Files
gstack/test/skill-routing-e2e.test.ts
Garry Tan b805aa0113 feat: Confusion Protocol, Hermes + GBrain hosts, brain-first resolver (v0.18.0.0) (#1005)
* feat: add Confusion Protocol to preamble resolver

Injects a high-stakes ambiguity gate at preamble tier >= 2 so all
workflow skills get it. Fires when Claude encounters architectural
decisions, data model changes, destructive operations, or contradictory
requirements. Does NOT fire on routine coding.

Addresses Karpathy failure mode #1 (wrong assumptions) with an
inline STOP gate instead of relying on workflow skill invocation.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: add Hermes and GBrain host configs

Hermes: tool rewrites for terminal/read_file/patch/delegate_task,
paths to ~/.hermes/skills/gstack, AGENTS.md config file.

GBrain: coding skills become brain-aware when GBrain mod is installed.
Same tool rewrites as OpenClaw (agents spawn Claude Code via ACP).
GBRAIN_CONTEXT_LOAD and GBRAIN_SAVE_RESULTS NOT suppressed on gbrain
host, enabling brain-first lookup and save-to-brain behavior.

Both registered in hosts/index.ts with setup script redirect messages.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: GBrain resolver — brain-first lookup and save-to-brain

New scripts/resolvers/gbrain.ts with two resolver functions:
- GBRAIN_CONTEXT_LOAD: search brain for context before skill starts
- GBRAIN_SAVE_RESULTS: save skill output to brain after completion

Placeholders added to 4 thinking skill templates (office-hours,
investigate, plan-ceo-review, retro). Resolves to empty string on
all hosts except gbrain via suppressedResolvers.

GBRAIN suppression added to all 9 non-gbrain host configs.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: wire slop:diff into /review as advisory diagnostic

Adds Step 3.5 to the review template: runs bun run slop:diff against
the base branch to catch AI code quality issues (empty catches,
redundant return await, overcomplicated abstractions). Advisory only,
never blocking. Skips silently if slop-scan is not installed.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* docs: add Karpathy compatibility note to README

Positions gstack as the workflow enforcement layer for Karpathy-style
CLAUDE.md rules (17K stars). Links to forrestchang/andrej-karpathy-skills.
Maps each Karpathy failure mode to the gstack skill that addresses it.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: improve native OpenClaw thinking skills

office-hours: add design doc path visibility message after writing
ceo-review: add HARD GATE reminder at review section transitions
retro: add non-git context support (check memory for meeting notes)

Mirrors template improvements to hand-crafted native skills.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* chore: update tests and golden fixtures for new hosts

- Host count: 8 → 10 (hermes, gbrain)
- OpenClaw adapter test: expects undefined (dead code removed)
- Golden ship fixtures: updated with Confusion Protocol + vendoring

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* chore: regenerate all SKILL.md files

Regenerated from templates after Confusion Protocol, GBrain resolver
placeholders, slop:diff in review, HARD GATE reminders, investigation
learnings, design doc visibility, and retro non-git context changes.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* docs: update project documentation for v0.18.0.0

- CHANGELOG: add v0.18.0.0 entry (Confusion Protocol, Hermes, GBrain,
  slop in review, Karpathy note, skill improvements)
- CLAUDE.md: add hermes.ts and gbrain.ts to hosts listing
- README.md: update agent count 8→10, add Hermes + GBrain to table
- VERSION: bump to 0.18.0.0

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* chore: sync package.json version to 0.18.0.0

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: extract Step 0 from review SKILL.md in E2E test

The review-base-branch E2E test was copying the full 1493-line
review/SKILL.md into the test fixture. The agent spent 8+ turns
reading it in chunks, leaving only 7 turns for actual work, causing
error_max_turns on every attempt.

Now extracts only Step 0 (base branch detection, ~50 lines) which is
all the test actually needs. Follows the CLAUDE.md rule: "NEVER copy
a full SKILL.md file into an E2E test fixture."

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: update GBrain and Hermes host configs for v0.10.0 integration

GBrain: add 'triggers' to keepFields so generated skills pass
checkResolvable() validation. Add version compat comment.

Hermes: un-suppress GBRAIN_CONTEXT_LOAD and GBRAIN_SAVE_RESULTS.
The resolvers handle GBrain-not-installed gracefully, so Hermes
agents with GBrain as a mod get brain features automatically.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: GBrain resolver DX improvements and preamble health check

Resolver changes:
- gbrain query → gbrain search (fast keyword search, not expensive hybrid)
- Add keyword extraction guidance for agents
- Show explicit gbrain put_page syntax with --title, --tags, heredoc
- Add entity enrichment with false-positive filter
- Name throttle error patterns (exit code 1, stderr keywords)
- Add data-research routing for investigate skill
- Expand skillSaveMap from 4 to 8 entries
- Add brain operation telemetry summary

Preamble changes:
- Add gbrain doctor --fast --json health check for gbrain/hermes hosts
- Parse check failures/warnings count
- Show failing check details when score < 50

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: preserve keepFields in allowlist frontmatter mode

The allowlist mode hard-coded name + description reconstruction but
never iterated keepFields for additional fields. Adding 'triggers'
to keepFields was a no-op because the field was silently stripped.

Now iterates keepFields and preserves any field beyond name/description
from the source template frontmatter, including YAML arrays.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: add triggers to all 38 skill templates

Multi-word, skill-specific trigger keywords for GBrain's RESOLVER.md
router. Each skill gets 3-6 triggers derived from its "Use when asked
to..." description text. Avoids single generic words that would collide
across skills (e.g., "debug this" not "debug").

These are distinct from voice-triggers (speech-to-text aliases) and
serve GBrain's checkResolvable() validation.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* chore: regenerate all SKILL.md files and update golden fixtures

Regenerated from updated templates (triggers, brain placeholders,
resolver DX improvements, preamble health check). Golden fixtures
updated to match.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: settings-hook remove exits 1 when nothing to remove

gstack-settings-hook remove was exiting 0 when settings.json didn't
exist, causing gstack-uninstall to report "SessionStart hook" as
removed on clean systems where nothing was installed.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* docs: update project documentation for GBrain v0.10.0 integration

ARCHITECTURE.md: added GBRAIN_CONTEXT_LOAD and GBRAIN_SAVE_RESULTS
to resolver table.

CHANGELOG.md: expanded v0.18.0.0 entry with GBrain v0.10.0 integration
details (triggers, expanded brain-awareness, DX improvements, Hermes
brain support), updated date.

CLAUDE.md: added gbrain to resolvers/ directory comment.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: routing E2E stops writing to user's ~/.claude/skills/

installSkills() was copying SKILL.md files to both project-level
(.claude/skills/ in tmpDir) and user-level (~/.claude/skills/).
Writing to the user's real install fails when symlinks point to
different worktrees or dangling targets (ENOENT on copyFileSync).

Now installs to project-level only. The test already sets cwd to
the tmpDir, so project-level discovery works.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* chore: scale Gemini E2E back to smoke test

Gemini CLI gets lost in worktrees on complex tasks (review times out
at 600s, discover-skill hits exit 124). Nobody uses Gemini for gstack
skill execution. Replace the two failing tests (gemini-discover-skill
and gemini-review-findings) with a single smoke test that verifies
Gemini can start and read the README. 90s timeout, no skill invocation.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-16 10:41:38 -07:00

602 lines
26 KiB
TypeScript

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.
* Installs to project-level (.claude/skills/) only. Writing to the user's
* ~/.claude/skills/ is unsafe: it may contain symlinks from the real gstack
* install that point to different worktrees or dangling targets. */
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',
];
const targetBase = path.join(tmpDir, '.claude', 'skills');
for (const skill of skillDirs) {
const srcPath = path.join(ROOT, skill, 'SKILL.md');
if (!fs.existsSync(srcPath)) continue;
const skillName = skill || 'gstack';
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);
});