mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-17 09:41:28 +08:00
Merge branch 'main' into garrytan/team-supabase-store
Brings in 48 commits from main (v0.15.7–v0.15.16): deterministic slugs, TabSession refactor, pair-agent tunnel fix, content security layers, community security wave, team-friendly install, interactive snapshots. Conflict resolution: - .gitignore: merged both sides (kept .factory/ + added .kiro/.opencode/ .slate/.cursor/.openclaw/ from main) - open-gstack-browser/SKILL.md: accepted main (renamed from .factory/) - setup-team-sync/SKILL.md: regenerated via gen:skill-docs - test/fixtures/golden/*: updated golden baselines for ship SKILL.md - codex-ship-SKILL.md: accepted main (renamed from .factory/) - package.json version: synced to VERSION (0.15.16.0) - bin/gstack-uninstall: check settings file exists before claiming SessionStart hook removal (fixes false positive on clean systems) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
@@ -213,11 +213,20 @@ describe('gen-skill-docs', () => {
|
||||
expect(browseTmpl).toContain('{{PREAMBLE}}');
|
||||
});
|
||||
|
||||
test('generated SKILL.md contains contributor mode check', () => {
|
||||
test('generated SKILL.md contains operational self-improvement (replaced contributor mode)', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('Contributor Mode');
|
||||
expect(content).toContain('gstack_contributor');
|
||||
expect(content).toContain('contributor-logs');
|
||||
expect(content).not.toContain('Contributor Mode');
|
||||
expect(content).not.toContain('gstack_contributor');
|
||||
expect(content).not.toContain('contributor-logs');
|
||||
expect(content).toContain('Operational Self-Improvement');
|
||||
expect(content).toContain('gstack-learnings-log');
|
||||
expect(content).toContain('gstack-learnings-search --limit 3');
|
||||
});
|
||||
|
||||
test('generated SKILL.md with LEARNINGS_LOG contains operational type', () => {
|
||||
// Check a skill that has LEARNINGS_LOG (e.g., review)
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('operational');
|
||||
});
|
||||
|
||||
test('generated SKILL.md contains session awareness', () => {
|
||||
@@ -586,10 +595,12 @@ describe('REVIEW_DASHBOARD resolver', () => {
|
||||
expect(content).toContain('/plan-ceo-review');
|
||||
});
|
||||
|
||||
test('plan-design-review chaining mentions eng and ceo reviews', () => {
|
||||
test('plan-design-review chaining mentions eng, ceo, and design skills', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'plan-design-review', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('/plan-eng-review');
|
||||
expect(content).toContain('/plan-ceo-review');
|
||||
expect(content).toContain('/design-shotgun');
|
||||
expect(content).toContain('/design-html');
|
||||
});
|
||||
|
||||
test('ship does NOT contain review chaining', () => {
|
||||
@@ -605,7 +616,8 @@ 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',
|
||||
@@ -617,33 +629,40 @@ 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');
|
||||
}
|
||||
@@ -662,11 +681,12 @@ 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', () => {
|
||||
@@ -681,6 +701,35 @@ 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 = [
|
||||
@@ -700,6 +749,22 @@ describe('TEST_COVERAGE_AUDIT placeholders', () => {
|
||||
expect(shipSkill).toContain(phrase);
|
||||
}
|
||||
});
|
||||
|
||||
test('ship SKILL.md contains review army specialist dispatch', () => {
|
||||
expect(shipSkill).toContain('Specialist Dispatch');
|
||||
expect(shipSkill).toContain('Step 3.55');
|
||||
expect(shipSkill).toContain('Step 3.56');
|
||||
});
|
||||
|
||||
test('ship SKILL.md contains cross-review finding dedup', () => {
|
||||
expect(shipSkill).toContain('Cross-review finding dedup');
|
||||
expect(shipSkill).toContain('Step 3.57');
|
||||
});
|
||||
|
||||
test('ship SKILL.md contains re-run idempotency behavior', () => {
|
||||
expect(shipSkill).toContain('Re-run behavior (idempotency)');
|
||||
expect(shipSkill).toContain('Never skip a verification step');
|
||||
});
|
||||
});
|
||||
|
||||
// --- {{TEST_FAILURE_TRIAGE}} resolver tests ---
|
||||
@@ -868,12 +933,9 @@ 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');
|
||||
});
|
||||
});
|
||||
@@ -942,6 +1004,18 @@ describe('Plan status footer in preamble', () => {
|
||||
});
|
||||
});
|
||||
|
||||
// --- Skill invocation during plan mode in preamble ---
|
||||
|
||||
describe('Skill invocation during plan mode in preamble', () => {
|
||||
test('preamble contains skill invocation plan mode section', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'office-hours', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('Skill Invocation During Plan Mode');
|
||||
expect(content).toContain('precedence over generic plan mode behavior');
|
||||
expect(content).toContain('Do not continue the workflow');
|
||||
expect(content).toContain('cancel the skill or leave plan mode');
|
||||
});
|
||||
});
|
||||
|
||||
// --- {{SPEC_REVIEW_LOOP}} resolver tests ---
|
||||
|
||||
describe('SPEC_REVIEW_LOOP resolver', () => {
|
||||
@@ -1153,6 +1227,138 @@ describe('BENEFITS_FROM resolver', () => {
|
||||
expect(ceoContent).toContain('office-hours/SKILL.md');
|
||||
expect(engContent).toContain('office-hours/SKILL.md');
|
||||
});
|
||||
|
||||
test('BENEFITS_FROM delegates to INVOKE_SKILL pattern', () => {
|
||||
// Should contain the INVOKE_SKILL-style loading prose (not the old manual skip list)
|
||||
expect(engContent).toContain('Follow its instructions from top to bottom');
|
||||
expect(engContent).toContain('skipping these sections');
|
||||
expect(ceoContent).toContain('Follow its instructions from top to bottom');
|
||||
});
|
||||
});
|
||||
|
||||
// --- {{INVOKE_SKILL}} resolver tests ---
|
||||
|
||||
describe('INVOKE_SKILL resolver', () => {
|
||||
const ceoContent = fs.readFileSync(path.join(ROOT, 'plan-ceo-review', 'SKILL.md'), 'utf-8');
|
||||
|
||||
test('plan-ceo-review uses INVOKE_SKILL for mid-session office-hours fallback', () => {
|
||||
// The mid-session detection path should use INVOKE_SKILL-generated prose
|
||||
expect(ceoContent).toContain('office-hours/SKILL.md');
|
||||
expect(ceoContent).toContain('Follow its instructions from top to bottom');
|
||||
});
|
||||
|
||||
test('INVOKE_SKILL output includes default skip list', () => {
|
||||
expect(ceoContent).toContain('Preamble (run first)');
|
||||
expect(ceoContent).toContain('Telemetry (run last)');
|
||||
expect(ceoContent).toContain('AskUserQuestion Format');
|
||||
});
|
||||
|
||||
test('INVOKE_SKILL output includes error handling', () => {
|
||||
expect(ceoContent).toContain('If unreadable');
|
||||
expect(ceoContent).toContain('Could not load');
|
||||
});
|
||||
|
||||
test('template uses {{INVOKE_SKILL:office-hours}} placeholder', () => {
|
||||
const tmpl = fs.readFileSync(path.join(ROOT, 'plan-ceo-review', 'SKILL.md.tmpl'), 'utf-8');
|
||||
expect(tmpl).toContain('{{INVOKE_SKILL:office-hours}}');
|
||||
});
|
||||
});
|
||||
|
||||
// --- {{CHANGELOG_WORKFLOW}} resolver tests ---
|
||||
|
||||
describe('CHANGELOG_WORKFLOW resolver', () => {
|
||||
const shipContent = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
|
||||
|
||||
test('ship SKILL.md contains changelog workflow', () => {
|
||||
expect(shipContent).toContain('CHANGELOG (auto-generate)');
|
||||
expect(shipContent).toContain('git log <base>..HEAD --oneline');
|
||||
});
|
||||
|
||||
test('changelog workflow includes cross-check step', () => {
|
||||
expect(shipContent).toContain('Cross-check');
|
||||
expect(shipContent).toContain('Every commit must map to at least one bullet point');
|
||||
});
|
||||
|
||||
test('changelog workflow includes voice guidance', () => {
|
||||
expect(shipContent).toContain('Lead with what the user can now **do**');
|
||||
});
|
||||
|
||||
test('template uses {{CHANGELOG_WORKFLOW}} placeholder', () => {
|
||||
const tmpl = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md.tmpl'), 'utf-8');
|
||||
expect(tmpl).toContain('{{CHANGELOG_WORKFLOW}}');
|
||||
// Should NOT contain the old inline changelog content
|
||||
expect(tmpl).not.toContain('Group commits by theme');
|
||||
});
|
||||
|
||||
test('changelog workflow includes keep-changelog format', () => {
|
||||
expect(shipContent).toContain('### Added');
|
||||
expect(shipContent).toContain('### Fixed');
|
||||
});
|
||||
});
|
||||
|
||||
// --- Parameterized resolver infrastructure tests ---
|
||||
|
||||
describe('parameterized resolver support', () => {
|
||||
test('gen-skill-docs regex handles colon-separated args', () => {
|
||||
// Verify the template containing {{INVOKE_SKILL:office-hours}} was processed
|
||||
// without leaving unresolved placeholders
|
||||
const ceoContent = fs.readFileSync(path.join(ROOT, 'plan-ceo-review', 'SKILL.md'), 'utf-8');
|
||||
expect(ceoContent).not.toMatch(/\{\{INVOKE_SKILL:[^}]+\}\}/);
|
||||
});
|
||||
|
||||
test('templates with parameterized resolvers pass unresolved check', () => {
|
||||
// All generated SKILL.md files should have no unresolved {{...}} placeholders
|
||||
const skillDirs = fs.readdirSync(ROOT).filter(d =>
|
||||
fs.existsSync(path.join(ROOT, d, 'SKILL.md'))
|
||||
);
|
||||
for (const dir of skillDirs) {
|
||||
const content = fs.readFileSync(path.join(ROOT, dir, 'SKILL.md'), 'utf-8');
|
||||
const unresolved = content.match(/\{\{[A-Z_]+(?::[^}]*)?\}\}/g);
|
||||
if (unresolved) {
|
||||
throw new Error(`${dir}/SKILL.md has unresolved placeholders: ${unresolved.join(', ')}`);
|
||||
}
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
// --- Preamble routing injection tests ---
|
||||
|
||||
describe('preamble routing injection', () => {
|
||||
const shipContent = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
|
||||
|
||||
test('preamble bash checks for routing section in CLAUDE.md', () => {
|
||||
expect(shipContent).toContain('grep -q "## Skill routing" CLAUDE.md');
|
||||
expect(shipContent).toContain('HAS_ROUTING');
|
||||
});
|
||||
|
||||
test('preamble bash reads routing_declined config', () => {
|
||||
expect(shipContent).toContain('routing_declined');
|
||||
expect(shipContent).toContain('ROUTING_DECLINED');
|
||||
});
|
||||
|
||||
test('preamble includes routing injection AskUserQuestion', () => {
|
||||
expect(shipContent).toContain('Add routing rules to CLAUDE.md');
|
||||
expect(shipContent).toContain("I'll invoke skills manually");
|
||||
});
|
||||
|
||||
test('routing injection respects prior decline', () => {
|
||||
expect(shipContent).toContain('ROUTING_DECLINED');
|
||||
expect(shipContent).toMatch(/routing_declined.*true/);
|
||||
});
|
||||
|
||||
test('routing injection only fires when all conditions met', () => {
|
||||
// Must be: HAS_ROUTING=no AND ROUTING_DECLINED=false AND PROACTIVE_PROMPTED=yes
|
||||
expect(shipContent).toContain('HAS_ROUTING');
|
||||
expect(shipContent).toContain('ROUTING_DECLINED');
|
||||
expect(shipContent).toContain('PROACTIVE_PROMPTED');
|
||||
});
|
||||
|
||||
test('routing section content includes key routing rules', () => {
|
||||
expect(shipContent).toContain('invoke office-hours');
|
||||
expect(shipContent).toContain('invoke investigate');
|
||||
expect(shipContent).toContain('invoke ship');
|
||||
expect(shipContent).toContain('invoke qa');
|
||||
});
|
||||
});
|
||||
|
||||
// --- {{DESIGN_OUTSIDE_VOICES}} resolver tests ---
|
||||
@@ -1470,10 +1676,9 @@ 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', () => {
|
||||
@@ -1550,7 +1755,10 @@ describe('Codex generation (--host codex)', () => {
|
||||
test('Claude output unchanged: all Claude skills have zero Codex paths', () => {
|
||||
for (const skill of ALL_SKILLS) {
|
||||
const content = fs.readFileSync(path.join(ROOT, skill.dir, 'SKILL.md'), 'utf-8');
|
||||
expect(content).not.toContain('~/.codex/');
|
||||
// pair-agent legitimately documents how Codex agents store credentials
|
||||
if (skill.dir !== 'pair-agent') {
|
||||
expect(content).not.toContain('~/.codex/');
|
||||
}
|
||||
// gstack-upgrade legitimately references .agents/skills for cross-platform detection
|
||||
if (skill.dir !== 'gstack-upgrade') {
|
||||
expect(content).not.toContain('.agents/skills');
|
||||
@@ -1709,19 +1917,95 @@ describe('Factory generation (--host factory)', () => {
|
||||
});
|
||||
});
|
||||
|
||||
// ─── Parameterized host smoke tests (config-driven) ─────────
|
||||
|
||||
import { ALL_HOST_CONFIGS, getExternalHosts } from '../hosts/index';
|
||||
|
||||
describe('Parameterized host smoke tests', () => {
|
||||
for (const hostConfig of getExternalHosts()) {
|
||||
describe(`${hostConfig.displayName} (--host ${hostConfig.name})`, () => {
|
||||
const hostDir = path.join(ROOT, hostConfig.hostSubdir, 'skills');
|
||||
|
||||
test('generates output that exists on disk', () => {
|
||||
// Generated dir should exist (created by earlier bun run gen:skill-docs --host all)
|
||||
if (!fs.existsSync(hostDir)) {
|
||||
// Generate if not already done
|
||||
Bun.spawnSync(['bun', 'run', 'scripts/gen-skill-docs.ts', '--host', hostConfig.name], {
|
||||
cwd: ROOT, stdout: 'pipe', stderr: 'pipe',
|
||||
});
|
||||
}
|
||||
expect(fs.existsSync(hostDir)).toBe(true);
|
||||
const skills = fs.readdirSync(hostDir).filter(d =>
|
||||
fs.existsSync(path.join(hostDir, d, 'SKILL.md'))
|
||||
);
|
||||
expect(skills.length).toBeGreaterThan(0);
|
||||
});
|
||||
|
||||
test('no .claude/skills path leakage in non-root skills', () => {
|
||||
if (!fs.existsSync(hostDir)) return; // skip if not generated
|
||||
const skills = fs.readdirSync(hostDir);
|
||||
for (const skill of skills) {
|
||||
// Skip root gstack skill — it contains preamble with intentional .claude/skills
|
||||
// fallback paths for binary lookup and skill prefix instructions
|
||||
if (skill === 'gstack') continue;
|
||||
const skillMd = path.join(hostDir, skill, 'SKILL.md');
|
||||
if (!fs.existsSync(skillMd)) continue;
|
||||
const content = fs.readFileSync(skillMd, 'utf-8');
|
||||
// Strip bash blocks (which have legitimate fallback paths)
|
||||
const noBash = content.replace(/```bash\n[\s\S]*?```/g, '');
|
||||
const leaks = noBash.split('\n').filter(l => l.includes('.claude/skills'));
|
||||
if (leaks.length > 0) {
|
||||
throw new Error(`${skill}: .claude/skills leakage:\n${leaks.slice(0, 3).join('\n')}`);
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
test('frontmatter has name and description', () => {
|
||||
if (!fs.existsSync(hostDir)) return;
|
||||
const skills = fs.readdirSync(hostDir);
|
||||
for (const skill of skills) {
|
||||
const skillMd = path.join(hostDir, skill, 'SKILL.md');
|
||||
if (!fs.existsSync(skillMd)) continue;
|
||||
const content = fs.readFileSync(skillMd, 'utf-8');
|
||||
expect(content).toMatch(/^---\n/);
|
||||
expect(content).toMatch(/^name:\s/m);
|
||||
expect(content).toMatch(/^description:\s/m);
|
||||
}
|
||||
});
|
||||
|
||||
test('--dry-run freshness check passes', () => {
|
||||
const result = Bun.spawnSync(
|
||||
['bun', 'run', 'scripts/gen-skill-docs.ts', '--host', hostConfig.name, '--dry-run'],
|
||||
{ cwd: ROOT, stdout: 'pipe', stderr: 'pipe' }
|
||||
);
|
||||
expect(result.exitCode).toBe(0);
|
||||
const output = result.stdout.toString();
|
||||
expect(output).not.toContain('STALE');
|
||||
});
|
||||
|
||||
if (hostConfig.generation.skipSkills?.includes('codex')) {
|
||||
test('/codex skill excluded', () => {
|
||||
expect(fs.existsSync(path.join(hostDir, 'gstack-codex', 'SKILL.md'))).toBe(false);
|
||||
});
|
||||
}
|
||||
});
|
||||
}
|
||||
});
|
||||
|
||||
// ─── --host all tests ────────────────────────────────────────
|
||||
|
||||
describe('--host all', () => {
|
||||
test('--host all generates for claude, codex, and factory', () => {
|
||||
test('--host all generates for all registered hosts', () => {
|
||||
const result = Bun.spawnSync(['bun', 'run', 'scripts/gen-skill-docs.ts', '--host', 'all', '--dry-run'], {
|
||||
cwd: ROOT, stdout: 'pipe', stderr: 'pipe',
|
||||
});
|
||||
expect(result.exitCode).toBe(0);
|
||||
const output = result.stdout.toString();
|
||||
// All three hosts should appear in output
|
||||
// All hosts should appear in output
|
||||
expect(output).toContain('FRESH: SKILL.md'); // claude
|
||||
expect(output).toContain('FRESH: .agents/skills/'); // codex
|
||||
expect(output).toContain('FRESH: .factory/skills/'); // factory
|
||||
for (const hostConfig of getExternalHosts()) {
|
||||
expect(output).toContain(`FRESH: ${hostConfig.hostSubdir}/skills/`);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
@@ -1792,12 +2076,43 @@ describe('setup script validation', () => {
|
||||
expect(fnBody).toContain('gstack*');
|
||||
});
|
||||
|
||||
test('link_claude_skill_dirs creates relative symlinks', () => {
|
||||
// Claude links should be relative: ln -snf "gstack/skill_name"
|
||||
test('link_claude_skill_dirs creates real directories with absolute SKILL.md symlinks', () => {
|
||||
// Claude links should be real directories with absolute SKILL.md symlinks
|
||||
// to ensure Claude Code discovers them as top-level skills (not nested under gstack/)
|
||||
const fnStart = setupContent.indexOf('link_claude_skill_dirs()');
|
||||
const fnEnd = setupContent.indexOf('}', setupContent.indexOf('linked[@]}', fnStart));
|
||||
const fnBody = setupContent.slice(fnStart, fnEnd);
|
||||
expect(fnBody).toContain('ln -snf "gstack/$skill_name"');
|
||||
expect(fnBody).toContain('mkdir -p "$target"');
|
||||
expect(fnBody).toContain('ln -snf "$gstack_dir/$dir_name/SKILL.md" "$target/SKILL.md"');
|
||||
});
|
||||
|
||||
// REGRESSION: cleanup functions must handle both old symlinks AND new real-directory pattern
|
||||
test('cleanup functions handle real directories with symlinked SKILL.md', () => {
|
||||
// cleanup_old_claude_symlinks must detect and remove real dirs with SKILL.md symlinks
|
||||
const cleanupOldStart = setupContent.indexOf('cleanup_old_claude_symlinks()');
|
||||
const cleanupOldEnd = setupContent.indexOf('}', setupContent.indexOf('cleaned up old', cleanupOldStart));
|
||||
const cleanupOldBody = setupContent.slice(cleanupOldStart, cleanupOldEnd);
|
||||
expect(cleanupOldBody).toContain('-d "$old_target"');
|
||||
expect(cleanupOldBody).toContain('-L "$old_target/SKILL.md"');
|
||||
expect(cleanupOldBody).toContain('rm -rf "$old_target"');
|
||||
|
||||
// cleanup_prefixed_claude_symlinks must also handle the new pattern
|
||||
const cleanupPrefixedStart = setupContent.indexOf('cleanup_prefixed_claude_symlinks()');
|
||||
const cleanupPrefixedEnd = setupContent.indexOf('}', setupContent.indexOf('cleaned up prefixed', cleanupPrefixedStart));
|
||||
const cleanupPrefixedBody = setupContent.slice(cleanupPrefixedStart, cleanupPrefixedEnd);
|
||||
expect(cleanupPrefixedBody).toContain('-d "$prefixed_target"');
|
||||
expect(cleanupPrefixedBody).toContain('-L "$prefixed_target/SKILL.md"');
|
||||
expect(cleanupPrefixedBody).toContain('rm -rf "$prefixed_target"');
|
||||
});
|
||||
|
||||
// REGRESSION: link function must upgrade old directory symlinks
|
||||
test('link_claude_skill_dirs removes old directory symlinks before creating real dirs', () => {
|
||||
const fnStart = setupContent.indexOf('link_claude_skill_dirs()');
|
||||
const fnEnd = setupContent.indexOf('}', setupContent.indexOf('linked[@]}', fnStart));
|
||||
const fnBody = setupContent.slice(fnStart, fnEnd);
|
||||
// Must check for and remove old symlinks before mkdir
|
||||
expect(fnBody).toContain('if [ -L "$target" ]');
|
||||
expect(fnBody).toContain('rm -f "$target"');
|
||||
});
|
||||
|
||||
test('setup supports --host auto|claude|codex|kiro', () => {
|
||||
@@ -2036,6 +2351,100 @@ describe('telemetry', () => {
|
||||
});
|
||||
});
|
||||
|
||||
describe('community fixes wave', () => {
|
||||
// Helper to get all generated SKILL.md files
|
||||
function getAllSkillMds(): Array<{ name: string; content: string }> {
|
||||
const results: Array<{ name: string; content: string }> = [];
|
||||
const rootPath = path.join(ROOT, 'SKILL.md');
|
||||
if (fs.existsSync(rootPath)) {
|
||||
results.push({ name: 'root', content: fs.readFileSync(rootPath, 'utf-8') });
|
||||
}
|
||||
for (const entry of fs.readdirSync(ROOT, { withFileTypes: true })) {
|
||||
if (!entry.isDirectory() || entry.name.startsWith('.') || entry.name === 'node_modules') continue;
|
||||
const skillPath = path.join(ROOT, entry.name, 'SKILL.md');
|
||||
if (fs.existsSync(skillPath)) {
|
||||
results.push({ name: entry.name, content: fs.readFileSync(skillPath, 'utf-8') });
|
||||
}
|
||||
}
|
||||
return results;
|
||||
}
|
||||
|
||||
// #594 — Discoverability: every SKILL.md.tmpl description contains "gstack"
|
||||
test('every SKILL.md.tmpl description contains "gstack"', () => {
|
||||
for (const skill of ALL_SKILLS) {
|
||||
const tmplPath = skill.dir === '.' ? path.join(ROOT, 'SKILL.md.tmpl') : path.join(ROOT, skill.dir, 'SKILL.md.tmpl');
|
||||
const content = fs.readFileSync(tmplPath, 'utf-8');
|
||||
const desc = extractDescription(content);
|
||||
expect(desc.toLowerCase()).toContain('gstack');
|
||||
}
|
||||
});
|
||||
|
||||
// #594 — Discoverability: first line of each description is under 120 chars
|
||||
test('every SKILL.md.tmpl description first line is under 120 chars', () => {
|
||||
for (const skill of ALL_SKILLS) {
|
||||
const tmplPath = skill.dir === '.' ? path.join(ROOT, 'SKILL.md.tmpl') : path.join(ROOT, skill.dir, 'SKILL.md.tmpl');
|
||||
const content = fs.readFileSync(tmplPath, 'utf-8');
|
||||
const desc = extractDescription(content);
|
||||
const firstLine = desc.split('\n')[0];
|
||||
expect(firstLine.length).toBeLessThanOrEqual(120);
|
||||
}
|
||||
});
|
||||
|
||||
// #573 — Feature signals: ship/SKILL.md contains feature signal detection
|
||||
test('ship/SKILL.md contains feature signal detection in Step 4', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
|
||||
expect(content.toLowerCase()).toContain('feature signal');
|
||||
});
|
||||
|
||||
// #510 — Context warnings: no SKILL.md contains "running low on context"
|
||||
test('no generated SKILL.md contains "running low on context"', () => {
|
||||
const skills = getAllSkillMds();
|
||||
for (const { name, content } of skills) {
|
||||
expect(content).not.toContain('running low on context');
|
||||
}
|
||||
});
|
||||
|
||||
// #510 — Context warnings: plan-eng-review has explicit anti-warning
|
||||
test('plan-eng-review/SKILL.md contains "Do not preemptively warn"', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'plan-eng-review', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('Do not preemptively warn');
|
||||
});
|
||||
|
||||
// #474 — Safety Net: no SKILL.md uses find with -delete
|
||||
test('no generated SKILL.md contains find with -delete flag', () => {
|
||||
const skills = getAllSkillMds();
|
||||
for (const { name, content } of skills) {
|
||||
// Match find commands that use -delete (but not prose mentioning the word "delete")
|
||||
const lines = content.split('\n');
|
||||
for (const line of lines) {
|
||||
if (line.includes('find ') && line.includes('-delete')) {
|
||||
throw new Error(`${name}/SKILL.md contains find with -delete: ${line.trim()}`);
|
||||
}
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
// #467 — Telemetry: preamble JSONL writes are gated by telemetry setting
|
||||
test('preamble JSONL writes are inside telemetry conditional', () => {
|
||||
const preamble = fs.readFileSync(path.join(ROOT, 'scripts/resolvers/preamble.ts'), 'utf-8');
|
||||
// Find all skill-usage.jsonl write lines
|
||||
const lines = preamble.split('\n');
|
||||
for (let i = 0; i < lines.length; i++) {
|
||||
if (lines[i].includes('skill-usage.jsonl') && lines[i].includes('>>')) {
|
||||
// Look backwards for a telemetry conditional within 5 lines
|
||||
let foundConditional = false;
|
||||
for (let j = i - 1; j >= Math.max(0, i - 5); j--) {
|
||||
if (lines[j].includes('_TEL') && lines[j].includes('off')) {
|
||||
foundConditional = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
expect(foundConditional).toBe(true);
|
||||
}
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe('codex commands must not use inline $(git rev-parse --show-toplevel) for cwd', () => {
|
||||
// Regression test: inline $(git rev-parse --show-toplevel) in codex exec -C
|
||||
// or codex review without cd evaluates in whatever cwd the background shell
|
||||
@@ -2123,3 +2532,207 @@ describe('codex commands must not use inline $(git rev-parse --show-toplevel) fo
|
||||
expect(violations).toEqual([]);
|
||||
});
|
||||
});
|
||||
|
||||
// ─── Learnings + Confidence Resolver Tests ─────────────────────
|
||||
|
||||
describe('LEARNINGS_SEARCH resolver', () => {
|
||||
const SEARCH_SKILLS = ['review', 'ship', 'plan-eng-review', 'investigate', 'office-hours', 'plan-ceo-review'];
|
||||
|
||||
for (const skill of SEARCH_SKILLS) {
|
||||
test(`${skill} generated SKILL.md contains learnings search`, () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, skill, 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('Prior Learnings');
|
||||
expect(content).toContain('gstack-learnings-search');
|
||||
});
|
||||
}
|
||||
|
||||
test('learnings search includes cross-project config check', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('cross_project_learnings');
|
||||
expect(content).toContain('--cross-project');
|
||||
});
|
||||
|
||||
test('learnings search includes AskUserQuestion for first-time cross-project opt-in', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('Enable cross-project learnings');
|
||||
expect(content).toContain('project-scoped only');
|
||||
});
|
||||
|
||||
test('learnings search mentions prior learning applied display format', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('Prior learning applied');
|
||||
});
|
||||
});
|
||||
|
||||
describe('LEARNINGS_LOG resolver', () => {
|
||||
const LOG_SKILLS = ['review', 'retro', 'investigate'];
|
||||
|
||||
for (const skill of LOG_SKILLS) {
|
||||
test(`${skill} generated SKILL.md contains learnings log`, () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, skill, 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('Capture Learnings');
|
||||
expect(content).toContain('gstack-learnings-log');
|
||||
});
|
||||
}
|
||||
|
||||
test('learnings log documents all type values', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
for (const type of ['pattern', 'pitfall', 'preference', 'architecture', 'tool']) {
|
||||
expect(content).toContain(type);
|
||||
}
|
||||
});
|
||||
|
||||
test('learnings log documents all source values', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
for (const source of ['observed', 'user-stated', 'inferred', 'cross-model']) {
|
||||
expect(content).toContain(source);
|
||||
}
|
||||
});
|
||||
|
||||
test('learnings log includes files field for staleness detection', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('"files"');
|
||||
expect(content).toContain('staleness detection');
|
||||
});
|
||||
});
|
||||
|
||||
describe('CONFIDENCE_CALIBRATION resolver', () => {
|
||||
const CONFIDENCE_SKILLS = ['review', 'ship', 'plan-eng-review', 'cso'];
|
||||
|
||||
for (const skill of CONFIDENCE_SKILLS) {
|
||||
test(`${skill} generated SKILL.md contains confidence calibration`, () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, skill, 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('Confidence Calibration');
|
||||
expect(content).toContain('confidence score');
|
||||
});
|
||||
}
|
||||
|
||||
test('confidence calibration includes scoring rubric with all tiers', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('9-10');
|
||||
expect(content).toContain('7-8');
|
||||
expect(content).toContain('5-6');
|
||||
expect(content).toContain('3-4');
|
||||
expect(content).toContain('1-2');
|
||||
});
|
||||
|
||||
test('confidence calibration includes display rules', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('Show normally');
|
||||
expect(content).toContain('Suppress from main report');
|
||||
});
|
||||
|
||||
test('confidence calibration includes finding format example', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('[P1] (confidence:');
|
||||
expect(content).toContain('SQL injection');
|
||||
});
|
||||
|
||||
test('confidence calibration includes calibration learning feedback loop', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('calibration event');
|
||||
expect(content).toContain('Log the corrected pattern');
|
||||
});
|
||||
|
||||
test('skills without confidence calibration do NOT contain it', () => {
|
||||
// office-hours and retro do NOT use confidence calibration
|
||||
for (const skill of ['office-hours', 'retro']) {
|
||||
const content = fs.readFileSync(path.join(ROOT, skill, 'SKILL.md'), 'utf-8');
|
||||
expect(content).not.toContain('## Confidence Calibration');
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe('gen-skill-docs prefix warning (#620/#578)', () => {
|
||||
const { execSync } = require('child_process');
|
||||
|
||||
test('warns about skill_prefix when config has prefix=true', () => {
|
||||
const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-prefix-warn-'));
|
||||
try {
|
||||
// Create a fake ~/.gstack/config.yaml with skill_prefix: true
|
||||
const fakeHome = tmpDir;
|
||||
const fakeGstack = path.join(fakeHome, '.gstack');
|
||||
fs.mkdirSync(fakeGstack, { recursive: true });
|
||||
fs.writeFileSync(path.join(fakeGstack, 'config.yaml'), 'skill_prefix: true\n');
|
||||
|
||||
const output = execSync('bun run scripts/gen-skill-docs.ts', {
|
||||
cwd: ROOT,
|
||||
env: { ...process.env, HOME: fakeHome },
|
||||
encoding: 'utf-8',
|
||||
timeout: 30000,
|
||||
});
|
||||
expect(output).toContain('skill_prefix is true');
|
||||
expect(output).toContain('gstack-relink');
|
||||
} finally {
|
||||
fs.rmSync(tmpDir, { recursive: true, force: true });
|
||||
}
|
||||
});
|
||||
|
||||
test('no warning when skill_prefix is false or absent', () => {
|
||||
const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-prefix-warn-'));
|
||||
try {
|
||||
const fakeHome = tmpDir;
|
||||
const fakeGstack = path.join(fakeHome, '.gstack');
|
||||
fs.mkdirSync(fakeGstack, { recursive: true });
|
||||
fs.writeFileSync(path.join(fakeGstack, 'config.yaml'), 'skill_prefix: false\n');
|
||||
|
||||
const output = execSync('bun run scripts/gen-skill-docs.ts', {
|
||||
cwd: ROOT,
|
||||
env: { ...process.env, HOME: fakeHome },
|
||||
encoding: 'utf-8',
|
||||
timeout: 30000,
|
||||
});
|
||||
expect(output).not.toContain('skill_prefix is true');
|
||||
} finally {
|
||||
fs.rmSync(tmpDir, { recursive: true, force: true });
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe('voice-triggers processing', () => {
|
||||
const { extractVoiceTriggers, processVoiceTriggers } = require('../scripts/gen-skill-docs') as {
|
||||
extractVoiceTriggers: (content: string) => string[];
|
||||
processVoiceTriggers: (content: string) => string;
|
||||
};
|
||||
|
||||
test('extractVoiceTriggers parses valid YAML list', () => {
|
||||
const content = `---\nname: cso\ndescription: |\n Security audit.\nvoice-triggers:\n - "see-so"\n - "security review"\n---\nBody`;
|
||||
const triggers = extractVoiceTriggers(content);
|
||||
expect(triggers).toEqual(['see-so', 'security review']);
|
||||
});
|
||||
|
||||
test('extractVoiceTriggers returns [] when no field present', () => {
|
||||
const content = `---\nname: qa\ndescription: |\n QA testing.\n---\nBody`;
|
||||
expect(extractVoiceTriggers(content)).toEqual([]);
|
||||
});
|
||||
|
||||
test('processVoiceTriggers appends voice triggers to description', () => {
|
||||
const content = `---\nname: cso\ndescription: |\n Security audit. (gstack)\nvoice-triggers:\n - "see-so"\n - "security review"\n---\nBody`;
|
||||
const result = processVoiceTriggers(content);
|
||||
expect(result).toContain('Voice triggers (speech-to-text aliases): "see-so", "security review".');
|
||||
});
|
||||
|
||||
test('processVoiceTriggers strips voice-triggers field from output', () => {
|
||||
const content = `---\nname: cso\ndescription: |\n Security audit. (gstack)\nvoice-triggers:\n - "see-so"\n---\nBody`;
|
||||
const result = processVoiceTriggers(content);
|
||||
expect(result).not.toContain('voice-triggers:');
|
||||
});
|
||||
|
||||
test('processVoiceTriggers returns content unchanged when no voice-triggers', () => {
|
||||
const content = `---\nname: qa\ndescription: |\n QA testing.\n---\nBody`;
|
||||
expect(processVoiceTriggers(content)).toBe(content);
|
||||
});
|
||||
|
||||
test('generated CSO SKILL.md contains voice triggers in description', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'cso', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('"see-so"');
|
||||
expect(content).toContain('Voice triggers (speech-to-text aliases):');
|
||||
});
|
||||
|
||||
test('generated CSO SKILL.md does NOT contain raw voice-triggers field', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'cso', 'SKILL.md'), 'utf-8');
|
||||
const fmEnd = content.indexOf('\n---', 4);
|
||||
const frontmatter = content.slice(0, fmEnd);
|
||||
expect(frontmatter).not.toContain('voice-triggers:');
|
||||
});
|
||||
});
|
||||
|
||||
Reference in New Issue
Block a user