Files
gstack/test/skill-e2e-qa-workflow.test.ts
T
Garry TanandOpenAI Codex 9f81911136 v1.86.0.0 feat: route outside reviews by harness (#2850)
* feat: add a restricted and supervised Claude Code runner

Preserve configured authentication and models while enforcing tool access, strict completion JSON, bounded output and process cleanup. Cover argv, failure handling, session metadata and Windows process containment.

* feat: route outside reviews by harness and migrate wrapper installs

Use Claude Code from Codex and Codex from other supported hosts, with shared invocation rendering, positive gate validation and per-phase provenance. Rename /claude to /claude-code, repair managed shared and copied installations safely, and generate native Kiro skills. Add installed-workflow, failure-injection and live cross-harness regression coverage.

* test: recognize CEO mode labels without terminal spacing

The paid workflow rendered SCOPEEXPANSION at option 4, but its driver required a literal space. Match the leading mode title without cursor-spacing artifacts and ignore adjacent preview text. Preserve missing-target failures and downstream posture assertions.

* test: isolate plan-count fixtures before starting review workflows

Seed the complete test plan in a private git repository before launching Claude, so a bare slash command cannot review the live workspace while a delayed fixture message remains queued. Preserve count thresholds, parsers and budgets. Add initial-context and installed-discovery tests, and retain startup/terminal diagnostics on failed evaluations.

* test: stabilize review fixtures and Claude eval startup

Preserve source boundaries in workflow judge inputs, isolate CEO mode plans, and wait for interactive trust input readiness. Keep startup failure evidence and retain existing models, budgets, and assertions.

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* test: classify collapsed review modes and isolate seeded findings

Keep review questions out of the setup count when terminal cursor positioning removes spaces. State existing webhook safeguards so the five-finding control measures its seeded defects without accidental extra security and concurrency gaps. Preserve question bands and the paired control.

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* test: isolate browser daemon state across free shards

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* test: stabilize native review counting and interactive navigation

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* chore: prepare v1.82.0.0 release

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* fix: eliminate browser and process-cleanup test flakes

Pin every CI surface to Bun 1.4.0 to avoid extra-stdio finalizers closing
reused live sockets. Add an isolated GC/listener regression that fails on
Bun 1.3.13, and prevent coordinated rollback to an affected CI runtime.

Check renderer cleanup against the render's own staging directory so
concurrent renders cannot invalidate the assertion. Make the no-pgrep
process-tree walk tolerate disappearing /proc entries, and synchronize
its test fixture through child readiness and pipe EOF instead of sleeps.

Validation: 9,157 passed, 31 skipped, zero failures across 556 files with
retries disabled. Build, all-host generation freshness, and skill checks
passed. All three races have failing-before/passing-after regressions.

* fix: count completed native review questions in evals

* fix: drive review navigation from confirmed native choices

* fix: require complete section-loading eval reports

* test: isolate telemetry HTTP transport from local assertions

* fix: keep review input on the active native question

* test: let tunnel revocation daemon choose an available port

* test: allocate available ports for pairing and watchdog fixtures

* fix: stabilize planning eval navigation and phase reporting

* test: isolate installed runtime paths in planning evals

* test: stabilize review evidence and concurrent refresh fixtures

* fix: resolve design findings before editing the plan

* fix: honor and persist disabled outside plan reviews

* fix: preserve planning decisions and terminal evidence

Load installed host reviews at autoplan phase entry and wait for completed
reviewers and saved artifacts. Reuse approved remedies while preserving
individual finding decisions.

Drive interactive evals from the current terminal viewport, bind native
questions across scrolling, and require complete native report evidence.
Cover captured stale menus, permission lifecycles, setup classification,
and disabled-review tool availability with deterministic regressions.

Advance release metadata and the upgrade migration to the unclaimed
1.83.0.0 slot.

* fix: drive native review questions and preserve current plans

Use the native single-choice keyboard protocol and current terminal viewport,
with per-question navigation inside packets and completed-call coverage.
Keep permissions, multi-select menus, and Submit controls distinct.

Send Autoplan reviewers the amended implementation plan, keep its review record
separate, and supply retained application contracts in the chain fixture.
Clarify individual DevEx decisions and complete CEO fix options; use one active
plan destination for the section-loading report.

* fix: preserve complete plan-review decisions

* fix: recognize native plan dialogs and reviewer controls

* fix: preserve review decisions and phase completion

* fix: recognize completed reviews without losing findings

* fix: preserve review continuity and native eval completion

* test: fix native review completion and eval retry isolation

* test: handle native review menus and complete eval fixtures

* test: fix native review setup, completion, and isolation failures

* test: limit native skill discovery to runtime assets

* fix: bind Autoplan reviews to full ordered phase inputs

* test: fix planning eval routing, counting, and timeout handling

* chore: advance queued release to v1.84.0.0

* fix: preserve complete review inputs and planning decisions

* fix: reconcile review approvals and preserve phase obligations

* fix: preserve review obligations and unblock eval permissions

Carry recorded Autoplan requirements into blind phase inputs, require Eng
review approvals before exit, and exercise combined asynchronous flows in
CEO reviews. Correct native finding and handoff classification and unblock
repeated report edits using scoped request identities.

* fix: retain plan requirements and complete native review dialogs

* fix: complete native review prompts and retain plan references

* fix: preserve review inputs and classify native eval evidence

* fix: check competing completion orders in CEO reviews

* fix: recognize review decisions and require phase methodology

Require the current phase methodology before Autoplan snapshots. Correct
substantive decision, closed handoff, and cache-finding classification, and
honor the recommended implementation approach in native review dialogs.

Add captured-transcript regressions without changing review thresholds,
provider models, retries, or deadlines.

* test: bind native review decisions and close completed handoffs

* fix: complete review dialogs and verify methodology delivery

* fix: preserve review evidence and unblock native eval prompts

* fix: handle native review question completions

* fix: recognize native review narration and controls

* fix: count native review decisions and isolate eval fixtures

* test: verify seeded review coverage and current artifact permissions

* test: isolate model and brain-aware skill renders

* fix: repair native workflow evaluation and clarify review steps

* fix: stabilize workflow eval evidence and review guidance

* test: repair native workflow observation and fixture isolation

* fix: recognize completed workflow evidence and owned skill reads

* test: repair seeded workflow delivery and completion evidence

* test: recognize current review evidence across native forms

* test: handle native review variants and permission redraws

* fix: honor review preferences and recognize native eval evidence

* test: recognize completed review decisions and queued permissions

* test: match current review contracts and partial-line edits

* test: recognize completed workflow evidence and bounded human waits

* fix: preserve review entry gates and native eval interactions

* fix: recognize native workflow evidence and preserve review gates

* test: recognize current review evidence and preconfigure workflow fixtures

* test: recognize completed review findings and scoped artifact permissions

* fix: stabilize native workflow review and permission evidence

* fix: recognize current review evidence and scoped edit confirmations

Clarify Design and engineering review entry instructions and Design scoring.
Recognize required legacy coverage and public Autoplan completion recaps.
Bind the pending Edit confirmation to its exact file, ordered digest, and
one-request approval when a preceding command display remains visible.
Keep reviews within their existing size limits and preserve scope gates
when extracting workflow fixtures from either supported preamble header.

Keep failure outcomes, review thresholds, provider choices, and eval budgets.

* fix: recover review workflow progress and eval evidence

* fix: recognize valid review evidence and scope selection

* test: fix review evidence parsing and repeated artifact prompts

* test: recognize valid review decisions and pending native cards

* fix(plan-eng-review): keep final navigation consistent with approved tasks

* test: recognize valid review evidence and bind legacy diff requests

* fix: stabilize review eval evidence and harness repair guidance

* docs: update project documentation for v1.85.0.0

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* test: fix Windows CI fixtures and credential scan

Rebase captured JSON values and filesystem evidence using the appropriate
path convention. Compile native fake CLIs on Windows and synchronize pipe
holder readiness, with cleanup retained when assertions fail.

Assemble synthetic credential fixtures at runtime so the added-line scan
keeps enforcing the same gate without flagging its own rejection controls.

Discover generated skills directly for the empty-find regression check,
avoiding a recursive scan through saved evaluation artifacts and dependencies.

* fix: preserve source renders on Windows

Compare canonical generator paths using native separators so an output
sidecar pointing at the source cannot overwrite its skill or metadata.
Keep the regression fixture isolated from the real checkout and expose
freshness diagnostics before asserting subprocess status.

Detach Windows drain-test pipe holders from the fake provider's automatic
child cleanup while preserving the enclosing runner job and its assertions.

* fix: clarify outside review fallback and CEO decisions

Render one applicable own-harness fallback path and retain native review,
disabled policy, and missing-coverage semantics. Align report field names
and mode labels, and make the existing per-cut scope approval explicit.

Regenerate skill outputs and keep the workflow judge's model, thresholds,
and retry policy unchanged.

* chore: move release to free version slot (v1.86.0.0)

PR #2852 now claims v1.85.0.0. Align the release metadata and
rename migration so upgrades from that version still receive it.

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* fix: include engineering review prerequisites and restore branch context

* fix: recognize coverage diagrams and clarify design review instructions

* fix: preserve file identities and join Windows test processes

---------

Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-09-14 14:32:45 -07:00

443 lines
18 KiB
TypeScript

import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
import { JUDGE_MS, CAPTURE_MS, CAPTURE_LONG_MS } from './helpers/eval-budgets';
import { runSkillTest } from './helpers/session-runner';
import {
ROOT, browseBin, runId, evalsEnabled, selectedTests,
describeIfSelected, testConcurrentIfSelected,
copyDirSync, setupBrowseShims, logCost, recordE2E,
createEvalCollector, finalizeEvalCollector,
} from './helpers/e2e-helpers';
import { asideAvailable } from './helpers/aside-available';
import { startTestServer } from '../browse/test/test-server';
import { spawnSync } from 'child_process';
import * as fs from 'fs';
import * as path from 'path';
import * as os from 'os';
const evalCollector = createEvalCollector('e2e-qa-workflow');
// /qa and /qa-only drive the Aside browser first and fall back to the gstack
// browse binary. The browser-driving describes need one of the two — a live
// Aside or a built browse/dist/browse (CI builds it, so the Linux lane runs
// the fallback path). Neither → skip, never fail. qa-bootstrap opens no
// browser and is not gated.
const browserSelected = evalsEnabled && (asideAvailable() || fs.existsSync(browseBin)) ? selectedTests : [];
// The skill's BROWSER SETUP decides Aside vs fallback; the prompt only tells the
// agent where the fallback binary is (the hermetic HOME has no global install).
const browserPrompt = (skillMd: string) =>
`Follow the BROWSER SETUP section in ${skillMd} exactly: it probes for Aside first and falls back to the gstack browse binary. If it falls back, the browse binary is at ${browseBin} (B="${browseBin}"; find-browse is shimmed under browse/bin in this directory). Do not look for any other browser.`;
// --- B4: QA skill E2E ---
describeIfSelected('QA skill E2E', ['qa-quick'], () => {
let qaDir: string;
let testServer: ReturnType<typeof startTestServer>;
beforeAll(() => {
testServer = startTestServer();
qaDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-qa-'));
setupBrowseShims(qaDir);
// Copy qa skill files into tmpDir
copyDirSync(path.join(ROOT, 'qa'), path.join(qaDir, 'qa'));
// Create report directory
fs.mkdirSync(path.join(qaDir, 'qa-reports'), { recursive: true });
});
afterAll(() => {
testServer?.server?.stop();
try { fs.rmSync(qaDir, { recursive: true, force: true }); } catch {}
});
testConcurrentIfSelected('qa-quick', async () => {
const result = await runSkillTest({
prompt: `${browserPrompt('qa/SKILL.md')}
The test server is already running at: ${testServer.url}
Target page: ${testServer.url}/basic.html
Read the file qa/SKILL.md for the QA workflow instructions.
qa is a carved skill: when SKILL.md tells you to Read ~/.claude/skills/gstack/qa/sections/<file>, read qa/sections/<file> in this working directory instead (same content, local copy).
Skip the preamble bash block, lake intro, telemetry, and contributor mode sections — go straight to the QA workflow.
Run a Quick-depth QA test on ${testServer.url}/basic.html
Do NOT use AskUserQuestion — run Quick tier directly.
Do NOT try to start a server or discover ports — the URL above is ready.
Write your report to ${qaDir}/qa-reports/qa-report.md`,
workingDirectory: qaDir,
maxTurns: 35,
timeout: CAPTURE_MS,
testName: 'qa-quick',
runId,
});
logCost('/qa quick', result);
recordE2E(evalCollector, '/qa quick', 'QA skill E2E', result, {
passed: ['success', 'error_max_turns'].includes(result.exitReason),
});
// browseErrors can include false positives from hallucinated paths
if (result.browseErrors.length > 0) {
console.warn('/qa quick browse errors (non-fatal):', result.browseErrors);
}
// Accept error_max_turns — the agent doing thorough QA work is not a failure
expect(['success', 'error_max_turns']).toContain(result.exitReason);
}, CAPTURE_MS);
}, browserSelected);
// --- QA-Only E2E (report-only, no fixes) ---
describeIfSelected('QA-Only skill E2E', ['qa-only-no-fix'], () => {
let qaOnlyDir: string;
let testServer: ReturnType<typeof startTestServer>;
beforeAll(() => {
testServer = startTestServer();
qaOnlyDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-qa-only-'));
setupBrowseShims(qaOnlyDir);
// Copy qa-only skill files
copyDirSync(path.join(ROOT, 'qa-only'), path.join(qaOnlyDir, 'qa-only'));
// Copy qa templates (qa-only references qa/templates/qa-report-template.md)
fs.mkdirSync(path.join(qaOnlyDir, 'qa', 'templates'), { recursive: true });
fs.copyFileSync(
path.join(ROOT, 'qa', 'templates', 'qa-report-template.md'),
path.join(qaOnlyDir, 'qa', 'templates', 'qa-report-template.md'),
);
// Init git repo (qa-only checks for feature branch in diff-aware mode)
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: qaOnlyDir, stdio: 'pipe', timeout: 5000 });
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');
run('git', ['add', '.']);
run('git', ['commit', '-m', 'initial']);
});
afterAll(() => {
try { fs.rmSync(qaOnlyDir, { recursive: true, force: true }); } catch {}
});
testConcurrentIfSelected('qa-only-no-fix', async () => {
const result = await runSkillTest({
prompt: `${browserPrompt('qa-only/SKILL.md')}
Read the file qa-only/SKILL.md for the QA-only workflow instructions.
Skip the preamble bash block, lake intro, telemetry, and contributor mode sections — go straight to the QA workflow.
Run a Quick QA test on ${testServer.url}/qa-eval.html
Do NOT use AskUserQuestion — run Quick tier directly.
Write your report to ${qaOnlyDir}/qa-reports/qa-only-report.md`,
workingDirectory: qaOnlyDir,
maxTurns: 40,
allowedTools: ['Bash', 'Read', 'Write', 'Glob'], // NO Edit — the critical guardrail
timeout: CAPTURE_MS,
testName: 'qa-only-no-fix',
runId,
});
logCost('/qa-only', result);
// Verify Edit was not used — the critical guardrail for report-only mode.
// Glob is read-only and may be used for file discovery (e.g. finding SKILL.md).
const editCalls = result.toolCalls.filter(tc => tc.tool === 'Edit');
if (editCalls.length > 0) {
console.warn('qa-only used Edit tool:', editCalls.length, 'times');
}
const exitOk = ['success', 'error_max_turns'].includes(result.exitReason);
recordE2E(evalCollector, '/qa-only no-fix', 'QA-Only skill E2E', result, {
passed: exitOk && editCalls.length === 0,
});
expect(editCalls).toHaveLength(0);
// Accept error_max_turns — the agent doing thorough QA is not a failure
expect(['success', 'error_max_turns']).toContain(result.exitReason);
// Verify git working tree is still clean (no source modifications)
const gitStatus = spawnSync('git', ['status', '--porcelain'], {
cwd: qaOnlyDir, stdio: 'pipe', timeout: 30_000,
});
const statusLines = gitStatus.stdout.toString().trim().split('\n').filter(
(l: string) => l.trim() && !l.includes('.prompt-tmp') && !l.includes('.gstack/') && !l.includes('qa-reports/'),
);
expect(statusLines.filter((l: string) => l.startsWith(' M') || l.startsWith('M '))).toHaveLength(0);
}, CAPTURE_MS);
}, browserSelected);
// --- QA Fix Loop E2E ---
describeIfSelected('QA Fix Loop E2E', ['qa-fix-loop'], () => {
function createQaFixFixture() {
const qaFixDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-qa-fix-'));
setupBrowseShims(qaFixDir);
// Copy qa skill files
copyDirSync(path.join(ROOT, 'qa'), path.join(qaFixDir, 'qa'));
// Create a simple HTML page with obvious fixable bugs
fs.writeFileSync(path.join(qaFixDir, 'index.html'), `<!DOCTYPE html>
<html lang="en">
<head><meta charset="utf-8"><title>Test App</title></head>
<body>
<h1>Welcome to Test App</h1>
<nav>
<a href="/about">About</a>
<a href="/nonexistent-broken-page">Help</a> <!-- BUG: broken link -->
</nav>
<form id="contact">
<input type="text" name="name" placeholder="Name">
<input type="email" name="email" placeholder="Email">
<button type="submit" disabled>Send</button> <!-- BUG: permanently disabled -->
</form>
<img src="/missing-logo.png"> <!-- BUG: missing alt text -->
<script>console.error("TypeError: Cannot read property 'map' of undefined");</script> <!-- BUG: console error -->
</body>
</html>
`);
// Init git repo with clean working tree
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: qaFixDir, 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']);
// Start a local server serving from the working directory so fixes are reflected on refresh
const qaFixServer = Bun.serve({
port: 0,
hostname: '127.0.0.1',
fetch(req) {
const url = new URL(req.url);
let filePath = url.pathname === '/' ? '/index.html' : url.pathname;
filePath = filePath.replace(/^\//, '');
const fullPath = path.join(qaFixDir, filePath);
if (!fs.existsSync(fullPath)) {
return new Response('Not Found', { status: 404 });
}
const content = fs.readFileSync(fullPath, 'utf-8');
return new Response(content, {
headers: { 'Content-Type': 'text/html' },
});
},
});
const initial = spawnSync('git', ['rev-parse', 'HEAD'], {
cwd: qaFixDir, stdio: 'pipe', timeout: 5000,
});
if (initial.status !== 0) {
qaFixServer.stop();
fs.rmSync(qaFixDir, { recursive: true, force: true });
throw new Error('QA fixture initial commit failed');
}
return { qaFixDir, qaFixServer, initialCommit: initial.stdout.toString().trim() };
}
testConcurrentIfSelected('qa-fix-loop', async () => {
// A retry must receive the seeded defects again, not the first attempt's fixes.
const { qaFixDir, qaFixServer, initialCommit } = createQaFixFixture();
try {
const qaFixUrl = `http://127.0.0.1:${qaFixServer!.port}`;
const result = await runSkillTest({
prompt: `${browserPrompt('qa/SKILL.md')}
Read the file qa/SKILL.md for the QA workflow instructions.
qa is a carved skill: when SKILL.md tells you to Read ~/.claude/skills/gstack/qa/sections/<file>, read qa/sections/<file> in this working directory instead (same content, local copy).
Skip the preamble bash block, lake intro, telemetry, and contributor mode sections — go straight to the QA workflow.
Run a Quick-tier QA test on ${qaFixUrl}
The source code for this page is at ${qaFixDir}/index.html — you can fix bugs there.
Do NOT use AskUserQuestion — run Quick tier directly.
Write your report to ${qaFixDir}/qa-reports/qa-report.md
This is a test+fix loop: find bugs, fix them in the source code, commit each fix, and re-verify.`,
workingDirectory: qaFixDir,
maxTurns: 40,
allowedTools: ['Bash', 'Read', 'Write', 'Edit', 'Glob', 'Grep'],
timeout: CAPTURE_LONG_MS,
testName: 'qa-fix-loop',
runId,
});
logCost('/qa fix loop', result);
let passed = false;
try {
// Accept error_max_turns — fix loop may use many turns
expect(['success', 'error_max_turns']).toContain(result.exitReason);
// Verify at least one fix commit was made beyond the initial commit
const gitLog = spawnSync('git', ['log', '--oneline'], {
cwd: qaFixDir, stdio: 'pipe', timeout: 30_000,
});
const commits = gitLog.stdout.toString().trim().split('\n');
console.log(`/qa fix loop: ${commits.length} commits total (1 initial + ${commits.length - 1} fixes)`);
expect(commits.length).toBeGreaterThan(1);
// Verify a committed change to the seeded source, regardless of mutation tool.
// A report-only commit or an uncommitted edit cannot satisfy this contract.
const sourceDiff = spawnSync('git', ['diff', '--exit-code', initialCommit, 'HEAD', '--', 'index.html'], {
cwd: qaFixDir, stdio: 'pipe', timeout: 30_000,
});
expect(sourceDiff.status).toBe(1);
expect(sourceDiff.stdout.toString().trim().length).toBeGreaterThan(0);
passed = true;
} finally {
recordE2E(evalCollector, '/qa fix loop', 'QA Fix Loop E2E', result, { passed });
}
} finally {
qaFixServer.stop();
try { fs.rmSync(qaFixDir, { recursive: true, force: true }); } catch {}
}
}, CAPTURE_LONG_MS);
}, browserSelected);
// --- Test Bootstrap E2E ---
describeIfSelected('Test Bootstrap E2E', ['qa-bootstrap'], () => {
let bootstrapDir: string;
let bootstrapServer: ReturnType<typeof Bun.serve>;
beforeAll(() => {
bootstrapDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-bootstrap-'));
setupBrowseShims(bootstrapDir);
// Copy qa skill files
copyDirSync(path.join(ROOT, 'qa'), path.join(bootstrapDir, 'qa'));
// Create a minimal Node.js project with NO test framework
fs.writeFileSync(path.join(bootstrapDir, 'package.json'), JSON.stringify({
name: 'test-bootstrap-app',
version: '1.0.0',
type: 'module',
}, null, 2));
// Create a simple app file with a bug
fs.writeFileSync(path.join(bootstrapDir, 'app.js'), `
export function add(a, b) { return a + b; }
export function subtract(a, b) { return a - b; }
export function divide(a, b) { return a / b; } // BUG: no zero check
`);
// Create a simple HTML page with a bug
fs.writeFileSync(path.join(bootstrapDir, 'index.html'), `<!DOCTYPE html>
<html lang="en">
<head><meta charset="utf-8"><title>Bootstrap Test</title></head>
<body>
<h1>Test App</h1>
<a href="/nonexistent-page">Broken Link</a>
<script>console.error("ReferenceError: undefinedVar is not defined");</script>
</body>
</html>
`);
// Init git repo
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: bootstrapDir, 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']);
// Serve from working directory
bootstrapServer = Bun.serve({
port: 0,
hostname: '127.0.0.1',
fetch(req) {
const url = new URL(req.url);
let filePath = url.pathname === '/' ? '/index.html' : url.pathname;
filePath = filePath.replace(/^\//, '');
const fullPath = path.join(bootstrapDir, filePath);
if (!fs.existsSync(fullPath)) {
return new Response('Not Found', { status: 404 });
}
const content = fs.readFileSync(fullPath, 'utf-8');
return new Response(content, {
headers: { 'Content-Type': 'text/html' },
});
},
});
});
afterAll(() => {
bootstrapServer?.stop();
try { fs.rmSync(bootstrapDir, { recursive: true, force: true }); } catch {}
});
testConcurrentIfSelected('qa-bootstrap', async () => {
// Test ONLY the bootstrap phase — install vitest, create config, write one test
const bsDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-bs-'));
// Minimal Node.js project with no test framework
fs.writeFileSync(path.join(bsDir, 'package.json'), JSON.stringify({
name: 'bootstrap-test-app', version: '1.0.0', type: 'module',
}, null, 2));
fs.writeFileSync(path.join(bsDir, 'app.js'), `
export function add(a, b) { return a + b; }
export function subtract(a, b) { return a - b; }
export function divide(a, b) { return a / b; }
`);
// Init git repo
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: bsDir, 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']);
const result = await runSkillTest({
prompt: `This is a Node.js project with no test framework. It has a package.json and app.js with simple functions (add, subtract, divide).
Set up a test framework:
1. Install vitest: bun add -d vitest
2. Create vitest.config.ts with a minimal config
3. Write one test file (app.test.js) that tests the add() function
4. Run the test to verify it passes
5. Create TESTING.md explaining how to run tests
Do NOT fix any bugs. Do NOT use AskUserQuestion — just pick vitest.`,
workingDirectory: bsDir,
maxTurns: 12,
allowedTools: ['Bash', 'Read', 'Write', 'Edit', 'Glob'],
timeout: JUDGE_MS,
testName: 'qa-bootstrap',
runId,
});
logCost('/qa bootstrap', result);
const hasTestConfig = fs.existsSync(path.join(bsDir, 'vitest.config.ts'))
|| fs.existsSync(path.join(bsDir, 'vitest.config.js'));
const hasTestFile = fs.readdirSync(bsDir).some(f => f.includes('.test.'));
const hasTestingMd = fs.existsSync(path.join(bsDir, 'TESTING.md'));
recordE2E(evalCollector, '/qa bootstrap', 'Test Bootstrap E2E', result, {
passed: hasTestConfig && ['success', 'error_max_turns'].includes(result.exitReason),
});
expect(['success', 'error_max_turns']).toContain(result.exitReason);
expect(hasTestConfig).toBe(true);
console.log(`Test config: ${hasTestConfig}, Test file: ${hasTestFile}, TESTING.md: ${hasTestingMd}`);
try { fs.rmSync(bsDir, { recursive: true, force: true }); } catch {}
}, JUDGE_MS);
});
// Module-level afterAll — finalize eval collector after all tests complete.
// Explicit 60s timeout: finalize does a JSON save + cross-run comparison and
// has been observed at 6.26s, past bun's 5s default hook timeout.
afterAll(async () => {
await finalizeEvalCollector(evalCollector);
}, 60_000);