gstack/test/skill-e2e-bws.test.ts at main · haessr/gstack

385 lines (323 loc) · 15.1 KB
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
import { runSkillTest } from './helpers/session-runner';
  ROOT, browseBin, runId, evalsEnabled,
  describeIfSelected, testConcurrentIfSelected,
  copyDirSync, setupBrowseShims, logCost, recordE2E,
  createEvalCollector, finalizeEvalCollector,
} from './helpers/e2e-helpers';
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-browse');
let testServer: ReturnType<typeof startTestServer>;
let tmpDir: string;
describeIfSelected('Skill E2E tests', [
  'browse-basic', 'browse-snapshot', 'skillmd-setup-discovery',
  'skillmd-no-local-binary', 'skillmd-outside-git', 'session-awareness',
  'operational-learning',
  beforeAll(() => {
    testServer = startTestServer();
    tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-'));
    setupBrowseShims(tmpDir);
    // Pre-warm the browse server so Chromium is already launched for tests.
    // In CI, Chromium can take 10-20s to launch (Docker + --no-sandbox).
    spawnSync(browseBin, ['goto', testServer.url], { cwd: tmpDir, timeout: 30000, stdio: 'pipe' });
  }, 45_000);
  afterAll(() => {
    testServer?.server?.stop();
    try { fs.rmSync(tmpDir, { recursive: true, force: true }); } catch {}
  testConcurrentIfSelected('browse-basic', async () => {
    const result = await runSkillTest({
      prompt: `You have a browse binary at ${browseBin}. Assign it to B variable and run these commands in sequence:
1. $B goto ${testServer.url}
2. $B snapshot -i
4. $B screenshot /tmp/skill-e2e-test.png
Report the results of each command.`,
      workingDirectory: tmpDir,
      maxTurns: 7,
      timeout: 60_000,
      testName: 'browse-basic',
      runId,
    logCost('browse basic', result);
    recordE2E(evalCollector, 'browse basic commands', 'Skill E2E tests', result);
    expect(result.browseErrors).toHaveLength(0);
    expect(result.exitReason).toBe('success');
  }, 90_000);
  testConcurrentIfSelected('browse-snapshot', async () => {
    const result = await runSkillTest({
      prompt: `You have a browse binary at ${browseBin}. Assign it to B variable and run:
1. $B goto ${testServer.url}
2. $B snapshot -i
3. $B snapshot -c
4. $B snapshot -D
5. $B snapshot -i -a -o /tmp/skill-e2e-annotated.png
Report what each command returned.`,
      workingDirectory: tmpDir,
      maxTurns: 9,
      timeout: 60_000,
      testName: 'browse-snapshot',
      runId,
    logCost('browse snapshot', result);
    recordE2E(evalCollector, 'browse snapshot flags', 'Skill E2E tests', result);
    // browseErrors can include false positives from hallucinated paths (e.g. "baltimore" vs "bangalore")
    if (result.browseErrors.length > 0) {
      console.warn('Browse errors (non-fatal):', result.browseErrors);
    expect(result.exitReason).toBe('success');
  }, 90_000);
  testConcurrentIfSelected('skillmd-setup-discovery', async () => {
    const skillMd = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
    const setupStart = skillMd.indexOf('## SETUP');
    const setupEnd = skillMd.indexOf('## IMPORTANT');
    const setupBlock = skillMd.slice(setupStart, setupEnd);
    // Guard: verify we extracted a valid setup block
    expect(setupBlock).toContain('browse/dist/browse');
    const result = await runSkillTest({
      prompt: `Follow these instructions to find the browse binary and run a basic command.
${setupBlock}
After finding the binary, run: $B goto ${testServer.url}
Then run: $B text
Report whether it worked.`,
      workingDirectory: tmpDir,
      maxTurns: 10,
      timeout: 60_000,
      testName: 'skillmd-setup-discovery',
      runId,
    recordE2E(evalCollector, 'SKILL.md setup block discovery', 'Skill E2E tests', result);
    expect(result.browseErrors).toHaveLength(0);
    expect(result.exitReason).toBe('success');
  }, 90_000);
  testConcurrentIfSelected('skillmd-no-local-binary', async () => {
    // Create a tmpdir with no browse binary — no local .claude/skills/gstack/browse/dist/browse
    const emptyDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-empty-'));
    const skillMd = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
    const setupStart = skillMd.indexOf('## SETUP');
    const setupEnd = skillMd.indexOf('## IMPORTANT');
    const setupBlock = skillMd.slice(setupStart, setupEnd);
    const result = await runSkillTest({
      prompt: `Follow these instructions exactly. Run the bash code block below and report what it outputs.
${setupBlock}
Report the exact output. Do NOT try to fix or install anything — just report what you see.`,
      workingDirectory: emptyDir,
      maxTurns: 5,
      timeout: 30_000,
      testName: 'skillmd-no-local-binary',
      runId,
    // Setup block should either find the global binary (READY) or show NEEDS_SETUP.
    // On dev machines with gstack installed globally, the fallback path
    // ~/.claude/skills/gstack/browse/dist/browse exists, so we get READY.
    // The important thing is it doesn't crash or give a confusing error.
    const allText = result.output || '';
    recordE2E(evalCollector, 'SKILL.md setup block (no local binary)', 'Skill E2E tests', result);
    expect(allText).toMatch(/READY|NEEDS_SETUP/);
    expect(result.exitReason).toBe('success');
    // Clean up
    try { fs.rmSync(emptyDir, { recursive: true, force: true }); } catch {}
  }, 60_000);
  testConcurrentIfSelected('skillmd-outside-git', async () => {
    // Create a tmpdir outside any git repo
    const nonGitDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-nogit-'));
    const skillMd = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
    const setupStart = skillMd.indexOf('## SETUP');
    const setupEnd = skillMd.indexOf('## IMPORTANT');
    const setupBlock = skillMd.slice(setupStart, setupEnd);
    const result = await runSkillTest({
      prompt: `Follow these instructions exactly. Run the bash code block below and report what it outputs.
${setupBlock}
Report the exact output — either "READY: <path>" or "NEEDS_SETUP".`,
      workingDirectory: nonGitDir,
      maxTurns: 5,
      timeout: 30_000,
      testName: 'skillmd-outside-git',
      runId,
    // Should either find global binary (READY) or show NEEDS_SETUP — not crash
    const allText = result.output || '';
    recordE2E(evalCollector, 'SKILL.md outside git repo', 'Skill E2E tests', result);
    expect(allText).toMatch(/READY|NEEDS_SETUP/);
    // Clean up
    try { fs.rmSync(nonGitDir, { recursive: true, force: true }); } catch {}
  }, 60_000);
  testConcurrentIfSelected('operational-learning', async () => {
    const opDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-oplearn-'));
    const gstackHome = path.join(opDir, '.gstack-home');
    // Init git repo
    const run = (cmd: string, args: string[]) =>
      spawnSync(cmd, args, { cwd: opDir, 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(opDir, 'app.ts'), 'console.log("hello");\n');
    run('git', ['add', '.']);
    run('git', ['commit', '-m', 'initial']);
    // Copy bin scripts
    const binDir = path.join(opDir, 'bin');
    fs.mkdirSync(binDir, { recursive: true });
    for (const script of ['gstack-learnings-log', 'gstack-slug']) {
      fs.copyFileSync(path.join(ROOT, 'bin', script), path.join(binDir, script));
      fs.chmodSync(path.join(binDir, script), 0o755);
    // gstack-learnings-log will create the project dir automatically via gstack-slug
    const result = await runSkillTest({
      prompt: `You just ran \`npm test\` in this project and it failed with this error:
Error: --experimental-vm-modules flag is required for ESM support in this project.
Run: npm test --experimental-vm-modules
Per the Operational Self-Improvement instructions below, log an operational learning about this failure.
## Operational Self-Improvement
Before completing, reflect on this session:
- Did any commands fail unexpectedly?
If yes, log an operational learning for future sessions:
GSTACK_HOME="${gstackHome}" ${binDir}/gstack-learnings-log '{"skill":"qa","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
Replace SHORT_KEY with a kebab-case key like "esm-vm-modules-flag".
Replace DESCRIPTION with a one-sentence description of what you learned.
Replace N with a confidence score 1-10.
Log the operational learning now. Then say what you logged.`,
      workingDirectory: opDir,
      maxTurns: 5,
      timeout: 30_000,
      testName: 'operational-learning',
      runId,
    logCost('operational learning', result);
    const exitOk = ['success', 'error_max_turns'].includes(result.exitReason);
    // Check if learnings file was created with an operational entry
    // The slug is derived from the git repo (dirname), so search all project dirs
    let hasOperational = false;
    const projectsDir = path.join(gstackHome, 'projects');
    if (fs.existsSync(projectsDir)) {
      for (const slug of fs.readdirSync(projectsDir)) {
        const lPath = path.join(projectsDir, slug, 'learnings.jsonl');
        if (fs.existsSync(lPath)) {
          const jsonl = fs.readFileSync(lPath, 'utf-8').trim();
          if (jsonl) {
            const entries = jsonl.split('\n').map(l => { try { return JSON.parse(l); } catch { return null; } }).filter(Boolean);
            const opEntry = entries.find(e => e.type === 'operational');
            if (opEntry) {
              hasOperational = true;
              console.log(`Operational learning logged: key="${opEntry.key}" insight="${opEntry.insight}" (slug: ${slug})`);
              break;
    recordE2E(evalCollector, 'operational learning', 'Skill E2E tests', result, {
      passed: exitOk && hasOperational,
    expect(exitOk).toBe(true);
    expect(hasOperational).toBe(true);
    // Clean up
    try { fs.rmSync(opDir, { recursive: true, force: true }); } catch {}
  }, 90_000);
  testConcurrentIfSelected('session-awareness', async () => {
    const sessionDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-session-'));
    // 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', '-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');
    run('git', ['add', '.']);
    run('git', ['commit', '-m', 'init']);
    run('git', ['checkout', '-b', 'feature/add-payments']);
    // Add a remote so the agent can derive a project name
    run('git', ['remote', 'add', 'origin', 'https://github.com/acme/billing-app.git']);
    // Extract AskUserQuestion format instructions from a generated SKILL.md.
    // ROOT/SKILL.md is the browse skill (Tier 1) and does NOT contain the
    // "## AskUserQuestion Format" section — that block is only emitted for
    // Tier 2+ skills by scripts/resolvers/preamble.ts. Use office-hours/SKILL.md
    // (Tier 3) which always has the format guidance baked in. Falls back to
    // the first SKILL.md that contains the header so a future template move
    // doesn't break this test again.
    let skillMdPath = path.join(ROOT, 'office-hours', 'SKILL.md');
    let skillMd = '';
    if (fs.existsSync(skillMdPath)) {
      skillMd = fs.readFileSync(skillMdPath, 'utf-8');
    if (!skillMd.includes('## AskUserQuestion Format')) {
      // Fallback: scan top-level skill dirs for the first match.
      const skillDirs = fs.readdirSync(ROOT, { withFileTypes: true })
        .filter(d => d.isDirectory())
        .map(d => path.join(ROOT, d.name, 'SKILL.md'));
      for (const candidate of skillDirs) {
        if (!fs.existsSync(candidate)) continue;
        const content = fs.readFileSync(candidate, 'utf-8');
        if (content.includes('## AskUserQuestion Format')) {
          skillMd = content;
          skillMdPath = candidate;
          break;
    const aqStart = skillMd.indexOf('## AskUserQuestion Format');
    const aqEnd = skillMd.indexOf('\n## ', aqStart + 1);
    const aqBlock = aqStart >= 0
      ? skillMd.slice(aqStart, aqEnd > 0 ? aqEnd : undefined)
      : '';
    const outputPath = path.join(sessionDir, 'question-output.md');
    const result = await runSkillTest({
      prompt: `You are running a gstack skill. The session preamble detected _SESSIONS=4 (the user has 4 gstack windows open).
You are on branch feature/add-payments in the billing-app project. You were reviewing a plan to add Stripe integration.
You've hit a decision point: the plan doesn't specify whether to use Stripe Checkout (hosted) or Stripe Elements (embedded). You need to ask the user which approach to use.
Since this is non-interactive, DO NOT actually call AskUserQuestion. Instead, write the EXACT text you would display to the user (the full AskUserQuestion content) to the file: ${outputPath}
Remember: _SESSIONS=4, so ELI16 mode is active. The user is juggling multiple windows and may not remember what this conversation is about. Re-ground them.`,
      workingDirectory: sessionDir,
      maxTurns: 8,
      timeout: 60_000,
      testName: 'session-awareness',
      runId,
    logCost('session awareness', result);
    recordE2E(evalCollector, 'session awareness ELI16', 'Skill E2E tests', result);
    // Verify the output contains ELI16 re-grounding context
    if (fs.existsSync(outputPath)) {
      const output = fs.readFileSync(outputPath, 'utf-8');
      const lower = output.toLowerCase();
      // Must mention project name
      expect(lower.includes('billing') || lower.includes('acme')).toBe(true);
      // Must mention branch
      expect(lower.includes('payment') || lower.includes('feature')).toBe(true);
      // Must mention what we're working on
      expect(lower.includes('stripe') || lower.includes('checkout') || lower.includes('payment')).toBe(true);
      // Must have a recommendation or structured options
      expect(
        output.includes('RECOMMENDATION') ||
        lower.includes('recommend') ||
        lower.includes('option a') ||
        lower.includes('which do you want') ||
        lower.includes('which approach')
      ).toBe(true);
    } else {
      // Check agent output as fallback
      const output = result.output || '';
      const lowerOut = output.toLowerCase();
      expect(
        output.includes('RECOMMENDATION') ||
        lowerOut.includes('recommend') ||
        lowerOut.includes('option a') ||
        lowerOut.includes('which do you want') ||
        lowerOut.includes('which approach')
      ).toBe(true);
    // Clean up
    try { fs.rmSync(sessionDir, { recursive: true, force: true }); } catch {}
  }, 90_000);
// Module-level afterAll — finalize eval collector after all tests complete
afterAll(async () => {
  await finalizeEvalCollector(evalCollector);
Provide feedback

Saved searches

Use saved searches to filter your results more quickly

FilesExpand file tree

skill-e2e-bws.test.ts

Latest commit

History

skill-e2e-bws.test.ts

File metadata and controls
