walkthrough: CLI surface honesty + discoverability fixes (validate-prd, watcher, set-status)#27
Merged
Merged
Conversation
Auto interactive-walkthrough of the Atlas CLI surfaces (5 reviewed, no P0/P1). Four evidence-backed fixes under TDD + Second-Check: - validate-prd Check 6: fail-closed on an ABSENT requirements section instead of vacuously passing + claiming 'all requirements are specific' (P2 honesty). - watcher permit reason: surface a cheating-winner discrepancy instead of masking it behind 'no to-be-slashed' (P2 legibility; the permit boolean is unchanged). - set-status --status: enumerate the valid status vocabulary in -h (P2). - engine-preflight/next-task/economy-report: add missing flag help (P3 consistency). RAG-ready runlogs under .i-walkthroughs/entries/. Offline suite 886 passed / 5 skipped. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Add .i-walkthroughs/ to .gitignore and remove the tracked runlog store from the index (local files kept). The RAG runlogs stay on disk but are no longer committed. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.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 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Auto
/interactive-walkthrough(headless adaptation) of the Atlas CLI surfaces. 5 surfaces reviewed by independent mini-phoenix reviewers running each command live. No P0/P1 — every surface is fundamentally solid. 4 evidence-backed fixes implemented under TDD with Second-Check + RAG runlogs.Surfaces reviewed
engine-preflightvalidate-prdwatcher-status/runnext-task/set-statustournament-status/economy-reportFixes in this PR (each: first-check → fix → Second-check → runlog)
validate-prdCheck 6 (P2 honesty). On a PRD with zero requirements it passed AND printed "All requirements are specific". Now fail-closed →passed:false, "No requirements section found".check6 passed:true,checks_passed:3, score:13check6 passed:false,checks_passed:2, score:8(grade still NEEDS_WORK; real PRDs unchanged, still 57/57)watcherpermit reason (P2 legibility). A blocked job with a cheating-winner discrepancy reported the benign "no to-be-slashed" instead of the discrepancy. Reordered the reason ladder most-serious-first; the permit boolean is unchanged.set-status --status(P2 discoverability). A required flag whose valid vocabulary was undiscoverable.-hnow enumeratespending, in-progress, done, review, deferred, cancelled, blocked(help-only — preserves the FR-28 error path, no argparsechoices).engine-preflight --no-configure,next-task --tag,economy-report --input.Deferred (recorded, not in this PR)
fallbackprovider status in the summary (P2) — a not-ready env can read as ready.task:null).|re-serialization; watcher-statusobservationsname overload).Verification
Full offline suite 886 passed / 5 skipped. Each fix has a
.i-walkthroughs/entries/<id>.mdrunlog withverdict:resolved,regression_scan:pass..i-walkthroughs/This PR re-introduces
.i-walkthroughs/(the RAG runlog store) — you removed it in the earlier prune. The skill requires committed, non-gitignored runlogs. If you'd rather keep the repo lean, say so and I'll gitignore it (runlogs become local-only) before you merge.🤖 Generated with Claude Code