mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-17 17:51:27 +08:00
Merge remote-tracking branch 'origin/main' into garrytan/codex-compat-wave2
# Conflicts: # .agents/skills/gstack-autoplan/SKILL.md # .agents/skills/gstack-benchmark/SKILL.md # .agents/skills/gstack-browse/SKILL.md # .agents/skills/gstack-canary/SKILL.md # .agents/skills/gstack-design-consultation/SKILL.md # .agents/skills/gstack-design-review/SKILL.md # .agents/skills/gstack-document-release/SKILL.md # .agents/skills/gstack-investigate/SKILL.md # .agents/skills/gstack-land-and-deploy/SKILL.md # .agents/skills/gstack-office-hours/SKILL.md # .agents/skills/gstack-plan-ceo-review/SKILL.md # .agents/skills/gstack-plan-design-review/SKILL.md # .agents/skills/gstack-plan-eng-review/SKILL.md # .agents/skills/gstack-qa-only/SKILL.md # .agents/skills/gstack-qa/SKILL.md # .agents/skills/gstack-retro/SKILL.md # .agents/skills/gstack-review/SKILL.md # .agents/skills/gstack-setup-browser-cookies/SKILL.md # .agents/skills/gstack-setup-deploy/SKILL.md # .agents/skills/gstack-ship/SKILL.md # .agents/skills/gstack/SKILL.md # .github/workflows/skill-docs.yml # README.md
This commit is contained in:
Garry Tan
@@ -457,6 +457,150 @@ describe('REVIEW_DASHBOARD resolver', () => {
|
||||
});
|
||||
});
|
||||
|
||||
// ─── Test Coverage Audit Resolver Tests ─────────────────────
|
||||
|
||||
describe('TEST_COVERAGE_AUDIT placeholders', () => {
|
||||
const planSkill = fs.readFileSync(path.join(ROOT, 'plan-eng-review', 'SKILL.md'), 'utf-8');
|
||||
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', () => {
|
||||
const sharedPhrases = [
|
||||
'Trace data flow',
|
||||
'Diagram the execution',
|
||||
'Quality scoring rubric',
|
||||
'★★★',
|
||||
'★★',
|
||||
'GAP',
|
||||
];
|
||||
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
|
||||
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]) {
|
||||
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]) {
|
||||
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]) {
|
||||
expect(skill).toContain('Test Framework Detection');
|
||||
expect(skill).toContain('CLAUDE.md');
|
||||
}
|
||||
});
|
||||
|
||||
test('plan mode adds tests to plan + includes test plan artifact', () => {
|
||||
expect(planSkill).toContain('Add missing tests to the plan');
|
||||
expect(planSkill).toContain('eng-review-test-plan');
|
||||
expect(planSkill).toContain('Test Plan Artifact');
|
||||
});
|
||||
|
||||
test('ship mode auto-generates tests + includes before/after count', () => {
|
||||
expect(shipSkill).toContain('Generate tests for uncovered paths');
|
||||
expect(shipSkill).toContain('Before/after test count');
|
||||
expect(shipSkill).toContain('30 code paths max');
|
||||
expect(shipSkill).toContain('ship-test-plan');
|
||||
});
|
||||
|
||||
test('review mode generates via Fix-First + gaps are INFORMATIONAL', () => {
|
||||
expect(reviewSkill).toContain('Fix-First');
|
||||
expect(reviewSkill).toContain('INFORMATIONAL');
|
||||
expect(reviewSkill).toContain('Step 4.75');
|
||||
expect(reviewSkill).toContain('subsumes the "Test Gaps" category');
|
||||
});
|
||||
|
||||
test('plan mode does NOT include ship-specific content', () => {
|
||||
expect(planSkill).not.toContain('Before/after test count');
|
||||
expect(planSkill).not.toContain('30 code paths max');
|
||||
expect(planSkill).not.toContain('ship-test-plan');
|
||||
});
|
||||
|
||||
test('review mode does NOT include test plan artifact', () => {
|
||||
expect(reviewSkill).not.toContain('Test Plan Artifact');
|
||||
expect(reviewSkill).not.toContain('eng-review-test-plan');
|
||||
expect(reviewSkill).not.toContain('ship-test-plan');
|
||||
});
|
||||
|
||||
// Regression guard: ship output contains key phrases from before the refactor
|
||||
test('ship SKILL.md regression guard — key phrases preserved', () => {
|
||||
const regressionPhrases = [
|
||||
'100% coverage is the goal',
|
||||
'ASCII coverage diagram',
|
||||
'processPayment',
|
||||
'refundPayment',
|
||||
'billing.test.ts',
|
||||
'checkout.e2e.ts',
|
||||
'COVERAGE:',
|
||||
'QUALITY:',
|
||||
'GAPS:',
|
||||
'Code paths:',
|
||||
'User flows:',
|
||||
];
|
||||
for (const phrase of regressionPhrases) {
|
||||
expect(shipSkill).toContain(phrase);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
// --- {{TEST_FAILURE_TRIAGE}} resolver tests ---
|
||||
|
||||
describe('TEST_FAILURE_TRIAGE resolver', () => {
|
||||
const shipSkill = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
|
||||
|
||||
test('contains all 4 triage steps', () => {
|
||||
expect(shipSkill).toContain('Step T1: Classify each failure');
|
||||
expect(shipSkill).toContain('Step T2: Handle in-branch failures');
|
||||
expect(shipSkill).toContain('Step T3: Handle pre-existing failures');
|
||||
expect(shipSkill).toContain('Step T4: Execute the chosen action');
|
||||
});
|
||||
|
||||
test('T1 includes classification criteria (in-branch vs pre-existing)', () => {
|
||||
expect(shipSkill).toContain('In-branch');
|
||||
expect(shipSkill).toContain('Likely pre-existing');
|
||||
expect(shipSkill).toContain('git diff origin/');
|
||||
});
|
||||
|
||||
test('T3 branches on REPO_MODE (solo vs collaborative)', () => {
|
||||
expect(shipSkill).toContain('REPO_MODE');
|
||||
expect(shipSkill).toContain('solo');
|
||||
expect(shipSkill).toContain('collaborative');
|
||||
});
|
||||
|
||||
test('solo mode offers fix-now, TODO, and skip options', () => {
|
||||
expect(shipSkill).toContain('Investigate and fix now');
|
||||
expect(shipSkill).toContain('Add as P0 TODO');
|
||||
expect(shipSkill).toContain('Skip');
|
||||
});
|
||||
|
||||
test('collaborative mode offers blame + assign option', () => {
|
||||
expect(shipSkill).toContain('Blame + assign GitHub issue');
|
||||
expect(shipSkill).toContain('gh issue create');
|
||||
});
|
||||
|
||||
test('defaults ambiguous failures to in-branch (safety)', () => {
|
||||
expect(shipSkill).toContain('When ambiguous, default to in-branch');
|
||||
});
|
||||
});
|
||||
|
||||
// --- {{PLAN_FILE_REVIEW_REPORT}} resolver tests ---
|
||||
|
||||
describe('PLAN_FILE_REVIEW_REPORT resolver', () => {
|
||||
@@ -652,11 +796,11 @@ describe('Codex generation (--host codex)', () => {
|
||||
test('Codex review step stripped from Codex-host ship and review', () => {
|
||||
const shipContent = fs.readFileSync(path.join(AGENTS_DIR, 'gstack-ship', 'SKILL.md'), 'utf-8');
|
||||
expect(shipContent).not.toContain('codex review --base');
|
||||
expect(shipContent).not.toContain('Investigate and fix');
|
||||
expect(shipContent).not.toContain('CODEX_REVIEWS');
|
||||
|
||||
const reviewContent = fs.readFileSync(path.join(AGENTS_DIR, 'gstack-review', 'SKILL.md'), 'utf-8');
|
||||
expect(reviewContent).not.toContain('codex review --base');
|
||||
expect(reviewContent).not.toContain('Investigate and fix');
|
||||
expect(reviewContent).not.toContain('CODEX_REVIEWS');
|
||||
});
|
||||
|
||||
test('--host codex --dry-run freshness', () => {
|
||||
|
||||
Reference in New Issue
Block a user