voyage/tests/fixtures
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
..
bakeoff feat(voyage): S10 — NW2 part A (Workflow port + fidelity harness + smoke) 2026-06-18 14:40:19 +02:00
bakeoff-rich feat(eval): SKAL-1·4b offline gold-scored output eval 2026-06-30 09:00:33 +02:00
red-first feat(measure): the yardstick prints Voyage's three numbers with denominators from the source, and it is RED 2026-09-22 21:50:06 +02:00
session-orders feat(execute)!: hand waves over as session orders, never start Claude Code (green) 2026-09-27 15:35:22 +02:00
session-state test(ultraplan-local): add session-state fixtures 2026-05-01 20:21:50 +02:00
synthesis feat(voyage): S12 — NW3 synthesis-agent built + measured → declined per measurement [skip-docs] 2026-06-18 17:58:39 +02:00
token-usage feat(stats): add pure token-usage parser + cache-aware cost derivation 2026-06-26 14:32:10 +02:00
trekreview feat(review): the review is a gate - verdict in the file, CC engine, project memory 2026-10-06 19:45:52 +02:00
brief-effort-fable.md test(validators): cover fable accept + unknown-model reject in both gate layers 2026-07-02 16:56:26 +02:00
brief-effort-high.md test(voyage): add 4 brief fixtures for v5.1.1 runtime scenarios 2026-05-14 21:34:51 +02:00
brief-effort-low.md test(voyage): add 4 brief fixtures for v5.1.1 runtime scenarios 2026-05-14 21:34:51 +02:00
brief-effort-standard.md test(voyage): add 4 brief fixtures for v5.1.1 runtime scenarios 2026-05-14 21:34:51 +02:00
brief-success-criteria.md fix(verification): the criteria runner screens with an ALLOWLIST, not a denylist 2026-09-18 02:51:40 +02:00
brief-v21-no-signals.md test(voyage): add 4 brief fixtures for v5.1.1 runtime scenarios 2026-05-14 21:34:51 +02:00
brief-with-phase-signals.md feat(voyage): bump trekbrief-template to brief_version 2.1 + add phase_signals fixtures 2026-05-13 21:09:57 +02:00
brief-without-phase-signals.md feat(voyage): bump trekbrief-template to brief_version 2.1 + add phase_signals fixtures 2026-05-13 21:09:57 +02:00
criteria-exit-0.sh fix(verification): the criteria runner screens with an ALLOWLIST, not a denylist 2026-09-18 02:51:40 +02:00
criteria-exit-1.sh fix(verification): the criteria runner screens with an ALLOWLIST, not a denylist 2026-09-18 02:51:40 +02:00
end-state-frozen.json fix(end-state): a behaviour probe must FELL a stub, not just name a test 2026-09-18 02:56:22 +02:00
expected.prom feat(trekresearch): emit and export the five STORM measurement fields 2026-08-09 15:01:15 +02:00
jsonl-schemas.md fix(execute): the Phase 8 payload goes on stdin; /trekreview findings closed 2026-10-05 18:16:46 +02:00
plan-fase-narrative.md chore(release): ultraplan-local v3.1.0 2026-05-01 06:31:42 +02:00
plan-profile-drift.md feat(voyage): emit MANIFEST_PROFILE_DRIFT warning in plan-validator strict mode — brief assumption 7 2026-05-09 10:02:53 +02:00
plan-verification-fails.md fix(verification): the criteria runner screens with an ALLOWLIST, not a denylist 2026-09-18 02:51:40 +02:00
plan-verification-passes.md fix(verification): the criteria runner screens with an ALLOWLIST, not a denylist 2026-09-18 02:51:40 +02:00
plan-with-profile.md feat(voyage): add lib/profiles/resolver.mjs — locked interface SC #5-#9 2026-05-09 09:29:01 +02:00
plan-without-profile.md feat(voyage): add lib/profiles/resolver.mjs — locked interface SC #5-#9 2026-05-09 09:29:01 +02:00
profile-invalid-enum.yaml feat(voyage): add lib/validators/profile-validator.mjs — SC #1, #2, #3 2026-05-09 09:26:23 +02:00
profile-invalid-model.yaml feat(voyage): add lib/validators/profile-validator.mjs — SC #1, #2, #3 2026-05-09 09:26:23 +02:00
research-deep-research-adapted.md test(trekresearch): pin deep-research adapter output contract 2026-06-30 13:38:09 +02:00
stats-sample.jsonl feat(trekresearch): emit and export the five STORM measurement fields 2026-08-09 15:01:15 +02:00
stats-with-profile.jsonl feat(voyage): add 5 additive profile fields to JSONL stats — SC #11 2026-05-09 09:40:21 +02:00