~cytrogen/gstack

ref: 6169273d16b7ab8690943241fa802e5a1ca85305 gstack/test/skill-routing-e2e.test.ts -rw-r--r-- 26.7 KiB
6169273d — Garry Tan feat: /design-html works from any starting point (v0.15.1.0) (#734) 8 days ago
                                                                                
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
import { describe, test, expect, afterAll } from 'bun:test';
import { runSkillTest } from './helpers/session-runner';
import type { SkillTestResult } from './helpers/session-runner';
import { EvalCollector } from './helpers/eval-store';
import type { EvalTestEntry } from './helpers/eval-store';
import { selectTests, detectBaseBranch, getChangedFiles, E2E_TOUCHFILES, E2E_TIERS, GLOBAL_TOUCHFILES } from './helpers/touchfiles';
import { spawnSync } from 'child_process';
import * as fs from 'fs';
import * as path from 'path';
import * as os from 'os';

const ROOT = path.resolve(import.meta.dir, '..');

// Skip unless EVALS=1.
const evalsEnabled = !!process.env.EVALS;
const describeE2E = evalsEnabled ? describe : describe.skip;

// Eval result collector
const evalCollector = evalsEnabled ? new EvalCollector('e2e-routing') : null;

// Unique run ID for this session
const runId = new Date().toISOString().replace(/[:.]/g, '').replace('T', '-').slice(0, 15);

// --- Diff-based test selection ---
// Journey routing tests use E2E_TOUCHFILES (entries prefixed 'journey-' in touchfiles.ts).
let selectedTests: string[] | null = null;

if (evalsEnabled && !process.env.EVALS_ALL) {
  const baseBranch = process.env.EVALS_BASE
    || detectBaseBranch(ROOT)
    || 'main';
  const changedFiles = getChangedFiles(baseBranch, ROOT);

  if (changedFiles.length > 0) {
    const selection = selectTests(changedFiles, E2E_TOUCHFILES, GLOBAL_TOUCHFILES);
    selectedTests = selection.selected;
    process.stderr.write(`\nRouting E2E selection (${selection.reason}): ${selection.selected.length}/${Object.keys(E2E_TOUCHFILES).length} tests\n`);
    if (selection.skipped.length > 0) {
      process.stderr.write(`  Skipped: ${selection.skipped.join(', ')}\n`);
    }
    process.stderr.write('\n');
  }
}

// Apply EVALS_TIER filter (same logic as e2e-helpers.ts)
if (evalsEnabled && process.env.EVALS_TIER) {
  const tier = process.env.EVALS_TIER as 'gate' | 'periodic';
  const tierTests = Object.entries(E2E_TIERS)
    .filter(([, t]) => t === tier)
    .map(([name]) => name);

  if (selectedTests === null) {
    selectedTests = tierTests;
  } else {
    selectedTests = selectedTests.filter(t => tierTests.includes(t));
  }
  process.stderr.write(`Routing EVALS_TIER=${tier}: ${selectedTests.length} tests\n\n`);
}

// --- Helper functions ---

/** Copy all SKILL.md files for auto-discovery.
 *  Install to BOTH project-level (.claude/skills/) AND user-level (~/.claude/skills/)
 *  because Claude Code discovers skills from both locations. In CI containers,
 *  $HOME may differ from the working directory, so we need both paths to ensure
 *  the Skill tool appears in Claude's available tools list. */
function installSkills(tmpDir: string) {
  const skillDirs = [
    '', // root gstack SKILL.md
    'qa', 'qa-only', 'ship', 'review', 'plan-ceo-review', 'plan-eng-review',
    'plan-design-review', 'design-review', 'design-consultation', 'retro',
    'document-release', 'investigate', 'office-hours', 'browse', 'setup-browser-cookies',
    'gstack-upgrade', 'humanizer',
  ];

  // Install to both project-level and user-level skill directories
  const homeDir = process.env.HOME || os.homedir();
  const installTargets = [
    path.join(tmpDir, '.claude', 'skills'),        // project-level
    path.join(homeDir, '.claude', 'skills'),        // user-level (~/.claude/skills/)
  ];

  for (const skill of skillDirs) {
    const srcPath = path.join(ROOT, skill, 'SKILL.md');
    if (!fs.existsSync(srcPath)) continue;

    const skillName = skill || 'gstack';

    for (const targetBase of installTargets) {
      const destDir = path.join(targetBase, skillName);
      fs.mkdirSync(destDir, { recursive: true });
      fs.copyFileSync(srcPath, path.join(destDir, 'SKILL.md'));
    }
  }

  // Write a CLAUDE.md with explicit routing instructions.
  // The skill descriptions in system-reminder aren't strong enough to override
  // Claude's default behavior of answering directly. A CLAUDE.md instruction
  // puts routing rules in project context which Claude weighs more heavily.
  fs.writeFileSync(path.join(tmpDir, 'CLAUDE.md'), `# Project Instructions

## Skill routing

When the user's request matches an available skill, ALWAYS invoke it using the Skill
tool as your FIRST action. Do NOT answer directly, do NOT use other tools first.
The skill has specialized workflows that produce better results than ad-hoc answers.

Key routing rules:
- Product ideas, "is this worth building", brainstorming → invoke office-hours
- Bugs, errors, "why is this broken", 500 errors → invoke investigate
- Ship, deploy, push, create PR → invoke ship
- QA, test the site, find bugs → invoke qa
- Code review, check my diff → invoke review
- Update docs after shipping → invoke document-release
- Weekly retro → invoke retro
- Design system, brand → invoke design-consultation
- Visual audit, design polish → invoke design-review
- Architecture review → invoke plan-eng-review
`);
}

/** Init a git repo with config */
function initGitRepo(dir: string) {
  const run = (cmd: string, args: string[]) =>
    spawnSync(cmd, args, { cwd: dir, stdio: 'pipe', timeout: 5000 });
  run('git', ['init']);
  run('git', ['config', 'user.email', 'test@test.com']);
  run('git', ['config', 'user.name', 'Test']);
}

/**
 * Create a routing test working directory.
 * Uses the actual repo checkout (ROOT) which has CLAUDE.md, .claude/skills/,
 * and full project context. This matches the local environment where routing
 * tests pass reliably. In containerized CI, bare tmpDirs lack the context
 * Claude needs to make correct routing decisions.
 */
function createRoutingWorkDir(suffix: string): string {
  // Clone the repo checkout into a tmpDir so concurrent tests don't interfere
  const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), `routing-${suffix}-`));
  // Copy essential context files
  const filesToCopy = ['CLAUDE.md', 'README.md', 'package.json', 'ETHOS.md'];
  for (const f of filesToCopy) {
    const src = path.join(ROOT, f);
    if (fs.existsSync(src)) fs.copyFileSync(src, path.join(tmpDir, f));
  }
  // Copy skill files
  installSkills(tmpDir);
  // Init git
  initGitRepo(tmpDir);
  spawnSync('git', ['add', '.'], { cwd: tmpDir, stdio: 'pipe', timeout: 5000 });
  spawnSync('git', ['commit', '-m', 'initial'], { cwd: tmpDir, stdio: 'pipe', timeout: 5000 });
  return tmpDir;
}

function logCost(label: string, result: { costEstimate: { turnsUsed: number; estimatedTokens: number; estimatedCost: number }; duration: number }) {
  const { turnsUsed, estimatedTokens, estimatedCost } = result.costEstimate;
  const durationSec = Math.round(result.duration / 1000);
  console.log(`${label}: $${estimatedCost.toFixed(2)} (${turnsUsed} turns, ${(estimatedTokens / 1000).toFixed(1)}k tokens, ${durationSec}s)`);
}

function recordRouting(name: string, result: SkillTestResult, expectedSkill: string, actualSkill: string | undefined) {
  evalCollector?.addTest({
    name,
    suite: 'Skill Routing E2E',
    tier: 'e2e',
    passed: actualSkill === expectedSkill,
    duration_ms: result.duration,
    cost_usd: result.costEstimate.estimatedCost,
    transcript: result.transcript,
    output: result.output?.slice(0, 2000),
    turns_used: result.costEstimate.turnsUsed,
    exit_reason: result.exitReason,
  });
}

// Skip individual tests based on selectedTests (diff + tier filtering)
const testIfSelected = (name: string, fn: () => Promise<void>, timeout?: number) => {
  if (selectedTests !== null && !selectedTests.includes(name)) {
    test.skip(name, () => {});
  } else {
    test.concurrent(name, fn, timeout);
  }
};

// --- Tests ---

describeE2E('Skill Routing E2E — Developer Journey', () => {
  afterAll(() => {
    evalCollector?.finalize();
  });

  testIfSelected('journey-ideation', async () => {
    const tmpDir = createRoutingWorkDir('ideation');
    try {

      const testName = 'journey-ideation';
      const expectedSkill = 'office-hours';
      const result = await runSkillTest({
        prompt: "I've been thinking about building a waitlist management tool for restaurants. The existing solutions are expensive and overcomplicated. I want something simple — a tablet app where hosts can add parties, see wait times, and text customers when their table is ready. Help me think through whether this is worth building and what the key design decisions are.",
        workingDirectory: tmpDir,
        maxTurns: 5,
        allowedTools: ['Skill', 'Read', 'Bash', 'Glob', 'Grep'],
        timeout: 60_000,
        testName,
        runId,
      });

      const skillCalls = result.toolCalls.filter(tc => tc.tool === 'Skill');
      const actualSkill = skillCalls.length > 0 ? skillCalls[0]?.input?.skill : undefined;

      logCost(`journey: ${testName}`, result);
      recordRouting(testName, result, expectedSkill, actualSkill);

      expect(skillCalls.length, `Expected Skill tool to be called but got 0 calls. Claude may have answered directly without invoking a skill. Tool calls: ${result.toolCalls.map(tc => tc.tool).join(', ')}`).toBeGreaterThan(0);
      expect([expectedSkill], `Expected skill ${expectedSkill} but got ${actualSkill}`).toContain(actualSkill);
    } finally {
      fs.rmSync(tmpDir, { recursive: true, force: true });
    }
  }, 150_000);

  testIfSelected('journey-plan-eng', async () => {
    const tmpDir = createRoutingWorkDir('plan-eng');
    try {
      fs.writeFileSync(path.join(tmpDir, 'plan.md'), `# Waitlist App Architecture

## Components
- REST API (Express.js)
- PostgreSQL database
- React frontend
- SMS integration (Twilio)

## Data Model
- restaurants (id, name, settings)
- parties (id, restaurant_id, name, size, phone, status, created_at)
- wait_estimates (id, restaurant_id, avg_wait_minutes)

## API Endpoints
- POST /api/parties - add party to waitlist
- GET /api/parties - list current waitlist
- PATCH /api/parties/:id/status - update party status
- GET /api/estimate - get current wait estimate
`);
      spawnSync('git', ['add', '.'], { cwd: tmpDir, stdio: 'pipe', timeout: 5000 });
      spawnSync('git', ['commit', '-m', 'initial'], { cwd: tmpDir, stdio: 'pipe', timeout: 5000 });

      const testName = 'journey-plan-eng';
      const expectedSkill = 'plan-eng-review';
      const result = await runSkillTest({
        prompt: "I wrote up a plan for the waitlist app in plan.md. Can you take a look at the architecture and make sure I'm not missing any edge cases or failure modes before I start coding?",
        workingDirectory: tmpDir,
        maxTurns: 5,
        allowedTools: ['Skill', 'Read', 'Bash', 'Glob', 'Grep'],
        timeout: 60_000,
        testName,
        runId,
      });

      const skillCalls = result.toolCalls.filter(tc => tc.tool === 'Skill');
      const actualSkill = skillCalls.length > 0 ? skillCalls[0]?.input?.skill : undefined;

      logCost(`journey: ${testName}`, result);
      recordRouting(testName, result, expectedSkill, actualSkill);

      expect(skillCalls.length, `Expected Skill tool to be called but got 0 calls. Claude may have answered directly without invoking a skill. Tool calls: ${result.toolCalls.map(tc => tc.tool).join(', ')}`).toBeGreaterThan(0);
      expect([expectedSkill], `Expected skill ${expectedSkill} but got ${actualSkill}`).toContain(actualSkill);
    } finally {
      fs.rmSync(tmpDir, { recursive: true, force: true });
    }
  }, 150_000);

  // Removed: journey-think-bigger
  // Tested ambiguous routing ("think bigger" → plan-ceo-review) but Claude
  // legitimately answers directly instead of routing. Never passed reliably.
  // The other 10 journey tests cover routing with clear signals.

  testIfSelected('journey-debug', async () => {
    const tmpDir = createRoutingWorkDir('debug');
    try {
      const run = (cmd: string, args: string[]) =>
        spawnSync(cmd, args, { cwd: tmpDir, stdio: 'pipe', timeout: 5000 });

      fs.mkdirSync(path.join(tmpDir, 'src'), { recursive: true });
      fs.writeFileSync(path.join(tmpDir, 'src/api.ts'), `
import express from 'express';
const app = express();

app.get('/api/waitlist', async (req, res) => {
  const db = req.app.locals.db;
  const parties = await db.query('SELECT * FROM parties WHERE status = $1', ['waiting']);
  res.json(parties.rows);
});

export default app;
`);
      fs.writeFileSync(path.join(tmpDir, 'error.log'), `
[2026-03-18T10:23:45Z] ERROR: GET /api/waitlist - 500 Internal Server Error
  TypeError: Cannot read properties of undefined (reading 'query')
    at /src/api.ts:5:32
    at Layer.handle [as handle_request] (/node_modules/express/lib/router/layer.js:95:5)
[2026-03-18T10:23:46Z] ERROR: GET /api/waitlist - 500 Internal Server Error
  TypeError: Cannot read properties of undefined (reading 'query')
`);

      run('git', ['add', '.']);
      run('git', ['commit', '-m', 'initial']);
      run('git', ['checkout', '-b', 'feature/waitlist-api']);

      const testName = 'journey-debug';
      const expectedSkill = 'investigate';
      const result = await runSkillTest({
        prompt: "The GET /api/waitlist endpoint was working fine yesterday but now it's returning 500 errors. The tests are passing locally but the endpoint fails when I hit it with curl. Can you figure out what's going on?",
        workingDirectory: tmpDir,
        maxTurns: 5,
        allowedTools: ['Skill', 'Read', 'Bash', 'Glob', 'Grep'],
        timeout: 60_000,
        testName,
        runId,
      });

      const skillCalls = result.toolCalls.filter(tc => tc.tool === 'Skill');
      const actualSkill = skillCalls.length > 0 ? skillCalls[0]?.input?.skill : undefined;

      logCost(`journey: ${testName}`, result);
      recordRouting(testName, result, expectedSkill, actualSkill);

      expect(skillCalls.length, `Expected Skill tool to be called but got 0 calls. Claude may have answered directly without invoking a skill. Tool calls: ${result.toolCalls.map(tc => tc.tool).join(', ')}`).toBeGreaterThan(0);
      const validSkills = ['investigate', 'qa'];
      expect(validSkills, `Expected one of ${validSkills.join('/')} but got ${actualSkill}`).toContain(actualSkill);
    } finally {
      fs.rmSync(tmpDir, { recursive: true, force: true });
    }
  }, 150_000);

  testIfSelected('journey-qa', async () => {
    const tmpDir = createRoutingWorkDir('qa');
    try {
      fs.writeFileSync(path.join(tmpDir, 'package.json'), JSON.stringify({ name: 'waitlist-app', scripts: { dev: 'next dev' } }, null, 2));
      fs.mkdirSync(path.join(tmpDir, 'src'), { recursive: true });
      fs.writeFileSync(path.join(tmpDir, 'src/index.html'), '<html><body><h1>Waitlist App</h1></body></html>');
      spawnSync('git', ['add', '.'], { cwd: tmpDir, stdio: 'pipe', timeout: 5000 });
      spawnSync('git', ['commit', '-m', 'initial'], { cwd: tmpDir, stdio: 'pipe', timeout: 5000 });

      const testName = 'journey-qa';
      const expectedSkill = 'qa';
      const alternateSkills = ['qa-only', 'browse'];
      const result = await runSkillTest({
        prompt: "I think the app is mostly working now. Can you go through the site and test everything — find any bugs and fix them?",
        workingDirectory: tmpDir,
        maxTurns: 5,
        allowedTools: ['Skill', 'Read', 'Bash', 'Glob', 'Grep'],
        timeout: 60_000,
        testName,
        runId,
      });

      const skillCalls = result.toolCalls.filter(tc => tc.tool === 'Skill');
      const actualSkill = skillCalls.length > 0 ? skillCalls[0]?.input?.skill : undefined;
      const acceptable = [expectedSkill, ...alternateSkills];

      logCost(`journey: ${testName}`, result);
      recordRouting(testName, result, expectedSkill, actualSkill);

      expect(skillCalls.length, `Expected Skill tool to be called but got 0 calls. Claude may have answered directly without invoking a skill. Tool calls: ${result.toolCalls.map(tc => tc.tool).join(', ')}`).toBeGreaterThan(0);
      expect(acceptable, `Expected skill ${expectedSkill} but got ${actualSkill}`).toContain(actualSkill);
    } finally {
      fs.rmSync(tmpDir, { recursive: true, force: true });
    }
  }, 150_000);

  testIfSelected('journey-code-review', async () => {
    const tmpDir = createRoutingWorkDir('code-review');
    try {
      const run = (cmd: string, args: string[]) =>
        spawnSync(cmd, args, { cwd: tmpDir, stdio: 'pipe', timeout: 5000 });

      fs.writeFileSync(path.join(tmpDir, 'app.ts'), '// base\n');
      run('git', ['add', '.']);
      run('git', ['commit', '-m', 'add base app']);
      run('git', ['checkout', '-b', 'feature/add-waitlist']);
      fs.writeFileSync(path.join(tmpDir, 'app.ts'), '// updated with waitlist feature\nimport { WaitlistService } from "./waitlist";\n');
      fs.writeFileSync(path.join(tmpDir, 'waitlist.ts'), 'export class WaitlistService {\n  async addParty(name: string, size: number) {\n    // TODO: implement\n  }\n}\n');
      run('git', ['add', '.']);
      run('git', ['commit', '-m', 'feat: add waitlist service']);

      const testName = 'journey-code-review';
      const expectedSkill = 'review';
      const result = await runSkillTest({
        prompt: "I'm about to merge this into main. Can you look over my changes and flag anything risky before I land it?",
        workingDirectory: tmpDir,
        maxTurns: 5,
        allowedTools: ['Skill', 'Read', 'Bash', 'Glob', 'Grep'],
        timeout: 120_000,
        testName,
        runId,
      });

      const skillCalls = result.toolCalls.filter(tc => tc.tool === 'Skill');
      const actualSkill = skillCalls.length > 0 ? skillCalls[0]?.input?.skill : undefined;

      logCost(`journey: ${testName}`, result);
      recordRouting(testName, result, expectedSkill, actualSkill);

      expect(skillCalls.length, `Expected Skill tool to be called but got 0 calls. Claude may have answered directly without invoking a skill. Tool calls: ${result.toolCalls.map(tc => tc.tool).join(', ')}`).toBeGreaterThan(0);
      expect([expectedSkill], `Expected skill ${expectedSkill} but got ${actualSkill}`).toContain(actualSkill);
    } finally {
      fs.rmSync(tmpDir, { recursive: true, force: true });
    }
  }, 150_000);

  testIfSelected('journey-ship', async () => {
    const tmpDir = createRoutingWorkDir('ship');
    try {
      const run = (cmd: string, args: string[]) =>
        spawnSync(cmd, args, { cwd: tmpDir, stdio: 'pipe', timeout: 5000 });

      fs.writeFileSync(path.join(tmpDir, 'app.ts'), '// base\n');
      run('git', ['add', '.']);
      run('git', ['commit', '-m', 'add base app']);
      run('git', ['checkout', '-b', 'feature/waitlist']);
      fs.writeFileSync(path.join(tmpDir, 'app.ts'), '// waitlist feature\n');
      run('git', ['add', '.']);
      run('git', ['commit', '-m', 'feat: waitlist']);

      const testName = 'journey-ship';
      const expectedSkill = 'ship';
      const result = await runSkillTest({
        prompt: "This looks good. Let's get it deployed — push the code up and create a PR.",
        workingDirectory: tmpDir,
        maxTurns: 5,
        allowedTools: ['Skill', 'Read', 'Bash', 'Glob', 'Grep'],
        timeout: 60_000,
        testName,
        runId,
      });

      const skillCalls = result.toolCalls.filter(tc => tc.tool === 'Skill');
      const actualSkill = skillCalls.length > 0 ? skillCalls[0]?.input?.skill : undefined;

      logCost(`journey: ${testName}`, result);
      recordRouting(testName, result, expectedSkill, actualSkill);

      expect(skillCalls.length, `Expected Skill tool to be called but got 0 calls. Claude may have answered directly without invoking a skill. Tool calls: ${result.toolCalls.map(tc => tc.tool).join(', ')}`).toBeGreaterThan(0);
      expect([expectedSkill], `Expected skill ${expectedSkill} but got ${actualSkill}`).toContain(actualSkill);
    } finally {
      fs.rmSync(tmpDir, { recursive: true, force: true });
    }
  }, 150_000);

  testIfSelected('journey-docs', async () => {
    const tmpDir = createRoutingWorkDir('docs');
    try {
      const run = (cmd: string, args: string[]) =>
        spawnSync(cmd, args, { cwd: tmpDir, stdio: 'pipe', timeout: 5000 });

      fs.writeFileSync(path.join(tmpDir, 'README.md'), '# Waitlist App\nA simple waitlist management tool.\n');
      fs.mkdirSync(path.join(tmpDir, 'src'), { recursive: true });
      fs.writeFileSync(path.join(tmpDir, 'src/api.ts'), '// API code\n');
      run('git', ['add', '.']);
      run('git', ['commit', '-m', 'feat: ship waitlist feature']);

      const testName = 'journey-docs';
      const expectedSkill = 'document-release';
      const result = await runSkillTest({
        prompt: "We just shipped the waitlist feature. Can you go through the README and any other docs and make sure they match what we actually built?",
        workingDirectory: tmpDir,
        maxTurns: 5,
        allowedTools: ['Skill', 'Read', 'Bash', 'Glob', 'Grep'],
        timeout: 60_000,
        testName,
        runId,
      });

      const skillCalls = result.toolCalls.filter(tc => tc.tool === 'Skill');
      const actualSkill = skillCalls.length > 0 ? skillCalls[0]?.input?.skill : undefined;

      logCost(`journey: ${testName}`, result);
      recordRouting(testName, result, expectedSkill, actualSkill);

      expect(skillCalls.length, `Expected Skill tool to be called but got 0 calls. Claude may have answered directly without invoking a skill. Tool calls: ${result.toolCalls.map(tc => tc.tool).join(', ')}`).toBeGreaterThan(0);
      expect([expectedSkill], `Expected skill ${expectedSkill} but got ${actualSkill}`).toContain(actualSkill);
    } finally {
      fs.rmSync(tmpDir, { recursive: true, force: true });
    }
  }, 150_000);

  testIfSelected('journey-retro', async () => {
    const tmpDir = createRoutingWorkDir('retro');
    try {
      const run = (cmd: string, args: string[]) =>
        spawnSync(cmd, args, { cwd: tmpDir, stdio: 'pipe', timeout: 5000 });

      fs.writeFileSync(path.join(tmpDir, 'api.ts'), 'export function getParties() { return []; }\n');
      run('git', ['add', '.']);
      run('git', ['commit', '-m', 'feat: add parties API', '--date', '2026-03-12T09:30:00']);

      fs.writeFileSync(path.join(tmpDir, 'ui.tsx'), 'export function WaitlistView() { return <div>Waitlist</div>; }\n');
      run('git', ['add', '.']);
      run('git', ['commit', '-m', 'feat: add waitlist UI', '--date', '2026-03-13T14:00:00']);

      fs.writeFileSync(path.join(tmpDir, 'README.md'), '# Waitlist App\n');
      run('git', ['add', '.']);
      run('git', ['commit', '-m', 'docs: add README', '--date', '2026-03-14T16:00:00']);

      const testName = 'journey-retro';
      const expectedSkill = 'retro';
      const result = await runSkillTest({
        prompt: "It's Friday. What did we ship this week? I want to do a quick retrospective on what the team accomplished.",
        workingDirectory: tmpDir,
        maxTurns: 5,
        allowedTools: ['Skill', 'Read', 'Bash', 'Glob', 'Grep'],
        timeout: 120_000,
        testName,
        runId,
      });

      const skillCalls = result.toolCalls.filter(tc => tc.tool === 'Skill');
      const actualSkill = skillCalls.length > 0 ? skillCalls[0]?.input?.skill : undefined;

      logCost(`journey: ${testName}`, result);
      recordRouting(testName, result, expectedSkill, actualSkill);

      expect(skillCalls.length, `Expected Skill tool to be called but got 0 calls. Claude may have answered directly without invoking a skill. Tool calls: ${result.toolCalls.map(tc => tc.tool).join(', ')}`).toBeGreaterThan(0);
      expect([expectedSkill], `Expected skill ${expectedSkill} but got ${actualSkill}`).toContain(actualSkill);
    } finally {
      fs.rmSync(tmpDir, { recursive: true, force: true });
    }
  }, 150_000);

  testIfSelected('journey-design-system', async () => {
    const tmpDir = createRoutingWorkDir('design-system');
    try {

      const testName = 'journey-design-system';
      const expectedSkill = 'design-consultation';
      const result = await runSkillTest({
        prompt: "Before we build the UI, I want to establish a design system — typography, colors, spacing, the whole thing. Can you put together brand guidelines for this project?",
        workingDirectory: tmpDir,
        maxTurns: 5,
        allowedTools: ['Skill', 'Read', 'Bash', 'Glob', 'Grep'],
        timeout: 60_000,
        testName,
        runId,
      });

      const skillCalls = result.toolCalls.filter(tc => tc.tool === 'Skill');
      const actualSkill = skillCalls.length > 0 ? skillCalls[0]?.input?.skill : undefined;

      logCost(`journey: ${testName}`, result);
      recordRouting(testName, result, expectedSkill, actualSkill);

      expect(skillCalls.length, `Expected Skill tool to be called but got 0 calls. Claude may have answered directly without invoking a skill. Tool calls: ${result.toolCalls.map(tc => tc.tool).join(', ')}`).toBeGreaterThan(0);
      expect([expectedSkill], `Expected skill ${expectedSkill} but got ${actualSkill}`).toContain(actualSkill);
    } finally {
      fs.rmSync(tmpDir, { recursive: true, force: true });
    }
  }, 150_000);

  testIfSelected('journey-visual-qa', async () => {
    const tmpDir = createRoutingWorkDir('visual-qa');
    try {
      const run = (cmd: string, args: string[]) =>
        spawnSync(cmd, args, { cwd: tmpDir, stdio: 'pipe', timeout: 5000 });

      fs.mkdirSync(path.join(tmpDir, 'src'), { recursive: true });
      fs.writeFileSync(path.join(tmpDir, 'src/styles.css'), `
body { font-family: sans-serif; }
.header { font-size: 24px; margin: 20px; }
.card { padding: 16px; margin: 8px; border: 1px solid #ccc; }
.button { background: #007bff; color: white; padding: 10px 20px; }
`);
      fs.writeFileSync(path.join(tmpDir, 'src/index.html'), `
<html>
<head><link rel="stylesheet" href="styles.css"></head>
<body>
  <div class="header">Waitlist</div>
  <div class="card">Party of 4 - Smith</div>
  <div class="card">Party of 2 - Jones</div>
</body>
</html>
`);
      run('git', ['add', '.']);
      run('git', ['commit', '-m', 'initial UI']);

      const testName = 'journey-visual-qa';
      const expectedSkill = 'design-review';
      const result = await runSkillTest({
        prompt: "Something looks off on the site. The spacing between sections is inconsistent and the font sizes don't feel right. Can you audit the visual design and fix anything that doesn't look polished?",
        workingDirectory: tmpDir,
        maxTurns: 5,
        allowedTools: ['Skill', 'Read', 'Bash', 'Glob', 'Grep'],
        timeout: 60_000,
        testName,
        runId,
      });

      const skillCalls = result.toolCalls.filter(tc => tc.tool === 'Skill');
      const actualSkill = skillCalls.length > 0 ? skillCalls[0]?.input?.skill : undefined;

      logCost(`journey: ${testName}`, result);
      recordRouting(testName, result, expectedSkill, actualSkill);

      expect(skillCalls.length, `Expected Skill tool to be called but got 0 calls. Claude may have answered directly without invoking a skill. Tool calls: ${result.toolCalls.map(tc => tc.tool).join(', ')}`).toBeGreaterThan(0);
      const validSkills = ['design-review', 'qa', 'qa-only', 'browse'];
      expect(validSkills, `Expected one of ${validSkills.join('/')} but got ${actualSkill}`).toContain(actualSkill);
    } finally {
      fs.rmSync(tmpDir, { recursive: true, force: true });
    }
  }, 150_000);
});