mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-16 01:02:13 +08:00
feat: Review Army — parallel specialist reviewers for /review (v0.14.3.0) (#692)
* feat: extend gstack-diff-scope with SCOPE_MIGRATIONS, SCOPE_API, SCOPE_AUTH
Three new scope signals for Review Army specialist activation:
- SCOPE_MIGRATIONS: db/migrate/, prisma/migrations/, alembic/, *.sql
- SCOPE_API: *controller*, *route*, *endpoint*, *.graphql, openapi.*
- SCOPE_AUTH: *auth*, *session*, *jwt*, *oauth*, *permission*, *role*
* feat: add 7 specialist checklist files for Review Army
- testing.md (always-on): coverage gaps, flaky patterns, security enforcement
- maintainability.md (always-on): dead code, DRY, stale comments
- security.md (conditional): OWASP deep analysis, auth bypass, injection
- performance.md (conditional): N+1 queries, bundle impact, complexity
- data-migration.md (conditional): reversibility, lock duration, backfill
- api-contract.md (conditional): breaking changes, versioning, error format
- red-team.md (conditional): adversarial analysis, cross-cutting concerns
All use standard header with JSON output schema and NO FINDINGS fallback.
* feat: Review Army resolver — parallel specialist dispatch + merge
New resolver in review-army.ts generates template prose for:
- Stack detection and specialist selection
- Parallel Agent tool dispatch with learning-informed prompts
- JSON finding collection, fingerprint dedup, consensus highlighting
- PR quality score computation
- Red Team conditional dispatch
Registered as REVIEW_ARMY in resolvers/index.ts.
* refactor: restructure /review template for Review Army
- Replace Steps 4-4.75 with CRITICAL pass + {{REVIEW_ARMY}}
- Remove {{DESIGN_REVIEW_LITE}} and {{TEST_COVERAGE_AUDIT_REVIEW}}
(subsumed into Design and Testing specialists respectively)
- Extract specialist-covered categories from checklist.md
- Keep CRITICAL + uncovered INFORMATIONAL in main agent pass
* test: Review Army — 14 diff-scope tests + 7 E2E tests
- test/diff-scope.test.ts: 14 tests for all 9 scope signals
- test/skill-e2e-review-army.test.ts: 7 E2E tests
Gate: migration safety, N+1 detection, delivery audit,
quality score, JSON findings
Periodic: red team, consensus
- Updated gen-skill-docs tests for new review structure
- Added touchfile entries and tier classifications
* docs: update SELF_LEARNING_V0.md with Release 2 status + Release 2.5
Mark Release 2 (Review Army) as in-progress. Add Release 2.5 for
deferred expansions (E1 adaptive gating, E3 test stubs, E5 cross-review
dedup, E7 specialist tracking).
* chore: bump version and changelog (v0.14.3.0)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
@@ -607,7 +607,8 @@ describe('TEST_COVERAGE_AUDIT placeholders', () => {
|
||||
const shipSkill = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
|
||||
const reviewSkill = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
|
||||
test('all three modes share codepath tracing methodology', () => {
|
||||
test('plan and ship modes share codepath tracing methodology', () => {
|
||||
// Review mode delegates test coverage to the Testing specialist subagent (Review Army)
|
||||
const sharedPhrases = [
|
||||
'Trace data flow',
|
||||
'Diagram the execution',
|
||||
@@ -619,33 +620,40 @@ describe('TEST_COVERAGE_AUDIT placeholders', () => {
|
||||
for (const phrase of sharedPhrases) {
|
||||
expect(planSkill).toContain(phrase);
|
||||
expect(shipSkill).toContain(phrase);
|
||||
expect(reviewSkill).toContain(phrase);
|
||||
}
|
||||
// Plan mode traces the plan, not a git diff
|
||||
expect(planSkill).toContain('Trace every codepath in the plan');
|
||||
expect(planSkill).not.toContain('git diff origin');
|
||||
// Ship and review modes trace the diff
|
||||
// Ship mode traces the diff
|
||||
expect(shipSkill).toContain('Trace every codepath changed');
|
||||
expect(reviewSkill).toContain('Trace every codepath changed');
|
||||
});
|
||||
|
||||
test('all three modes include E2E decision matrix', () => {
|
||||
for (const skill of [planSkill, shipSkill, reviewSkill]) {
|
||||
test('review mode uses Review Army for specialist dispatch', () => {
|
||||
expect(reviewSkill).toContain('Review Army');
|
||||
expect(reviewSkill).toContain('Specialist Dispatch');
|
||||
expect(reviewSkill).toContain('testing.md');
|
||||
});
|
||||
|
||||
test('plan and ship modes include E2E decision matrix', () => {
|
||||
// Review mode delegates to Testing specialist
|
||||
for (const skill of [planSkill, shipSkill]) {
|
||||
expect(skill).toContain('E2E Test Decision Matrix');
|
||||
expect(skill).toContain('→E2E');
|
||||
expect(skill).toContain('→EVAL');
|
||||
}
|
||||
});
|
||||
|
||||
test('all three modes include regression rule', () => {
|
||||
for (const skill of [planSkill, shipSkill, reviewSkill]) {
|
||||
test('plan and ship modes include regression rule', () => {
|
||||
// Review mode delegates to Testing specialist
|
||||
for (const skill of [planSkill, shipSkill]) {
|
||||
expect(skill).toContain('REGRESSION RULE');
|
||||
expect(skill).toContain('IRON RULE');
|
||||
}
|
||||
});
|
||||
|
||||
test('all three modes include test framework detection', () => {
|
||||
for (const skill of [planSkill, shipSkill, reviewSkill]) {
|
||||
test('plan and ship modes include test framework detection', () => {
|
||||
// Review mode delegates to Testing specialist
|
||||
for (const skill of [planSkill, shipSkill]) {
|
||||
expect(skill).toContain('Test Framework Detection');
|
||||
expect(skill).toContain('CLAUDE.md');
|
||||
}
|
||||
@@ -664,11 +672,12 @@ describe('TEST_COVERAGE_AUDIT placeholders', () => {
|
||||
expect(shipSkill).toContain('ship-test-plan');
|
||||
});
|
||||
|
||||
test('review mode generates via Fix-First + gaps are INFORMATIONAL', () => {
|
||||
test('review mode uses Fix-First + Review Army for specialist coverage', () => {
|
||||
expect(reviewSkill).toContain('Fix-First');
|
||||
expect(reviewSkill).toContain('INFORMATIONAL');
|
||||
expect(reviewSkill).toContain('Step 4.75');
|
||||
expect(reviewSkill).toContain('subsumes the "Test Gaps" category');
|
||||
// Review Army handles test coverage via Testing specialist subagent
|
||||
expect(reviewSkill).toContain('Review Army');
|
||||
expect(reviewSkill).toContain('Testing');
|
||||
});
|
||||
|
||||
test('plan mode does NOT include ship-specific content', () => {
|
||||
@@ -683,6 +692,35 @@ describe('TEST_COVERAGE_AUDIT placeholders', () => {
|
||||
expect(reviewSkill).not.toContain('ship-test-plan');
|
||||
});
|
||||
|
||||
test('review/specialists/ directory has all expected checklist files', () => {
|
||||
const specDir = path.join(ROOT, 'review', 'specialists');
|
||||
const expected = [
|
||||
'testing.md',
|
||||
'maintainability.md',
|
||||
'security.md',
|
||||
'performance.md',
|
||||
'data-migration.md',
|
||||
'api-contract.md',
|
||||
'red-team.md',
|
||||
];
|
||||
for (const f of expected) {
|
||||
expect(fs.existsSync(path.join(specDir, f))).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
test('each specialist file has standard header with scope and output format', () => {
|
||||
const specDir = path.join(ROOT, 'review', 'specialists');
|
||||
const files = fs.readdirSync(specDir).filter(f => f.endsWith('.md'));
|
||||
for (const f of files) {
|
||||
const content = fs.readFileSync(path.join(specDir, f), 'utf-8');
|
||||
// All specialist files must have Scope and Output/JSON in header
|
||||
expect(content).toContain('Scope:');
|
||||
expect(content.toLowerCase()).toMatch(/output|json/);
|
||||
// Must define NO FINDINGS behavior
|
||||
expect(content).toContain('NO FINDINGS');
|
||||
}
|
||||
});
|
||||
|
||||
// Regression guard: ship output contains key phrases from before the refactor
|
||||
test('ship SKILL.md regression guard — key phrases preserved', () => {
|
||||
const regressionPhrases = [
|
||||
@@ -870,12 +908,9 @@ describe('Coverage gate in ship', () => {
|
||||
expect(shipSkill).toContain('could not determine percentage — skipping');
|
||||
});
|
||||
|
||||
test('review SKILL.md contains coverage WARNING', () => {
|
||||
expect(reviewSkill).toContain('COVERAGE WARNING');
|
||||
expect(reviewSkill).toContain('Consider writing tests before running /ship');
|
||||
});
|
||||
|
||||
test('review coverage warning is INFORMATIONAL', () => {
|
||||
test('review SKILL.md delegates coverage to Testing specialist', () => {
|
||||
// Coverage audit moved to Testing specialist subagent in Review Army
|
||||
expect(reviewSkill).toContain('testing.md');
|
||||
expect(reviewSkill).toContain('INFORMATIONAL');
|
||||
});
|
||||
});
|
||||
@@ -1604,10 +1639,9 @@ describe('Codex generation (--host codex)', () => {
|
||||
const content = fs.readFileSync(path.join(AGENTS_DIR, 'gstack-review', 'SKILL.md'), 'utf-8');
|
||||
// Correct: references to sidecar files use gstack/review/ path
|
||||
expect(content).toContain('.agents/skills/gstack/review/checklist.md');
|
||||
expect(content).toContain('.agents/skills/gstack/review/design-checklist.md');
|
||||
// design-checklist.md is now referenced via Review Army specialist (Claude only, stripped for Codex)
|
||||
// Wrong: must NOT reference gstack-review/checklist.md (file doesn't exist there)
|
||||
expect(content).not.toContain('.agents/skills/gstack-review/checklist.md');
|
||||
expect(content).not.toContain('.agents/skills/gstack-review/design-checklist.md');
|
||||
});
|
||||
|
||||
test('sidecar paths in ship skill point to gstack/review/ for pre-landing review', () => {
|
||||
|
||||
Reference in New Issue
Block a user