CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-05-06 13:45:35 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into garrytan/team-supabase-store

Browse Source 
Resolved conflicts across 23 files. Key merge decisions:
- Adopted main's TemplateContext type in gen-skill-docs.ts
- Adopted main's new features (trigger phrases, codex integration,
  analytics, proactive config, review chaining)
- Replaced gstack-review-log/gstack-review-read helpers with inline
  approach using $PROJECTS_DIR/$SLUG/reviews/$BRANCH.jsonl paths
- Added "commit":"COMMIT" field to all review log entries (from main)
- Kept our $PROJECTS_DIR/$SLUG path reorganization throughout
- Added Codex E2E test from main + our E2E isolation cleanup

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-03-19 17:16:08 -07:00
parent fb7fe3d280 bd834aeadb
commit 0ffb4e9ec5
84 changed files with 8122 additions and 1234 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/skill-e2e.test.ts
+86 -16
View File
@@ -394,7 +394,7 @@ File a contributor report about this issue. Then tell me what you filed.`,
// Set up a git repo so there's project/branch context to reference
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: sessionDir, stdio: 'pipe', timeout: 5000 });
run('git', ['init']);
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
fs.writeFileSync(path.join(sessionDir, 'app.rb'), '# my app\n');
@@ -525,7 +525,7 @@ describeIfSelected('Review skill E2E', ['review-sql-injection'], () => {
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: reviewDir, stdio: 'pipe', timeout: 5000 });
run('git', ['init']);
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
@@ -582,7 +582,7 @@ describeIfSelected('Review enum completeness E2E', ['review-enum-completeness'],
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: enumDir, stdio: 'pipe', timeout: 5000 });
run('git', ['init']);
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
@@ -654,7 +654,7 @@ describeE2E('Review design lite E2E', () => {
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: designDir, stdio: 'pipe', timeout: 5000 });
run('git', ['init']);
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
@@ -917,7 +917,7 @@ describeIfSelected('Plan CEO Review E2E', ['plan-ceo-review'], () => {
spawnSync(cmd, args, { cwd: planDir, stdio: 'pipe', timeout: 5000 });
// Init git repo (CEO review SKILL.md has a "System Audit" step that runs git)
run('git', ['init']);
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
@@ -1003,7 +1003,7 @@ describeIfSelected('Plan CEO Review SELECTIVE EXPANSION E2E', ['plan-ceo-review-
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: planDir, stdio: 'pipe', timeout: 5000 });
run('git', ['init']);
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
@@ -1086,7 +1086,7 @@ describeIfSelected('Plan Eng Review E2E', ['plan-eng-review'], () => {
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: planDir, stdio: 'pipe', timeout: 5000 });
run('git', ['init']);
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
@@ -1181,7 +1181,7 @@ describeIfSelected('Retro E2E', ['retro'], () => {
spawnSync(cmd, args, { cwd: retroDir, stdio: 'pipe', timeout: 5000 });
// Create a git repo with varied commit history
run('git', ['init']);
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'dev@example.com']);
run('git', ['config', 'user.name', 'Dev']);
@@ -1280,7 +1280,7 @@ describeIfSelected('QA-Only skill E2E', ['qa-only-no-fix'], () => {
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: qaOnlyDir, stdio: 'pipe', timeout: 5000 });
run('git', ['init']);
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
fs.writeFileSync(path.join(qaOnlyDir, 'index.html'), '<h1>Test</h1>\n');
@@ -1380,7 +1380,7 @@ describeIfSelected('QA Fix Loop E2E', ['qa-fix-loop'], () => {
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: qaFixDir, stdio: 'pipe', timeout: 5000 });
run('git', ['init']);
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
run('git', ['add', '.']);
@@ -1467,7 +1467,7 @@ describeIfSelected('Plan-Eng-Review Test-Plan Artifact E2E', ['plan-eng-review-a
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: planDir, stdio: 'pipe', timeout: 5000 });
run('git', ['init']);
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
@@ -1776,7 +1776,7 @@ describeIfSelected('Document-Release skill E2E', ['document-release'], () => {
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: docReleaseDir, stdio: 'pipe', timeout: 5000 });
run('git', ['init']);
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
@@ -2029,7 +2029,7 @@ describeIfSelected('Design Consultation E2E', [
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: designDir, stdio: 'pipe', timeout: 5000 });
run('git', ['init']);
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
@@ -2301,7 +2301,7 @@ describeIfSelected('Plan Design Review E2E', ['plan-design-review-plan-mode', 'p
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: reviewDir, stdio: 'pipe', timeout: 5000 });
run('git', ['init']);
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
@@ -2452,7 +2452,7 @@ describeIfSelected('Design Review E2E', ['design-review-fix'], () => {
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: qaDesignDir, stdio: 'pipe', timeout: 5000 });
run('git', ['init']);
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
@@ -2619,7 +2619,7 @@ export function divide(a, b) { return a / b; } // BUG: no zero check
// Init git repo
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: bootstrapDir, stdio: 'pipe', timeout: 5000 });
run('git', ['init']);
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
run('git', ['add', '.']);
@@ -2840,6 +2840,76 @@ Output the diagram directly.`,
}, 180_000);
});
// --- Codex skill E2E ---
describeIfSelected('Codex skill E2E', ['codex-review'], () => {
let codexDir: string;
beforeAll(() => {
codexDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-codex-'));
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: codexDir, stdio: 'pipe', timeout: 5000 });
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
// Commit a clean base on main
fs.writeFileSync(path.join(codexDir, 'app.rb'), '# clean base\nclass App\nend\n');
run('git', ['add', 'app.rb']);
run('git', ['commit', '-m', 'initial commit']);
// Create feature branch with vulnerable code (reuse review fixture)
run('git', ['checkout', '-b', 'feature/add-vuln']);
const vulnContent = fs.readFileSync(path.join(ROOT, 'test', 'fixtures', 'review-eval-vuln.rb'), 'utf-8');
fs.writeFileSync(path.join(codexDir, 'user_controller.rb'), vulnContent);
run('git', ['add', 'user_controller.rb']);
run('git', ['commit', '-m', 'add vulnerable controller']);
// Copy the codex skill file
fs.copyFileSync(path.join(ROOT, 'codex', 'SKILL.md'), path.join(codexDir, 'codex-SKILL.md'));
});
afterAll(() => {
try { fs.rmSync(codexDir, { recursive: true, force: true }); } catch {}
});
test('/codex review produces findings and GATE verdict', async () => {
// Check codex is available — skip if not installed
const codexCheck = spawnSync('which', ['codex'], { stdio: 'pipe', timeout: 3000 });
if (codexCheck.status !== 0) {
console.warn('codex CLI not installed — skipping E2E test');
return;
}
const result = await runSkillTest({
prompt: `You are in a git repo on branch feature/add-vuln with changes against main.
Read codex-SKILL.md for the /codex skill instructions.
Run /codex review to review the current diff against main.
Write the full output (including the GATE verdict) to ${codexDir}/codex-output.md`,
workingDirectory: codexDir,
maxTurns: 10,
timeout: 300_000,
testName: 'codex-review',
runId,
});
logCost('/codex review', result);
recordE2E('/codex review', 'Codex skill E2E', result);
expect(result.exitReason).toBe('success');
// Check that output file was created with review content
const outputPath = path.join(codexDir, 'codex-output.md');
if (fs.existsSync(outputPath)) {
const output = fs.readFileSync(outputPath, 'utf-8');
// Should contain the CODEX SAYS header or GATE verdict
const hasCodexOutput = output.includes('CODEX') || output.includes('GATE') || output.includes('codex');
expect(hasCodexOutput).toBe(true);
}
}, 360_000);
});
// Module-level afterAll — finalize eval collector and clean up E2E isolation
afterAll(async () => {
if (evalCollector) {