production-grade.
The
{ blockers }verdict convention —parseVerdict()/isPassing()read the verdict from a prompt's text (last fencedjsonblock wins, bare-object fallback). The loop now gates on the outcome, not just execution:PromptOutcomecarriesverdictand apassingflag (executed and no blockers), andcontinueOnError: falsestops on!passing. This answers the open note in #113.Backward compatible: with no verdict reported
passing === ok, so existing prompts/gates are unchanged. Passverdict: nullfor an execution-only gate.This is what bootstrap's full-fledged loop (#122) repeats against until blockers is empty.
Tests: verdict parser (fenced/bare/last-wins/empty), loop gating (blockers not-passing, gate-stop, backward-compat,
verdict: null), and the bundle loading frombuiltinLibrary(). Full suite 140 green.Closes #121.