voyage/scripts
Kjell Tore Guttormsen d88245c06e
feat(review): the review is a gate - verdict in the file, CC engine, project memory
Ordre 5 (wave 1, P11 + P5), review_version 1.1.

- K7: `verdict: ALLOW | WARN | BLOCK` is required in review.md (strict
  error, soft warning for 1.0 reviews). New CLI lib/review/verdict-gate.mjs:
  0 = ALLOW/WARN, 1 = BLOCK, 2 = could not decide (never green); a verdict
  greener than the file's own BLOCKERs or JSON block is exit 2. Realpath
  main guard (the old file:// guard exits 0 under a symlink - measured).
- No finding is struck for length: succinctness trims only MINOR/SUGGESTION
  text (catalogue tier), keeps BLOCKER/MAJOR whole, counts trims; the
  coordinator lists what it declined to judge.
- Claude Code's /code-review and /security-review run as the engine via the
  Skill tool (never --fix/--comment/--post/ultra); lib/review/engine-findings.mjs
  turns their findings into a reviewer payload; two catalogue keys
  (CODE_REVIEW_DEFECT, SECURITY_REVIEW_VULNERABILITY), catalogue 12 -> 14.
  An engine that did not run forbids ALLOW.
- Every BLOCKER is written as a numbered `### Step R<n>` with its source
  finding (strict error REVIEW_MISSING_REMEDIATION_STEP).
- P5: lib/review/recurrence.mjs - a finding class in two review.md files
  (current + git history, no new store) becomes one proposal, routed by the
  catalogue's memory_route; written only between Voyage markers in
  .claude/rules/voyage-review-lessons.md under a size budget, CLAUDE.md gets
  a pointer only; the operator approves every line (Phase 8.7).
- Workflow substrate: catalogue enum in step; a missing reviewer or engine
  forbids ALLOW there too (it returned ALLOW on zero findings before).
- Fixtures review-run-A/B said WARN over a BLOCKER; now BLOCK.

Borrowed and credited in code: Superpowers (declined-to-judge), ai-native-sdlc
(cap only nits; mistake/fix/check), Spec Kit (managed block; converge steps),
Pocock (retro routing), Kiro (verdict file + gate; evidence per lesson),
Cherny (engine -> brief control order; review -> memory; budget).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-06 19:45:52 +02:00
..
annotate.mjs docs: remove dead references to a retired repository (green) 2026-09-23 12:28:05 +02:00
bakeoff-armA-merge.mjs feat(voyage): S10 part B — NW2 full bake-off (rich fixture) → verdict POSITIVE 2026-06-18 15:44:24 +02:00
bakeoff-fidelity.mjs feat(voyage): S10 part B — NW2 full bake-off (rich fixture) → verdict POSITIVE 2026-06-18 15:44:24 +02:00
comparison-gate.mjs feat(measure): the comparison gate counts the 14 areas against five frameworks and the tidy denominator, and it is RED [skip-docs] 2026-10-02 20:31:14 +02:00
end-state-gate.mjs fix(end-state): a behaviour probe must FELL a stub, not just name a test 2026-09-18 02:56:22 +02:00
end-state-registry.json fix(end-state): a behaviour probe must FELL a stub, not just name a test 2026-09-18 02:56:22 +02:00
gen-expected-prom.mjs feat(voyage): add lib/exporters/textfile-format.mjs — Prometheus text-format pure transform SC #12 2026-05-09 09:30:58 +02:00
storm-measure.mjs fix(storm-measure): check BOTH halves of the activation SC, not just the count delta 2026-08-12 23:01:59 +02:00
synthesis-measure.mjs feat(voyage): S12 — NW3 synthesis-agent built + measured → declined per measurement [skip-docs] 2026-06-18 17:58:39 +02:00
trekreview-armB.workflow.mjs feat(review): the review is a gate - verdict in the file, CC engine, project memory 2026-10-06 19:45:52 +02:00
yardstick.mjs fix(yardstick): use counts an order only when a Voyage record names its id (green) 2026-10-04 19:53:31 +02:00