merge: incorporate origin/main into community-mode branch

Resolve conflict in gen-skill-docs.ts by keeping both the detailed
error field instructions (community-mode) and the new Plan Status
Footer section (main).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-03-22 21:33:16 -07:00
100 changed files with 11735 additions and 14785 deletions
+76
View File
@@ -0,0 +1,76 @@
/**
* Shared fixture for test coverage audit E2E tests.
*
* Creates a Node.js project with billing source code that has intentional
* test coverage gaps: processPayment has happy-path-only tests,
* refundPayment has no tests at all.
*
* Used by: ship-coverage-audit E2E, review-coverage-audit E2E
*/
import * as fs from 'fs';
import * as path from 'path';
import { spawnSync } from 'child_process';
export function createCoverageAuditFixture(dir: string): void {
// Create a Node.js project WITH test framework but coverage gaps
fs.writeFileSync(path.join(dir, 'package.json'), JSON.stringify({
name: 'test-coverage-app',
version: '1.0.0',
type: 'module',
scripts: { test: 'echo "no tests yet"' },
devDependencies: { vitest: '^1.0.0' },
}, null, 2));
// Create vitest config
fs.writeFileSync(path.join(dir, 'vitest.config.ts'),
`import { defineConfig } from 'vitest/config';\nexport default defineConfig({ test: {} });\n`);
fs.writeFileSync(path.join(dir, 'VERSION'), '0.1.0.0\n');
fs.writeFileSync(path.join(dir, 'CHANGELOG.md'), '# Changelog\n');
// Create source file with multiple code paths
fs.mkdirSync(path.join(dir, 'src'), { recursive: true });
fs.writeFileSync(path.join(dir, 'src', 'billing.ts'), `
export function processPayment(amount: number, currency: string) {
if (amount <= 0) throw new Error('Invalid amount');
if (currency !== 'USD' && currency !== 'EUR') throw new Error('Unsupported currency');
return { status: 'success', amount, currency };
}
export function refundPayment(paymentId: string, reason: string) {
if (!paymentId) throw new Error('Payment ID required');
if (!reason) throw new Error('Reason required');
return { status: 'refunded', paymentId, reason };
}
`);
// Create a test directory with ONE test (partial coverage)
fs.mkdirSync(path.join(dir, 'test'), { recursive: true });
fs.writeFileSync(path.join(dir, 'test', 'billing.test.ts'), `
import { describe, test, expect } from 'vitest';
import { processPayment } from '../src/billing';
describe('processPayment', () => {
test('processes valid payment', () => {
const result = processPayment(100, 'USD');
expect(result.status).toBe('success');
});
// GAP: no test for invalid amount
// GAP: no test for unsupported currency
// GAP: refundPayment not tested at all
});
`);
// Init git repo with main branch
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: dir, stdio: 'pipe', timeout: 5000 });
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
run('git', ['add', '.']);
run('git', ['commit', '-m', 'initial commit']);
// Create feature branch
run('git', ['checkout', '-b', 'feature/billing']);
}
+471 -11
View File
@@ -5,6 +5,39 @@ import * as fs from 'fs';
import * as path from 'path';
const ROOT = path.resolve(import.meta.dir, '..');
const MAX_SKILL_DESCRIPTION_LENGTH = 1024;
function extractDescription(content: string): string {
const fmEnd = content.indexOf('\n---', 4);
expect(fmEnd).toBeGreaterThan(0);
const frontmatter = content.slice(4, fmEnd);
const lines = frontmatter.split('\n');
let description = '';
let inDescription = false;
const descLines: string[] = [];
for (const line of lines) {
if (line.match(/^description:\s*\|?\s*$/)) {
inDescription = true;
continue;
}
if (line.match(/^description:\s*\S/)) {
return line.replace(/^description:\s*/, '').trim();
}
if (inDescription) {
if (line === '' || line.match(/^\s/)) {
descLines.push(line.replace(/^ /, ''));
} else {
break;
}
}
}
if (descLines.length > 0) {
description = descLines.join('\n').trim();
}
return description;
}
// Dynamic template discovery — matches the generator's findTemplates() behavior.
// New skills automatically get test coverage without updating a static list.
@@ -98,6 +131,14 @@ describe('gen-skill-docs', () => {
}
});
test(`every generated SKILL.md description stays within ${MAX_SKILL_DESCRIPTION_LENGTH} chars`, () => {
for (const skill of ALL_SKILLS) {
const content = fs.readFileSync(path.join(ROOT, skill.dir, 'SKILL.md'), 'utf-8');
const description = extractDescription(content);
expect(description.length).toBeLessThanOrEqual(MAX_SKILL_DESCRIPTION_LENGTH);
}
});
test('generated files are fresh (match --dry-run)', () => {
const result = Bun.spawnSync(['bun', 'run', 'scripts/gen-skill-docs.ts', '--dry-run'], {
cwd: ROOT,
@@ -416,6 +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', () => {
@@ -440,6 +625,20 @@ describe('PLAN_FILE_REVIEW_REPORT resolver', () => {
});
});
// --- Plan status footer in preamble ---
describe('Plan status footer in preamble', () => {
test('preamble contains plan status footer', () => {
// Read any skill that uses PREAMBLE
const content = fs.readFileSync(path.join(ROOT, 'office-hours', 'SKILL.md'), 'utf-8');
expect(content).toContain('Plan Status Footer');
expect(content).toContain('GSTACK REVIEW REPORT');
expect(content).toContain('gstack-review-read');
expect(content).toContain('ExitPlanMode');
expect(content).toContain('NO REVIEWS YET');
});
});
// --- {{SPEC_REVIEW_LOOP}} resolver tests ---
describe('SPEC_REVIEW_LOOP resolver', () => {
@@ -506,6 +705,50 @@ describe('DESIGN_SKETCH resolver', () => {
});
});
// --- {{CODEX_SECOND_OPINION}} resolver tests ---
describe('CODEX_SECOND_OPINION resolver', () => {
const content = fs.readFileSync(path.join(ROOT, 'office-hours', 'SKILL.md'), 'utf-8');
const codexContent = fs.readFileSync(path.join(ROOT, '.agents', 'skills', 'gstack-office-hours', 'SKILL.md'), 'utf-8');
test('Phase 3.5 section appears in office-hours SKILL.md', () => {
expect(content).toContain('Phase 3.5: Cross-Model Second Opinion');
});
test('contains codex exec invocation', () => {
expect(content).toContain('codex exec');
});
test('contains opt-in AskUserQuestion text', () => {
expect(content).toContain('second opinion from a different AI model');
});
test('contains cross-model synthesis instructions', () => {
expect(content).toMatch(/[Ss]ynthesis/);
expect(content).toContain('Where Claude agrees with Codex');
});
test('contains premise revision check', () => {
expect(content).toContain('Codex challenged premise');
});
test('contains error handling for auth, timeout, and empty', () => {
expect(content).toMatch(/[Aa]uth.*fail/);
expect(content).toMatch(/[Tt]imeout/);
expect(content).toMatch(/[Ee]mpty response/);
});
test('Codex host variant does NOT contain the Phase 3.5 resolver output', () => {
// The resolver returns '' for codex host, so the interactive section is stripped.
// Static template references to "Phase 3.5" in prose/conditionals are fine.
// Other resolvers (design review lite) may contain CODEX_NOT_AVAILABLE, so we
// check for Phase 3.5-specific markers only.
expect(codexContent).not.toContain('Phase 3.5: Cross-Model Second Opinion');
expect(codexContent).not.toContain('TMPERR_OH');
expect(codexContent).not.toContain('gstack-codex-oh-');
});
});
// --- {{BENEFITS_FROM}} resolver tests ---
describe('BENEFITS_FROM resolver', () => {
@@ -530,6 +773,126 @@ describe('BENEFITS_FROM resolver', () => {
const qaContent = fs.readFileSync(path.join(ROOT, 'qa', 'SKILL.md'), 'utf-8');
expect(qaContent).not.toContain('Prerequisite Skill Offer');
});
test('inline invocation — no "another window" language', () => {
expect(ceoContent).not.toContain('another window');
expect(engContent).not.toContain('another window');
});
test('inline invocation — read-and-follow path present', () => {
expect(ceoContent).toContain('office-hours/SKILL.md');
expect(engContent).toContain('office-hours/SKILL.md');
});
});
// --- {{DESIGN_OUTSIDE_VOICES}} resolver tests ---
describe('DESIGN_OUTSIDE_VOICES resolver', () => {
test('plan-design-review contains outside voices section', () => {
const content = fs.readFileSync(path.join(ROOT, 'plan-design-review', 'SKILL.md'), 'utf-8');
expect(content).toContain('Design Outside Voices');
expect(content).toContain('CODEX_AVAILABLE');
expect(content).toContain('LITMUS SCORECARD');
});
test('design-review contains outside voices section', () => {
const content = fs.readFileSync(path.join(ROOT, 'design-review', 'SKILL.md'), 'utf-8');
expect(content).toContain('Design Outside Voices');
expect(content).toContain('source audit');
});
test('design-consultation contains outside voices section', () => {
const content = fs.readFileSync(path.join(ROOT, 'design-consultation', 'SKILL.md'), 'utf-8');
expect(content).toContain('Design Outside Voices');
expect(content).toContain('design direction');
});
test('branches correctly per skillName — different prompts', () => {
const planContent = fs.readFileSync(path.join(ROOT, 'plan-design-review', 'SKILL.md'), 'utf-8');
const consultContent = fs.readFileSync(path.join(ROOT, 'design-consultation', 'SKILL.md'), 'utf-8');
// plan-design-review uses analytical prompt (high reasoning)
expect(planContent).toContain('model_reasoning_effort="high"');
// design-consultation uses creative prompt (medium reasoning)
expect(consultContent).toContain('model_reasoning_effort="medium"');
});
});
// --- {{DESIGN_HARD_RULES}} resolver tests ---
describe('DESIGN_HARD_RULES resolver', () => {
test('plan-design-review Pass 4 contains hard rules', () => {
const content = fs.readFileSync(path.join(ROOT, 'plan-design-review', 'SKILL.md'), 'utf-8');
expect(content).toContain('Design Hard Rules');
expect(content).toContain('Classifier');
expect(content).toContain('MARKETING/LANDING PAGE');
expect(content).toContain('APP UI');
});
test('design-review contains hard rules', () => {
const content = fs.readFileSync(path.join(ROOT, 'design-review', 'SKILL.md'), 'utf-8');
expect(content).toContain('Design Hard Rules');
});
test('includes all 3 rule sets', () => {
const content = fs.readFileSync(path.join(ROOT, 'plan-design-review', 'SKILL.md'), 'utf-8');
expect(content).toContain('Landing page rules');
expect(content).toContain('App UI rules');
expect(content).toContain('Universal rules');
});
test('references shared AI slop blacklist items', () => {
const content = fs.readFileSync(path.join(ROOT, 'plan-design-review', 'SKILL.md'), 'utf-8');
expect(content).toContain('3-column feature grid');
expect(content).toContain('Purple/violet/indigo');
});
test('includes OpenAI hard rejection criteria', () => {
const content = fs.readFileSync(path.join(ROOT, 'plan-design-review', 'SKILL.md'), 'utf-8');
expect(content).toContain('Generic SaaS card grid');
expect(content).toContain('Carousel with no narrative purpose');
});
test('includes OpenAI litmus checks', () => {
const content = fs.readFileSync(path.join(ROOT, 'plan-design-review', 'SKILL.md'), 'utf-8');
expect(content).toContain('Brand/product unmistakable');
expect(content).toContain('premium with all decorative shadows removed');
});
});
// --- Extended DESIGN_SKETCH resolver tests ---
describe('DESIGN_SKETCH extended with outside voices', () => {
const content = fs.readFileSync(path.join(ROOT, 'office-hours', 'SKILL.md'), 'utf-8');
test('contains outside design voices step', () => {
expect(content).toContain('Outside design voices');
});
test('offers opt-in via AskUserQuestion', () => {
expect(content).toContain('outside design perspectives');
});
test('still contains original wireframe steps', () => {
expect(content).toContain('wireframe');
expect(content).toContain('$B goto');
});
});
// --- Extended DESIGN_REVIEW_LITE resolver tests ---
describe('DESIGN_REVIEW_LITE extended with Codex', () => {
const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
test('contains Codex design voice block', () => {
expect(content).toContain('Codex design voice');
expect(content).toContain('CODEX (design)');
});
test('still contains original checklist steps', () => {
expect(content).toContain('design-checklist.md');
expect(content).toContain('SCOPE_FRONTEND');
});
});
// ─── Codex Generation Tests ─────────────────────────────────
@@ -537,6 +900,11 @@ describe('BENEFITS_FROM resolver', () => {
describe('Codex generation (--host codex)', () => {
const AGENTS_DIR = path.join(ROOT, '.agents', 'skills');
// .agents/ is gitignored (v0.11.2.0) — generate on demand for tests
Bun.spawnSync(['bun', 'run', 'scripts/gen-skill-docs.ts', '--host', 'codex'], {
cwd: ROOT, stdout: 'pipe', stderr: 'pipe',
});
// Dynamic discovery of expected Codex skills: all templates except /codex
const CODEX_SKILLS = (() => {
const skills: Array<{ dir: string; codexName: string }> = [];
@@ -611,11 +979,11 @@ 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', () => {
@@ -683,11 +1051,14 @@ describe('Codex generation (--host codex)', () => {
}
});
test('Codex preamble uses codex paths', () => {
test('Codex preamble resolves runtime assets from repo-local or global gstack roots', () => {
// Check a skill that has a preamble (review is a good candidate)
const content = fs.readFileSync(path.join(AGENTS_DIR, 'gstack-review', 'SKILL.md'), 'utf-8');
expect(content).toContain('~/.codex/skills/gstack');
expect(content).toContain('.agents/skills/gstack');
expect(content).toContain('GSTACK_ROOT');
expect(content).toContain('$_ROOT/.agents/skills/gstack');
expect(content).toContain('$GSTACK_BIN/gstack-config');
expect(content).toContain('$GSTACK_ROOT/gstack-upgrade/SKILL.md');
expect(content).not.toContain('~/.codex/skills/gstack/bin/gstack-config get telemetry');
});
// ─── Path rewriting regression tests ─────────────────────────
@@ -725,9 +1096,9 @@ describe('Codex generation (--host codex)', () => {
// Test each of the 4 path rewrite rules individually
const content = fs.readFileSync(path.join(AGENTS_DIR, 'gstack-review', 'SKILL.md'), 'utf-8');
// Rule 1: ~/.claude/skills/gstack → ~/.codex/skills/gstack
// Rule 1: ~/.claude/skills/gstack → $GSTACK_ROOT
expect(content).not.toContain('~/.claude/skills/gstack');
expect(content).toContain('~/.codex/skills/gstack');
expect(content).toContain('$GSTACK_ROOT');
// Rule 2: .claude/skills/gstack → .agents/skills/gstack
expect(content).not.toContain('.claude/skills/gstack');
@@ -746,6 +1117,9 @@ describe('Codex generation (--host codex)', () => {
// No skill should reference Claude paths
expect(content).not.toContain('~/.claude/skills');
expect(content).not.toContain('.claude/skills');
if (content.includes('gstack-config') || content.includes('gstack-update-check') || content.includes('gstack-telemetry-log')) {
expect(content).toContain('$GSTACK_ROOT');
}
// If a skill references checklist.md, it must use the correct sidecar path
if (content.includes('checklist.md') && !content.includes('design-checklist.md')) {
expect(content).not.toContain('gstack-review/checklist.md');
@@ -776,9 +1150,24 @@ describe('Codex generation (--host codex)', () => {
for (const skill of ALL_SKILLS) {
const content = fs.readFileSync(path.join(ROOT, skill.dir, 'SKILL.md'), 'utf-8');
expect(content).not.toContain('~/.codex/');
expect(content).not.toContain('.agents/skills');
// gstack-upgrade legitimately references .agents/skills for cross-platform detection
if (skill.dir !== 'gstack-upgrade') {
expect(content).not.toContain('.agents/skills');
}
}
});
// ─── Design outside voices: Codex host guard ─────────────────
test('codex host produces empty outside voices in design-review', () => {
const codexContent = fs.readFileSync(path.join(AGENTS_DIR, 'gstack-design-review', 'SKILL.md'), 'utf-8');
expect(codexContent).not.toContain('Design Outside Voices');
});
test('codex host does not include Codex design block in ship', () => {
const codexContent = fs.readFileSync(path.join(AGENTS_DIR, 'gstack-ship', 'SKILL.md'), 'utf-8');
expect(codexContent).not.toContain('Codex design voice');
});
});
// ─── Setup script validation ─────────────────────────────────
@@ -812,8 +1201,31 @@ describe('setup script validation', () => {
setupContent.indexOf('# 5. Install for Codex'),
setupContent.indexOf('# 6. Create')
);
expect(codexSection).toContain('create_codex_runtime_root');
expect(codexSection).toContain('link_codex_skill_dirs');
expect(codexSection).not.toContain('link_claude_skill_dirs');
expect(codexSection).not.toContain('ln -snf "$GSTACK_DIR" "$CODEX_GSTACK"');
});
test('Codex install prefers repo-local .agents/skills when setup runs from there', () => {
expect(setupContent).toContain('SKILLS_PARENT_BASENAME');
expect(setupContent).toContain('CODEX_REPO_LOCAL=0');
expect(setupContent).toContain('[ "$SKILLS_PARENT_BASENAME" = ".agents" ]');
expect(setupContent).toContain('CODEX_REPO_LOCAL=1');
expect(setupContent).toContain('CODEX_SKILLS="$INSTALL_SKILLS_DIR"');
});
test('setup separates install path from source path for symlinked repo-local installs', () => {
expect(setupContent).toContain('INSTALL_GSTACK_DIR=');
expect(setupContent).toContain('SOURCE_GSTACK_DIR=');
expect(setupContent).toContain('INSTALL_SKILLS_DIR=');
expect(setupContent).toContain('CODEX_GSTACK="$INSTALL_GSTACK_DIR"');
expect(setupContent).toContain('link_codex_skill_dirs "$SOURCE_GSTACK_DIR" "$CODEX_SKILLS"');
});
test('Codex installs always create sidecar runtime assets for the real skill target', () => {
expect(setupContent).toContain('if [ "$INSTALL_CODEX" -eq 1 ]; then');
expect(setupContent).toContain('create_agents_sidecar "$SOURCE_GSTACK_DIR"');
});
test('link_codex_skill_dirs reads from .agents/skills/', () => {
@@ -833,14 +1245,40 @@ describe('setup script validation', () => {
expect(fnBody).toContain('ln -snf "gstack/$skill_name"');
});
test('setup supports --host auto|claude|codex', () => {
test('setup supports --host auto|claude|codex|kiro', () => {
expect(setupContent).toContain('--host');
expect(setupContent).toContain('claude|codex|auto');
expect(setupContent).toContain('claude|codex|kiro|auto');
});
test('auto mode detects claude and codex binaries', () => {
test('auto mode detects claude, codex, and kiro binaries', () => {
expect(setupContent).toContain('command -v claude');
expect(setupContent).toContain('command -v codex');
expect(setupContent).toContain('command -v kiro-cli');
});
// T1: Sidecar skip guard — prevents .agents/skills/gstack from being linked as a skill
test('link_codex_skill_dirs skips the gstack sidecar directory', () => {
const fnStart = setupContent.indexOf('link_codex_skill_dirs()');
const fnEnd = setupContent.indexOf('}', setupContent.indexOf('done', fnStart));
const fnBody = setupContent.slice(fnStart, fnEnd);
expect(fnBody).toContain('[ "$skill_name" = "gstack" ] && continue');
});
// T2: Dynamic $GSTACK_ROOT paths in generated Codex preambles
test('generated Codex preambles use dynamic GSTACK_ROOT paths', () => {
const codexSkillDir = path.join(ROOT, '.agents', 'skills', 'gstack-ship');
if (!fs.existsSync(codexSkillDir)) return; // skip if .agents/ not generated
const content = fs.readFileSync(path.join(codexSkillDir, 'SKILL.md'), 'utf-8');
expect(content).toContain('GSTACK_ROOT=');
expect(content).toContain('$GSTACK_BIN/');
});
// T3: Kiro host support in setup script
test('setup supports --host kiro with install section and sed rewrites', () => {
expect(setupContent).toContain('INSTALL_KIRO=');
expect(setupContent).toContain('kiro-cli');
expect(setupContent).toContain('KIRO_SKILLS=');
expect(setupContent).toContain('~/.kiro/skills/gstack');
});
test('create_agents_sidecar links runtime assets', () => {
@@ -853,6 +1291,28 @@ describe('setup script validation', () => {
expect(fnBody).toContain('review');
expect(fnBody).toContain('qa');
});
test('create_codex_runtime_root exposes only runtime assets', () => {
const fnStart = setupContent.indexOf('create_codex_runtime_root()');
const fnEnd = setupContent.indexOf('}', setupContent.indexOf('done', setupContent.indexOf('review/', fnStart)));
const fnBody = setupContent.slice(fnStart, fnEnd);
expect(fnBody).toContain('gstack/SKILL.md');
expect(fnBody).toContain('browse/dist');
expect(fnBody).toContain('browse/bin');
expect(fnBody).toContain('gstack-upgrade/SKILL.md');
// Review runtime assets (individual files, not the whole dir)
expect(fnBody).toContain('checklist.md');
expect(fnBody).toContain('design-checklist.md');
expect(fnBody).toContain('greptile-triage.md');
expect(fnBody).toContain('TODOS-format.md');
expect(fnBody).not.toContain('ln -snf "$gstack_dir" "$codex_gstack"');
});
test('direct Codex installs are migrated out of ~/.codex/skills/gstack', () => {
expect(setupContent).toContain('migrate_direct_codex_install');
expect(setupContent).toContain('$HOME/.gstack/repos/gstack');
expect(setupContent).toContain('avoid duplicate skill discovery');
});
});
describe('telemetry', () => {
+187
View File
@@ -0,0 +1,187 @@
import { describe, test, expect, beforeEach, afterEach } from "bun:test";
import { mkdtempSync, mkdirSync, writeFileSync, rmSync, existsSync } from "fs";
import { join } from "path";
import { tmpdir } from "os";
import { spawnSync } from "child_process";
// Import normalizeRemoteUrl for unit testing
// We test the script end-to-end via CLI and normalizeRemoteUrl via import
const scriptPath = join(import.meta.dir, "..", "bin", "gstack-global-discover.ts");
describe("gstack-global-discover", () => {
describe("normalizeRemoteUrl", () => {
// Dynamically import to test the exported function
let normalizeRemoteUrl: (url: string) => string;
beforeEach(async () => {
const mod = await import("../bin/gstack-global-discover.ts");
normalizeRemoteUrl = mod.normalizeRemoteUrl;
});
test("strips .git suffix", () => {
expect(normalizeRemoteUrl("https://github.com/user/repo.git")).toBe(
"https://github.com/user/repo"
);
});
test("converts SSH to HTTPS", () => {
expect(normalizeRemoteUrl("git@github.com:user/repo.git")).toBe(
"https://github.com/user/repo"
);
});
test("converts SSH without .git to HTTPS", () => {
expect(normalizeRemoteUrl("git@github.com:user/repo")).toBe(
"https://github.com/user/repo"
);
});
test("lowercases host", () => {
expect(normalizeRemoteUrl("https://GitHub.COM/user/repo")).toBe(
"https://github.com/user/repo"
);
});
test("SSH and HTTPS for same repo normalize to same URL", () => {
const ssh = normalizeRemoteUrl("git@github.com:garrytan/gstack.git");
const https = normalizeRemoteUrl("https://github.com/garrytan/gstack.git");
const httpsNoDotGit = normalizeRemoteUrl("https://github.com/garrytan/gstack");
expect(ssh).toBe(https);
expect(https).toBe(httpsNoDotGit);
});
test("handles local: URLs consistently", () => {
const result = normalizeRemoteUrl("local:/tmp/my-repo");
// local: gets parsed as a URL scheme — the important thing is consistency
expect(result).toContain("/tmp/my-repo");
});
test("handles GitLab SSH URLs", () => {
expect(normalizeRemoteUrl("git@gitlab.com:org/project.git")).toBe(
"https://gitlab.com/org/project"
);
});
});
describe("CLI", () => {
test("--help exits 0 and prints usage", () => {
const result = spawnSync("bun", ["run", scriptPath, "--help"], {
encoding: "utf-8",
timeout: 10000,
});
expect(result.status).toBe(0);
expect(result.stderr).toContain("--since");
});
test("no args exits 1 with error", () => {
const result = spawnSync("bun", ["run", scriptPath], {
encoding: "utf-8",
timeout: 10000,
});
expect(result.status).toBe(1);
expect(result.stderr).toContain("--since is required");
});
test("invalid window format exits 1", () => {
const result = spawnSync("bun", ["run", scriptPath, "--since", "abc"], {
encoding: "utf-8",
timeout: 10000,
});
expect(result.status).toBe(1);
expect(result.stderr).toContain("Invalid window format");
});
test("--since 7d produces valid JSON", () => {
const result = spawnSync(
"bun",
["run", scriptPath, "--since", "7d", "--format", "json"],
{ encoding: "utf-8", timeout: 30000 }
);
expect(result.status).toBe(0);
const json = JSON.parse(result.stdout);
expect(json).toHaveProperty("window", "7d");
expect(json).toHaveProperty("repos");
expect(json).toHaveProperty("total_sessions");
expect(json).toHaveProperty("total_repos");
expect(json).toHaveProperty("tools");
expect(Array.isArray(json.repos)).toBe(true);
});
test("--since 7d --format summary produces readable output", () => {
const result = spawnSync(
"bun",
["run", scriptPath, "--since", "7d", "--format", "summary"],
{ encoding: "utf-8", timeout: 30000 }
);
expect(result.status).toBe(0);
expect(result.stdout).toContain("Window: 7d");
expect(result.stdout).toContain("Sessions:");
expect(result.stdout).toContain("Repos:");
});
test("--since 1h returns results (may be empty)", () => {
const result = spawnSync(
"bun",
["run", scriptPath, "--since", "1h", "--format", "json"],
{ encoding: "utf-8", timeout: 30000 }
);
expect(result.status).toBe(0);
const json = JSON.parse(result.stdout);
expect(json.total_sessions).toBeGreaterThanOrEqual(0);
});
});
describe("discovery output structure", () => {
test("repos have required fields", () => {
const result = spawnSync(
"bun",
["run", scriptPath, "--since", "30d", "--format", "json"],
{ encoding: "utf-8", timeout: 30000 }
);
expect(result.status).toBe(0);
const json = JSON.parse(result.stdout);
for (const repo of json.repos) {
expect(repo).toHaveProperty("name");
expect(repo).toHaveProperty("remote");
expect(repo).toHaveProperty("paths");
expect(repo).toHaveProperty("sessions");
expect(Array.isArray(repo.paths)).toBe(true);
expect(repo.paths.length).toBeGreaterThan(0);
expect(repo.sessions).toHaveProperty("claude_code");
expect(repo.sessions).toHaveProperty("codex");
expect(repo.sessions).toHaveProperty("gemini");
}
});
test("tools summary matches repo data", () => {
const result = spawnSync(
"bun",
["run", scriptPath, "--since", "30d", "--format", "json"],
{ encoding: "utf-8", timeout: 30000 }
);
const json = JSON.parse(result.stdout);
// Total sessions should equal sum across tools
const toolTotal =
json.tools.claude_code.total_sessions +
json.tools.codex.total_sessions +
json.tools.gemini.total_sessions;
expect(json.total_sessions).toBe(toolTotal);
});
test("deduplicates Conductor workspaces by remote", () => {
const result = spawnSync(
"bun",
["run", scriptPath, "--since", "30d", "--format", "json"],
{ encoding: "utf-8", timeout: 30000 }
);
const json = JSON.parse(result.stdout);
// Check that no two repos share the same normalized remote
const remotes = json.repos.map((r: any) => r.remote);
const uniqueRemotes = new Set(remotes);
expect(remotes.length).toBe(uniqueRemotes.size);
});
});
});
+19 -10
View File
@@ -70,7 +70,7 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
'plan-eng-review-artifact': ['plan-eng-review/**'],
// Ship
'ship-base-branch': ['ship/**'],
'ship-base-branch': ['ship/**', 'bin/gstack-repo-mode'],
'ship-local-workflow': ['ship/**', 'scripts/gen-skill-docs.ts'],
// Setup browser cookies
@@ -80,6 +80,9 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
'retro': ['retro/**'],
'retro-base-branch': ['retro/**'],
// Global discover
'global-discover': ['bin/gstack-global-discover.ts', 'test/global-discover.test.ts'],
// Document-release
'document-release': ['document-release/**'],
@@ -95,17 +98,20 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
'gemini-review-findings': ['review/**', '.agents/skills/gstack-review/**', 'test/helpers/gemini-session-runner.ts'],
// Ship coverage audit
'ship-coverage-audit': ['ship/**'],
// Coverage audit (shared fixture) + triage
'ship-coverage-audit': ['ship/**', 'test/fixtures/coverage-audit-fixture.ts', 'bin/gstack-repo-mode'],
'review-coverage-audit': ['review/**', 'test/fixtures/coverage-audit-fixture.ts'],
'plan-eng-coverage-audit': ['plan-eng-review/**', 'test/fixtures/coverage-audit-fixture.ts'],
'ship-triage': ['ship/**', 'bin/gstack-repo-mode'],
// Design
'design-consultation-core': ['design-consultation/**'],
'design-consultation-existing': ['design-consultation/**'],
'design-consultation-research': ['design-consultation/**'],
'design-consultation-preview': ['design-consultation/**'],
'plan-design-review-plan-mode': ['plan-design-review/**'],
'plan-design-review-no-ui-scope': ['plan-design-review/**'],
'design-review-fix': ['design-review/**', 'browse/src/**'],
'design-consultation-core': ['design-consultation/**', 'scripts/gen-skill-docs.ts'],
'design-consultation-existing': ['design-consultation/**', 'scripts/gen-skill-docs.ts'],
'design-consultation-research': ['design-consultation/**', 'scripts/gen-skill-docs.ts'],
'design-consultation-preview': ['design-consultation/**', 'scripts/gen-skill-docs.ts'],
'plan-design-review-plan-mode': ['plan-design-review/**', 'scripts/gen-skill-docs.ts'],
'plan-design-review-no-ui-scope': ['plan-design-review/**', 'scripts/gen-skill-docs.ts'],
'design-review-fix': ['design-review/**', 'browse/src/**', 'scripts/gen-skill-docs.ts'],
// gstack-upgrade
'gstack-upgrade-happy-path': ['gstack-upgrade/**'],
@@ -116,6 +122,9 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
'benchmark-workflow': ['benchmark/**', 'browse/src/**'],
'setup-deploy-workflow': ['setup-deploy/**', 'scripts/gen-skill-docs.ts'],
// Autoplan
'autoplan-core': ['autoplan/**', 'plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**'],
// Skill routing — journey-stage tests (depend on ALL skill descriptions)
'journey-ideation': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
'journey-plan-eng': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
File diff suppressed because it is too large Load Diff
+112 -2
View File
@@ -99,6 +99,20 @@ describe('SKILL.md command validation', () => {
const result = validateSkill(skill);
expect(result.snapshotFlagErrors).toHaveLength(0);
});
test('all $B commands in autoplan/SKILL.md are valid browse commands', () => {
const skill = path.join(ROOT, 'autoplan', 'SKILL.md');
if (!fs.existsSync(skill)) return;
const result = validateSkill(skill);
expect(result.invalid).toHaveLength(0);
});
test('all snapshot flags in autoplan/SKILL.md are valid', () => {
const skill = path.join(ROOT, 'autoplan', 'SKILL.md');
if (!fs.existsSync(skill)) return;
const result = validateSkill(skill);
expect(result.snapshotFlagErrors).toHaveLength(0);
});
});
describe('Command registry consistency', () => {
@@ -227,6 +241,7 @@ describe('Update check preamble', () => {
'benchmark/SKILL.md',
'land-and-deploy/SKILL.md',
'setup-deploy/SKILL.md',
'cso/SKILL.md',
];
for (const skill of skillsWithUpdateCheck) {
@@ -543,6 +558,7 @@ describe('v0.4.1 preamble features', () => {
'benchmark/SKILL.md',
'land-and-deploy/SKILL.md',
'setup-deploy/SKILL.md',
'cso/SKILL.md',
];
for (const skill of skillsWithPreamble) {
@@ -821,7 +837,7 @@ describe('Completeness Principle in generated SKILL.md files', () => {
'design-review/SKILL.md',
'design-consultation/SKILL.md',
'document-release/SKILL.md',
];
'cso/SKILL.md', ];
for (const skill of skillsWithPreamble) {
test(`${skill} contains Completeness Principle section`, () => {
@@ -979,6 +995,34 @@ describe('gstack-slug', () => {
expect(lines[0]).toMatch(/^SLUG=.+/);
expect(lines[1]).toMatch(/^BRANCH=.+/);
});
test('output values contain only safe characters (no shell metacharacters)', () => {
const result = Bun.spawnSync([SLUG_BIN], { cwd: ROOT, stdout: 'pipe', stderr: 'pipe' });
const slug = result.stdout.toString().match(/SLUG=(.*)/)?.[1] ?? '';
const branch = result.stdout.toString().match(/BRANCH=(.*)/)?.[1] ?? '';
// Only alphanumeric, dot, dash, underscore are allowed (#133)
expect(slug).toMatch(/^[a-zA-Z0-9._-]+$/);
expect(branch).toMatch(/^[a-zA-Z0-9._-]+$/);
});
test('eval sets variables under bash with set -euo pipefail', () => {
const result = Bun.spawnSync(
['bash', '-c', 'set -euo pipefail; eval "$(./bin/gstack-slug 2>/dev/null)"; echo "SLUG=$SLUG"; echo "BRANCH=$BRANCH"'],
{ cwd: ROOT, stdout: 'pipe', stderr: 'pipe' }
);
expect(result.exitCode).toBe(0);
const output = result.stdout.toString();
expect(output).toMatch(/^SLUG=.+/m);
expect(output).toMatch(/^BRANCH=.+/m);
});
test('no templates or bin scripts use source process substitution for gstack-slug', () => {
const result = Bun.spawnSync(
['grep', '-r', 'source <(.*gstack-slug', '--include=*.tmpl', '--include=gstack-review-*', '.'],
{ cwd: ROOT, stdout: 'pipe', stderr: 'pipe' }
);
// grep returns exit code 1 when no matches found — that's what we want
expect(result.stdout.toString().trim()).toBe('');
});
});
// --- Test Bootstrap validation ---
@@ -1303,12 +1347,18 @@ describe('Codex skill', () => {
});
test('codex-host ship/review do NOT contain adversarial review step', () => {
// .agents/ is gitignored — generate on demand
Bun.spawnSync(['bun', 'run', 'scripts/gen-skill-docs.ts', '--host', 'codex'], {
cwd: ROOT, stdout: 'pipe', stderr: 'pipe',
});
const shipContent = fs.readFileSync(path.join(ROOT, '.agents', 'skills', '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(ROOT, '.agents', 'skills', 'gstack-review', 'SKILL.md'), 'utf-8');
expect(reviewContent).not.toContain('codex review --base');
expect(reviewContent).not.toContain('codex_reviews');
expect(reviewContent).not.toContain('CODEX_REVIEWS');
expect(reviewContent).not.toContain('adversarial-review');
expect(reviewContent).not.toContain('Investigate and fix');
});
@@ -1375,6 +1425,11 @@ describe('Skill trigger phrases', () => {
describe('Codex skill validation', () => {
const AGENTS_DIR = path.join(ROOT, '.agents', 'skills');
// .agents/ is gitignored (v0.11.2.0) — generate on demand for tests
Bun.spawnSync(['bun', 'run', 'scripts/gen-skill-docs.ts', '--host', 'codex'], {
cwd: ROOT, stdout: 'pipe', stderr: 'pipe',
});
// Discover all Claude skills with templates (except /codex which is Claude-only)
const CLAUDE_SKILLS_WITH_TEMPLATES = (() => {
const skills: string[] = [];
@@ -1436,3 +1491,58 @@ describe('Codex skill validation', () => {
}
});
});
// --- Repo mode and test failure triage validation ---
describe('Repo mode preamble validation', () => {
test('generated SKILL.md preamble contains REPO_MODE output', () => {
const content = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
expect(content).toContain('REPO_MODE:');
expect(content).toContain('gstack-repo-mode');
});
test('generated SKILL.md contains See Something Say Something section', () => {
const content = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
expect(content).toContain('See Something, Say Something');
expect(content).toContain('REPO_MODE');
expect(content).toContain('solo');
expect(content).toContain('collaborative');
});
});
describe('Test failure triage in ship skill', () => {
test('ship/SKILL.md contains Test Failure Ownership Triage', () => {
const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
expect(content).toContain('Test Failure Ownership Triage');
});
test('ship/SKILL.md triage uses git diff for classification', () => {
const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
expect(content).toContain('git diff origin/<base>...HEAD --name-only');
});
test('ship/SKILL.md triage has solo and collaborative paths', () => {
const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
expect(content).toContain('REPO_MODE');
expect(content).toContain('solo');
expect(content).toContain('collaborative');
expect(content).toContain('Investigate and fix now');
expect(content).toContain('Add as P0 TODO');
});
test('ship/SKILL.md triage has GitHub issue assignment for collaborative mode', () => {
const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
expect(content).toContain('gh issue create');
expect(content).toContain('--assignee');
});
test('{{TEST_FAILURE_TRIAGE}} placeholder is fully resolved in ship/SKILL.md', () => {
const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
expect(content).not.toContain('{{TEST_FAILURE_TRIAGE}}');
});
test('ship/SKILL.md uses in-branch language for stop condition', () => {
const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
expect(content).toContain('In-branch test failures');
});
});
+3 -2
View File
@@ -79,8 +79,9 @@ describe('selectTests', () => {
expect(result.selected).toContain('plan-ceo-review');
expect(result.selected).toContain('plan-ceo-review-selective');
expect(result.selected).toContain('plan-ceo-review-benefits');
expect(result.selected.length).toBe(3);
expect(result.skipped.length).toBe(Object.keys(E2E_TOUCHFILES).length - 3);
expect(result.selected).toContain('autoplan-core');
expect(result.selected.length).toBe(4);
expect(result.skipped.length).toBe(Object.keys(E2E_TOUCHFILES).length - 4);
});
test('global touchfile triggers ALL tests', () => {